| 10532 2 62 380 378 9 48 11114 379 10534 382 48 9 11163 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* I/O iterator iteration building functions. * * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef _LINUX_IOV_ITER_H #define _LINUX_IOV_ITER_H #include <linux/uio.h> #include <linux/bvec.h> #include <linux/folio_queue.h> typedef size_t (*iov_step_f)(void *iter_base, size_t progress, size_t len, void *priv, void *priv2); typedef size_t (*iov_ustep_f)(void __user *iter_base, size_t progress, size_t len, void *priv, void *priv2); /* * Handle ITER_UBUF. */ static __always_inline size_t iterate_ubuf(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_ustep_f step) { void __user *base = iter->ubuf; size_t progress = 0, remain; remain = step(base + iter->iov_offset, 0, len, priv, priv2); progress = len - remain; iter->iov_offset += progress; iter->count -= progress; return progress; } /* * Handle ITER_IOVEC. */ static __always_inline size_t iterate_iovec(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_ustep_f step) { const struct iovec *p = iter->__iov; size_t progress = 0, skip = iter->iov_offset; do { size_t remain, consumed; size_t part = min(len, p->iov_len - skip); if (likely(part)) { remain = step(p->iov_base + skip, progress, part, priv, priv2); consumed = part - remain; progress += consumed; skip += consumed; len -= consumed; if (skip < p->iov_len) break; } p++; skip = 0; } while (len); iter->nr_segs -= p - iter->__iov; iter->__iov = p; iter->iov_offset = skip; iter->count -= progress; return progress; } /* * Handle ITER_KVEC. */ static __always_inline size_t iterate_kvec(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { const struct kvec *p = iter->kvec; size_t progress = 0, skip = iter->iov_offset; do { size_t remain, consumed; size_t part = min(len, p->iov_len - skip); if (likely(part)) { remain = step(p->iov_base + skip, progress, part, priv, priv2); consumed = part - remain; progress += consumed; skip += consumed; len -= consumed; if (skip < p->iov_len) break; } p++; skip = 0; } while (len); iter->nr_segs -= p - iter->kvec; iter->kvec = p; iter->iov_offset = skip; iter->count -= progress; return progress; } /* * Handle ITER_BVEC. */ static __always_inline size_t iterate_bvec(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { const struct bio_vec *p = iter->bvec; size_t progress = 0, skip = iter->iov_offset; do { size_t remain, consumed; size_t offset = p->bv_offset + skip, part; void *kaddr = kmap_local_page(p->bv_page + offset / PAGE_SIZE); part = min3(len, (size_t)(p->bv_len - skip), (size_t)(PAGE_SIZE - offset % PAGE_SIZE)); remain = step(kaddr + offset % PAGE_SIZE, progress, part, priv, priv2); kunmap_local(kaddr); consumed = part - remain; len -= consumed; progress += consumed; skip += consumed; if (skip >= p->bv_len) { skip = 0; p++; } if (remain) break; } while (len); iter->nr_segs -= p - iter->bvec; iter->bvec = p; iter->iov_offset = skip; iter->count -= progress; return progress; } /* * Handle ITER_FOLIOQ. */ static __always_inline size_t iterate_folioq(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { const struct folio_queue *folioq = iter->folioq; unsigned int slot = iter->folioq_slot; size_t progress = 0, skip = iter->iov_offset; if (slot == folioq_nr_slots(folioq)) { /* The iterator may have been extended. */ folioq = folioq->next; slot = 0; } do { struct folio *folio = folioq_folio(folioq, slot); size_t part, remain, consumed; size_t fsize; void *base; if (!folio) break; fsize = folioq_folio_size(folioq, slot); base = kmap_local_folio(folio, skip); part = umin(len, PAGE_SIZE - skip % PAGE_SIZE); remain = step(base, progress, part, priv, priv2); kunmap_local(base); consumed = part - remain; len -= consumed; progress += consumed; skip += consumed; if (skip >= fsize) { skip = 0; slot++; if (slot == folioq_nr_slots(folioq) && folioq->next) { folioq = folioq->next; slot = 0; } } if (remain) break; } while (len); iter->folioq_slot = slot; iter->folioq = folioq; iter->iov_offset = skip; iter->count -= progress; return progress; } /* * Handle ITER_XARRAY. */ static __always_inline size_t iterate_xarray(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { struct folio *folio; size_t progress = 0; loff_t start = iter->xarray_start + iter->iov_offset; pgoff_t index = start / PAGE_SIZE; XA_STATE(xas, iter->xarray, index); rcu_read_lock(); xas_for_each(&xas, folio, ULONG_MAX) { size_t remain, consumed, offset, part, flen; if (xas_retry(&xas, folio)) continue; if (WARN_ON(xa_is_value(folio))) break; if (WARN_ON(folio_test_hugetlb(folio))) break; offset = offset_in_folio(folio, start + progress); flen = min(folio_size(folio) - offset, len); while (flen) { void *base = kmap_local_folio(folio, offset); part = min_t(size_t, flen, PAGE_SIZE - offset_in_page(offset)); remain = step(base, progress, part, priv, priv2); kunmap_local(base); consumed = part - remain; progress += consumed; len -= consumed; if (remain || len == 0) goto out; flen -= consumed; offset += consumed; } } out: rcu_read_unlock(); iter->iov_offset += progress; iter->count -= progress; return progress; } /* * Handle ITER_DISCARD. */ static __always_inline size_t iterate_discard(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { size_t progress = len; iter->count -= progress; return progress; } /** * iterate_and_advance2 - Iterate over an iterator * @iter: The iterator to iterate over. * @len: The amount to iterate over. * @priv: Data for the step functions. * @priv2: More data for the step functions. * @ustep: Function for UBUF/IOVEC iterators; given __user addresses. * @step: Function for other iterators; given kernel addresses. * * Iterate over the next part of an iterator, up to the specified length. The * buffer is presented in segments, which for kernel iteration are broken up by * physical pages and mapped, with the mapped address being presented. * * Two step functions, @step and @ustep, must be provided, one for handling * mapped kernel addresses and the other is given user addresses which have the * potential to fault since no pinning is performed. * * The step functions are passed the address and length of the segment, @priv, * @priv2 and the amount of data so far iterated over (which can, for example, * be added to @priv to point to the right part of a second buffer). The step * functions should return the amount of the segment they didn't process (ie. 0 * indicates complete processsing). * * This function returns the amount of data processed (ie. 0 means nothing was * processed and the value of @len means processes to completion). */ static __always_inline size_t iterate_and_advance2(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_ustep_f ustep, iov_step_f step) { if (unlikely(iter->count < len)) len = iter->count; if (unlikely(!len)) return 0; if (likely(iter_is_ubuf(iter))) return iterate_ubuf(iter, len, priv, priv2, ustep); if (likely(iter_is_iovec(iter))) return iterate_iovec(iter, len, priv, priv2, ustep); if (iov_iter_is_bvec(iter)) return iterate_bvec(iter, len, priv, priv2, step); if (iov_iter_is_kvec(iter)) return iterate_kvec(iter, len, priv, priv2, step); if (iov_iter_is_folioq(iter)) return iterate_folioq(iter, len, priv, priv2, step); if (iov_iter_is_xarray(iter)) return iterate_xarray(iter, len, priv, priv2, step); return iterate_discard(iter, len, priv, priv2, step); } /** * iterate_and_advance - Iterate over an iterator * @iter: The iterator to iterate over. * @len: The amount to iterate over. * @priv: Data for the step functions. * @ustep: Function for UBUF/IOVEC iterators; given __user addresses. * @step: Function for other iterators; given kernel addresses. * * As iterate_and_advance2(), but priv2 is always NULL. */ static __always_inline size_t iterate_and_advance(struct iov_iter *iter, size_t len, void *priv, iov_ustep_f ustep, iov_step_f step) { return iterate_and_advance2(iter, len, priv, NULL, ustep, step); } /** * iterate_and_advance_kernel - Iterate over a kernel-internal iterator * @iter: The iterator to iterate over. * @len: The amount to iterate over. * @priv: Data for the step functions. * @priv2: More data for the step functions. * @step: Function for other iterators; given kernel addresses. * * Iterate over the next part of an iterator, up to the specified length. The * buffer is presented in segments, which for kernel iteration are broken up by * physical pages and mapped, with the mapped address being presented. * * [!] Note This will only handle BVEC, KVEC, FOLIOQ, XARRAY and DISCARD-type * iterators; it will not handle UBUF or IOVEC-type iterators. * * A step functions, @step, must be provided, one for handling mapped kernel * addresses and the other is given user addresses which have the potential to * fault since no pinning is performed. * * The step functions are passed the address and length of the segment, @priv, * @priv2 and the amount of data so far iterated over (which can, for example, * be added to @priv to point to the right part of a second buffer). The step * functions should return the amount of the segment they didn't process (ie. 0 * indicates complete processsing). * * This function returns the amount of data processed (ie. 0 means nothing was * processed and the value of @len means processes to completion). */ static __always_inline size_t iterate_and_advance_kernel(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { if (unlikely(iter->count < len)) len = iter->count; if (unlikely(!len)) return 0; if (iov_iter_is_bvec(iter)) return iterate_bvec(iter, len, priv, priv2, step); if (iov_iter_is_kvec(iter)) return iterate_kvec(iter, len, priv, priv2, step); if (iov_iter_is_folioq(iter)) return iterate_folioq(iter, len, priv, priv2, step); if (iov_iter_is_xarray(iter)) return iterate_xarray(iter, len, priv, priv2, step); return iterate_discard(iter, len, priv, priv2, step); } #endif /* _LINUX_IOV_ITER_H */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SEQ_BUF_H #define _LINUX_SEQ_BUF_H #include <linux/bug.h> #include <linux/minmax.h> #include <linux/seq_file.h> #include <linux/types.h> /* * Trace sequences are used to allow a function to call several other functions * to create a string of data to use. */ /** * struct seq_buf - seq buffer structure * @buffer: pointer to the buffer * @size: size of the buffer * @len: the amount of data inside the buffer */ struct seq_buf { char *buffer; size_t size; size_t len; }; #define DECLARE_SEQ_BUF(NAME, SIZE) \ struct seq_buf NAME = { \ .buffer = (char[SIZE]) { 0 }, \ .size = SIZE, \ } static inline void seq_buf_clear(struct seq_buf *s) { s->len = 0; if (s->size) s->buffer[0] = '\0'; } static inline void seq_buf_init(struct seq_buf *s, char *buf, unsigned int size) { s->buffer = buf; s->size = size; seq_buf_clear(s); } /* * seq_buf have a buffer that might overflow. When this happens * len is set to be greater than size. */ static inline bool seq_buf_has_overflowed(struct seq_buf *s) { return s->len > s->size; } static inline void seq_buf_set_overflow(struct seq_buf *s) { s->len = s->size + 1; } /* * How much buffer is left on the seq_buf? */ static inline unsigned int seq_buf_buffer_left(struct seq_buf *s) { if (seq_buf_has_overflowed(s)) return 0; return s->size - s->len; } /* How much buffer was written? */ static inline unsigned int seq_buf_used(struct seq_buf *s) { return min(s->len, s->size); } /** * seq_buf_str - get NUL-terminated C string from seq_buf * @s: the seq_buf handle * * This makes sure that the buffer in @s is NUL-terminated and * safe to read as a string. * * Note, if this is called when the buffer has overflowed, then * the last byte of the buffer is zeroed, and the len will still * point passed it. * * After this function is called, s->buffer is safe to use * in string operations. * * Returns: @s->buf after making sure it is terminated. */ static inline const char *seq_buf_str(struct seq_buf *s) { if (WARN_ON(s->size == 0)) return ""; if (seq_buf_buffer_left(s)) s->buffer[s->len] = 0; else s->buffer[s->size - 1] = 0; return s->buffer; } /** * seq_buf_get_buf - get buffer to write arbitrary data to * @s: the seq_buf handle * @bufp: the beginning of the buffer is stored here * * Returns: the number of bytes available in the buffer, or zero if * there's no space. */ static inline size_t seq_buf_get_buf(struct seq_buf *s, char **bufp) { WARN_ON(s->len > s->size + 1); if (s->len < s->size) { *bufp = s->buffer + s->len; return s->size - s->len; } *bufp = NULL; return 0; } /** * seq_buf_commit - commit data to the buffer * @s: the seq_buf handle * @num: the number of bytes to commit * * Commit @num bytes of data written to a buffer previously acquired * by seq_buf_get_buf(). To signal an error condition, or that the data * didn't fit in the available space, pass a negative @num value. */ static inline void seq_buf_commit(struct seq_buf *s, int num) { if (num < 0) { seq_buf_set_overflow(s); } else { /* num must be negative on overflow */ BUG_ON(s->len + num > s->size); s->len += num; } } extern __printf(2, 3) int seq_buf_printf(struct seq_buf *s, const char *fmt, ...); extern __printf(2, 0) int seq_buf_vprintf(struct seq_buf *s, const char *fmt, va_list args); extern int seq_buf_print_seq(struct seq_file *m, struct seq_buf *s); extern int seq_buf_to_user(struct seq_buf *s, char __user *ubuf, size_t start, int cnt); extern int seq_buf_puts(struct seq_buf *s, const char *str); extern int seq_buf_putc(struct seq_buf *s, unsigned char c); extern int seq_buf_putmem(struct seq_buf *s, const void *mem, unsigned int len); extern int seq_buf_putmem_hex(struct seq_buf *s, const void *mem, unsigned int len); extern int seq_buf_path(struct seq_buf *s, const struct path *path, const char *esc); extern int seq_buf_hex_dump(struct seq_buf *s, const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, bool ascii); #ifdef CONFIG_BINARY_PRINTF extern int seq_buf_bprintf(struct seq_buf *s, const char *fmt, const u32 *binary); #endif void seq_buf_do_printk(struct seq_buf *s, const char *lvl); #endif /* _LINUX_SEQ_BUF_H */ |
| 60 1993 2031 2031 2032 194 1983 49 46 2052 1915 1928 47 47 47 47 47 47 20 47 46 46 2 91 47 47 166 168 167 70 69 32 5 83 1 2027 2052 2034 2028 1916 1915 5 1912 35 2028 1918 2023 2036 1557 1488 2052 12 2032 2039 2052 165 2176 2196 1899 394 400 1056 1060 1056 1056 1013 1402 2189 1891 1710 49 49 2 6 6 6 6 4 1 2 3 5 3 3 7 2 2 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de> * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007 Timesys Corp., Thomas Gleixner * * High-resolution kernel timers * * In contrast to the low-resolution timeout API, aka timer wheel, * hrtimers provide finer resolution and accuracy depending on system * configuration and capabilities. * * Started by: Thomas Gleixner and Ingo Molnar * * Credits: * Based on the original timer wheel code * * Help, testing, suggestions, bugfixes, improvements were * provided by: * * George Anzinger, Andrew Morton, Steven Rostedt, Roman Zippel * et. al. */ #include <linux/cpu.h> #include <linux/export.h> #include <linux/percpu.h> #include <linux/hrtimer.h> #include <linux/notifier.h> #include <linux/syscalls.h> #include <linux/interrupt.h> #include <linux/tick.h> #include <linux/err.h> #include <linux/debugobjects.h> #include <linux/sched/signal.h> #include <linux/sched/sysctl.h> #include <linux/sched/rt.h> #include <linux/sched/deadline.h> #include <linux/sched/nohz.h> #include <linux/sched/debug.h> #include <linux/sched/isolation.h> #include <linux/timer.h> #include <linux/freezer.h> #include <linux/compat.h> #include <linux/uaccess.h> #include <trace/events/timer.h> #include "tick-internal.h" /* * Masks for selecting the soft and hard context timers from * cpu_base->active */ #define MASK_SHIFT (HRTIMER_BASE_MONOTONIC_SOFT) #define HRTIMER_ACTIVE_HARD ((1U << MASK_SHIFT) - 1) #define HRTIMER_ACTIVE_SOFT (HRTIMER_ACTIVE_HARD << MASK_SHIFT) #define HRTIMER_ACTIVE_ALL (HRTIMER_ACTIVE_SOFT | HRTIMER_ACTIVE_HARD) /* * The timer bases: * * There are more clockids than hrtimer bases. Thus, we index * into the timer bases by the hrtimer_base_type enum. When trying * to reach a base using a clockid, hrtimer_clockid_to_base() * is used to convert from clockid to the proper hrtimer_base_type. */ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = { .lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock), .clock_base = { { .index = HRTIMER_BASE_MONOTONIC, .clockid = CLOCK_MONOTONIC, .get_time = &ktime_get, }, { .index = HRTIMER_BASE_REALTIME, .clockid = CLOCK_REALTIME, .get_time = &ktime_get_real, }, { .index = HRTIMER_BASE_BOOTTIME, .clockid = CLOCK_BOOTTIME, .get_time = &ktime_get_boottime, }, { .index = HRTIMER_BASE_TAI, .clockid = CLOCK_TAI, .get_time = &ktime_get_clocktai, }, { .index = HRTIMER_BASE_MONOTONIC_SOFT, .clockid = CLOCK_MONOTONIC, .get_time = &ktime_get, }, { .index = HRTIMER_BASE_REALTIME_SOFT, .clockid = CLOCK_REALTIME, .get_time = &ktime_get_real, }, { .index = HRTIMER_BASE_BOOTTIME_SOFT, .clockid = CLOCK_BOOTTIME, .get_time = &ktime_get_boottime, }, { .index = HRTIMER_BASE_TAI_SOFT, .clockid = CLOCK_TAI, .get_time = &ktime_get_clocktai, }, } }; static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = { /* Make sure we catch unsupported clockids */ [0 ... MAX_CLOCKS - 1] = HRTIMER_MAX_CLOCK_BASES, [CLOCK_REALTIME] = HRTIMER_BASE_REALTIME, [CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC, [CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME, [CLOCK_TAI] = HRTIMER_BASE_TAI, }; /* * Functions and macros which are different for UP/SMP systems are kept in a * single place */ #ifdef CONFIG_SMP /* * We require the migration_base for lock_hrtimer_base()/switch_hrtimer_base() * such that hrtimer_callback_running() can unconditionally dereference * timer->base->cpu_base */ static struct hrtimer_cpu_base migration_cpu_base = { .clock_base = { { .cpu_base = &migration_cpu_base, .seq = SEQCNT_RAW_SPINLOCK_ZERO(migration_cpu_base.seq, &migration_cpu_base.lock), }, }, }; #define migration_base migration_cpu_base.clock_base[0] static inline bool is_migration_base(struct hrtimer_clock_base *base) { return base == &migration_base; } /* * We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock * means that all timers which are tied to this base via timer->base are * locked, and the base itself is locked too. * * So __run_timers/migrate_timers can safely modify all timers which could * be found on the lists/queues. * * When the timer's base is locked, and the timer removed from list, it is * possible to set timer->base = &migration_base and drop the lock: the timer * remains locked. */ static struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) __acquires(&timer->base->lock) { struct hrtimer_clock_base *base; for (;;) { base = READ_ONCE(timer->base); if (likely(base != &migration_base)) { raw_spin_lock_irqsave(&base->cpu_base->lock, *flags); if (likely(base == timer->base)) return base; /* The timer has migrated to another CPU: */ raw_spin_unlock_irqrestore(&base->cpu_base->lock, *flags); } cpu_relax(); } } /* * We do not migrate the timer when it is expiring before the next * event on the target cpu. When high resolution is enabled, we cannot * reprogram the target cpu hardware and we would cause it to fire * late. To keep it simple, we handle the high resolution enabled and * disabled case similar. * * Called with cpu_base->lock of target cpu held. */ static int hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base) { ktime_t expires; expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset); return expires < new_base->cpu_base->expires_next; } static inline struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base, int pinned) { #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) if (static_branch_likely(&timers_migration_enabled) && !pinned) return &per_cpu(hrtimer_bases, get_nohz_timer_target()); #endif return base; } /* * We switch the timer base to a power-optimized selected CPU target, * if: * - NO_HZ_COMMON is enabled * - timer migration is enabled * - the timer callback is not running * - the timer is not the first expiring timer on the new target * * If one of the above requirements is not fulfilled we move the timer * to the current CPU or leave it on the previously assigned CPU if * the timer callback is currently running. */ static inline struct hrtimer_clock_base * switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base, int pinned) { struct hrtimer_cpu_base *new_cpu_base, *this_cpu_base; struct hrtimer_clock_base *new_base; int basenum = base->index; this_cpu_base = this_cpu_ptr(&hrtimer_bases); new_cpu_base = get_target_base(this_cpu_base, pinned); again: new_base = &new_cpu_base->clock_base[basenum]; if (base != new_base) { /* * We are trying to move timer to new_base. * However we can't change timer's base while it is running, * so we keep it on the same CPU. No hassle vs. reprogramming * the event source in the high resolution case. The softirq * code will take care of this when the timer function has * completed. There is no conflict as we hold the lock until * the timer is enqueued. */ if (unlikely(hrtimer_callback_running(timer))) return base; /* See the comment in lock_hrtimer_base() */ WRITE_ONCE(timer->base, &migration_base); raw_spin_unlock(&base->cpu_base->lock); raw_spin_lock(&new_base->cpu_base->lock); if (new_cpu_base != this_cpu_base && hrtimer_check_target(timer, new_base)) { raw_spin_unlock(&new_base->cpu_base->lock); raw_spin_lock(&base->cpu_base->lock); new_cpu_base = this_cpu_base; WRITE_ONCE(timer->base, base); goto again; } WRITE_ONCE(timer->base, new_base); } else { if (new_cpu_base != this_cpu_base && hrtimer_check_target(timer, new_base)) { new_cpu_base = this_cpu_base; goto again; } } return new_base; } #else /* CONFIG_SMP */ static inline bool is_migration_base(struct hrtimer_clock_base *base) { return false; } static inline struct hrtimer_clock_base * lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) __acquires(&timer->base->cpu_base->lock) { struct hrtimer_clock_base *base = timer->base; raw_spin_lock_irqsave(&base->cpu_base->lock, *flags); return base; } # define switch_hrtimer_base(t, b, p) (b) #endif /* !CONFIG_SMP */ /* * Functions for the union type storage format of ktime_t which are * too large for inlining: */ #if BITS_PER_LONG < 64 /* * Divide a ktime value by a nanosecond value */ s64 __ktime_divns(const ktime_t kt, s64 div) { int sft = 0; s64 dclc; u64 tmp; dclc = ktime_to_ns(kt); tmp = dclc < 0 ? -dclc : dclc; /* Make sure the divisor is less than 2^32: */ while (div >> 32) { sft++; div >>= 1; } tmp >>= sft; do_div(tmp, (u32) div); return dclc < 0 ? -tmp : tmp; } EXPORT_SYMBOL_GPL(__ktime_divns); #endif /* BITS_PER_LONG >= 64 */ /* * Add two ktime values and do a safety check for overflow: */ ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs) { ktime_t res = ktime_add_unsafe(lhs, rhs); /* * We use KTIME_SEC_MAX here, the maximum timeout which we can * return to user space in a timespec: */ if (res < 0 || res < lhs || res < rhs) res = ktime_set(KTIME_SEC_MAX, 0); return res; } EXPORT_SYMBOL_GPL(ktime_add_safe); #ifdef CONFIG_DEBUG_OBJECTS_TIMERS static const struct debug_obj_descr hrtimer_debug_descr; static void *hrtimer_debug_hint(void *addr) { return ((struct hrtimer *) addr)->function; } /* * fixup_init is called when: * - an active object is initialized */ static bool hrtimer_fixup_init(void *addr, enum debug_obj_state state) { struct hrtimer *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: hrtimer_cancel(timer); debug_object_init(timer, &hrtimer_debug_descr); return true; default: return false; } } /* * fixup_activate is called when: * - an active object is activated * - an unknown non-static object is activated */ static bool hrtimer_fixup_activate(void *addr, enum debug_obj_state state) { switch (state) { case ODEBUG_STATE_ACTIVE: WARN_ON(1); fallthrough; default: return false; } } /* * fixup_free is called when: * - an active object is freed */ static bool hrtimer_fixup_free(void *addr, enum debug_obj_state state) { struct hrtimer *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: hrtimer_cancel(timer); debug_object_free(timer, &hrtimer_debug_descr); return true; default: return false; } } static const struct debug_obj_descr hrtimer_debug_descr = { .name = "hrtimer", .debug_hint = hrtimer_debug_hint, .fixup_init = hrtimer_fixup_init, .fixup_activate = hrtimer_fixup_activate, .fixup_free = hrtimer_fixup_free, }; static inline void debug_hrtimer_init(struct hrtimer *timer) { debug_object_init(timer, &hrtimer_debug_descr); } static inline void debug_hrtimer_init_on_stack(struct hrtimer *timer) { debug_object_init_on_stack(timer, &hrtimer_debug_descr); } static inline void debug_hrtimer_activate(struct hrtimer *timer, enum hrtimer_mode mode) { debug_object_activate(timer, &hrtimer_debug_descr); } static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { debug_object_deactivate(timer, &hrtimer_debug_descr); } void destroy_hrtimer_on_stack(struct hrtimer *timer) { debug_object_free(timer, &hrtimer_debug_descr); } EXPORT_SYMBOL_GPL(destroy_hrtimer_on_stack); #else static inline void debug_hrtimer_init(struct hrtimer *timer) { } static inline void debug_hrtimer_init_on_stack(struct hrtimer *timer) { } static inline void debug_hrtimer_activate(struct hrtimer *timer, enum hrtimer_mode mode) { } static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { } #endif static inline void debug_init(struct hrtimer *timer, clockid_t clockid, enum hrtimer_mode mode) { debug_hrtimer_init(timer); trace_hrtimer_init(timer, clockid, mode); } static inline void debug_init_on_stack(struct hrtimer *timer, clockid_t clockid, enum hrtimer_mode mode) { debug_hrtimer_init_on_stack(timer); trace_hrtimer_init(timer, clockid, mode); } static inline void debug_activate(struct hrtimer *timer, enum hrtimer_mode mode) { debug_hrtimer_activate(timer, mode); trace_hrtimer_start(timer, mode); } static inline void debug_deactivate(struct hrtimer *timer) { debug_hrtimer_deactivate(timer); trace_hrtimer_cancel(timer); } static struct hrtimer_clock_base * __next_base(struct hrtimer_cpu_base *cpu_base, unsigned int *active) { unsigned int idx; if (!*active) return NULL; idx = __ffs(*active); *active &= ~(1U << idx); return &cpu_base->clock_base[idx]; } #define for_each_active_base(base, cpu_base, active) \ while ((base = __next_base((cpu_base), &(active)))) static ktime_t __hrtimer_next_event_base(struct hrtimer_cpu_base *cpu_base, const struct hrtimer *exclude, unsigned int active, ktime_t expires_next) { struct hrtimer_clock_base *base; ktime_t expires; for_each_active_base(base, cpu_base, active) { struct timerqueue_node *next; struct hrtimer *timer; next = timerqueue_getnext(&base->active); timer = container_of(next, struct hrtimer, node); if (timer == exclude) { /* Get to the next timer in the queue. */ next = timerqueue_iterate_next(next); if (!next) continue; timer = container_of(next, struct hrtimer, node); } expires = ktime_sub(hrtimer_get_expires(timer), base->offset); if (expires < expires_next) { expires_next = expires; /* Skip cpu_base update if a timer is being excluded. */ if (exclude) continue; if (timer->is_soft) cpu_base->softirq_next_timer = timer; else cpu_base->next_timer = timer; } } /* * clock_was_set() might have changed base->offset of any of * the clock bases so the result might be negative. Fix it up * to prevent a false positive in clockevents_program_event(). */ if (expires_next < 0) expires_next = 0; return expires_next; } /* * Recomputes cpu_base::*next_timer and returns the earliest expires_next * but does not set cpu_base::*expires_next, that is done by * hrtimer[_force]_reprogram and hrtimer_interrupt only. When updating * cpu_base::*expires_next right away, reprogramming logic would no longer * work. * * When a softirq is pending, we can ignore the HRTIMER_ACTIVE_SOFT bases, * those timers will get run whenever the softirq gets handled, at the end of * hrtimer_run_softirq(), hrtimer_update_softirq_timer() will re-add these bases. * * Therefore softirq values are those from the HRTIMER_ACTIVE_SOFT clock bases. * The !softirq values are the minima across HRTIMER_ACTIVE_ALL, unless an actual * softirq is pending, in which case they're the minima of HRTIMER_ACTIVE_HARD. * * @active_mask must be one of: * - HRTIMER_ACTIVE_ALL, * - HRTIMER_ACTIVE_SOFT, or * - HRTIMER_ACTIVE_HARD. */ static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base, unsigned int active_mask) { unsigned int active; struct hrtimer *next_timer = NULL; ktime_t expires_next = KTIME_MAX; if (!cpu_base->softirq_activated && (active_mask & HRTIMER_ACTIVE_SOFT)) { active = cpu_base->active_bases & HRTIMER_ACTIVE_SOFT; cpu_base->softirq_next_timer = NULL; expires_next = __hrtimer_next_event_base(cpu_base, NULL, active, KTIME_MAX); next_timer = cpu_base->softirq_next_timer; } if (active_mask & HRTIMER_ACTIVE_HARD) { active = cpu_base->active_bases & HRTIMER_ACTIVE_HARD; cpu_base->next_timer = next_timer; expires_next = __hrtimer_next_event_base(cpu_base, NULL, active, expires_next); } return expires_next; } static ktime_t hrtimer_update_next_event(struct hrtimer_cpu_base *cpu_base) { ktime_t expires_next, soft = KTIME_MAX; /* * If the soft interrupt has already been activated, ignore the * soft bases. They will be handled in the already raised soft * interrupt. */ if (!cpu_base->softirq_activated) { soft = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_SOFT); /* * Update the soft expiry time. clock_settime() might have * affected it. */ cpu_base->softirq_expires_next = soft; } expires_next = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_HARD); /* * If a softirq timer is expiring first, update cpu_base->next_timer * and program the hardware with the soft expiry time. */ if (expires_next > soft) { cpu_base->next_timer = cpu_base->softirq_next_timer; expires_next = soft; } return expires_next; } static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) { ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset; ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset; ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset; ktime_t now = ktime_get_update_offsets_now(&base->clock_was_set_seq, offs_real, offs_boot, offs_tai); base->clock_base[HRTIMER_BASE_REALTIME_SOFT].offset = *offs_real; base->clock_base[HRTIMER_BASE_BOOTTIME_SOFT].offset = *offs_boot; base->clock_base[HRTIMER_BASE_TAI_SOFT].offset = *offs_tai; return now; } /* * Is the high resolution mode active ? */ static inline int hrtimer_hres_active(struct hrtimer_cpu_base *cpu_base) { return IS_ENABLED(CONFIG_HIGH_RES_TIMERS) ? cpu_base->hres_active : 0; } static void __hrtimer_reprogram(struct hrtimer_cpu_base *cpu_base, struct hrtimer *next_timer, ktime_t expires_next) { cpu_base->expires_next = expires_next; /* * If hres is not active, hardware does not have to be * reprogrammed yet. * * If a hang was detected in the last timer interrupt then we * leave the hang delay active in the hardware. We want the * system to make progress. That also prevents the following * scenario: * T1 expires 50ms from now * T2 expires 5s from now * * T1 is removed, so this code is called and would reprogram * the hardware to 5s from now. Any hrtimer_start after that * will not reprogram the hardware due to hang_detected being * set. So we'd effectively block all timers until the T2 event * fires. */ if (!hrtimer_hres_active(cpu_base) || cpu_base->hang_detected) return; tick_program_event(expires_next, 1); } /* * Reprogram the event source with checking both queues for the * next event * Called with interrupts disabled and base->lock held */ static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal) { ktime_t expires_next; expires_next = hrtimer_update_next_event(cpu_base); if (skip_equal && expires_next == cpu_base->expires_next) return; __hrtimer_reprogram(cpu_base, cpu_base->next_timer, expires_next); } /* High resolution timer related functions */ #ifdef CONFIG_HIGH_RES_TIMERS /* * High resolution timer enabled ? */ static bool hrtimer_hres_enabled __read_mostly = true; unsigned int hrtimer_resolution __read_mostly = LOW_RES_NSEC; EXPORT_SYMBOL_GPL(hrtimer_resolution); /* * Enable / Disable high resolution mode */ static int __init setup_hrtimer_hres(char *str) { return (kstrtobool(str, &hrtimer_hres_enabled) == 0); } __setup("highres=", setup_hrtimer_hres); /* * hrtimer_high_res_enabled - query, if the highres mode is enabled */ static inline int hrtimer_is_hres_enabled(void) { return hrtimer_hres_enabled; } static void retrigger_next_event(void *arg); /* * Switch to high resolution mode */ static void hrtimer_switch_to_hres(void) { struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases); if (tick_init_highres()) { pr_warn("Could not switch to high resolution mode on CPU %u\n", base->cpu); return; } base->hres_active = 1; hrtimer_resolution = HIGH_RES_NSEC; tick_setup_sched_timer(true); /* "Retrigger" the interrupt to get things going */ retrigger_next_event(NULL); } #else static inline int hrtimer_is_hres_enabled(void) { return 0; } static inline void hrtimer_switch_to_hres(void) { } #endif /* CONFIG_HIGH_RES_TIMERS */ /* * Retrigger next event is called after clock was set with interrupts * disabled through an SMP function call or directly from low level * resume code. * * This is only invoked when: * - CONFIG_HIGH_RES_TIMERS is enabled. * - CONFIG_NOHZ_COMMON is enabled * * For the other cases this function is empty and because the call sites * are optimized out it vanishes as well, i.e. no need for lots of * #ifdeffery. */ static void retrigger_next_event(void *arg) { struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases); /* * When high resolution mode or nohz is active, then the offsets of * CLOCK_REALTIME/TAI/BOOTTIME have to be updated. Otherwise the * next tick will take care of that. * * If high resolution mode is active then the next expiring timer * must be reevaluated and the clock event device reprogrammed if * necessary. * * In the NOHZ case the update of the offset and the reevaluation * of the next expiring timer is enough. The return from the SMP * function call will take care of the reprogramming in case the * CPU was in a NOHZ idle sleep. */ if (!hrtimer_hres_active(base) && !tick_nohz_active) return; raw_spin_lock(&base->lock); hrtimer_update_base(base); if (hrtimer_hres_active(base)) hrtimer_force_reprogram(base, 0); else hrtimer_update_next_event(base); raw_spin_unlock(&base->lock); } /* * When a timer is enqueued and expires earlier than the already enqueued * timers, we have to check, whether it expires earlier than the timer for * which the clock event device was armed. * * Called with interrupts disabled and base->cpu_base.lock held */ static void hrtimer_reprogram(struct hrtimer *timer, bool reprogram) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); struct hrtimer_clock_base *base = timer->base; ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset); WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0); /* * CLOCK_REALTIME timer might be requested with an absolute * expiry time which is less than base->offset. Set it to 0. */ if (expires < 0) expires = 0; if (timer->is_soft) { /* * soft hrtimer could be started on a remote CPU. In this * case softirq_expires_next needs to be updated on the * remote CPU. The soft hrtimer will not expire before the * first hard hrtimer on the remote CPU - * hrtimer_check_target() prevents this case. */ struct hrtimer_cpu_base *timer_cpu_base = base->cpu_base; if (timer_cpu_base->softirq_activated) return; if (!ktime_before(expires, timer_cpu_base->softirq_expires_next)) return; timer_cpu_base->softirq_next_timer = timer; timer_cpu_base->softirq_expires_next = expires; if (!ktime_before(expires, timer_cpu_base->expires_next) || !reprogram) return; } /* * If the timer is not on the current cpu, we cannot reprogram * the other cpus clock event device. */ if (base->cpu_base != cpu_base) return; if (expires >= cpu_base->expires_next) return; /* * If the hrtimer interrupt is running, then it will reevaluate the * clock bases and reprogram the clock event device. */ if (cpu_base->in_hrtirq) return; cpu_base->next_timer = timer; __hrtimer_reprogram(cpu_base, timer, expires); } static bool update_needs_ipi(struct hrtimer_cpu_base *cpu_base, unsigned int active) { struct hrtimer_clock_base *base; unsigned int seq; ktime_t expires; /* * Update the base offsets unconditionally so the following * checks whether the SMP function call is required works. * * The update is safe even when the remote CPU is in the hrtimer * interrupt or the hrtimer soft interrupt and expiring affected * bases. Either it will see the update before handling a base or * it will see it when it finishes the processing and reevaluates * the next expiring timer. */ seq = cpu_base->clock_was_set_seq; hrtimer_update_base(cpu_base); /* * If the sequence did not change over the update then the * remote CPU already handled it. */ if (seq == cpu_base->clock_was_set_seq) return false; /* * If the remote CPU is currently handling an hrtimer interrupt, it * will reevaluate the first expiring timer of all clock bases * before reprogramming. Nothing to do here. */ if (cpu_base->in_hrtirq) return false; /* * Walk the affected clock bases and check whether the first expiring * timer in a clock base is moving ahead of the first expiring timer of * @cpu_base. If so, the IPI must be invoked because per CPU clock * event devices cannot be remotely reprogrammed. */ active &= cpu_base->active_bases; for_each_active_base(base, cpu_base, active) { struct timerqueue_node *next; next = timerqueue_getnext(&base->active); expires = ktime_sub(next->expires, base->offset); if (expires < cpu_base->expires_next) return true; /* Extra check for softirq clock bases */ if (base->clockid < HRTIMER_BASE_MONOTONIC_SOFT) continue; if (cpu_base->softirq_activated) continue; if (expires < cpu_base->softirq_expires_next) return true; } return false; } /* * Clock was set. This might affect CLOCK_REALTIME, CLOCK_TAI and * CLOCK_BOOTTIME (for late sleep time injection). * * This requires to update the offsets for these clocks * vs. CLOCK_MONOTONIC. When high resolution timers are enabled, then this * also requires to eventually reprogram the per CPU clock event devices * when the change moves an affected timer ahead of the first expiring * timer on that CPU. Obviously remote per CPU clock event devices cannot * be reprogrammed. The other reason why an IPI has to be sent is when the * system is in !HIGH_RES and NOHZ mode. The NOHZ mode updates the offsets * in the tick, which obviously might be stopped, so this has to bring out * the remote CPU which might sleep in idle to get this sorted. */ void clock_was_set(unsigned int bases) { struct hrtimer_cpu_base *cpu_base = raw_cpu_ptr(&hrtimer_bases); cpumask_var_t mask; int cpu; if (!hrtimer_hres_active(cpu_base) && !tick_nohz_active) goto out_timerfd; if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) { on_each_cpu(retrigger_next_event, NULL, 1); goto out_timerfd; } /* Avoid interrupting CPUs if possible */ cpus_read_lock(); for_each_online_cpu(cpu) { unsigned long flags; cpu_base = &per_cpu(hrtimer_bases, cpu); raw_spin_lock_irqsave(&cpu_base->lock, flags); if (update_needs_ipi(cpu_base, bases)) cpumask_set_cpu(cpu, mask); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); } preempt_disable(); smp_call_function_many(mask, retrigger_next_event, NULL, 1); preempt_enable(); cpus_read_unlock(); free_cpumask_var(mask); out_timerfd: timerfd_clock_was_set(); } static void clock_was_set_work(struct work_struct *work) { clock_was_set(CLOCK_SET_WALL); } static DECLARE_WORK(hrtimer_work, clock_was_set_work); /* * Called from timekeeping code to reprogram the hrtimer interrupt device * on all cpus and to notify timerfd. */ void clock_was_set_delayed(void) { schedule_work(&hrtimer_work); } /* * Called during resume either directly from via timekeeping_resume() * or in the case of s2idle from tick_unfreeze() to ensure that the * hrtimers are up to date. */ void hrtimers_resume_local(void) { lockdep_assert_irqs_disabled(); /* Retrigger on the local CPU */ retrigger_next_event(NULL); } /* * Counterpart to lock_hrtimer_base above: */ static inline void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) __releases(&timer->base->cpu_base->lock) { raw_spin_unlock_irqrestore(&timer->base->cpu_base->lock, *flags); } /** * hrtimer_forward() - forward the timer expiry * @timer: hrtimer to forward * @now: forward past this time * @interval: the interval to forward * * Forward the timer expiry so it will expire in the future. * * .. note:: * This only updates the timer expiry value and does not requeue the timer. * * There is also a variant of the function hrtimer_forward_now(). * * Context: Can be safely called from the callback function of @timer. If called * from other contexts @timer must neither be enqueued nor running the * callback and the caller needs to take care of serialization. * * Return: The number of overruns are returned. */ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) { u64 orun = 1; ktime_t delta; delta = ktime_sub(now, hrtimer_get_expires(timer)); if (delta < 0) return 0; if (WARN_ON(timer->state & HRTIMER_STATE_ENQUEUED)) return 0; if (interval < hrtimer_resolution) interval = hrtimer_resolution; if (unlikely(delta >= interval)) { s64 incr = ktime_to_ns(interval); orun = ktime_divns(delta, incr); hrtimer_add_expires_ns(timer, incr * orun); if (hrtimer_get_expires_tv64(timer) > now) return orun; /* * This (and the ktime_add() below) is the * correction for exact: */ orun++; } hrtimer_add_expires(timer, interval); return orun; } EXPORT_SYMBOL_GPL(hrtimer_forward); /* * enqueue_hrtimer - internal function to (re)start a timer * * The timer is inserted in expiry order. Insertion into the * red black tree is O(log(n)). Must hold the base lock. * * Returns 1 when the new timer is the leftmost timer in the tree. */ static int enqueue_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, enum hrtimer_mode mode) { debug_activate(timer, mode); WARN_ON_ONCE(!base->cpu_base->online); base->cpu_base->active_bases |= 1 << base->index; /* Pairs with the lockless read in hrtimer_is_queued() */ WRITE_ONCE(timer->state, HRTIMER_STATE_ENQUEUED); return timerqueue_add(&base->active, &timer->node); } /* * __remove_hrtimer - internal function to remove a timer * * Caller must hold the base lock. * * High resolution timer mode reprograms the clock event device when the * timer is the one which expires next. The caller can disable this by setting * reprogram to zero. This is useful, when the context does a reprogramming * anyway (e.g. timer interrupt) */ static void __remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, u8 newstate, int reprogram) { struct hrtimer_cpu_base *cpu_base = base->cpu_base; u8 state = timer->state; /* Pairs with the lockless read in hrtimer_is_queued() */ WRITE_ONCE(timer->state, newstate); if (!(state & HRTIMER_STATE_ENQUEUED)) return; if (!timerqueue_del(&base->active, &timer->node)) cpu_base->active_bases &= ~(1 << base->index); /* * Note: If reprogram is false we do not update * cpu_base->next_timer. This happens when we remove the first * timer on a remote cpu. No harm as we never dereference * cpu_base->next_timer. So the worst thing what can happen is * an superfluous call to hrtimer_force_reprogram() on the * remote cpu later on if the same timer gets enqueued again. */ if (reprogram && timer == cpu_base->next_timer) hrtimer_force_reprogram(cpu_base, 1); } /* * remove hrtimer, called with base lock held */ static inline int remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool restart, bool keep_local) { u8 state = timer->state; if (state & HRTIMER_STATE_ENQUEUED) { bool reprogram; /* * Remove the timer and force reprogramming when high * resolution mode is active and the timer is on the current * CPU. If we remove a timer on another CPU, reprogramming is * skipped. The interrupt event on this CPU is fired and * reprogramming happens in the interrupt handler. This is a * rare case and less expensive than a smp call. */ debug_deactivate(timer); reprogram = base->cpu_base == this_cpu_ptr(&hrtimer_bases); /* * If the timer is not restarted then reprogramming is * required if the timer is local. If it is local and about * to be restarted, avoid programming it twice (on removal * and a moment later when it's requeued). */ if (!restart) state = HRTIMER_STATE_INACTIVE; else reprogram &= !keep_local; __remove_hrtimer(timer, base, state, reprogram); return 1; } return 0; } static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) { #ifdef CONFIG_TIME_LOW_RES /* * CONFIG_TIME_LOW_RES indicates that the system has no way to return * granular time values. For relative timers we add hrtimer_resolution * (i.e. one jiffy) to prevent short timeouts. */ timer->is_rel = mode & HRTIMER_MODE_REL; if (timer->is_rel) tim = ktime_add_safe(tim, hrtimer_resolution); #endif return tim; } static void hrtimer_update_softirq_timer(struct hrtimer_cpu_base *cpu_base, bool reprogram) { ktime_t expires; /* * Find the next SOFT expiration. */ expires = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_SOFT); /* * reprogramming needs to be triggered, even if the next soft * hrtimer expires at the same time than the next hard * hrtimer. cpu_base->softirq_expires_next needs to be updated! */ if (expires == KTIME_MAX) return; /* * cpu_base->*next_timer is recomputed by __hrtimer_get_next_event() * cpu_base->*expires_next is only set by hrtimer_reprogram() */ hrtimer_reprogram(cpu_base->softirq_next_timer, reprogram); } static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 delta_ns, const enum hrtimer_mode mode, struct hrtimer_clock_base *base) { struct hrtimer_clock_base *new_base; bool force_local, first; /* * If the timer is on the local cpu base and is the first expiring * timer then this might end up reprogramming the hardware twice * (on removal and on enqueue). To avoid that by prevent the * reprogram on removal, keep the timer local to the current CPU * and enforce reprogramming after it is queued no matter whether * it is the new first expiring timer again or not. */ force_local = base->cpu_base == this_cpu_ptr(&hrtimer_bases); force_local &= base->cpu_base->next_timer == timer; /* * Remove an active timer from the queue. In case it is not queued * on the current CPU, make sure that remove_hrtimer() updates the * remote data correctly. * * If it's on the current CPU and the first expiring timer, then * skip reprogramming, keep the timer local and enforce * reprogramming later if it was the first expiring timer. This * avoids programming the underlying clock event twice (once at * removal and once after enqueue). */ remove_hrtimer(timer, base, true, force_local); if (mode & HRTIMER_MODE_REL) tim = ktime_add_safe(tim, base->get_time()); tim = hrtimer_update_lowres(timer, tim, mode); hrtimer_set_expires_range_ns(timer, tim, delta_ns); /* Switch the timer base, if necessary: */ if (!force_local) { new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED); } else { new_base = base; } first = enqueue_hrtimer(timer, new_base, mode); if (!force_local) return first; /* * Timer was forced to stay on the current CPU to avoid * reprogramming on removal and enqueue. Force reprogram the * hardware by evaluating the new first expiring timer. */ hrtimer_force_reprogram(new_base->cpu_base, 1); return 0; } /** * hrtimer_start_range_ns - (re)start an hrtimer * @timer: the timer to be added * @tim: expiry time * @delta_ns: "slack" range for the timer * @mode: timer mode: absolute (HRTIMER_MODE_ABS) or * relative (HRTIMER_MODE_REL), and pinned (HRTIMER_MODE_PINNED); * softirq based mode is considered for debug purpose only! */ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 delta_ns, const enum hrtimer_mode mode) { struct hrtimer_clock_base *base; unsigned long flags; if (WARN_ON_ONCE(!timer->function)) return; /* * Check whether the HRTIMER_MODE_SOFT bit and hrtimer.is_soft * match on CONFIG_PREEMPT_RT = n. With PREEMPT_RT check the hard * expiry mode because unmarked timers are moved to softirq expiry. */ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) WARN_ON_ONCE(!(mode & HRTIMER_MODE_SOFT) ^ !timer->is_soft); else WARN_ON_ONCE(!(mode & HRTIMER_MODE_HARD) ^ !timer->is_hard); base = lock_hrtimer_base(timer, &flags); if (__hrtimer_start_range_ns(timer, tim, delta_ns, mode, base)) hrtimer_reprogram(timer, true); unlock_hrtimer_base(timer, &flags); } EXPORT_SYMBOL_GPL(hrtimer_start_range_ns); /** * hrtimer_try_to_cancel - try to deactivate a timer * @timer: hrtimer to stop * * Returns: * * * 0 when the timer was not active * * 1 when the timer was active * * -1 when the timer is currently executing the callback function and * cannot be stopped */ int hrtimer_try_to_cancel(struct hrtimer *timer) { struct hrtimer_clock_base *base; unsigned long flags; int ret = -1; /* * Check lockless first. If the timer is not active (neither * enqueued nor running the callback, nothing to do here. The * base lock does not serialize against a concurrent enqueue, * so we can avoid taking it. */ if (!hrtimer_active(timer)) return 0; base = lock_hrtimer_base(timer, &flags); if (!hrtimer_callback_running(timer)) ret = remove_hrtimer(timer, base, false, false); unlock_hrtimer_base(timer, &flags); return ret; } EXPORT_SYMBOL_GPL(hrtimer_try_to_cancel); #ifdef CONFIG_PREEMPT_RT static void hrtimer_cpu_base_init_expiry_lock(struct hrtimer_cpu_base *base) { spin_lock_init(&base->softirq_expiry_lock); } static void hrtimer_cpu_base_lock_expiry(struct hrtimer_cpu_base *base) __acquires(&base->softirq_expiry_lock) { spin_lock(&base->softirq_expiry_lock); } static void hrtimer_cpu_base_unlock_expiry(struct hrtimer_cpu_base *base) __releases(&base->softirq_expiry_lock) { spin_unlock(&base->softirq_expiry_lock); } /* * The counterpart to hrtimer_cancel_wait_running(). * * If there is a waiter for cpu_base->expiry_lock, then it was waiting for * the timer callback to finish. Drop expiry_lock and reacquire it. That * allows the waiter to acquire the lock and make progress. */ static void hrtimer_sync_wait_running(struct hrtimer_cpu_base *cpu_base, unsigned long flags) { if (atomic_read(&cpu_base->timer_waiters)) { raw_spin_unlock_irqrestore(&cpu_base->lock, flags); spin_unlock(&cpu_base->softirq_expiry_lock); spin_lock(&cpu_base->softirq_expiry_lock); raw_spin_lock_irq(&cpu_base->lock); } } /* * This function is called on PREEMPT_RT kernels when the fast path * deletion of a timer failed because the timer callback function was * running. * * This prevents priority inversion: if the soft irq thread is preempted * in the middle of a timer callback, then calling del_timer_sync() can * lead to two issues: * * - If the caller is on a remote CPU then it has to spin wait for the timer * handler to complete. This can result in unbound priority inversion. * * - If the caller originates from the task which preempted the timer * handler on the same CPU, then spin waiting for the timer handler to * complete is never going to end. */ void hrtimer_cancel_wait_running(const struct hrtimer *timer) { /* Lockless read. Prevent the compiler from reloading it below */ struct hrtimer_clock_base *base = READ_ONCE(timer->base); /* * Just relax if the timer expires in hard interrupt context or if * it is currently on the migration base. */ if (!timer->is_soft || is_migration_base(base)) { cpu_relax(); return; } /* * Mark the base as contended and grab the expiry lock, which is * held by the softirq across the timer callback. Drop the lock * immediately so the softirq can expire the next timer. In theory * the timer could already be running again, but that's more than * unlikely and just causes another wait loop. */ atomic_inc(&base->cpu_base->timer_waiters); spin_lock_bh(&base->cpu_base->softirq_expiry_lock); atomic_dec(&base->cpu_base->timer_waiters); spin_unlock_bh(&base->cpu_base->softirq_expiry_lock); } #else static inline void hrtimer_cpu_base_init_expiry_lock(struct hrtimer_cpu_base *base) { } static inline void hrtimer_cpu_base_lock_expiry(struct hrtimer_cpu_base *base) { } static inline void hrtimer_cpu_base_unlock_expiry(struct hrtimer_cpu_base *base) { } static inline void hrtimer_sync_wait_running(struct hrtimer_cpu_base *base, unsigned long flags) { } #endif /** * hrtimer_cancel - cancel a timer and wait for the handler to finish. * @timer: the timer to be cancelled * * Returns: * 0 when the timer was not active * 1 when the timer was active */ int hrtimer_cancel(struct hrtimer *timer) { int ret; do { ret = hrtimer_try_to_cancel(timer); if (ret < 0) hrtimer_cancel_wait_running(timer); } while (ret < 0); return ret; } EXPORT_SYMBOL_GPL(hrtimer_cancel); /** * __hrtimer_get_remaining - get remaining time for the timer * @timer: the timer to read * @adjust: adjust relative timers when CONFIG_TIME_LOW_RES=y */ ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust) { unsigned long flags; ktime_t rem; lock_hrtimer_base(timer, &flags); if (IS_ENABLED(CONFIG_TIME_LOW_RES) && adjust) rem = hrtimer_expires_remaining_adjusted(timer); else rem = hrtimer_expires_remaining(timer); unlock_hrtimer_base(timer, &flags); return rem; } EXPORT_SYMBOL_GPL(__hrtimer_get_remaining); #ifdef CONFIG_NO_HZ_COMMON /** * hrtimer_get_next_event - get the time until next expiry event * * Returns the next expiry time or KTIME_MAX if no timer is pending. */ u64 hrtimer_get_next_event(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); u64 expires = KTIME_MAX; unsigned long flags; raw_spin_lock_irqsave(&cpu_base->lock, flags); if (!hrtimer_hres_active(cpu_base)) expires = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_ALL); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); return expires; } /** * hrtimer_next_event_without - time until next expiry event w/o one timer * @exclude: timer to exclude * * Returns the next expiry time over all timers except for the @exclude one or * KTIME_MAX if none of them is pending. */ u64 hrtimer_next_event_without(const struct hrtimer *exclude) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); u64 expires = KTIME_MAX; unsigned long flags; raw_spin_lock_irqsave(&cpu_base->lock, flags); if (hrtimer_hres_active(cpu_base)) { unsigned int active; if (!cpu_base->softirq_activated) { active = cpu_base->active_bases & HRTIMER_ACTIVE_SOFT; expires = __hrtimer_next_event_base(cpu_base, exclude, active, KTIME_MAX); } active = cpu_base->active_bases & HRTIMER_ACTIVE_HARD; expires = __hrtimer_next_event_base(cpu_base, exclude, active, expires); } raw_spin_unlock_irqrestore(&cpu_base->lock, flags); return expires; } #endif static inline int hrtimer_clockid_to_base(clockid_t clock_id) { if (likely(clock_id < MAX_CLOCKS)) { int base = hrtimer_clock_to_base_table[clock_id]; if (likely(base != HRTIMER_MAX_CLOCK_BASES)) return base; } WARN(1, "Invalid clockid %d. Using MONOTONIC\n", clock_id); return HRTIMER_BASE_MONOTONIC; } static enum hrtimer_restart hrtimer_dummy_timeout(struct hrtimer *unused) { return HRTIMER_NORESTART; } static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, enum hrtimer_mode mode) { bool softtimer = !!(mode & HRTIMER_MODE_SOFT); struct hrtimer_cpu_base *cpu_base; int base; /* * On PREEMPT_RT enabled kernels hrtimers which are not explicitly * marked for hard interrupt expiry mode are moved into soft * interrupt context for latency reasons and because the callbacks * can invoke functions which might sleep on RT, e.g. spin_lock(). */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(mode & HRTIMER_MODE_HARD)) softtimer = true; memset(timer, 0, sizeof(struct hrtimer)); cpu_base = raw_cpu_ptr(&hrtimer_bases); /* * POSIX magic: Relative CLOCK_REALTIME timers are not affected by * clock modifications, so they needs to become CLOCK_MONOTONIC to * ensure POSIX compliance. */ if (clock_id == CLOCK_REALTIME && mode & HRTIMER_MODE_REL) clock_id = CLOCK_MONOTONIC; base = softtimer ? HRTIMER_MAX_CLOCK_BASES / 2 : 0; base += hrtimer_clockid_to_base(clock_id); timer->is_soft = softtimer; timer->is_hard = !!(mode & HRTIMER_MODE_HARD); timer->base = &cpu_base->clock_base[base]; timerqueue_init(&timer->node); } static void __hrtimer_setup(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), clockid_t clock_id, enum hrtimer_mode mode) { __hrtimer_init(timer, clock_id, mode); if (WARN_ON_ONCE(!function)) timer->function = hrtimer_dummy_timeout; else timer->function = function; } /** * hrtimer_init - initialize a timer to the given clock * @timer: the timer to be initialized * @clock_id: the clock to be used * @mode: The modes which are relevant for initialization: * HRTIMER_MODE_ABS, HRTIMER_MODE_REL, HRTIMER_MODE_ABS_SOFT, * HRTIMER_MODE_REL_SOFT * * The PINNED variants of the above can be handed in, * but the PINNED bit is ignored as pinning happens * when the hrtimer is started */ void hrtimer_init(struct hrtimer *timer, clockid_t clock_id, enum hrtimer_mode mode) { debug_init(timer, clock_id, mode); __hrtimer_init(timer, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_init); /** * hrtimer_setup - initialize a timer to the given clock * @timer: the timer to be initialized * @function: the callback function * @clock_id: the clock to be used * @mode: The modes which are relevant for initialization: * HRTIMER_MODE_ABS, HRTIMER_MODE_REL, HRTIMER_MODE_ABS_SOFT, * HRTIMER_MODE_REL_SOFT * * The PINNED variants of the above can be handed in, * but the PINNED bit is ignored as pinning happens * when the hrtimer is started */ void hrtimer_setup(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), clockid_t clock_id, enum hrtimer_mode mode) { debug_init(timer, clock_id, mode); __hrtimer_setup(timer, function, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_setup); /** * hrtimer_setup_on_stack - initialize a timer on stack memory * @timer: The timer to be initialized * @function: the callback function * @clock_id: The clock to be used * @mode: The timer mode * * Similar to hrtimer_setup(), except that this one must be used if struct hrtimer is in stack * memory. */ void hrtimer_setup_on_stack(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), clockid_t clock_id, enum hrtimer_mode mode) { debug_init_on_stack(timer, clock_id, mode); __hrtimer_setup(timer, function, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_setup_on_stack); /* * A timer is active, when it is enqueued into the rbtree or the * callback function is running or it's in the state of being migrated * to another cpu. * * It is important for this function to not return a false negative. */ bool hrtimer_active(const struct hrtimer *timer) { struct hrtimer_clock_base *base; unsigned int seq; do { base = READ_ONCE(timer->base); seq = raw_read_seqcount_begin(&base->seq); if (timer->state != HRTIMER_STATE_INACTIVE || base->running == timer) return true; } while (read_seqcount_retry(&base->seq, seq) || base != READ_ONCE(timer->base)); return false; } EXPORT_SYMBOL_GPL(hrtimer_active); /* * The write_seqcount_barrier()s in __run_hrtimer() split the thing into 3 * distinct sections: * * - queued: the timer is queued * - callback: the timer is being ran * - post: the timer is inactive or (re)queued * * On the read side we ensure we observe timer->state and cpu_base->running * from the same section, if anything changed while we looked at it, we retry. * This includes timer->base changing because sequence numbers alone are * insufficient for that. * * The sequence numbers are required because otherwise we could still observe * a false negative if the read side got smeared over multiple consecutive * __run_hrtimer() invocations. */ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base, struct hrtimer_clock_base *base, struct hrtimer *timer, ktime_t *now, unsigned long flags) __must_hold(&cpu_base->lock) { enum hrtimer_restart (*fn)(struct hrtimer *); bool expires_in_hardirq; int restart; lockdep_assert_held(&cpu_base->lock); debug_deactivate(timer); base->running = timer; /* * Separate the ->running assignment from the ->state assignment. * * As with a regular write barrier, this ensures the read side in * hrtimer_active() cannot observe base->running == NULL && * timer->state == INACTIVE. */ raw_write_seqcount_barrier(&base->seq); __remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, 0); fn = timer->function; /* * Clear the 'is relative' flag for the TIME_LOW_RES case. If the * timer is restarted with a period then it becomes an absolute * timer. If its not restarted it does not matter. */ if (IS_ENABLED(CONFIG_TIME_LOW_RES)) timer->is_rel = false; /* * The timer is marked as running in the CPU base, so it is * protected against migration to a different CPU even if the lock * is dropped. */ raw_spin_unlock_irqrestore(&cpu_base->lock, flags); trace_hrtimer_expire_entry(timer, now); expires_in_hardirq = lockdep_hrtimer_enter(timer); restart = fn(timer); lockdep_hrtimer_exit(expires_in_hardirq); trace_hrtimer_expire_exit(timer); raw_spin_lock_irq(&cpu_base->lock); /* * Note: We clear the running state after enqueue_hrtimer and * we do not reprogram the event hardware. Happens either in * hrtimer_start_range_ns() or in hrtimer_interrupt() * * Note: Because we dropped the cpu_base->lock above, * hrtimer_start_range_ns() can have popped in and enqueued the timer * for us already. */ if (restart != HRTIMER_NORESTART && !(timer->state & HRTIMER_STATE_ENQUEUED)) enqueue_hrtimer(timer, base, HRTIMER_MODE_ABS); /* * Separate the ->running assignment from the ->state assignment. * * As with a regular write barrier, this ensures the read side in * hrtimer_active() cannot observe base->running.timer == NULL && * timer->state == INACTIVE. */ raw_write_seqcount_barrier(&base->seq); WARN_ON_ONCE(base->running != timer); base->running = NULL; } static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now, unsigned long flags, unsigned int active_mask) { struct hrtimer_clock_base *base; unsigned int active = cpu_base->active_bases & active_mask; for_each_active_base(base, cpu_base, active) { struct timerqueue_node *node; ktime_t basenow; basenow = ktime_add(now, base->offset); while ((node = timerqueue_getnext(&base->active))) { struct hrtimer *timer; timer = container_of(node, struct hrtimer, node); /* * The immediate goal for using the softexpires is * minimizing wakeups, not running timers at the * earliest interrupt after their soft expiration. * This allows us to avoid using a Priority Search * Tree, which can answer a stabbing query for * overlapping intervals and instead use the simple * BST we already have. * We don't add extra wakeups by delaying timers that * are right-of a not yet expired timer, because that * timer will have to trigger a wakeup anyway. */ if (basenow < hrtimer_get_softexpires_tv64(timer)) break; __run_hrtimer(cpu_base, base, timer, &basenow, flags); if (active_mask == HRTIMER_ACTIVE_SOFT) hrtimer_sync_wait_running(cpu_base, flags); } } } static __latent_entropy void hrtimer_run_softirq(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); unsigned long flags; ktime_t now; hrtimer_cpu_base_lock_expiry(cpu_base); raw_spin_lock_irqsave(&cpu_base->lock, flags); now = hrtimer_update_base(cpu_base); __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_SOFT); cpu_base->softirq_activated = 0; hrtimer_update_softirq_timer(cpu_base, true); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); hrtimer_cpu_base_unlock_expiry(cpu_base); } #ifdef CONFIG_HIGH_RES_TIMERS /* * High resolution timer interrupt * Called with interrupts disabled */ void hrtimer_interrupt(struct clock_event_device *dev) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); ktime_t expires_next, now, entry_time, delta; unsigned long flags; int retries = 0; BUG_ON(!cpu_base->hres_active); cpu_base->nr_events++; dev->next_event = KTIME_MAX; raw_spin_lock_irqsave(&cpu_base->lock, flags); entry_time = now = hrtimer_update_base(cpu_base); retry: cpu_base->in_hrtirq = 1; /* * We set expires_next to KTIME_MAX here with cpu_base->lock * held to prevent that a timer is enqueued in our queue via * the migration code. This does not affect enqueueing of * timers which run their callback and need to be requeued on * this CPU. */ cpu_base->expires_next = KTIME_MAX; if (!ktime_before(now, cpu_base->softirq_expires_next)) { cpu_base->softirq_expires_next = KTIME_MAX; cpu_base->softirq_activated = 1; raise_timer_softirq(HRTIMER_SOFTIRQ); } __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD); /* Reevaluate the clock bases for the [soft] next expiry */ expires_next = hrtimer_update_next_event(cpu_base); /* * Store the new expiry value so the migration code can verify * against it. */ cpu_base->expires_next = expires_next; cpu_base->in_hrtirq = 0; raw_spin_unlock_irqrestore(&cpu_base->lock, flags); /* Reprogramming necessary ? */ if (!tick_program_event(expires_next, 0)) { cpu_base->hang_detected = 0; return; } /* * The next timer was already expired due to: * - tracing * - long lasting callbacks * - being scheduled away when running in a VM * * We need to prevent that we loop forever in the hrtimer * interrupt routine. We give it 3 attempts to avoid * overreacting on some spurious event. * * Acquire base lock for updating the offsets and retrieving * the current time. */ raw_spin_lock_irqsave(&cpu_base->lock, flags); now = hrtimer_update_base(cpu_base); cpu_base->nr_retries++; if (++retries < 3) goto retry; /* * Give the system a chance to do something else than looping * here. We stored the entry time, so we know exactly how long * we spent here. We schedule the next event this amount of * time away. */ cpu_base->nr_hangs++; cpu_base->hang_detected = 1; raw_spin_unlock_irqrestore(&cpu_base->lock, flags); delta = ktime_sub(now, entry_time); if ((unsigned int)delta > cpu_base->max_hang_time) cpu_base->max_hang_time = (unsigned int) delta; /* * Limit it to a sensible value as we enforce a longer * delay. Give the CPU at least 100ms to catch up. */ if (delta > 100 * NSEC_PER_MSEC) expires_next = ktime_add_ns(now, 100 * NSEC_PER_MSEC); else expires_next = ktime_add(now, delta); tick_program_event(expires_next, 1); pr_warn_once("hrtimer: interrupt took %llu ns\n", ktime_to_ns(delta)); } #endif /* !CONFIG_HIGH_RES_TIMERS */ /* * Called from run_local_timers in hardirq context every jiffy */ void hrtimer_run_queues(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); unsigned long flags; ktime_t now; if (hrtimer_hres_active(cpu_base)) return; /* * This _is_ ugly: We have to check periodically, whether we * can switch to highres and / or nohz mode. The clocksource * switch happens with xtime_lock held. Notification from * there only sets the check bit in the tick_oneshot code, * otherwise we might deadlock vs. xtime_lock. */ if (tick_check_oneshot_change(!hrtimer_is_hres_enabled())) { hrtimer_switch_to_hres(); return; } raw_spin_lock_irqsave(&cpu_base->lock, flags); now = hrtimer_update_base(cpu_base); if (!ktime_before(now, cpu_base->softirq_expires_next)) { cpu_base->softirq_expires_next = KTIME_MAX; cpu_base->softirq_activated = 1; raise_timer_softirq(HRTIMER_SOFTIRQ); } __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); } /* * Sleep related functions: */ static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer) { struct hrtimer_sleeper *t = container_of(timer, struct hrtimer_sleeper, timer); struct task_struct *task = t->task; t->task = NULL; if (task) wake_up_process(task); return HRTIMER_NORESTART; } /** * hrtimer_sleeper_start_expires - Start a hrtimer sleeper timer * @sl: sleeper to be started * @mode: timer mode abs/rel * * Wrapper around hrtimer_start_expires() for hrtimer_sleeper based timers * to allow PREEMPT_RT to tweak the delivery mode (soft/hardirq context) */ void hrtimer_sleeper_start_expires(struct hrtimer_sleeper *sl, enum hrtimer_mode mode) { /* * Make the enqueue delivery mode check work on RT. If the sleeper * was initialized for hard interrupt delivery, force the mode bit. * This is a special case for hrtimer_sleepers because * __hrtimer_init_sleeper() determines the delivery mode on RT so the * fiddling with this decision is avoided at the call sites. */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && sl->timer.is_hard) mode |= HRTIMER_MODE_HARD; hrtimer_start_expires(&sl->timer, mode); } EXPORT_SYMBOL_GPL(hrtimer_sleeper_start_expires); static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode) { /* * On PREEMPT_RT enabled kernels hrtimers which are not explicitly * marked for hard interrupt expiry mode are moved into soft * interrupt context either for latency reasons or because the * hrtimer callback takes regular spinlocks or invokes other * functions which are not suitable for hard interrupt context on * PREEMPT_RT. * * The hrtimer_sleeper callback is RT compatible in hard interrupt * context, but there is a latency concern: Untrusted userspace can * spawn many threads which arm timers for the same expiry time on * the same CPU. That causes a latency spike due to the wakeup of * a gazillion threads. * * OTOH, privileged real-time user space applications rely on the * low latency of hard interrupt wakeups. If the current task is in * a real-time scheduling class, mark the mode for hard interrupt * expiry. */ if (IS_ENABLED(CONFIG_PREEMPT_RT)) { if (rt_or_dl_task_policy(current) && !(mode & HRTIMER_MODE_SOFT)) mode |= HRTIMER_MODE_HARD; } __hrtimer_init(&sl->timer, clock_id, mode); sl->timer.function = hrtimer_wakeup; sl->task = current; } /** * hrtimer_setup_sleeper_on_stack - initialize a sleeper in stack memory * @sl: sleeper to be initialized * @clock_id: the clock to be used * @mode: timer mode abs/rel */ void hrtimer_setup_sleeper_on_stack(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode) { debug_init_on_stack(&sl->timer, clock_id, mode); __hrtimer_init_sleeper(sl, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_setup_sleeper_on_stack); int nanosleep_copyout(struct restart_block *restart, struct timespec64 *ts) { switch(restart->nanosleep.type) { #ifdef CONFIG_COMPAT_32BIT_TIME case TT_COMPAT: if (put_old_timespec32(ts, restart->nanosleep.compat_rmtp)) return -EFAULT; break; #endif case TT_NATIVE: if (put_timespec64(ts, restart->nanosleep.rmtp)) return -EFAULT; break; default: BUG(); } return -ERESTART_RESTARTBLOCK; } static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode) { struct restart_block *restart; do { set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); hrtimer_sleeper_start_expires(t, mode); if (likely(t->task)) schedule(); hrtimer_cancel(&t->timer); mode = HRTIMER_MODE_ABS; } while (t->task && !signal_pending(current)); __set_current_state(TASK_RUNNING); if (!t->task) return 0; restart = ¤t->restart_block; if (restart->nanosleep.type != TT_NONE) { ktime_t rem = hrtimer_expires_remaining(&t->timer); struct timespec64 rmt; if (rem <= 0) return 0; rmt = ktime_to_timespec64(rem); return nanosleep_copyout(restart, &rmt); } return -ERESTART_RESTARTBLOCK; } static long __sched hrtimer_nanosleep_restart(struct restart_block *restart) { struct hrtimer_sleeper t; int ret; hrtimer_setup_sleeper_on_stack(&t, restart->nanosleep.clockid, HRTIMER_MODE_ABS); hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires); ret = do_nanosleep(&t, HRTIMER_MODE_ABS); destroy_hrtimer_on_stack(&t.timer); return ret; } long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode, const clockid_t clockid) { struct restart_block *restart; struct hrtimer_sleeper t; int ret = 0; hrtimer_setup_sleeper_on_stack(&t, clockid, mode); hrtimer_set_expires_range_ns(&t.timer, rqtp, current->timer_slack_ns); ret = do_nanosleep(&t, mode); if (ret != -ERESTART_RESTARTBLOCK) goto out; /* Absolute timers do not update the rmtp value and restart: */ if (mode == HRTIMER_MODE_ABS) { ret = -ERESTARTNOHAND; goto out; } restart = ¤t->restart_block; restart->nanosleep.clockid = t.timer.base->clockid; restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer); set_restart_fn(restart, hrtimer_nanosleep_restart); out: destroy_hrtimer_on_stack(&t.timer); return ret; } #ifdef CONFIG_64BIT SYSCALL_DEFINE2(nanosleep, struct __kernel_timespec __user *, rqtp, struct __kernel_timespec __user *, rmtp) { struct timespec64 tu; if (get_timespec64(&tu, rqtp)) return -EFAULT; if (!timespec64_valid(&tu)) return -EINVAL; current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE; current->restart_block.nanosleep.rmtp = rmtp; return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL, CLOCK_MONOTONIC); } #endif #ifdef CONFIG_COMPAT_32BIT_TIME SYSCALL_DEFINE2(nanosleep_time32, struct old_timespec32 __user *, rqtp, struct old_timespec32 __user *, rmtp) { struct timespec64 tu; if (get_old_timespec32(&tu, rqtp)) return -EFAULT; if (!timespec64_valid(&tu)) return -EINVAL; current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE; current->restart_block.nanosleep.compat_rmtp = rmtp; return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL, CLOCK_MONOTONIC); } #endif /* * Functions related to boot-time initialization: */ int hrtimers_prepare_cpu(unsigned int cpu) { struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu); int i; for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { struct hrtimer_clock_base *clock_b = &cpu_base->clock_base[i]; clock_b->cpu_base = cpu_base; seqcount_raw_spinlock_init(&clock_b->seq, &cpu_base->lock); timerqueue_init_head(&clock_b->active); } cpu_base->cpu = cpu; cpu_base->active_bases = 0; cpu_base->hres_active = 0; cpu_base->hang_detected = 0; cpu_base->next_timer = NULL; cpu_base->softirq_next_timer = NULL; cpu_base->expires_next = KTIME_MAX; cpu_base->softirq_expires_next = KTIME_MAX; cpu_base->online = 1; hrtimer_cpu_base_init_expiry_lock(cpu_base); return 0; } #ifdef CONFIG_HOTPLUG_CPU static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base, struct hrtimer_clock_base *new_base) { struct hrtimer *timer; struct timerqueue_node *node; while ((node = timerqueue_getnext(&old_base->active))) { timer = container_of(node, struct hrtimer, node); BUG_ON(hrtimer_callback_running(timer)); debug_deactivate(timer); /* * Mark it as ENQUEUED not INACTIVE otherwise the * timer could be seen as !active and just vanish away * under us on another CPU */ __remove_hrtimer(timer, old_base, HRTIMER_STATE_ENQUEUED, 0); timer->base = new_base; /* * Enqueue the timers on the new cpu. This does not * reprogram the event device in case the timer * expires before the earliest on this CPU, but we run * hrtimer_interrupt after we migrated everything to * sort out already expired timers and reprogram the * event device. */ enqueue_hrtimer(timer, new_base, HRTIMER_MODE_ABS); } } int hrtimers_cpu_dying(unsigned int dying_cpu) { int i, ncpu = cpumask_any_and(cpu_active_mask, housekeeping_cpumask(HK_TYPE_TIMER)); struct hrtimer_cpu_base *old_base, *new_base; old_base = this_cpu_ptr(&hrtimer_bases); new_base = &per_cpu(hrtimer_bases, ncpu); /* * The caller is globally serialized and nobody else * takes two locks at once, deadlock is not possible. */ raw_spin_lock(&old_base->lock); raw_spin_lock_nested(&new_base->lock, SINGLE_DEPTH_NESTING); for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { migrate_hrtimer_list(&old_base->clock_base[i], &new_base->clock_base[i]); } /* * The migration might have changed the first expiring softirq * timer on this CPU. Update it. */ __hrtimer_get_next_event(new_base, HRTIMER_ACTIVE_SOFT); /* Tell the other CPU to retrigger the next event */ smp_call_function_single(ncpu, retrigger_next_event, NULL, 0); raw_spin_unlock(&new_base->lock); old_base->online = 0; raw_spin_unlock(&old_base->lock); return 0; } #endif /* CONFIG_HOTPLUG_CPU */ void __init hrtimers_init(void) { hrtimers_prepare_cpu(smp_processor_id()); open_softirq(HRTIMER_SOFTIRQ, hrtimer_run_softirq); } |
| 1 4 4 1 3 1 1 2 2 2 1 1 1 1 1 2 2 2 2 2 13 1 7 6 2 4 5 3 2 3 1 1 5 3 1 1 2 1 1 7 3 1 3 2 2 2 1 1 9 1 2 8 1 1 1 1 1 2 2 2 2 4 1 3 4 3 3 3 3 3 1 3 7 1 4 1 1 4 1 1 2 2 10 4 4 1 6 1 1 5 1 3 1 1 1 2 12 1 4 7 2 1 1 7 1 1 2 2 1 3 3 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 1 1 1 1 1 1 1 1 1 1 1 1 24 1 4 1 4 5 3 2 3 1 1 6 1 1 1 3 1 1 2 2 1 4 1 1 2 3 3 3 1 2 1 2 1 1 1 2 1 1 6 1 3 4 1 1 4 1 2 2 2 2 1 5 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 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 | // SPDX-License-Identifier: GPL-2.0 /* * cfg80211 - wext compat code * * This is temporary code until all wireless functionality is migrated * into cfg80211, when that happens all the exports here go away and * we directly assign the wireless handlers of wireless interfaces. * * Copyright 2008-2009 Johannes Berg <johannes@sipsolutions.net> * Copyright (C) 2019-2023 Intel Corporation */ #include <linux/export.h> #include <linux/wireless.h> #include <linux/nl80211.h> #include <linux/if_arp.h> #include <linux/etherdevice.h> #include <linux/slab.h> #include <net/iw_handler.h> #include <net/cfg80211.h> #include <net/cfg80211-wext.h> #include "wext-compat.h" #include "core.h" #include "rdev-ops.h" int cfg80211_wext_giwname(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { strcpy(wrqu->name, "IEEE 802.11"); return 0; } int cfg80211_wext_siwmode(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { __u32 *mode = &wrqu->mode; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev; struct vif_params vifparams; enum nl80211_iftype type; int ret; rdev = wiphy_to_rdev(wdev->wiphy); switch (*mode) { case IW_MODE_INFRA: type = NL80211_IFTYPE_STATION; break; case IW_MODE_ADHOC: type = NL80211_IFTYPE_ADHOC; break; case IW_MODE_MONITOR: type = NL80211_IFTYPE_MONITOR; break; default: return -EINVAL; } if (type == wdev->iftype) return 0; memset(&vifparams, 0, sizeof(vifparams)); wiphy_lock(wdev->wiphy); ret = cfg80211_change_iface(rdev, dev, type, &vifparams); wiphy_unlock(wdev->wiphy); return ret; } int cfg80211_wext_giwmode(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { __u32 *mode = &wrqu->mode; struct wireless_dev *wdev = dev->ieee80211_ptr; if (!wdev) return -EOPNOTSUPP; switch (wdev->iftype) { case NL80211_IFTYPE_AP: *mode = IW_MODE_MASTER; break; case NL80211_IFTYPE_STATION: *mode = IW_MODE_INFRA; break; case NL80211_IFTYPE_ADHOC: *mode = IW_MODE_ADHOC; break; case NL80211_IFTYPE_MONITOR: *mode = IW_MODE_MONITOR; break; case NL80211_IFTYPE_WDS: *mode = IW_MODE_REPEAT; break; case NL80211_IFTYPE_AP_VLAN: *mode = IW_MODE_SECOND; /* FIXME */ break; default: *mode = IW_MODE_AUTO; break; } return 0; } int cfg80211_wext_giwrange(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_point *data = &wrqu->data; struct wireless_dev *wdev = dev->ieee80211_ptr; struct iw_range *range = (struct iw_range *) extra; enum nl80211_band band; int i, c = 0; if (!wdev) return -EOPNOTSUPP; data->length = sizeof(struct iw_range); memset(range, 0, sizeof(struct iw_range)); range->we_version_compiled = WIRELESS_EXT; range->we_version_source = 21; range->retry_capa = IW_RETRY_LIMIT; range->retry_flags = IW_RETRY_LIMIT; range->min_retry = 0; range->max_retry = 255; range->min_rts = 0; range->max_rts = 2347; range->min_frag = 256; range->max_frag = 2346; range->max_encoding_tokens = 4; range->max_qual.updated = IW_QUAL_NOISE_INVALID; switch (wdev->wiphy->signal_type) { case CFG80211_SIGNAL_TYPE_NONE: break; case CFG80211_SIGNAL_TYPE_MBM: range->max_qual.level = (u8)-110; range->max_qual.qual = 70; range->avg_qual.qual = 35; range->max_qual.updated |= IW_QUAL_DBM; range->max_qual.updated |= IW_QUAL_QUAL_UPDATED; range->max_qual.updated |= IW_QUAL_LEVEL_UPDATED; break; case CFG80211_SIGNAL_TYPE_UNSPEC: range->max_qual.level = 100; range->max_qual.qual = 100; range->avg_qual.qual = 50; range->max_qual.updated |= IW_QUAL_QUAL_UPDATED; range->max_qual.updated |= IW_QUAL_LEVEL_UPDATED; break; } range->avg_qual.level = range->max_qual.level / 2; range->avg_qual.noise = range->max_qual.noise / 2; range->avg_qual.updated = range->max_qual.updated; for (i = 0; i < wdev->wiphy->n_cipher_suites; i++) { switch (wdev->wiphy->cipher_suites[i]) { case WLAN_CIPHER_SUITE_TKIP: range->enc_capa |= (IW_ENC_CAPA_CIPHER_TKIP | IW_ENC_CAPA_WPA); break; case WLAN_CIPHER_SUITE_CCMP: range->enc_capa |= (IW_ENC_CAPA_CIPHER_CCMP | IW_ENC_CAPA_WPA2); break; case WLAN_CIPHER_SUITE_WEP40: range->encoding_size[range->num_encoding_sizes++] = WLAN_KEY_LEN_WEP40; break; case WLAN_CIPHER_SUITE_WEP104: range->encoding_size[range->num_encoding_sizes++] = WLAN_KEY_LEN_WEP104; break; } } for (band = 0; band < NUM_NL80211_BANDS; band ++) { struct ieee80211_supported_band *sband; sband = wdev->wiphy->bands[band]; if (!sband) continue; for (i = 0; i < sband->n_channels && c < IW_MAX_FREQUENCIES; i++) { struct ieee80211_channel *chan = &sband->channels[i]; if (!(chan->flags & IEEE80211_CHAN_DISABLED)) { range->freq[c].i = ieee80211_frequency_to_channel( chan->center_freq); range->freq[c].m = chan->center_freq; range->freq[c].e = 6; c++; } } } range->num_channels = c; range->num_frequency = c; IW_EVENT_CAPA_SET_KERNEL(range->event_capa); IW_EVENT_CAPA_SET(range->event_capa, SIOCGIWAP); IW_EVENT_CAPA_SET(range->event_capa, SIOCGIWSCAN); if (wdev->wiphy->max_scan_ssids > 0) range->scan_capa |= IW_SCAN_CAPA_ESSID; return 0; } /** * cfg80211_wext_freq - get wext frequency for non-"auto" * @freq: the wext freq encoding * * Returns: a frequency, or a negative error code, or 0 for auto. */ int cfg80211_wext_freq(struct iw_freq *freq) { /* * Parse frequency - return 0 for auto and * -EINVAL for impossible things. */ if (freq->e == 0) { enum nl80211_band band = NL80211_BAND_2GHZ; if (freq->m < 0) return 0; if (freq->m > 14) band = NL80211_BAND_5GHZ; return ieee80211_channel_to_frequency(freq->m, band); } else { int i, div = 1000000; for (i = 0; i < freq->e; i++) div /= 10; if (div <= 0) return -EINVAL; return freq->m / div; } } int cfg80211_wext_siwrts(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *rts = &wrqu->rts; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); u32 orts = wdev->wiphy->rts_threshold; int err; wiphy_lock(&rdev->wiphy); if (rts->disabled || !rts->fixed) { wdev->wiphy->rts_threshold = (u32) -1; } else if (rts->value < 0) { err = -EINVAL; goto out; } else { wdev->wiphy->rts_threshold = rts->value; } err = rdev_set_wiphy_params(rdev, WIPHY_PARAM_RTS_THRESHOLD); if (err) wdev->wiphy->rts_threshold = orts; out: wiphy_unlock(&rdev->wiphy); return err; } int cfg80211_wext_giwrts(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *rts = &wrqu->rts; struct wireless_dev *wdev = dev->ieee80211_ptr; rts->value = wdev->wiphy->rts_threshold; rts->disabled = rts->value == (u32) -1; rts->fixed = 1; return 0; } int cfg80211_wext_siwfrag(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *frag = &wrqu->frag; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); u32 ofrag = wdev->wiphy->frag_threshold; int err; wiphy_lock(&rdev->wiphy); if (frag->disabled || !frag->fixed) { wdev->wiphy->frag_threshold = (u32) -1; } else if (frag->value < 256) { err = -EINVAL; goto out; } else { /* Fragment length must be even, so strip LSB. */ wdev->wiphy->frag_threshold = frag->value & ~0x1; } err = rdev_set_wiphy_params(rdev, WIPHY_PARAM_FRAG_THRESHOLD); if (err) wdev->wiphy->frag_threshold = ofrag; out: wiphy_unlock(&rdev->wiphy); return err; } int cfg80211_wext_giwfrag(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *frag = &wrqu->frag; struct wireless_dev *wdev = dev->ieee80211_ptr; frag->value = wdev->wiphy->frag_threshold; frag->disabled = frag->value == (u32) -1; frag->fixed = 1; return 0; } static int cfg80211_wext_siwretry(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *retry = &wrqu->retry; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); u32 changed = 0; u8 olong = wdev->wiphy->retry_long; u8 oshort = wdev->wiphy->retry_short; int err; if (retry->disabled || retry->value < 1 || retry->value > 255 || (retry->flags & IW_RETRY_TYPE) != IW_RETRY_LIMIT) return -EINVAL; wiphy_lock(&rdev->wiphy); if (retry->flags & IW_RETRY_LONG) { wdev->wiphy->retry_long = retry->value; changed |= WIPHY_PARAM_RETRY_LONG; } else if (retry->flags & IW_RETRY_SHORT) { wdev->wiphy->retry_short = retry->value; changed |= WIPHY_PARAM_RETRY_SHORT; } else { wdev->wiphy->retry_short = retry->value; wdev->wiphy->retry_long = retry->value; changed |= WIPHY_PARAM_RETRY_LONG; changed |= WIPHY_PARAM_RETRY_SHORT; } err = rdev_set_wiphy_params(rdev, changed); if (err) { wdev->wiphy->retry_short = oshort; wdev->wiphy->retry_long = olong; } wiphy_unlock(&rdev->wiphy); return err; } int cfg80211_wext_giwretry(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *retry = &wrqu->retry; struct wireless_dev *wdev = dev->ieee80211_ptr; retry->disabled = 0; if (retry->flags == 0 || (retry->flags & IW_RETRY_SHORT)) { /* * First return short value, iwconfig will ask long value * later if needed */ retry->flags |= IW_RETRY_LIMIT | IW_RETRY_SHORT; retry->value = wdev->wiphy->retry_short; if (wdev->wiphy->retry_long == wdev->wiphy->retry_short) retry->flags |= IW_RETRY_LONG; return 0; } if (retry->flags & IW_RETRY_LONG) { retry->flags = IW_RETRY_LIMIT | IW_RETRY_LONG; retry->value = wdev->wiphy->retry_long; } return 0; } static int cfg80211_set_encryption(struct cfg80211_registered_device *rdev, struct net_device *dev, bool pairwise, const u8 *addr, bool remove, bool tx_key, int idx, struct key_params *params) { struct wireless_dev *wdev = dev->ieee80211_ptr; int err, i; bool rejoin = false; if (wdev->valid_links) return -EINVAL; if (pairwise && !addr) return -EINVAL; /* * In many cases we won't actually need this, but it's better * to do it first in case the allocation fails. Don't use wext. */ if (!wdev->wext.keys) { wdev->wext.keys = kzalloc(sizeof(*wdev->wext.keys), GFP_KERNEL); if (!wdev->wext.keys) return -ENOMEM; for (i = 0; i < 4; i++) wdev->wext.keys->params[i].key = wdev->wext.keys->data[i]; } if (wdev->iftype != NL80211_IFTYPE_ADHOC && wdev->iftype != NL80211_IFTYPE_STATION) return -EOPNOTSUPP; if (params->cipher == WLAN_CIPHER_SUITE_AES_CMAC) { if (!wdev->connected) return -ENOLINK; if (!rdev->ops->set_default_mgmt_key) return -EOPNOTSUPP; if (idx < 4 || idx > 5) return -EINVAL; } else if (idx < 0 || idx > 3) return -EINVAL; if (remove) { err = 0; if (wdev->connected || (wdev->iftype == NL80211_IFTYPE_ADHOC && wdev->u.ibss.current_bss)) { /* * If removing the current TX key, we will need to * join a new IBSS without the privacy bit clear. */ if (idx == wdev->wext.default_key && wdev->iftype == NL80211_IFTYPE_ADHOC) { cfg80211_leave_ibss(rdev, wdev->netdev, true); rejoin = true; } if (!pairwise && addr && !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN)) err = -ENOENT; else err = rdev_del_key(rdev, dev, -1, idx, pairwise, addr); } wdev->wext.connect.privacy = false; /* * Applications using wireless extensions expect to be * able to delete keys that don't exist, so allow that. */ if (err == -ENOENT) err = 0; if (!err) { if (!addr && idx < 4) { memset(wdev->wext.keys->data[idx], 0, sizeof(wdev->wext.keys->data[idx])); wdev->wext.keys->params[idx].key_len = 0; wdev->wext.keys->params[idx].cipher = 0; } if (idx == wdev->wext.default_key) wdev->wext.default_key = -1; else if (idx == wdev->wext.default_mgmt_key) wdev->wext.default_mgmt_key = -1; } if (!err && rejoin) err = cfg80211_ibss_wext_join(rdev, wdev); return err; } if (addr) tx_key = false; if (cfg80211_validate_key_settings(rdev, params, idx, pairwise, addr)) return -EINVAL; err = 0; if (wdev->connected || (wdev->iftype == NL80211_IFTYPE_ADHOC && wdev->u.ibss.current_bss)) err = rdev_add_key(rdev, dev, -1, idx, pairwise, addr, params); else if (params->cipher != WLAN_CIPHER_SUITE_WEP40 && params->cipher != WLAN_CIPHER_SUITE_WEP104) return -EINVAL; if (err) return err; /* * We only need to store WEP keys, since they're the only keys that * can be set before a connection is established and persist after * disconnecting. */ if (!addr && (params->cipher == WLAN_CIPHER_SUITE_WEP40 || params->cipher == WLAN_CIPHER_SUITE_WEP104)) { wdev->wext.keys->params[idx] = *params; memcpy(wdev->wext.keys->data[idx], params->key, params->key_len); wdev->wext.keys->params[idx].key = wdev->wext.keys->data[idx]; } if ((params->cipher == WLAN_CIPHER_SUITE_WEP40 || params->cipher == WLAN_CIPHER_SUITE_WEP104) && (tx_key || (!addr && wdev->wext.default_key == -1))) { if (wdev->connected || (wdev->iftype == NL80211_IFTYPE_ADHOC && wdev->u.ibss.current_bss)) { /* * If we are getting a new TX key from not having * had one before we need to join a new IBSS with * the privacy bit set. */ if (wdev->iftype == NL80211_IFTYPE_ADHOC && wdev->wext.default_key == -1) { cfg80211_leave_ibss(rdev, wdev->netdev, true); rejoin = true; } err = rdev_set_default_key(rdev, dev, -1, idx, true, true); } if (!err) { wdev->wext.default_key = idx; if (rejoin) err = cfg80211_ibss_wext_join(rdev, wdev); } return err; } if (params->cipher == WLAN_CIPHER_SUITE_AES_CMAC && (tx_key || (!addr && wdev->wext.default_mgmt_key == -1))) { if (wdev->connected || (wdev->iftype == NL80211_IFTYPE_ADHOC && wdev->u.ibss.current_bss)) err = rdev_set_default_mgmt_key(rdev, dev, -1, idx); if (!err) wdev->wext.default_mgmt_key = idx; return err; } return 0; } static int cfg80211_wext_siwencode(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *keybuf) { struct iw_point *erq = &wrqu->encoding; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int idx, err; bool remove = false; struct key_params params; if (wdev->iftype != NL80211_IFTYPE_STATION && wdev->iftype != NL80211_IFTYPE_ADHOC) return -EOPNOTSUPP; /* no use -- only MFP (set_default_mgmt_key) is optional */ if (!rdev->ops->del_key || !rdev->ops->add_key || !rdev->ops->set_default_key) return -EOPNOTSUPP; wiphy_lock(&rdev->wiphy); if (wdev->valid_links) { err = -EOPNOTSUPP; goto out; } idx = erq->flags & IW_ENCODE_INDEX; if (idx == 0) { idx = wdev->wext.default_key; if (idx < 0) idx = 0; } else if (idx < 1 || idx > 4) { err = -EINVAL; goto out; } else { idx--; } if (erq->flags & IW_ENCODE_DISABLED) remove = true; else if (erq->length == 0) { /* No key data - just set the default TX key index */ err = 0; if (wdev->connected || (wdev->iftype == NL80211_IFTYPE_ADHOC && wdev->u.ibss.current_bss)) err = rdev_set_default_key(rdev, dev, -1, idx, true, true); if (!err) wdev->wext.default_key = idx; goto out; } memset(¶ms, 0, sizeof(params)); params.key = keybuf; params.key_len = erq->length; if (erq->length == 5) { params.cipher = WLAN_CIPHER_SUITE_WEP40; } else if (erq->length == 13) { params.cipher = WLAN_CIPHER_SUITE_WEP104; } else if (!remove) { err = -EINVAL; goto out; } err = cfg80211_set_encryption(rdev, dev, false, NULL, remove, wdev->wext.default_key == -1, idx, ¶ms); out: wiphy_unlock(&rdev->wiphy); return err; } static int cfg80211_wext_siwencodeext(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_point *erq = &wrqu->encoding; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct iw_encode_ext *ext = (struct iw_encode_ext *) extra; const u8 *addr; int idx; bool remove = false; struct key_params params; u32 cipher; int ret; if (wdev->iftype != NL80211_IFTYPE_STATION && wdev->iftype != NL80211_IFTYPE_ADHOC) return -EOPNOTSUPP; /* no use -- only MFP (set_default_mgmt_key) is optional */ if (!rdev->ops->del_key || !rdev->ops->add_key || !rdev->ops->set_default_key) return -EOPNOTSUPP; if (wdev->valid_links) return -EOPNOTSUPP; switch (ext->alg) { case IW_ENCODE_ALG_NONE: remove = true; cipher = 0; break; case IW_ENCODE_ALG_WEP: if (ext->key_len == 5) cipher = WLAN_CIPHER_SUITE_WEP40; else if (ext->key_len == 13) cipher = WLAN_CIPHER_SUITE_WEP104; else return -EINVAL; break; case IW_ENCODE_ALG_TKIP: cipher = WLAN_CIPHER_SUITE_TKIP; break; case IW_ENCODE_ALG_CCMP: cipher = WLAN_CIPHER_SUITE_CCMP; break; case IW_ENCODE_ALG_AES_CMAC: cipher = WLAN_CIPHER_SUITE_AES_CMAC; break; default: return -EOPNOTSUPP; } if (erq->flags & IW_ENCODE_DISABLED) remove = true; idx = erq->flags & IW_ENCODE_INDEX; if (cipher == WLAN_CIPHER_SUITE_AES_CMAC) { if (idx < 4 || idx > 5) { idx = wdev->wext.default_mgmt_key; if (idx < 0) return -EINVAL; } else idx--; } else { if (idx < 1 || idx > 4) { idx = wdev->wext.default_key; if (idx < 0) return -EINVAL; } else idx--; } addr = ext->addr.sa_data; if (is_broadcast_ether_addr(addr)) addr = NULL; memset(¶ms, 0, sizeof(params)); params.key = ext->key; params.key_len = ext->key_len; params.cipher = cipher; if (ext->ext_flags & IW_ENCODE_EXT_RX_SEQ_VALID) { params.seq = ext->rx_seq; params.seq_len = 6; } wiphy_lock(wdev->wiphy); ret = cfg80211_set_encryption( rdev, dev, !(ext->ext_flags & IW_ENCODE_EXT_GROUP_KEY), addr, remove, ext->ext_flags & IW_ENCODE_EXT_SET_TX_KEY, idx, ¶ms); wiphy_unlock(wdev->wiphy); return ret; } static int cfg80211_wext_giwencode(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *keybuf) { struct iw_point *erq = &wrqu->encoding; struct wireless_dev *wdev = dev->ieee80211_ptr; int idx; if (wdev->iftype != NL80211_IFTYPE_STATION && wdev->iftype != NL80211_IFTYPE_ADHOC) return -EOPNOTSUPP; idx = erq->flags & IW_ENCODE_INDEX; if (idx == 0) { idx = wdev->wext.default_key; if (idx < 0) idx = 0; } else if (idx < 1 || idx > 4) return -EINVAL; else idx--; erq->flags = idx + 1; if (!wdev->wext.keys || !wdev->wext.keys->params[idx].cipher) { erq->flags |= IW_ENCODE_DISABLED; erq->length = 0; return 0; } erq->length = min_t(size_t, erq->length, wdev->wext.keys->params[idx].key_len); memcpy(keybuf, wdev->wext.keys->params[idx].key, erq->length); erq->flags |= IW_ENCODE_ENABLED; return 0; } static int cfg80211_wext_siwfreq(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_freq *wextfreq = &wrqu->freq; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_chan_def chandef = { .width = NL80211_CHAN_WIDTH_20_NOHT, }; int freq, ret; wiphy_lock(&rdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_STATION: ret = cfg80211_mgd_wext_siwfreq(dev, info, wextfreq, extra); break; case NL80211_IFTYPE_ADHOC: ret = cfg80211_ibss_wext_siwfreq(dev, info, wextfreq, extra); break; case NL80211_IFTYPE_MONITOR: freq = cfg80211_wext_freq(wextfreq); if (freq < 0) { ret = freq; break; } if (freq == 0) { ret = -EINVAL; break; } chandef.center_freq1 = freq; chandef.chan = ieee80211_get_channel(&rdev->wiphy, freq); if (!chandef.chan) { ret = -EINVAL; break; } ret = cfg80211_set_monitor_channel(rdev, dev, &chandef); break; case NL80211_IFTYPE_MESH_POINT: freq = cfg80211_wext_freq(wextfreq); if (freq < 0) { ret = freq; break; } if (freq == 0) { ret = -EINVAL; break; } chandef.center_freq1 = freq; chandef.chan = ieee80211_get_channel(&rdev->wiphy, freq); if (!chandef.chan) { ret = -EINVAL; break; } ret = cfg80211_set_mesh_channel(rdev, wdev, &chandef); break; default: ret = -EOPNOTSUPP; break; } wiphy_unlock(&rdev->wiphy); return ret; } static int cfg80211_wext_giwfreq(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_freq *freq = &wrqu->freq; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_chan_def chandef = {}; int ret; wiphy_lock(&rdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_STATION: ret = cfg80211_mgd_wext_giwfreq(dev, info, freq, extra); break; case NL80211_IFTYPE_ADHOC: ret = cfg80211_ibss_wext_giwfreq(dev, info, freq, extra); break; case NL80211_IFTYPE_MONITOR: if (!rdev->ops->get_channel) { ret = -EINVAL; break; } ret = rdev_get_channel(rdev, wdev, 0, &chandef); if (ret) break; freq->m = chandef.chan->center_freq; freq->e = 6; ret = 0; break; default: ret = -EINVAL; break; } wiphy_unlock(&rdev->wiphy); return ret; } static int cfg80211_wext_siwtxpower(struct net_device *dev, struct iw_request_info *info, union iwreq_data *data, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); enum nl80211_tx_power_setting type; int dbm = 0; int ret; if ((data->txpower.flags & IW_TXPOW_TYPE) != IW_TXPOW_DBM) return -EINVAL; if (data->txpower.flags & IW_TXPOW_RANGE) return -EINVAL; if (!rdev->ops->set_tx_power) return -EOPNOTSUPP; /* only change when not disabling */ if (!data->txpower.disabled) { rfkill_set_sw_state(rdev->wiphy.rfkill, false); if (data->txpower.fixed) { /* * wext doesn't support negative values, see * below where it's for automatic */ if (data->txpower.value < 0) return -EINVAL; dbm = data->txpower.value; type = NL80211_TX_POWER_FIXED; /* TODO: do regulatory check! */ } else { /* * Automatic power level setting, max being the value * passed in from userland. */ if (data->txpower.value < 0) { type = NL80211_TX_POWER_AUTOMATIC; } else { dbm = data->txpower.value; type = NL80211_TX_POWER_LIMITED; } } } else { if (rfkill_set_sw_state(rdev->wiphy.rfkill, true)) schedule_work(&rdev->rfkill_block); return 0; } wiphy_lock(&rdev->wiphy); ret = rdev_set_tx_power(rdev, wdev, type, DBM_TO_MBM(dbm)); wiphy_unlock(&rdev->wiphy); return ret; } static int cfg80211_wext_giwtxpower(struct net_device *dev, struct iw_request_info *info, union iwreq_data *data, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int err, val; if ((data->txpower.flags & IW_TXPOW_TYPE) != IW_TXPOW_DBM) return -EINVAL; if (data->txpower.flags & IW_TXPOW_RANGE) return -EINVAL; if (!rdev->ops->get_tx_power) return -EOPNOTSUPP; wiphy_lock(&rdev->wiphy); err = rdev_get_tx_power(rdev, wdev, &val); wiphy_unlock(&rdev->wiphy); if (err) return err; /* well... oh well */ data->txpower.fixed = 1; data->txpower.disabled = rfkill_blocked(rdev->wiphy.rfkill); data->txpower.value = val; data->txpower.flags = IW_TXPOW_DBM; return 0; } static int cfg80211_set_auth_alg(struct wireless_dev *wdev, s32 auth_alg) { int nr_alg = 0; if (!auth_alg) return -EINVAL; if (auth_alg & ~(IW_AUTH_ALG_OPEN_SYSTEM | IW_AUTH_ALG_SHARED_KEY | IW_AUTH_ALG_LEAP)) return -EINVAL; if (auth_alg & IW_AUTH_ALG_OPEN_SYSTEM) { nr_alg++; wdev->wext.connect.auth_type = NL80211_AUTHTYPE_OPEN_SYSTEM; } if (auth_alg & IW_AUTH_ALG_SHARED_KEY) { nr_alg++; wdev->wext.connect.auth_type = NL80211_AUTHTYPE_SHARED_KEY; } if (auth_alg & IW_AUTH_ALG_LEAP) { nr_alg++; wdev->wext.connect.auth_type = NL80211_AUTHTYPE_NETWORK_EAP; } if (nr_alg > 1) wdev->wext.connect.auth_type = NL80211_AUTHTYPE_AUTOMATIC; return 0; } static int cfg80211_set_wpa_version(struct wireless_dev *wdev, u32 wpa_versions) { if (wpa_versions & ~(IW_AUTH_WPA_VERSION_WPA | IW_AUTH_WPA_VERSION_WPA2| IW_AUTH_WPA_VERSION_DISABLED)) return -EINVAL; if ((wpa_versions & IW_AUTH_WPA_VERSION_DISABLED) && (wpa_versions & (IW_AUTH_WPA_VERSION_WPA| IW_AUTH_WPA_VERSION_WPA2))) return -EINVAL; if (wpa_versions & IW_AUTH_WPA_VERSION_DISABLED) wdev->wext.connect.crypto.wpa_versions &= ~(NL80211_WPA_VERSION_1|NL80211_WPA_VERSION_2); if (wpa_versions & IW_AUTH_WPA_VERSION_WPA) wdev->wext.connect.crypto.wpa_versions |= NL80211_WPA_VERSION_1; if (wpa_versions & IW_AUTH_WPA_VERSION_WPA2) wdev->wext.connect.crypto.wpa_versions |= NL80211_WPA_VERSION_2; return 0; } static int cfg80211_set_cipher_group(struct wireless_dev *wdev, u32 cipher) { if (cipher & IW_AUTH_CIPHER_WEP40) wdev->wext.connect.crypto.cipher_group = WLAN_CIPHER_SUITE_WEP40; else if (cipher & IW_AUTH_CIPHER_WEP104) wdev->wext.connect.crypto.cipher_group = WLAN_CIPHER_SUITE_WEP104; else if (cipher & IW_AUTH_CIPHER_TKIP) wdev->wext.connect.crypto.cipher_group = WLAN_CIPHER_SUITE_TKIP; else if (cipher & IW_AUTH_CIPHER_CCMP) wdev->wext.connect.crypto.cipher_group = WLAN_CIPHER_SUITE_CCMP; else if (cipher & IW_AUTH_CIPHER_AES_CMAC) wdev->wext.connect.crypto.cipher_group = WLAN_CIPHER_SUITE_AES_CMAC; else if (cipher & IW_AUTH_CIPHER_NONE) wdev->wext.connect.crypto.cipher_group = 0; else return -EINVAL; return 0; } static int cfg80211_set_cipher_pairwise(struct wireless_dev *wdev, u32 cipher) { int nr_ciphers = 0; u32 *ciphers_pairwise = wdev->wext.connect.crypto.ciphers_pairwise; if (cipher & IW_AUTH_CIPHER_WEP40) { ciphers_pairwise[nr_ciphers] = WLAN_CIPHER_SUITE_WEP40; nr_ciphers++; } if (cipher & IW_AUTH_CIPHER_WEP104) { ciphers_pairwise[nr_ciphers] = WLAN_CIPHER_SUITE_WEP104; nr_ciphers++; } if (cipher & IW_AUTH_CIPHER_TKIP) { ciphers_pairwise[nr_ciphers] = WLAN_CIPHER_SUITE_TKIP; nr_ciphers++; } if (cipher & IW_AUTH_CIPHER_CCMP) { ciphers_pairwise[nr_ciphers] = WLAN_CIPHER_SUITE_CCMP; nr_ciphers++; } if (cipher & IW_AUTH_CIPHER_AES_CMAC) { ciphers_pairwise[nr_ciphers] = WLAN_CIPHER_SUITE_AES_CMAC; nr_ciphers++; } BUILD_BUG_ON(NL80211_MAX_NR_CIPHER_SUITES < 5); wdev->wext.connect.crypto.n_ciphers_pairwise = nr_ciphers; return 0; } static int cfg80211_set_key_mgt(struct wireless_dev *wdev, u32 key_mgt) { int nr_akm_suites = 0; if (key_mgt & ~(IW_AUTH_KEY_MGMT_802_1X | IW_AUTH_KEY_MGMT_PSK)) return -EINVAL; if (key_mgt & IW_AUTH_KEY_MGMT_802_1X) { wdev->wext.connect.crypto.akm_suites[nr_akm_suites] = WLAN_AKM_SUITE_8021X; nr_akm_suites++; } if (key_mgt & IW_AUTH_KEY_MGMT_PSK) { wdev->wext.connect.crypto.akm_suites[nr_akm_suites] = WLAN_AKM_SUITE_PSK; nr_akm_suites++; } wdev->wext.connect.crypto.n_akm_suites = nr_akm_suites; return 0; } static int cfg80211_wext_siwauth(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *data = &wrqu->param; struct wireless_dev *wdev = dev->ieee80211_ptr; if (wdev->iftype != NL80211_IFTYPE_STATION) return -EOPNOTSUPP; switch (data->flags & IW_AUTH_INDEX) { case IW_AUTH_PRIVACY_INVOKED: wdev->wext.connect.privacy = data->value; return 0; case IW_AUTH_WPA_VERSION: return cfg80211_set_wpa_version(wdev, data->value); case IW_AUTH_CIPHER_GROUP: return cfg80211_set_cipher_group(wdev, data->value); case IW_AUTH_KEY_MGMT: return cfg80211_set_key_mgt(wdev, data->value); case IW_AUTH_CIPHER_PAIRWISE: return cfg80211_set_cipher_pairwise(wdev, data->value); case IW_AUTH_80211_AUTH_ALG: return cfg80211_set_auth_alg(wdev, data->value); case IW_AUTH_WPA_ENABLED: case IW_AUTH_RX_UNENCRYPTED_EAPOL: case IW_AUTH_DROP_UNENCRYPTED: case IW_AUTH_MFP: return 0; default: return -EOPNOTSUPP; } } static int cfg80211_wext_giwauth(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { /* XXX: what do we need? */ return -EOPNOTSUPP; } static int cfg80211_wext_siwpower(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *wrq = &wrqu->power; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); bool ps; int timeout = wdev->ps_timeout; int err; if (wdev->iftype != NL80211_IFTYPE_STATION) return -EINVAL; if (!rdev->ops->set_power_mgmt) return -EOPNOTSUPP; if (wrq->disabled) { ps = false; } else { switch (wrq->flags & IW_POWER_MODE) { case IW_POWER_ON: /* If not specified */ case IW_POWER_MODE: /* If set all mask */ case IW_POWER_ALL_R: /* If explicitly state all */ ps = true; break; default: /* Otherwise we ignore */ return -EINVAL; } if (wrq->flags & ~(IW_POWER_MODE | IW_POWER_TIMEOUT)) return -EINVAL; if (wrq->flags & IW_POWER_TIMEOUT) timeout = wrq->value / 1000; } wiphy_lock(&rdev->wiphy); err = rdev_set_power_mgmt(rdev, dev, ps, timeout); wiphy_unlock(&rdev->wiphy); if (err) return err; wdev->ps = ps; wdev->ps_timeout = timeout; return 0; } static int cfg80211_wext_giwpower(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *wrq = &wrqu->power; struct wireless_dev *wdev = dev->ieee80211_ptr; wrq->disabled = !wdev->ps; return 0; } static int cfg80211_wext_siwrate(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *rate = &wrqu->bitrate; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_bitrate_mask mask; u32 fixed, maxrate; struct ieee80211_supported_band *sband; int band, ridx, ret; bool match = false; if (!rdev->ops->set_bitrate_mask) return -EOPNOTSUPP; memset(&mask, 0, sizeof(mask)); fixed = 0; maxrate = (u32)-1; if (rate->value < 0) { /* nothing */ } else if (rate->fixed) { fixed = rate->value / 100000; } else { maxrate = rate->value / 100000; } for (band = 0; band < NUM_NL80211_BANDS; band++) { sband = wdev->wiphy->bands[band]; if (sband == NULL) continue; for (ridx = 0; ridx < sband->n_bitrates; ridx++) { struct ieee80211_rate *srate = &sband->bitrates[ridx]; if (fixed == srate->bitrate) { mask.control[band].legacy = 1 << ridx; match = true; break; } if (srate->bitrate <= maxrate) { mask.control[band].legacy |= 1 << ridx; match = true; } } } if (!match) return -EINVAL; wiphy_lock(&rdev->wiphy); if (dev->ieee80211_ptr->valid_links) ret = -EOPNOTSUPP; else ret = rdev_set_bitrate_mask(rdev, dev, 0, NULL, &mask); wiphy_unlock(&rdev->wiphy); return ret; } static int cfg80211_wext_giwrate(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *rate = &wrqu->bitrate; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct station_info sinfo = {}; u8 addr[ETH_ALEN]; int err; if (wdev->iftype != NL80211_IFTYPE_STATION) return -EOPNOTSUPP; if (!rdev->ops->get_station) return -EOPNOTSUPP; err = 0; if (!wdev->valid_links && wdev->links[0].client.current_bss) memcpy(addr, wdev->links[0].client.current_bss->pub.bssid, ETH_ALEN); else err = -EOPNOTSUPP; if (err) return err; wiphy_lock(&rdev->wiphy); err = rdev_get_station(rdev, dev, addr, &sinfo); wiphy_unlock(&rdev->wiphy); if (err) return err; if (!(sinfo.filled & BIT_ULL(NL80211_STA_INFO_TX_BITRATE))) { err = -EOPNOTSUPP; goto free; } rate->value = 100000 * cfg80211_calculate_bitrate(&sinfo.txrate); free: cfg80211_sinfo_release_content(&sinfo); return err; } /* Get wireless statistics. Called by /proc/net/wireless and by SIOCGIWSTATS */ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); /* we are under RTNL - globally locked - so can use static structs */ static struct iw_statistics wstats; static struct station_info sinfo = {}; u8 bssid[ETH_ALEN]; int ret; if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION) return NULL; if (!rdev->ops->get_station) return NULL; /* Grab BSSID of current BSS, if any */ wiphy_lock(&rdev->wiphy); if (wdev->valid_links || !wdev->links[0].client.current_bss) { wiphy_unlock(&rdev->wiphy); return NULL; } memcpy(bssid, wdev->links[0].client.current_bss->pub.bssid, ETH_ALEN); memset(&sinfo, 0, sizeof(sinfo)); ret = rdev_get_station(rdev, dev, bssid, &sinfo); wiphy_unlock(&rdev->wiphy); if (ret) return NULL; memset(&wstats, 0, sizeof(wstats)); switch (rdev->wiphy.signal_type) { case CFG80211_SIGNAL_TYPE_MBM: if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_SIGNAL)) { int sig = sinfo.signal; wstats.qual.updated |= IW_QUAL_LEVEL_UPDATED; wstats.qual.updated |= IW_QUAL_QUAL_UPDATED; wstats.qual.updated |= IW_QUAL_DBM; wstats.qual.level = sig; if (sig < -110) sig = -110; else if (sig > -40) sig = -40; wstats.qual.qual = sig + 110; break; } fallthrough; case CFG80211_SIGNAL_TYPE_UNSPEC: if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_SIGNAL)) { wstats.qual.updated |= IW_QUAL_LEVEL_UPDATED; wstats.qual.updated |= IW_QUAL_QUAL_UPDATED; wstats.qual.level = sinfo.signal; wstats.qual.qual = sinfo.signal; break; } fallthrough; default: wstats.qual.updated |= IW_QUAL_LEVEL_INVALID; wstats.qual.updated |= IW_QUAL_QUAL_INVALID; } wstats.qual.updated |= IW_QUAL_NOISE_INVALID; if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_RX_DROP_MISC)) wstats.discard.misc = sinfo.rx_dropped_misc; if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_TX_FAILED)) wstats.discard.retries = sinfo.tx_failed; cfg80211_sinfo_release_content(&sinfo); return &wstats; } static int cfg80211_wext_siwap(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct sockaddr *ap_addr = &wrqu->ap_addr; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int ret; wiphy_lock(&rdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: ret = cfg80211_ibss_wext_siwap(dev, info, ap_addr, extra); break; case NL80211_IFTYPE_STATION: ret = cfg80211_mgd_wext_siwap(dev, info, ap_addr, extra); break; default: ret = -EOPNOTSUPP; break; } wiphy_unlock(&rdev->wiphy); return ret; } static int cfg80211_wext_giwap(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct sockaddr *ap_addr = &wrqu->ap_addr; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int ret; wiphy_lock(&rdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: ret = cfg80211_ibss_wext_giwap(dev, info, ap_addr, extra); break; case NL80211_IFTYPE_STATION: ret = cfg80211_mgd_wext_giwap(dev, info, ap_addr, extra); break; default: ret = -EOPNOTSUPP; break; } wiphy_unlock(&rdev->wiphy); return ret; } static int cfg80211_wext_siwessid(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *ssid) { struct iw_point *data = &wrqu->data; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int ret; wiphy_lock(&rdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: ret = cfg80211_ibss_wext_siwessid(dev, info, data, ssid); break; case NL80211_IFTYPE_STATION: ret = cfg80211_mgd_wext_siwessid(dev, info, data, ssid); break; default: ret = -EOPNOTSUPP; break; } wiphy_unlock(&rdev->wiphy); return ret; } static int cfg80211_wext_giwessid(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *ssid) { struct iw_point *data = &wrqu->data; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int ret; data->flags = 0; data->length = 0; wiphy_lock(&rdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: ret = cfg80211_ibss_wext_giwessid(dev, info, data, ssid); break; case NL80211_IFTYPE_STATION: ret = cfg80211_mgd_wext_giwessid(dev, info, data, ssid); break; default: ret = -EOPNOTSUPP; break; } wiphy_unlock(&rdev->wiphy); return ret; } static int cfg80211_wext_siwpmksa(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_pmksa cfg_pmksa; struct iw_pmksa *pmksa = (struct iw_pmksa *)extra; int ret; memset(&cfg_pmksa, 0, sizeof(struct cfg80211_pmksa)); if (wdev->iftype != NL80211_IFTYPE_STATION) return -EINVAL; cfg_pmksa.bssid = pmksa->bssid.sa_data; cfg_pmksa.pmkid = pmksa->pmkid; wiphy_lock(&rdev->wiphy); switch (pmksa->cmd) { case IW_PMKSA_ADD: if (!rdev->ops->set_pmksa) { ret = -EOPNOTSUPP; break; } ret = rdev_set_pmksa(rdev, dev, &cfg_pmksa); break; case IW_PMKSA_REMOVE: if (!rdev->ops->del_pmksa) { ret = -EOPNOTSUPP; break; } ret = rdev_del_pmksa(rdev, dev, &cfg_pmksa); break; case IW_PMKSA_FLUSH: if (!rdev->ops->flush_pmksa) { ret = -EOPNOTSUPP; break; } ret = rdev_flush_pmksa(rdev, dev); break; default: ret = -EOPNOTSUPP; break; } wiphy_unlock(&rdev->wiphy); return ret; } static const iw_handler cfg80211_handlers[] = { IW_HANDLER(SIOCGIWNAME, cfg80211_wext_giwname), IW_HANDLER(SIOCSIWFREQ, cfg80211_wext_siwfreq), IW_HANDLER(SIOCGIWFREQ, cfg80211_wext_giwfreq), IW_HANDLER(SIOCSIWMODE, cfg80211_wext_siwmode), IW_HANDLER(SIOCGIWMODE, cfg80211_wext_giwmode), IW_HANDLER(SIOCGIWRANGE, cfg80211_wext_giwrange), IW_HANDLER(SIOCSIWAP, cfg80211_wext_siwap), IW_HANDLER(SIOCGIWAP, cfg80211_wext_giwap), IW_HANDLER(SIOCSIWMLME, cfg80211_wext_siwmlme), IW_HANDLER(SIOCSIWSCAN, cfg80211_wext_siwscan), IW_HANDLER(SIOCGIWSCAN, cfg80211_wext_giwscan), IW_HANDLER(SIOCSIWESSID, cfg80211_wext_siwessid), IW_HANDLER(SIOCGIWESSID, cfg80211_wext_giwessid), IW_HANDLER(SIOCSIWRATE, cfg80211_wext_siwrate), IW_HANDLER(SIOCGIWRATE, cfg80211_wext_giwrate), IW_HANDLER(SIOCSIWRTS, cfg80211_wext_siwrts), IW_HANDLER(SIOCGIWRTS, cfg80211_wext_giwrts), IW_HANDLER(SIOCSIWFRAG, cfg80211_wext_siwfrag), IW_HANDLER(SIOCGIWFRAG, cfg80211_wext_giwfrag), IW_HANDLER(SIOCSIWTXPOW, cfg80211_wext_siwtxpower), IW_HANDLER(SIOCGIWTXPOW, cfg80211_wext_giwtxpower), IW_HANDLER(SIOCSIWRETRY, cfg80211_wext_siwretry), IW_HANDLER(SIOCGIWRETRY, cfg80211_wext_giwretry), IW_HANDLER(SIOCSIWENCODE, cfg80211_wext_siwencode), IW_HANDLER(SIOCGIWENCODE, cfg80211_wext_giwencode), IW_HANDLER(SIOCSIWPOWER, cfg80211_wext_siwpower), IW_HANDLER(SIOCGIWPOWER, cfg80211_wext_giwpower), IW_HANDLER(SIOCSIWGENIE, cfg80211_wext_siwgenie), IW_HANDLER(SIOCSIWAUTH, cfg80211_wext_siwauth), IW_HANDLER(SIOCGIWAUTH, cfg80211_wext_giwauth), IW_HANDLER(SIOCSIWENCODEEXT, cfg80211_wext_siwencodeext), IW_HANDLER(SIOCSIWPMKSA, cfg80211_wext_siwpmksa), }; const struct iw_handler_def cfg80211_wext_handler = { .num_standard = ARRAY_SIZE(cfg80211_handlers), .standard = cfg80211_handlers, .get_wireless_stats = cfg80211_wireless_stats, }; |
| 1 2 1 1 1 1 1 5 1 1 1 1 1 2 2 7 2 1 3 2 9 9 9 3 9 2 2 543 1 544 538 540 2 1 8 7 11 11 3 1 1 1 1 3 1 1 1 2 2 2 2 2 456 453 182 196 439 440 301 302 302 286 287 286 882 440 440 881 524 538 192 171 25 215 24 182 16 16 16 2 2 14 1 1 5 8 1 1 1 26 1 1 1 1 1 1 1 1 1 17 17 1 2 1 1 5 1 1 1 1 15 14 2 10 7 3 13 13 3 2 8 2 6 6 1 4 16 3 2 7 1 1 7 2 4 4 4 21 21 5 2 1 2 2 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/types.h> #include <linux/skbuff.h> #include <linux/socket.h> #include <linux/sysctl.h> #include <linux/net.h> #include <linux/module.h> #include <linux/if_arp.h> #include <linux/ipv6.h> #include <linux/mpls.h> #include <linux/netconf.h> #include <linux/nospec.h> #include <linux/vmalloc.h> #include <linux/percpu.h> #include <net/gso.h> #include <net/ip.h> #include <net/dst.h> #include <net/sock.h> #include <net/arp.h> #include <net/ip_fib.h> #include <net/netevent.h> #include <net/ip_tunnels.h> #include <net/netns/generic.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> #endif #include <net/ipv6_stubs.h> #include <net/rtnh.h> #include "internal.h" /* max memory we will use for mpls_route */ #define MAX_MPLS_ROUTE_MEM 4096 /* Maximum number of labels to look ahead at when selecting a path of * a multipath route */ #define MAX_MP_SELECT_LABELS 4 #define MPLS_NEIGH_TABLE_UNSPEC (NEIGH_LINK_TABLE + 1) static int label_limit = (1 << 20) - 1; static int ttl_max = 255; #if IS_ENABLED(CONFIG_NET_IP_TUNNEL) static size_t ipgre_mpls_encap_hlen(struct ip_tunnel_encap *e) { return sizeof(struct mpls_shim_hdr); } static const struct ip_tunnel_encap_ops mpls_iptun_ops = { .encap_hlen = ipgre_mpls_encap_hlen, }; static int ipgre_tunnel_encap_add_mpls_ops(void) { return ip_tunnel_encap_add_ops(&mpls_iptun_ops, TUNNEL_ENCAP_MPLS); } static void ipgre_tunnel_encap_del_mpls_ops(void) { ip_tunnel_encap_del_ops(&mpls_iptun_ops, TUNNEL_ENCAP_MPLS); } #else static int ipgre_tunnel_encap_add_mpls_ops(void) { return 0; } static void ipgre_tunnel_encap_del_mpls_ops(void) { } #endif static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt, struct nlmsghdr *nlh, struct net *net, u32 portid, unsigned int nlm_flags); static struct mpls_route *mpls_route_input_rcu(struct net *net, unsigned index) { struct mpls_route *rt = NULL; if (index < net->mpls.platform_labels) { struct mpls_route __rcu **platform_label = rcu_dereference(net->mpls.platform_label); rt = rcu_dereference(platform_label[index]); } return rt; } bool mpls_output_possible(const struct net_device *dev) { return dev && (dev->flags & IFF_UP) && netif_carrier_ok(dev); } EXPORT_SYMBOL_GPL(mpls_output_possible); static u8 *__mpls_nh_via(struct mpls_route *rt, struct mpls_nh *nh) { return (u8 *)nh + rt->rt_via_offset; } static const u8 *mpls_nh_via(const struct mpls_route *rt, const struct mpls_nh *nh) { return __mpls_nh_via((struct mpls_route *)rt, (struct mpls_nh *)nh); } static unsigned int mpls_nh_header_size(const struct mpls_nh *nh) { /* The size of the layer 2.5 labels to be added for this route */ return nh->nh_labels * sizeof(struct mpls_shim_hdr); } unsigned int mpls_dev_mtu(const struct net_device *dev) { /* The amount of data the layer 2 frame can hold */ return dev->mtu; } EXPORT_SYMBOL_GPL(mpls_dev_mtu); bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) { if (skb->len <= mtu) return false; if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; } EXPORT_SYMBOL_GPL(mpls_pkt_too_big); void mpls_stats_inc_outucastpkts(struct net_device *dev, const struct sk_buff *skb) { struct mpls_dev *mdev; if (skb->protocol == htons(ETH_P_MPLS_UC)) { mdev = mpls_dev_get(dev); if (mdev) MPLS_INC_STATS_LEN(mdev, skb->len, tx_packets, tx_bytes); } else if (skb->protocol == htons(ETH_P_IP)) { IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUT, skb->len); #if IS_ENABLED(CONFIG_IPV6) } else if (skb->protocol == htons(ETH_P_IPV6)) { struct inet6_dev *in6dev = __in6_dev_get(dev); if (in6dev) IP6_UPD_PO_STATS(dev_net(dev), in6dev, IPSTATS_MIB_OUT, skb->len); #endif } } EXPORT_SYMBOL_GPL(mpls_stats_inc_outucastpkts); static u32 mpls_multipath_hash(struct mpls_route *rt, struct sk_buff *skb) { struct mpls_entry_decoded dec; unsigned int mpls_hdr_len = 0; struct mpls_shim_hdr *hdr; bool eli_seen = false; int label_index; u32 hash = 0; for (label_index = 0; label_index < MAX_MP_SELECT_LABELS; label_index++) { mpls_hdr_len += sizeof(*hdr); if (!pskb_may_pull(skb, mpls_hdr_len)) break; /* Read and decode the current label */ hdr = mpls_hdr(skb) + label_index; dec = mpls_entry_decode(hdr); /* RFC6790 - reserved labels MUST NOT be used as keys * for the load-balancing function */ if (likely(dec.label >= MPLS_LABEL_FIRST_UNRESERVED)) { hash = jhash_1word(dec.label, hash); /* The entropy label follows the entropy label * indicator, so this means that the entropy * label was just added to the hash - no need to * go any deeper either in the label stack or in the * payload */ if (eli_seen) break; } else if (dec.label == MPLS_LABEL_ENTROPY) { eli_seen = true; } if (!dec.bos) continue; /* found bottom label; does skb have room for a header? */ if (pskb_may_pull(skb, mpls_hdr_len + sizeof(struct iphdr))) { const struct iphdr *v4hdr; v4hdr = (const struct iphdr *)(hdr + 1); if (v4hdr->version == 4) { hash = jhash_3words(ntohl(v4hdr->saddr), ntohl(v4hdr->daddr), v4hdr->protocol, hash); } else if (v4hdr->version == 6 && pskb_may_pull(skb, mpls_hdr_len + sizeof(struct ipv6hdr))) { const struct ipv6hdr *v6hdr; v6hdr = (const struct ipv6hdr *)(hdr + 1); hash = __ipv6_addr_jhash(&v6hdr->saddr, hash); hash = __ipv6_addr_jhash(&v6hdr->daddr, hash); hash = jhash_1word(v6hdr->nexthdr, hash); } } break; } return hash; } static struct mpls_nh *mpls_get_nexthop(struct mpls_route *rt, u8 index) { return (struct mpls_nh *)((u8 *)rt->rt_nh + index * rt->rt_nh_size); } /* number of alive nexthops (rt->rt_nhn_alive) and the flags for * a next hop (nh->nh_flags) are modified by netdev event handlers. * Since those fields can change at any moment, use READ_ONCE to * access both. */ static const struct mpls_nh *mpls_select_multipath(struct mpls_route *rt, struct sk_buff *skb) { u32 hash = 0; int nh_index = 0; int n = 0; u8 alive; /* No need to look further into packet if there's only * one path */ if (rt->rt_nhn == 1) return rt->rt_nh; alive = READ_ONCE(rt->rt_nhn_alive); if (alive == 0) return NULL; hash = mpls_multipath_hash(rt, skb); nh_index = hash % alive; if (alive == rt->rt_nhn) goto out; for_nexthops(rt) { unsigned int nh_flags = READ_ONCE(nh->nh_flags); if (nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) continue; if (n == nh_index) return nh; n++; } endfor_nexthops(rt); out: return mpls_get_nexthop(rt, nh_index); } static bool mpls_egress(struct net *net, struct mpls_route *rt, struct sk_buff *skb, struct mpls_entry_decoded dec) { enum mpls_payload_type payload_type; bool success = false; /* The IPv4 code below accesses through the IPv4 header * checksum, which is 12 bytes into the packet. * The IPv6 code below accesses through the IPv6 hop limit * which is 8 bytes into the packet. * * For all supported cases there should always be at least 12 * bytes of packet data present. The IPv4 header is 20 bytes * without options and the IPv6 header is always 40 bytes * long. */ if (!pskb_may_pull(skb, 12)) return false; payload_type = rt->rt_payload_type; if (payload_type == MPT_UNSPEC) payload_type = ip_hdr(skb)->version; switch (payload_type) { case MPT_IPV4: { struct iphdr *hdr4 = ip_hdr(skb); u8 new_ttl; skb->protocol = htons(ETH_P_IP); /* If propagating TTL, take the decremented TTL from * the incoming MPLS header, otherwise decrement the * TTL, but only if not 0 to avoid underflow. */ if (rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED || (rt->rt_ttl_propagate == MPLS_TTL_PROP_DEFAULT && net->mpls.ip_ttl_propagate)) new_ttl = dec.ttl; else new_ttl = hdr4->ttl ? hdr4->ttl - 1 : 0; csum_replace2(&hdr4->check, htons(hdr4->ttl << 8), htons(new_ttl << 8)); hdr4->ttl = new_ttl; success = true; break; } case MPT_IPV6: { struct ipv6hdr *hdr6 = ipv6_hdr(skb); skb->protocol = htons(ETH_P_IPV6); /* If propagating TTL, take the decremented TTL from * the incoming MPLS header, otherwise decrement the * hop limit, but only if not 0 to avoid underflow. */ if (rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED || (rt->rt_ttl_propagate == MPLS_TTL_PROP_DEFAULT && net->mpls.ip_ttl_propagate)) hdr6->hop_limit = dec.ttl; else if (hdr6->hop_limit) hdr6->hop_limit = hdr6->hop_limit - 1; success = true; break; } case MPT_UNSPEC: /* Should have decided which protocol it is by now */ break; } return success; } static int mpls_forward(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct net *net = dev_net(dev); struct mpls_shim_hdr *hdr; const struct mpls_nh *nh; struct mpls_route *rt; struct mpls_entry_decoded dec; struct net_device *out_dev; struct mpls_dev *out_mdev; struct mpls_dev *mdev; unsigned int hh_len; unsigned int new_header_size; unsigned int mtu; int err; /* Careful this entire function runs inside of an rcu critical section */ mdev = mpls_dev_get(dev); if (!mdev) goto drop; MPLS_INC_STATS_LEN(mdev, skb->len, rx_packets, rx_bytes); if (!mdev->input_enabled) { MPLS_INC_STATS(mdev, rx_dropped); goto drop; } if (skb->pkt_type != PACKET_HOST) goto err; if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) goto err; if (!pskb_may_pull(skb, sizeof(*hdr))) goto err; skb_dst_drop(skb); /* Read and decode the label */ hdr = mpls_hdr(skb); dec = mpls_entry_decode(hdr); rt = mpls_route_input_rcu(net, dec.label); if (!rt) { MPLS_INC_STATS(mdev, rx_noroute); goto drop; } nh = mpls_select_multipath(rt, skb); if (!nh) goto err; /* Pop the label */ skb_pull(skb, sizeof(*hdr)); skb_reset_network_header(skb); skb_orphan(skb); if (skb_warn_if_lro(skb)) goto err; skb_forward_csum(skb); /* Verify ttl is valid */ if (dec.ttl <= 1) goto err; /* Find the output device */ out_dev = nh->nh_dev; if (!mpls_output_possible(out_dev)) goto tx_err; /* Verify the destination can hold the packet */ new_header_size = mpls_nh_header_size(nh); mtu = mpls_dev_mtu(out_dev); if (mpls_pkt_too_big(skb, mtu - new_header_size)) goto tx_err; hh_len = LL_RESERVED_SPACE(out_dev); if (!out_dev->header_ops) hh_len = 0; /* Ensure there is enough space for the headers in the skb */ if (skb_cow(skb, hh_len + new_header_size)) goto tx_err; skb->dev = out_dev; skb->protocol = htons(ETH_P_MPLS_UC); dec.ttl -= 1; if (unlikely(!new_header_size && dec.bos)) { /* Penultimate hop popping */ if (!mpls_egress(dev_net(out_dev), rt, skb, dec)) goto err; } else { bool bos; int i; skb_push(skb, new_header_size); skb_reset_network_header(skb); /* Push the new labels */ hdr = mpls_hdr(skb); bos = dec.bos; for (i = nh->nh_labels - 1; i >= 0; i--) { hdr[i] = mpls_entry_encode(nh->nh_label[i], dec.ttl, 0, bos); bos = false; } } mpls_stats_inc_outucastpkts(out_dev, skb); /* If via wasn't specified then send out using device address */ if (nh->nh_via_table == MPLS_NEIGH_TABLE_UNSPEC) err = neigh_xmit(NEIGH_LINK_TABLE, out_dev, out_dev->dev_addr, skb); else err = neigh_xmit(nh->nh_via_table, out_dev, mpls_nh_via(rt, nh), skb); if (err) net_dbg_ratelimited("%s: packet transmission failed: %d\n", __func__, err); return 0; tx_err: out_mdev = out_dev ? mpls_dev_get(out_dev) : NULL; if (out_mdev) MPLS_INC_STATS(out_mdev, tx_errors); goto drop; err: MPLS_INC_STATS(mdev, rx_errors); drop: kfree_skb(skb); return NET_RX_DROP; } static struct packet_type mpls_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_MPLS_UC), .func = mpls_forward, }; static const struct nla_policy rtm_mpls_policy[RTA_MAX+1] = { [RTA_DST] = { .type = NLA_U32 }, [RTA_OIF] = { .type = NLA_U32 }, [RTA_TTL_PROPAGATE] = { .type = NLA_U8 }, }; struct mpls_route_config { u32 rc_protocol; u32 rc_ifindex; u8 rc_via_table; u8 rc_via_alen; u8 rc_via[MAX_VIA_ALEN]; u32 rc_label; u8 rc_ttl_propagate; u8 rc_output_labels; u32 rc_output_label[MAX_NEW_LABELS]; u32 rc_nlflags; enum mpls_payload_type rc_payload_type; struct nl_info rc_nlinfo; struct rtnexthop *rc_mp; int rc_mp_len; }; /* all nexthops within a route have the same size based on max * number of labels and max via length for a hop */ static struct mpls_route *mpls_rt_alloc(u8 num_nh, u8 max_alen, u8 max_labels) { u8 nh_size = MPLS_NH_SIZE(max_labels, max_alen); struct mpls_route *rt; size_t size; size = sizeof(*rt) + num_nh * nh_size; if (size > MAX_MPLS_ROUTE_MEM) return ERR_PTR(-EINVAL); rt = kzalloc(size, GFP_KERNEL); if (!rt) return ERR_PTR(-ENOMEM); rt->rt_nhn = num_nh; rt->rt_nhn_alive = num_nh; rt->rt_nh_size = nh_size; rt->rt_via_offset = MPLS_NH_VIA_OFF(max_labels); return rt; } static void mpls_rt_free(struct mpls_route *rt) { if (rt) kfree_rcu(rt, rt_rcu); } static void mpls_notify_route(struct net *net, unsigned index, struct mpls_route *old, struct mpls_route *new, const struct nl_info *info) { struct nlmsghdr *nlh = info ? info->nlh : NULL; unsigned portid = info ? info->portid : 0; int event = new ? RTM_NEWROUTE : RTM_DELROUTE; struct mpls_route *rt = new ? new : old; unsigned nlm_flags = (old && new) ? NLM_F_REPLACE : 0; /* Ignore reserved labels for now */ if (rt && (index >= MPLS_LABEL_FIRST_UNRESERVED)) rtmsg_lfib(event, index, rt, nlh, net, portid, nlm_flags); } static void mpls_route_update(struct net *net, unsigned index, struct mpls_route *new, const struct nl_info *info) { struct mpls_route __rcu **platform_label; struct mpls_route *rt; ASSERT_RTNL(); platform_label = rtnl_dereference(net->mpls.platform_label); rt = rtnl_dereference(platform_label[index]); rcu_assign_pointer(platform_label[index], new); mpls_notify_route(net, index, rt, new, info); /* If we removed a route free it now */ mpls_rt_free(rt); } static unsigned find_free_label(struct net *net) { struct mpls_route __rcu **platform_label; size_t platform_labels; unsigned index; platform_label = rtnl_dereference(net->mpls.platform_label); platform_labels = net->mpls.platform_labels; for (index = MPLS_LABEL_FIRST_UNRESERVED; index < platform_labels; index++) { if (!rtnl_dereference(platform_label[index])) return index; } return LABEL_NOT_SPECIFIED; } #if IS_ENABLED(CONFIG_INET) static struct net_device *inet_fib_lookup_dev(struct net *net, const void *addr) { struct net_device *dev; struct rtable *rt; struct in_addr daddr; memcpy(&daddr, addr, sizeof(struct in_addr)); rt = ip_route_output(net, daddr.s_addr, 0, 0, 0, RT_SCOPE_UNIVERSE); if (IS_ERR(rt)) return ERR_CAST(rt); dev = rt->dst.dev; dev_hold(dev); ip_rt_put(rt); return dev; } #else static struct net_device *inet_fib_lookup_dev(struct net *net, const void *addr) { return ERR_PTR(-EAFNOSUPPORT); } #endif #if IS_ENABLED(CONFIG_IPV6) static struct net_device *inet6_fib_lookup_dev(struct net *net, const void *addr) { struct net_device *dev; struct dst_entry *dst; struct flowi6 fl6; if (!ipv6_stub) return ERR_PTR(-EAFNOSUPPORT); memset(&fl6, 0, sizeof(fl6)); memcpy(&fl6.daddr, addr, sizeof(struct in6_addr)); dst = ipv6_stub->ipv6_dst_lookup_flow(net, NULL, &fl6, NULL); if (IS_ERR(dst)) return ERR_CAST(dst); dev = dst->dev; dev_hold(dev); dst_release(dst); return dev; } #else static struct net_device *inet6_fib_lookup_dev(struct net *net, const void *addr) { return ERR_PTR(-EAFNOSUPPORT); } #endif static struct net_device *find_outdev(struct net *net, struct mpls_route *rt, struct mpls_nh *nh, int oif) { struct net_device *dev = NULL; if (!oif) { switch (nh->nh_via_table) { case NEIGH_ARP_TABLE: dev = inet_fib_lookup_dev(net, mpls_nh_via(rt, nh)); break; case NEIGH_ND_TABLE: dev = inet6_fib_lookup_dev(net, mpls_nh_via(rt, nh)); break; case NEIGH_LINK_TABLE: break; } } else { dev = dev_get_by_index(net, oif); } if (!dev) return ERR_PTR(-ENODEV); if (IS_ERR(dev)) return dev; /* The caller is holding rtnl anyways, so release the dev reference */ dev_put(dev); return dev; } static int mpls_nh_assign_dev(struct net *net, struct mpls_route *rt, struct mpls_nh *nh, int oif) { struct net_device *dev = NULL; int err = -ENODEV; dev = find_outdev(net, rt, nh, oif); if (IS_ERR(dev)) { err = PTR_ERR(dev); dev = NULL; goto errout; } /* Ensure this is a supported device */ err = -EINVAL; if (!mpls_dev_get(dev)) goto errout; if ((nh->nh_via_table == NEIGH_LINK_TABLE) && (dev->addr_len != nh->nh_via_alen)) goto errout; nh->nh_dev = dev; if (!(dev->flags & IFF_UP)) { nh->nh_flags |= RTNH_F_DEAD; } else { unsigned int flags; flags = dev_get_flags(dev); if (!(flags & (IFF_RUNNING | IFF_LOWER_UP))) nh->nh_flags |= RTNH_F_LINKDOWN; } return 0; errout: return err; } static int nla_get_via(const struct nlattr *nla, u8 *via_alen, u8 *via_table, u8 via_addr[], struct netlink_ext_ack *extack) { struct rtvia *via = nla_data(nla); int err = -EINVAL; int alen; if (nla_len(nla) < offsetof(struct rtvia, rtvia_addr)) { NL_SET_ERR_MSG_ATTR(extack, nla, "Invalid attribute length for RTA_VIA"); goto errout; } alen = nla_len(nla) - offsetof(struct rtvia, rtvia_addr); if (alen > MAX_VIA_ALEN) { NL_SET_ERR_MSG_ATTR(extack, nla, "Invalid address length for RTA_VIA"); goto errout; } /* Validate the address family */ switch (via->rtvia_family) { case AF_PACKET: *via_table = NEIGH_LINK_TABLE; break; case AF_INET: *via_table = NEIGH_ARP_TABLE; if (alen != 4) goto errout; break; case AF_INET6: *via_table = NEIGH_ND_TABLE; if (alen != 16) goto errout; break; default: /* Unsupported address family */ goto errout; } memcpy(via_addr, via->rtvia_addr, alen); *via_alen = alen; err = 0; errout: return err; } static int mpls_nh_build_from_cfg(struct mpls_route_config *cfg, struct mpls_route *rt) { struct net *net = cfg->rc_nlinfo.nl_net; struct mpls_nh *nh = rt->rt_nh; int err; int i; if (!nh) return -ENOMEM; nh->nh_labels = cfg->rc_output_labels; for (i = 0; i < nh->nh_labels; i++) nh->nh_label[i] = cfg->rc_output_label[i]; nh->nh_via_table = cfg->rc_via_table; memcpy(__mpls_nh_via(rt, nh), cfg->rc_via, cfg->rc_via_alen); nh->nh_via_alen = cfg->rc_via_alen; err = mpls_nh_assign_dev(net, rt, nh, cfg->rc_ifindex); if (err) goto errout; if (nh->nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) rt->rt_nhn_alive--; return 0; errout: return err; } static int mpls_nh_build(struct net *net, struct mpls_route *rt, struct mpls_nh *nh, int oif, struct nlattr *via, struct nlattr *newdst, u8 max_labels, struct netlink_ext_ack *extack) { int err = -ENOMEM; if (!nh) goto errout; if (newdst) { err = nla_get_labels(newdst, max_labels, &nh->nh_labels, nh->nh_label, extack); if (err) goto errout; } if (via) { err = nla_get_via(via, &nh->nh_via_alen, &nh->nh_via_table, __mpls_nh_via(rt, nh), extack); if (err) goto errout; } else { nh->nh_via_table = MPLS_NEIGH_TABLE_UNSPEC; } err = mpls_nh_assign_dev(net, rt, nh, oif); if (err) goto errout; return 0; errout: return err; } static u8 mpls_count_nexthops(struct rtnexthop *rtnh, int len, u8 cfg_via_alen, u8 *max_via_alen, u8 *max_labels) { int remaining = len; u8 nhs = 0; *max_via_alen = 0; *max_labels = 0; while (rtnh_ok(rtnh, remaining)) { struct nlattr *nla, *attrs = rtnh_attrs(rtnh); int attrlen; u8 n_labels = 0; attrlen = rtnh_attrlen(rtnh); nla = nla_find(attrs, attrlen, RTA_VIA); if (nla && nla_len(nla) >= offsetof(struct rtvia, rtvia_addr)) { int via_alen = nla_len(nla) - offsetof(struct rtvia, rtvia_addr); if (via_alen <= MAX_VIA_ALEN) *max_via_alen = max_t(u16, *max_via_alen, via_alen); } nla = nla_find(attrs, attrlen, RTA_NEWDST); if (nla && nla_get_labels(nla, MAX_NEW_LABELS, &n_labels, NULL, NULL) != 0) return 0; *max_labels = max_t(u8, *max_labels, n_labels); /* number of nexthops is tracked by a u8. * Check for overflow. */ if (nhs == 255) return 0; nhs++; rtnh = rtnh_next(rtnh, &remaining); } /* leftover implies invalid nexthop configuration, discard it */ return remaining > 0 ? 0 : nhs; } static int mpls_nh_build_multi(struct mpls_route_config *cfg, struct mpls_route *rt, u8 max_labels, struct netlink_ext_ack *extack) { struct rtnexthop *rtnh = cfg->rc_mp; struct nlattr *nla_via, *nla_newdst; int remaining = cfg->rc_mp_len; int err = 0; u8 nhs = 0; change_nexthops(rt) { int attrlen; nla_via = NULL; nla_newdst = NULL; err = -EINVAL; if (!rtnh_ok(rtnh, remaining)) goto errout; /* neither weighted multipath nor any flags * are supported */ if (rtnh->rtnh_hops || rtnh->rtnh_flags) goto errout; attrlen = rtnh_attrlen(rtnh); if (attrlen > 0) { struct nlattr *attrs = rtnh_attrs(rtnh); nla_via = nla_find(attrs, attrlen, RTA_VIA); nla_newdst = nla_find(attrs, attrlen, RTA_NEWDST); } err = mpls_nh_build(cfg->rc_nlinfo.nl_net, rt, nh, rtnh->rtnh_ifindex, nla_via, nla_newdst, max_labels, extack); if (err) goto errout; if (nh->nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) rt->rt_nhn_alive--; rtnh = rtnh_next(rtnh, &remaining); nhs++; } endfor_nexthops(rt); rt->rt_nhn = nhs; return 0; errout: return err; } static bool mpls_label_ok(struct net *net, unsigned int *index, struct netlink_ext_ack *extack) { bool is_ok = true; /* Reserved labels may not be set */ if (*index < MPLS_LABEL_FIRST_UNRESERVED) { NL_SET_ERR_MSG(extack, "Invalid label - must be MPLS_LABEL_FIRST_UNRESERVED or higher"); is_ok = false; } /* The full 20 bit range may not be supported. */ if (is_ok && *index >= net->mpls.platform_labels) { NL_SET_ERR_MSG(extack, "Label >= configured maximum in platform_labels"); is_ok = false; } *index = array_index_nospec(*index, net->mpls.platform_labels); return is_ok; } static int mpls_route_add(struct mpls_route_config *cfg, struct netlink_ext_ack *extack) { struct mpls_route __rcu **platform_label; struct net *net = cfg->rc_nlinfo.nl_net; struct mpls_route *rt, *old; int err = -EINVAL; u8 max_via_alen; unsigned index; u8 max_labels; u8 nhs; index = cfg->rc_label; /* If a label was not specified during insert pick one */ if ((index == LABEL_NOT_SPECIFIED) && (cfg->rc_nlflags & NLM_F_CREATE)) { index = find_free_label(net); } if (!mpls_label_ok(net, &index, extack)) goto errout; /* Append makes no sense with mpls */ err = -EOPNOTSUPP; if (cfg->rc_nlflags & NLM_F_APPEND) { NL_SET_ERR_MSG(extack, "MPLS does not support route append"); goto errout; } err = -EEXIST; platform_label = rtnl_dereference(net->mpls.platform_label); old = rtnl_dereference(platform_label[index]); if ((cfg->rc_nlflags & NLM_F_EXCL) && old) goto errout; err = -EEXIST; if (!(cfg->rc_nlflags & NLM_F_REPLACE) && old) goto errout; err = -ENOENT; if (!(cfg->rc_nlflags & NLM_F_CREATE) && !old) goto errout; err = -EINVAL; if (cfg->rc_mp) { nhs = mpls_count_nexthops(cfg->rc_mp, cfg->rc_mp_len, cfg->rc_via_alen, &max_via_alen, &max_labels); } else { max_via_alen = cfg->rc_via_alen; max_labels = cfg->rc_output_labels; nhs = 1; } if (nhs == 0) { NL_SET_ERR_MSG(extack, "Route does not contain a nexthop"); goto errout; } rt = mpls_rt_alloc(nhs, max_via_alen, max_labels); if (IS_ERR(rt)) { err = PTR_ERR(rt); goto errout; } rt->rt_protocol = cfg->rc_protocol; rt->rt_payload_type = cfg->rc_payload_type; rt->rt_ttl_propagate = cfg->rc_ttl_propagate; if (cfg->rc_mp) err = mpls_nh_build_multi(cfg, rt, max_labels, extack); else err = mpls_nh_build_from_cfg(cfg, rt); if (err) goto freert; mpls_route_update(net, index, rt, &cfg->rc_nlinfo); return 0; freert: mpls_rt_free(rt); errout: return err; } static int mpls_route_del(struct mpls_route_config *cfg, struct netlink_ext_ack *extack) { struct net *net = cfg->rc_nlinfo.nl_net; unsigned index; int err = -EINVAL; index = cfg->rc_label; if (!mpls_label_ok(net, &index, extack)) goto errout; mpls_route_update(net, index, NULL, &cfg->rc_nlinfo); err = 0; errout: return err; } static void mpls_get_stats(struct mpls_dev *mdev, struct mpls_link_stats *stats) { struct mpls_pcpu_stats *p; int i; memset(stats, 0, sizeof(*stats)); for_each_possible_cpu(i) { struct mpls_link_stats local; unsigned int start; p = per_cpu_ptr(mdev->stats, i); do { start = u64_stats_fetch_begin(&p->syncp); local = p->stats; } while (u64_stats_fetch_retry(&p->syncp, start)); stats->rx_packets += local.rx_packets; stats->rx_bytes += local.rx_bytes; stats->tx_packets += local.tx_packets; stats->tx_bytes += local.tx_bytes; stats->rx_errors += local.rx_errors; stats->tx_errors += local.tx_errors; stats->rx_dropped += local.rx_dropped; stats->tx_dropped += local.tx_dropped; stats->rx_noroute += local.rx_noroute; } } static int mpls_fill_stats_af(struct sk_buff *skb, const struct net_device *dev) { struct mpls_link_stats *stats; struct mpls_dev *mdev; struct nlattr *nla; mdev = mpls_dev_get(dev); if (!mdev) return -ENODATA; nla = nla_reserve_64bit(skb, MPLS_STATS_LINK, sizeof(struct mpls_link_stats), MPLS_STATS_UNSPEC); if (!nla) return -EMSGSIZE; stats = nla_data(nla); mpls_get_stats(mdev, stats); return 0; } static size_t mpls_get_stats_af_size(const struct net_device *dev) { struct mpls_dev *mdev; mdev = mpls_dev_get(dev); if (!mdev) return 0; return nla_total_size_64bit(sizeof(struct mpls_link_stats)); } static int mpls_netconf_fill_devconf(struct sk_buff *skb, struct mpls_dev *mdev, u32 portid, u32 seq, int event, unsigned int flags, int type) { struct nlmsghdr *nlh; struct netconfmsg *ncm; bool all = false; nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct netconfmsg), flags); if (!nlh) return -EMSGSIZE; if (type == NETCONFA_ALL) all = true; ncm = nlmsg_data(nlh); ncm->ncm_family = AF_MPLS; if (nla_put_s32(skb, NETCONFA_IFINDEX, mdev->dev->ifindex) < 0) goto nla_put_failure; if ((all || type == NETCONFA_INPUT) && nla_put_s32(skb, NETCONFA_INPUT, READ_ONCE(mdev->input_enabled)) < 0) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int mpls_netconf_msgsize_devconf(int type) { int size = NLMSG_ALIGN(sizeof(struct netconfmsg)) + nla_total_size(4); /* NETCONFA_IFINDEX */ bool all = false; if (type == NETCONFA_ALL) all = true; if (all || type == NETCONFA_INPUT) size += nla_total_size(4); return size; } static void mpls_netconf_notify_devconf(struct net *net, int event, int type, struct mpls_dev *mdev) { struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(mpls_netconf_msgsize_devconf(type), GFP_KERNEL); if (!skb) goto errout; err = mpls_netconf_fill_devconf(skb, mdev, 0, 0, event, 0, type); if (err < 0) { /* -EMSGSIZE implies BUG in mpls_netconf_msgsize_devconf() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_MPLS_NETCONF, NULL, GFP_KERNEL); return; errout: rtnl_set_sk_err(net, RTNLGRP_MPLS_NETCONF, err); } static const struct nla_policy devconf_mpls_policy[NETCONFA_MAX + 1] = { [NETCONFA_IFINDEX] = { .len = sizeof(int) }, }; static int mpls_netconf_valid_get_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { int i, err; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(struct netconfmsg))) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for netconf get request"); return -EINVAL; } if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(struct netconfmsg), tb, NETCONFA_MAX, devconf_mpls_policy, extack); err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct netconfmsg), tb, NETCONFA_MAX, devconf_mpls_policy, extack); if (err) return err; for (i = 0; i <= NETCONFA_MAX; i++) { if (!tb[i]) continue; switch (i) { case NETCONFA_IFINDEX: break; default: NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in netconf get request"); return -EINVAL; } } return 0; } static int mpls_netconf_get_devconf(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[NETCONFA_MAX + 1]; struct net_device *dev; struct mpls_dev *mdev; struct sk_buff *skb; int ifindex; int err; err = mpls_netconf_valid_get_req(in_skb, nlh, tb, extack); if (err < 0) goto errout; err = -EINVAL; if (!tb[NETCONFA_IFINDEX]) goto errout; ifindex = nla_get_s32(tb[NETCONFA_IFINDEX]); dev = __dev_get_by_index(net, ifindex); if (!dev) goto errout; mdev = mpls_dev_get(dev); if (!mdev) goto errout; err = -ENOBUFS; skb = nlmsg_new(mpls_netconf_msgsize_devconf(NETCONFA_ALL), GFP_KERNEL); if (!skb) goto errout; err = mpls_netconf_fill_devconf(skb, mdev, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, 0, NETCONFA_ALL); if (err < 0) { /* -EMSGSIZE implies BUG in mpls_netconf_msgsize_devconf() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: return err; } static int mpls_netconf_dump_devconf(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); struct { unsigned long ifindex; } *ctx = (void *)cb->ctx; struct net_device *dev; struct mpls_dev *mdev; int err = 0; if (cb->strict_check) { struct netlink_ext_ack *extack = cb->extack; struct netconfmsg *ncm; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ncm))) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for netconf dump request"); return -EINVAL; } if (nlmsg_attrlen(nlh, sizeof(*ncm))) { NL_SET_ERR_MSG_MOD(extack, "Invalid data after header in netconf dump request"); return -EINVAL; } } rcu_read_lock(); for_each_netdev_dump(net, dev, ctx->ifindex) { mdev = mpls_dev_get(dev); if (!mdev) continue; err = mpls_netconf_fill_devconf(skb, mdev, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, NETCONFA_ALL); if (err < 0) break; } rcu_read_unlock(); return err; } #define MPLS_PERDEV_SYSCTL_OFFSET(field) \ (&((struct mpls_dev *)0)->field) static int mpls_conf_proc(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int oval = *(int *)ctl->data; int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write) { struct mpls_dev *mdev = ctl->extra1; int i = (int *)ctl->data - (int *)mdev; struct net *net = ctl->extra2; int val = *(int *)ctl->data; if (i == offsetof(struct mpls_dev, input_enabled) && val != oval) { mpls_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_INPUT, mdev); } } return ret; } static const struct ctl_table mpls_dev_table[] = { { .procname = "input", .maxlen = sizeof(int), .mode = 0644, .proc_handler = mpls_conf_proc, .data = MPLS_PERDEV_SYSCTL_OFFSET(input_enabled), }, }; static int mpls_dev_sysctl_register(struct net_device *dev, struct mpls_dev *mdev) { char path[sizeof("net/mpls/conf/") + IFNAMSIZ]; size_t table_size = ARRAY_SIZE(mpls_dev_table); struct net *net = dev_net(dev); struct ctl_table *table; int i; table = kmemdup(&mpls_dev_table, sizeof(mpls_dev_table), GFP_KERNEL); if (!table) goto out; /* Table data contains only offsets relative to the base of * the mdev at this point, so make them absolute. */ for (i = 0; i < table_size; i++) { table[i].data = (char *)mdev + (uintptr_t)table[i].data; table[i].extra1 = mdev; table[i].extra2 = net; } snprintf(path, sizeof(path), "net/mpls/conf/%s", dev->name); mdev->sysctl = register_net_sysctl_sz(net, path, table, table_size); if (!mdev->sysctl) goto free; mpls_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_ALL, mdev); return 0; free: kfree(table); out: mdev->sysctl = NULL; return -ENOBUFS; } static void mpls_dev_sysctl_unregister(struct net_device *dev, struct mpls_dev *mdev) { struct net *net = dev_net(dev); const struct ctl_table *table; if (!mdev->sysctl) return; table = mdev->sysctl->ctl_table_arg; unregister_net_sysctl_table(mdev->sysctl); kfree(table); mpls_netconf_notify_devconf(net, RTM_DELNETCONF, 0, mdev); } static struct mpls_dev *mpls_add_dev(struct net_device *dev) { struct mpls_dev *mdev; int err = -ENOMEM; int i; ASSERT_RTNL(); mdev = kzalloc(sizeof(*mdev), GFP_KERNEL); if (!mdev) return ERR_PTR(err); mdev->stats = alloc_percpu(struct mpls_pcpu_stats); if (!mdev->stats) goto free; for_each_possible_cpu(i) { struct mpls_pcpu_stats *mpls_stats; mpls_stats = per_cpu_ptr(mdev->stats, i); u64_stats_init(&mpls_stats->syncp); } mdev->dev = dev; err = mpls_dev_sysctl_register(dev, mdev); if (err) goto free; rcu_assign_pointer(dev->mpls_ptr, mdev); return mdev; free: free_percpu(mdev->stats); kfree(mdev); return ERR_PTR(err); } static void mpls_dev_destroy_rcu(struct rcu_head *head) { struct mpls_dev *mdev = container_of(head, struct mpls_dev, rcu); free_percpu(mdev->stats); kfree(mdev); } static int mpls_ifdown(struct net_device *dev, int event) { struct mpls_route __rcu **platform_label; struct net *net = dev_net(dev); unsigned index; platform_label = rtnl_dereference(net->mpls.platform_label); for (index = 0; index < net->mpls.platform_labels; index++) { struct mpls_route *rt = rtnl_dereference(platform_label[index]); bool nh_del = false; u8 alive = 0; if (!rt) continue; if (event == NETDEV_UNREGISTER) { u8 deleted = 0; for_nexthops(rt) { if (!nh->nh_dev || nh->nh_dev == dev) deleted++; if (nh->nh_dev == dev) nh_del = true; } endfor_nexthops(rt); /* if there are no more nexthops, delete the route */ if (deleted == rt->rt_nhn) { mpls_route_update(net, index, NULL, NULL); continue; } if (nh_del) { size_t size = sizeof(*rt) + rt->rt_nhn * rt->rt_nh_size; struct mpls_route *orig = rt; rt = kmemdup(orig, size, GFP_KERNEL); if (!rt) return -ENOMEM; } } change_nexthops(rt) { unsigned int nh_flags = nh->nh_flags; if (nh->nh_dev != dev) goto next; switch (event) { case NETDEV_DOWN: case NETDEV_UNREGISTER: nh_flags |= RTNH_F_DEAD; fallthrough; case NETDEV_CHANGE: nh_flags |= RTNH_F_LINKDOWN; break; } if (event == NETDEV_UNREGISTER) nh->nh_dev = NULL; if (nh->nh_flags != nh_flags) WRITE_ONCE(nh->nh_flags, nh_flags); next: if (!(nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))) alive++; } endfor_nexthops(rt); WRITE_ONCE(rt->rt_nhn_alive, alive); if (nh_del) mpls_route_update(net, index, rt, NULL); } return 0; } static void mpls_ifup(struct net_device *dev, unsigned int flags) { struct mpls_route __rcu **platform_label; struct net *net = dev_net(dev); unsigned index; u8 alive; platform_label = rtnl_dereference(net->mpls.platform_label); for (index = 0; index < net->mpls.platform_labels; index++) { struct mpls_route *rt = rtnl_dereference(platform_label[index]); if (!rt) continue; alive = 0; change_nexthops(rt) { unsigned int nh_flags = nh->nh_flags; if (!(nh_flags & flags)) { alive++; continue; } if (nh->nh_dev != dev) continue; alive++; nh_flags &= ~flags; WRITE_ONCE(nh->nh_flags, nh_flags); } endfor_nexthops(rt); WRITE_ONCE(rt->rt_nhn_alive, alive); } } static int mpls_dev_notify(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct mpls_dev *mdev; unsigned int flags; int err; if (event == NETDEV_REGISTER) { mdev = mpls_add_dev(dev); if (IS_ERR(mdev)) return notifier_from_errno(PTR_ERR(mdev)); return NOTIFY_OK; } mdev = mpls_dev_get(dev); if (!mdev) return NOTIFY_OK; switch (event) { case NETDEV_DOWN: err = mpls_ifdown(dev, event); if (err) return notifier_from_errno(err); break; case NETDEV_UP: flags = dev_get_flags(dev); if (flags & (IFF_RUNNING | IFF_LOWER_UP)) mpls_ifup(dev, RTNH_F_DEAD | RTNH_F_LINKDOWN); else mpls_ifup(dev, RTNH_F_DEAD); break; case NETDEV_CHANGE: flags = dev_get_flags(dev); if (flags & (IFF_RUNNING | IFF_LOWER_UP)) { mpls_ifup(dev, RTNH_F_DEAD | RTNH_F_LINKDOWN); } else { err = mpls_ifdown(dev, event); if (err) return notifier_from_errno(err); } break; case NETDEV_UNREGISTER: err = mpls_ifdown(dev, event); if (err) return notifier_from_errno(err); mdev = mpls_dev_get(dev); if (mdev) { mpls_dev_sysctl_unregister(dev, mdev); RCU_INIT_POINTER(dev->mpls_ptr, NULL); call_rcu(&mdev->rcu, mpls_dev_destroy_rcu); } break; case NETDEV_CHANGENAME: mdev = mpls_dev_get(dev); if (mdev) { mpls_dev_sysctl_unregister(dev, mdev); err = mpls_dev_sysctl_register(dev, mdev); if (err) return notifier_from_errno(err); } break; } return NOTIFY_OK; } static struct notifier_block mpls_dev_notifier = { .notifier_call = mpls_dev_notify, }; static int nla_put_via(struct sk_buff *skb, u8 table, const void *addr, int alen) { static const int table_to_family[NEIGH_NR_TABLES + 1] = { AF_INET, AF_INET6, AF_PACKET, }; struct nlattr *nla; struct rtvia *via; int family = AF_UNSPEC; nla = nla_reserve(skb, RTA_VIA, alen + 2); if (!nla) return -EMSGSIZE; if (table <= NEIGH_NR_TABLES) family = table_to_family[table]; via = nla_data(nla); via->rtvia_family = family; memcpy(via->rtvia_addr, addr, alen); return 0; } int nla_put_labels(struct sk_buff *skb, int attrtype, u8 labels, const u32 label[]) { struct nlattr *nla; struct mpls_shim_hdr *nla_label; bool bos; int i; nla = nla_reserve(skb, attrtype, labels*4); if (!nla) return -EMSGSIZE; nla_label = nla_data(nla); bos = true; for (i = labels - 1; i >= 0; i--) { nla_label[i] = mpls_entry_encode(label[i], 0, 0, bos); bos = false; } return 0; } EXPORT_SYMBOL_GPL(nla_put_labels); int nla_get_labels(const struct nlattr *nla, u8 max_labels, u8 *labels, u32 label[], struct netlink_ext_ack *extack) { unsigned len = nla_len(nla); struct mpls_shim_hdr *nla_label; u8 nla_labels; bool bos; int i; /* len needs to be an even multiple of 4 (the label size). Number * of labels is a u8 so check for overflow. */ if (len & 3 || len / 4 > 255) { NL_SET_ERR_MSG_ATTR(extack, nla, "Invalid length for labels attribute"); return -EINVAL; } /* Limit the number of new labels allowed */ nla_labels = len/4; if (nla_labels > max_labels) { NL_SET_ERR_MSG(extack, "Too many labels"); return -EINVAL; } /* when label == NULL, caller wants number of labels */ if (!label) goto out; nla_label = nla_data(nla); bos = true; for (i = nla_labels - 1; i >= 0; i--, bos = false) { struct mpls_entry_decoded dec; dec = mpls_entry_decode(nla_label + i); /* Ensure the bottom of stack flag is properly set * and ttl and tc are both clear. */ if (dec.ttl) { NL_SET_ERR_MSG_ATTR(extack, nla, "TTL in label must be 0"); return -EINVAL; } if (dec.tc) { NL_SET_ERR_MSG_ATTR(extack, nla, "Traffic class in label must be 0"); return -EINVAL; } if (dec.bos != bos) { NL_SET_BAD_ATTR(extack, nla); if (bos) { NL_SET_ERR_MSG(extack, "BOS bit must be set in first label"); } else { NL_SET_ERR_MSG(extack, "BOS bit can only be set in first label"); } return -EINVAL; } switch (dec.label) { case MPLS_LABEL_IMPLNULL: /* RFC3032: This is a label that an LSR may * assign and distribute, but which never * actually appears in the encapsulation. */ NL_SET_ERR_MSG_ATTR(extack, nla, "Implicit NULL Label (3) can not be used in encapsulation"); return -EINVAL; } label[i] = dec.label; } out: *labels = nla_labels; return 0; } EXPORT_SYMBOL_GPL(nla_get_labels); static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh, struct mpls_route_config *cfg, struct netlink_ext_ack *extack) { struct rtmsg *rtm; struct nlattr *tb[RTA_MAX+1]; int index; int err; err = nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_mpls_policy, extack); if (err < 0) goto errout; err = -EINVAL; rtm = nlmsg_data(nlh); if (rtm->rtm_family != AF_MPLS) { NL_SET_ERR_MSG(extack, "Invalid address family in rtmsg"); goto errout; } if (rtm->rtm_dst_len != 20) { NL_SET_ERR_MSG(extack, "rtm_dst_len must be 20 for MPLS"); goto errout; } if (rtm->rtm_src_len != 0) { NL_SET_ERR_MSG(extack, "rtm_src_len must be 0 for MPLS"); goto errout; } if (rtm->rtm_tos != 0) { NL_SET_ERR_MSG(extack, "rtm_tos must be 0 for MPLS"); goto errout; } if (rtm->rtm_table != RT_TABLE_MAIN) { NL_SET_ERR_MSG(extack, "MPLS only supports the main route table"); goto errout; } /* Any value is acceptable for rtm_protocol */ /* As mpls uses destination specific addresses * (or source specific address in the case of multicast) * all addresses have universal scope. */ if (rtm->rtm_scope != RT_SCOPE_UNIVERSE) { NL_SET_ERR_MSG(extack, "Invalid route scope - MPLS only supports UNIVERSE"); goto errout; } if (rtm->rtm_type != RTN_UNICAST) { NL_SET_ERR_MSG(extack, "Invalid route type - MPLS only supports UNICAST"); goto errout; } if (rtm->rtm_flags != 0) { NL_SET_ERR_MSG(extack, "rtm_flags must be 0 for MPLS"); goto errout; } cfg->rc_label = LABEL_NOT_SPECIFIED; cfg->rc_protocol = rtm->rtm_protocol; cfg->rc_via_table = MPLS_NEIGH_TABLE_UNSPEC; cfg->rc_ttl_propagate = MPLS_TTL_PROP_DEFAULT; cfg->rc_nlflags = nlh->nlmsg_flags; cfg->rc_nlinfo.portid = NETLINK_CB(skb).portid; cfg->rc_nlinfo.nlh = nlh; cfg->rc_nlinfo.nl_net = sock_net(skb->sk); for (index = 0; index <= RTA_MAX; index++) { struct nlattr *nla = tb[index]; if (!nla) continue; switch (index) { case RTA_OIF: cfg->rc_ifindex = nla_get_u32(nla); break; case RTA_NEWDST: if (nla_get_labels(nla, MAX_NEW_LABELS, &cfg->rc_output_labels, cfg->rc_output_label, extack)) goto errout; break; case RTA_DST: { u8 label_count; if (nla_get_labels(nla, 1, &label_count, &cfg->rc_label, extack)) goto errout; if (!mpls_label_ok(cfg->rc_nlinfo.nl_net, &cfg->rc_label, extack)) goto errout; break; } case RTA_GATEWAY: NL_SET_ERR_MSG(extack, "MPLS does not support RTA_GATEWAY attribute"); goto errout; case RTA_VIA: { if (nla_get_via(nla, &cfg->rc_via_alen, &cfg->rc_via_table, cfg->rc_via, extack)) goto errout; break; } case RTA_MULTIPATH: { cfg->rc_mp = nla_data(nla); cfg->rc_mp_len = nla_len(nla); break; } case RTA_TTL_PROPAGATE: { u8 ttl_propagate = nla_get_u8(nla); if (ttl_propagate > 1) { NL_SET_ERR_MSG_ATTR(extack, nla, "RTA_TTL_PROPAGATE can only be 0 or 1"); goto errout; } cfg->rc_ttl_propagate = ttl_propagate ? MPLS_TTL_PROP_ENABLED : MPLS_TTL_PROP_DISABLED; break; } default: NL_SET_ERR_MSG_ATTR(extack, nla, "Unknown attribute"); /* Unsupported attribute */ goto errout; } } err = 0; errout: return err; } static int mpls_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct mpls_route_config *cfg; int err; cfg = kzalloc(sizeof(*cfg), GFP_KERNEL); if (!cfg) return -ENOMEM; err = rtm_to_route_config(skb, nlh, cfg, extack); if (err < 0) goto out; err = mpls_route_del(cfg, extack); out: kfree(cfg); return err; } static int mpls_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct mpls_route_config *cfg; int err; cfg = kzalloc(sizeof(*cfg), GFP_KERNEL); if (!cfg) return -ENOMEM; err = rtm_to_route_config(skb, nlh, cfg, extack); if (err < 0) goto out; err = mpls_route_add(cfg, extack); out: kfree(cfg); return err; } static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event, u32 label, struct mpls_route *rt, int flags) { struct net_device *dev; struct nlmsghdr *nlh; struct rtmsg *rtm; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*rtm), flags); if (nlh == NULL) return -EMSGSIZE; rtm = nlmsg_data(nlh); rtm->rtm_family = AF_MPLS; rtm->rtm_dst_len = 20; rtm->rtm_src_len = 0; rtm->rtm_tos = 0; rtm->rtm_table = RT_TABLE_MAIN; rtm->rtm_protocol = rt->rt_protocol; rtm->rtm_scope = RT_SCOPE_UNIVERSE; rtm->rtm_type = RTN_UNICAST; rtm->rtm_flags = 0; if (nla_put_labels(skb, RTA_DST, 1, &label)) goto nla_put_failure; if (rt->rt_ttl_propagate != MPLS_TTL_PROP_DEFAULT) { bool ttl_propagate = rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED; if (nla_put_u8(skb, RTA_TTL_PROPAGATE, ttl_propagate)) goto nla_put_failure; } if (rt->rt_nhn == 1) { const struct mpls_nh *nh = rt->rt_nh; if (nh->nh_labels && nla_put_labels(skb, RTA_NEWDST, nh->nh_labels, nh->nh_label)) goto nla_put_failure; if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC && nla_put_via(skb, nh->nh_via_table, mpls_nh_via(rt, nh), nh->nh_via_alen)) goto nla_put_failure; dev = nh->nh_dev; if (dev && nla_put_u32(skb, RTA_OIF, dev->ifindex)) goto nla_put_failure; if (nh->nh_flags & RTNH_F_LINKDOWN) rtm->rtm_flags |= RTNH_F_LINKDOWN; if (nh->nh_flags & RTNH_F_DEAD) rtm->rtm_flags |= RTNH_F_DEAD; } else { struct rtnexthop *rtnh; struct nlattr *mp; u8 linkdown = 0; u8 dead = 0; mp = nla_nest_start_noflag(skb, RTA_MULTIPATH); if (!mp) goto nla_put_failure; for_nexthops(rt) { dev = nh->nh_dev; if (!dev) continue; rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh)); if (!rtnh) goto nla_put_failure; rtnh->rtnh_ifindex = dev->ifindex; if (nh->nh_flags & RTNH_F_LINKDOWN) { rtnh->rtnh_flags |= RTNH_F_LINKDOWN; linkdown++; } if (nh->nh_flags & RTNH_F_DEAD) { rtnh->rtnh_flags |= RTNH_F_DEAD; dead++; } if (nh->nh_labels && nla_put_labels(skb, RTA_NEWDST, nh->nh_labels, nh->nh_label)) goto nla_put_failure; if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC && nla_put_via(skb, nh->nh_via_table, mpls_nh_via(rt, nh), nh->nh_via_alen)) goto nla_put_failure; /* length of rtnetlink header + attributes */ rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *)rtnh; } endfor_nexthops(rt); if (linkdown == rt->rt_nhn) rtm->rtm_flags |= RTNH_F_LINKDOWN; if (dead == rt->rt_nhn) rtm->rtm_flags |= RTNH_F_DEAD; nla_nest_end(skb, mp); } nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } #if IS_ENABLED(CONFIG_INET) static int mpls_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, struct fib_dump_filter *filter, struct netlink_callback *cb) { return ip_valid_fib_dump_req(net, nlh, filter, cb); } #else static int mpls_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, struct fib_dump_filter *filter, struct netlink_callback *cb) { struct netlink_ext_ack *extack = cb->extack; struct nlattr *tb[RTA_MAX + 1]; struct rtmsg *rtm; int err, i; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for FIB dump request"); return -EINVAL; } rtm = nlmsg_data(nlh); if (rtm->rtm_dst_len || rtm->rtm_src_len || rtm->rtm_tos || rtm->rtm_table || rtm->rtm_scope || rtm->rtm_type || rtm->rtm_flags) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for FIB dump request"); return -EINVAL; } if (rtm->rtm_protocol) { filter->protocol = rtm->rtm_protocol; filter->filter_set = 1; cb->answer_flags = NLM_F_DUMP_FILTERED; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_mpls_policy, extack); if (err < 0) return err; for (i = 0; i <= RTA_MAX; ++i) { int ifindex; if (i == RTA_OIF) { ifindex = nla_get_u32(tb[i]); filter->dev = __dev_get_by_index(net, ifindex); if (!filter->dev) return -ENODEV; filter->filter_set = 1; } else if (tb[i]) { NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in dump request"); return -EINVAL; } } return 0; } #endif static bool mpls_rt_uses_dev(struct mpls_route *rt, const struct net_device *dev) { if (rt->rt_nhn == 1) { struct mpls_nh *nh = rt->rt_nh; if (nh->nh_dev == dev) return true; } else { for_nexthops(rt) { if (nh->nh_dev == dev) return true; } endfor_nexthops(rt); } return false; } static int mpls_dump_routes(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); struct mpls_route __rcu **platform_label; struct fib_dump_filter filter = { .rtnl_held = true, }; unsigned int flags = NLM_F_MULTI; size_t platform_labels; unsigned int index; ASSERT_RTNL(); if (cb->strict_check) { int err; err = mpls_valid_fib_dump_req(net, nlh, &filter, cb); if (err < 0) return err; /* for MPLS, there is only 1 table with fixed type and flags. * If either are set in the filter then return nothing. */ if ((filter.table_id && filter.table_id != RT_TABLE_MAIN) || (filter.rt_type && filter.rt_type != RTN_UNICAST) || filter.flags) return skb->len; } index = cb->args[0]; if (index < MPLS_LABEL_FIRST_UNRESERVED) index = MPLS_LABEL_FIRST_UNRESERVED; platform_label = rtnl_dereference(net->mpls.platform_label); platform_labels = net->mpls.platform_labels; if (filter.filter_set) flags |= NLM_F_DUMP_FILTERED; for (; index < platform_labels; index++) { struct mpls_route *rt; rt = rtnl_dereference(platform_label[index]); if (!rt) continue; if ((filter.dev && !mpls_rt_uses_dev(rt, filter.dev)) || (filter.protocol && rt->rt_protocol != filter.protocol)) continue; if (mpls_dump_route(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWROUTE, index, rt, flags) < 0) break; } cb->args[0] = index; return skb->len; } static inline size_t lfib_nlmsg_size(struct mpls_route *rt) { size_t payload = NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(4) /* RTA_DST */ + nla_total_size(1); /* RTA_TTL_PROPAGATE */ if (rt->rt_nhn == 1) { struct mpls_nh *nh = rt->rt_nh; if (nh->nh_dev) payload += nla_total_size(4); /* RTA_OIF */ if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC) /* RTA_VIA */ payload += nla_total_size(2 + nh->nh_via_alen); if (nh->nh_labels) /* RTA_NEWDST */ payload += nla_total_size(nh->nh_labels * 4); } else { /* each nexthop is packed in an attribute */ size_t nhsize = 0; for_nexthops(rt) { if (!nh->nh_dev) continue; nhsize += nla_total_size(sizeof(struct rtnexthop)); /* RTA_VIA */ if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC) nhsize += nla_total_size(2 + nh->nh_via_alen); if (nh->nh_labels) nhsize += nla_total_size(nh->nh_labels * 4); } endfor_nexthops(rt); /* nested attribute */ payload += nla_total_size(nhsize); } return payload; } static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt, struct nlmsghdr *nlh, struct net *net, u32 portid, unsigned int nlm_flags) { struct sk_buff *skb; u32 seq = nlh ? nlh->nlmsg_seq : 0; int err = -ENOBUFS; skb = nlmsg_new(lfib_nlmsg_size(rt), GFP_KERNEL); if (skb == NULL) goto errout; err = mpls_dump_route(skb, portid, seq, event, label, rt, nlm_flags); if (err < 0) { /* -EMSGSIZE implies BUG in lfib_nlmsg_size */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, portid, RTNLGRP_MPLS_ROUTE, nlh, GFP_KERNEL); return; errout: rtnl_set_sk_err(net, RTNLGRP_MPLS_ROUTE, err); } static int mpls_valid_getroute_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct rtmsg *rtm; int i, err; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for get route request"); return -EINVAL; } if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_mpls_policy, extack); rtm = nlmsg_data(nlh); if ((rtm->rtm_dst_len && rtm->rtm_dst_len != 20) || rtm->rtm_src_len || rtm->rtm_tos || rtm->rtm_table || rtm->rtm_protocol || rtm->rtm_scope || rtm->rtm_type) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for get route request"); return -EINVAL; } if (rtm->rtm_flags & ~RTM_F_FIB_MATCH) { NL_SET_ERR_MSG_MOD(extack, "Invalid flags for get route request"); return -EINVAL; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_mpls_policy, extack); if (err) return err; if ((tb[RTA_DST] || tb[RTA_NEWDST]) && !rtm->rtm_dst_len) { NL_SET_ERR_MSG_MOD(extack, "rtm_dst_len must be 20 for MPLS"); return -EINVAL; } for (i = 0; i <= RTA_MAX; i++) { if (!tb[i]) continue; switch (i) { case RTA_DST: case RTA_NEWDST: break; default: NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in get route request"); return -EINVAL; } } return 0; } static int mpls_getroute(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); u32 portid = NETLINK_CB(in_skb).portid; u32 in_label = LABEL_NOT_SPECIFIED; struct nlattr *tb[RTA_MAX + 1]; u32 labels[MAX_NEW_LABELS]; struct mpls_shim_hdr *hdr; unsigned int hdr_size = 0; const struct mpls_nh *nh; struct net_device *dev; struct mpls_route *rt; struct rtmsg *rtm, *r; struct nlmsghdr *nlh; struct sk_buff *skb; u8 n_labels; int err; err = mpls_valid_getroute_req(in_skb, in_nlh, tb, extack); if (err < 0) goto errout; rtm = nlmsg_data(in_nlh); if (tb[RTA_DST]) { u8 label_count; if (nla_get_labels(tb[RTA_DST], 1, &label_count, &in_label, extack)) { err = -EINVAL; goto errout; } if (!mpls_label_ok(net, &in_label, extack)) { err = -EINVAL; goto errout; } } rt = mpls_route_input_rcu(net, in_label); if (!rt) { err = -ENETUNREACH; goto errout; } if (rtm->rtm_flags & RTM_F_FIB_MATCH) { skb = nlmsg_new(lfib_nlmsg_size(rt), GFP_KERNEL); if (!skb) { err = -ENOBUFS; goto errout; } err = mpls_dump_route(skb, portid, in_nlh->nlmsg_seq, RTM_NEWROUTE, in_label, rt, 0); if (err < 0) { /* -EMSGSIZE implies BUG in lfib_nlmsg_size */ WARN_ON(err == -EMSGSIZE); goto errout_free; } return rtnl_unicast(skb, net, portid); } if (tb[RTA_NEWDST]) { if (nla_get_labels(tb[RTA_NEWDST], MAX_NEW_LABELS, &n_labels, labels, extack) != 0) { err = -EINVAL; goto errout; } hdr_size = n_labels * sizeof(struct mpls_shim_hdr); } skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) { err = -ENOBUFS; goto errout; } skb->protocol = htons(ETH_P_MPLS_UC); if (hdr_size) { bool bos; int i; if (skb_cow(skb, hdr_size)) { err = -ENOBUFS; goto errout_free; } skb_reserve(skb, hdr_size); skb_push(skb, hdr_size); skb_reset_network_header(skb); /* Push new labels */ hdr = mpls_hdr(skb); bos = true; for (i = n_labels - 1; i >= 0; i--) { hdr[i] = mpls_entry_encode(labels[i], 1, 0, bos); bos = false; } } nh = mpls_select_multipath(rt, skb); if (!nh) { err = -ENETUNREACH; goto errout_free; } if (hdr_size) { skb_pull(skb, hdr_size); skb_reset_network_header(skb); } nlh = nlmsg_put(skb, portid, in_nlh->nlmsg_seq, RTM_NEWROUTE, sizeof(*r), 0); if (!nlh) { err = -EMSGSIZE; goto errout_free; } r = nlmsg_data(nlh); r->rtm_family = AF_MPLS; r->rtm_dst_len = 20; r->rtm_src_len = 0; r->rtm_table = RT_TABLE_MAIN; r->rtm_type = RTN_UNICAST; r->rtm_scope = RT_SCOPE_UNIVERSE; r->rtm_protocol = rt->rt_protocol; r->rtm_flags = 0; if (nla_put_labels(skb, RTA_DST, 1, &in_label)) goto nla_put_failure; if (nh->nh_labels && nla_put_labels(skb, RTA_NEWDST, nh->nh_labels, nh->nh_label)) goto nla_put_failure; if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC && nla_put_via(skb, nh->nh_via_table, mpls_nh_via(rt, nh), nh->nh_via_alen)) goto nla_put_failure; dev = nh->nh_dev; if (dev && nla_put_u32(skb, RTA_OIF, dev->ifindex)) goto nla_put_failure; nlmsg_end(skb, nlh); err = rtnl_unicast(skb, net, portid); errout: return err; nla_put_failure: nlmsg_cancel(skb, nlh); err = -EMSGSIZE; errout_free: kfree_skb(skb); return err; } static int resize_platform_label_table(struct net *net, size_t limit) { size_t size = sizeof(struct mpls_route *) * limit; size_t old_limit; size_t cp_size; struct mpls_route __rcu **labels = NULL, **old; struct mpls_route *rt0 = NULL, *rt2 = NULL; unsigned index; if (size) { labels = kvzalloc(size, GFP_KERNEL); if (!labels) goto nolabels; } /* In case the predefined labels need to be populated */ if (limit > MPLS_LABEL_IPV4NULL) { struct net_device *lo = net->loopback_dev; rt0 = mpls_rt_alloc(1, lo->addr_len, 0); if (IS_ERR(rt0)) goto nort0; rt0->rt_nh->nh_dev = lo; rt0->rt_protocol = RTPROT_KERNEL; rt0->rt_payload_type = MPT_IPV4; rt0->rt_ttl_propagate = MPLS_TTL_PROP_DEFAULT; rt0->rt_nh->nh_via_table = NEIGH_LINK_TABLE; rt0->rt_nh->nh_via_alen = lo->addr_len; memcpy(__mpls_nh_via(rt0, rt0->rt_nh), lo->dev_addr, lo->addr_len); } if (limit > MPLS_LABEL_IPV6NULL) { struct net_device *lo = net->loopback_dev; rt2 = mpls_rt_alloc(1, lo->addr_len, 0); if (IS_ERR(rt2)) goto nort2; rt2->rt_nh->nh_dev = lo; rt2->rt_protocol = RTPROT_KERNEL; rt2->rt_payload_type = MPT_IPV6; rt2->rt_ttl_propagate = MPLS_TTL_PROP_DEFAULT; rt2->rt_nh->nh_via_table = NEIGH_LINK_TABLE; rt2->rt_nh->nh_via_alen = lo->addr_len; memcpy(__mpls_nh_via(rt2, rt2->rt_nh), lo->dev_addr, lo->addr_len); } rtnl_lock(); /* Remember the original table */ old = rtnl_dereference(net->mpls.platform_label); old_limit = net->mpls.platform_labels; /* Free any labels beyond the new table */ for (index = limit; index < old_limit; index++) mpls_route_update(net, index, NULL, NULL); /* Copy over the old labels */ cp_size = size; if (old_limit < limit) cp_size = old_limit * sizeof(struct mpls_route *); memcpy(labels, old, cp_size); /* If needed set the predefined labels */ if ((old_limit <= MPLS_LABEL_IPV6NULL) && (limit > MPLS_LABEL_IPV6NULL)) { RCU_INIT_POINTER(labels[MPLS_LABEL_IPV6NULL], rt2); rt2 = NULL; } if ((old_limit <= MPLS_LABEL_IPV4NULL) && (limit > MPLS_LABEL_IPV4NULL)) { RCU_INIT_POINTER(labels[MPLS_LABEL_IPV4NULL], rt0); rt0 = NULL; } /* Update the global pointers */ net->mpls.platform_labels = limit; rcu_assign_pointer(net->mpls.platform_label, labels); rtnl_unlock(); mpls_rt_free(rt2); mpls_rt_free(rt0); if (old) { synchronize_rcu(); kvfree(old); } return 0; nort2: mpls_rt_free(rt0); nort0: kvfree(labels); nolabels: return -ENOMEM; } static int mpls_platform_labels(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = table->data; int platform_labels = net->mpls.platform_labels; int ret; struct ctl_table tmp = { .procname = table->procname, .data = &platform_labels, .maxlen = sizeof(int), .mode = table->mode, .extra1 = SYSCTL_ZERO, .extra2 = &label_limit, }; ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && ret == 0) ret = resize_platform_label_table(net, platform_labels); return ret; } #define MPLS_NS_SYSCTL_OFFSET(field) \ (&((struct net *)0)->field) static const struct ctl_table mpls_table[] = { { .procname = "platform_labels", .data = NULL, .maxlen = sizeof(int), .mode = 0644, .proc_handler = mpls_platform_labels, }, { .procname = "ip_ttl_propagate", .data = MPLS_NS_SYSCTL_OFFSET(mpls.ip_ttl_propagate), .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "default_ttl", .data = MPLS_NS_SYSCTL_OFFSET(mpls.default_ttl), .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, .extra2 = &ttl_max, }, }; static int mpls_net_init(struct net *net) { size_t table_size = ARRAY_SIZE(mpls_table); struct ctl_table *table; int i; net->mpls.platform_labels = 0; net->mpls.platform_label = NULL; net->mpls.ip_ttl_propagate = 1; net->mpls.default_ttl = 255; table = kmemdup(mpls_table, sizeof(mpls_table), GFP_KERNEL); if (table == NULL) return -ENOMEM; /* Table data contains only offsets relative to the base of * the mdev at this point, so make them absolute. */ for (i = 0; i < table_size; i++) table[i].data = (char *)net + (uintptr_t)table[i].data; net->mpls.ctl = register_net_sysctl_sz(net, "net/mpls", table, table_size); if (net->mpls.ctl == NULL) { kfree(table); return -ENOMEM; } return 0; } static void mpls_net_exit(struct net *net) { struct mpls_route __rcu **platform_label; size_t platform_labels; const struct ctl_table *table; unsigned int index; table = net->mpls.ctl->ctl_table_arg; unregister_net_sysctl_table(net->mpls.ctl); kfree(table); /* An rcu grace period has passed since there was a device in * the network namespace (and thus the last in flight packet) * left this network namespace. This is because * unregister_netdevice_many and netdev_run_todo has completed * for each network device that was in this network namespace. * * As such no additional rcu synchronization is necessary when * freeing the platform_label table. */ rtnl_lock(); platform_label = rtnl_dereference(net->mpls.platform_label); platform_labels = net->mpls.platform_labels; for (index = 0; index < platform_labels; index++) { struct mpls_route *rt = rtnl_dereference(platform_label[index]); RCU_INIT_POINTER(platform_label[index], NULL); mpls_notify_route(net, index, rt, NULL, NULL); mpls_rt_free(rt); } rtnl_unlock(); kvfree(platform_label); } static struct pernet_operations mpls_net_ops = { .init = mpls_net_init, .exit = mpls_net_exit, }; static struct rtnl_af_ops mpls_af_ops __read_mostly = { .family = AF_MPLS, .fill_stats_af = mpls_fill_stats_af, .get_stats_af_size = mpls_get_stats_af_size, }; static const struct rtnl_msg_handler mpls_rtnl_msg_handlers[] __initdata_or_module = { {THIS_MODULE, PF_MPLS, RTM_NEWROUTE, mpls_rtm_newroute, NULL, 0}, {THIS_MODULE, PF_MPLS, RTM_DELROUTE, mpls_rtm_delroute, NULL, 0}, {THIS_MODULE, PF_MPLS, RTM_GETROUTE, mpls_getroute, mpls_dump_routes, 0}, {THIS_MODULE, PF_MPLS, RTM_GETNETCONF, mpls_netconf_get_devconf, mpls_netconf_dump_devconf, RTNL_FLAG_DUMP_UNLOCKED}, }; static int __init mpls_init(void) { int err; BUILD_BUG_ON(sizeof(struct mpls_shim_hdr) != 4); err = register_pernet_subsys(&mpls_net_ops); if (err) goto out; err = register_netdevice_notifier(&mpls_dev_notifier); if (err) goto out_unregister_pernet; dev_add_pack(&mpls_packet_type); err = rtnl_af_register(&mpls_af_ops); if (err) goto out_unregister_dev_type; err = rtnl_register_many(mpls_rtnl_msg_handlers); if (err) goto out_unregister_rtnl_af; err = ipgre_tunnel_encap_add_mpls_ops(); if (err) { pr_err("Can't add mpls over gre tunnel ops\n"); goto out_unregister_rtnl; } err = 0; out: return err; out_unregister_rtnl: rtnl_unregister_many(mpls_rtnl_msg_handlers); out_unregister_rtnl_af: rtnl_af_unregister(&mpls_af_ops); out_unregister_dev_type: dev_remove_pack(&mpls_packet_type); out_unregister_pernet: unregister_pernet_subsys(&mpls_net_ops); goto out; } module_init(mpls_init); static void __exit mpls_exit(void) { rtnl_unregister_all(PF_MPLS); rtnl_af_unregister(&mpls_af_ops); dev_remove_pack(&mpls_packet_type); unregister_netdevice_notifier(&mpls_dev_notifier); unregister_pernet_subsys(&mpls_net_ops); ipgre_tunnel_encap_del_mpls_ops(); } module_exit(mpls_exit); MODULE_DESCRIPTION("MultiProtocol Label Switching"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS_NETPROTO(PF_MPLS); |
| 182 | 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 | /* 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 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; }; /* * 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 *files_lookup_fd_raw(struct files_struct *files, unsigned int fd) { struct fdtable *fdt = rcu_dereference_raw(files->fdt); unsigned long mask = array_index_mask_nospec(fd, fdt->max_fds); struct file *needs_masking; /* * 'mask' is zero for an out-of-bounds fd, all ones for ok. * 'fd&mask' is 'fd' for ok, or 0 for out of bounds. * * Accessing fdt->fd[0] is ok, but needs masking of the result. */ needs_masking = rcu_dereference_raw(fdt->fd[fd&mask]); return (struct file *)(mask & (unsigned long)needs_masking); } static inline struct file *files_lookup_fd_locked(struct files_struct *files, unsigned int fd) { RCU_LOCKDEP_WARN(!lockdep_is_held(&files->file_lock), "suspicious rcu_dereference_check() usage"); return files_lookup_fd_raw(files, fd); } static inline bool close_on_exec(unsigned int fd, const struct files_struct *files) { return test_bit(fd, files_fdtable(files)->close_on_exec); } struct task_struct; void put_files_struct(struct files_struct *fs); int unshare_files(void); struct fd_range { unsigned int from, to; }; struct files_struct *dup_fd(struct files_struct *, struct fd_range *) __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 close_fd(unsigned int fd); extern struct file *file_close_fd(unsigned int fd); extern struct kmem_cache *files_cachep; #endif /* __LINUX_FDTABLE_H */ |
| 5 10 44 3 3 3 3 3 2 3 9 44 29 32 32 46 49 11 4 5 1 1 1 1 1 1 1 1 1 4 4 4 4 4 8 8 13 10 10 4 4 4 4 4 4 5 5 5 5 5 5 5 5 10 10 10 10 10 10 2 2 7 7 7 5 5 4 2 1 1 5 4 10 10 10 9 10 5 5 5 5 4 4 4 4 10 10 10 10 4 1 1 1 1 2 1 1 1 2 3 3 1 1 2 2 2 1 5 3 2 2 2 1 5 5 5 5 5 7 4 6 6 6 6 7 9 14 14 7 9 10 10 10 10 10 10 10 10 10 4 4 4 3 4 4 295 295 294 294 894 892 888 98 15 15 13 890 10 9 5 5 5 10 4 4 2 2 2 5 5 5 10 10 10 10 10 10 10 10 10 10 10 10 9 9 10 9 10 10 9 9 10 10 10 10 10 10 10 9 10 10 10 10 10 10 9 10 10 10 9 10 10 10 10 9 10 10 9 10 10 10 10 10 10 10 10 10 10 9 10 9 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 9 10 9 10 10 10 10 10 10 10 10 10 9 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 9 10 10 10 10 10 10 10 9 10 10 10 10 10 10 10 9 10 10 10 10 10 10 10 10 1 1 882 872 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * Copyright (c) 2004 Topspin Communications. All rights reserved. * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #include <linux/module.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/netdevice.h> #include <net/net_namespace.h> #include <linux/security.h> #include <linux/notifier.h> #include <linux/hashtable.h> #include <rdma/rdma_netlink.h> #include <rdma/ib_addr.h> #include <rdma/ib_cache.h> #include <rdma/rdma_counter.h> #include "core_priv.h" #include "restrack.h" MODULE_AUTHOR("Roland Dreier"); MODULE_DESCRIPTION("core kernel InfiniBand API"); MODULE_LICENSE("Dual BSD/GPL"); struct workqueue_struct *ib_comp_wq; struct workqueue_struct *ib_comp_unbound_wq; struct workqueue_struct *ib_wq; EXPORT_SYMBOL_GPL(ib_wq); static struct workqueue_struct *ib_unreg_wq; /* * Each of the three rwsem locks (devices, clients, client_data) protects the * xarray of the same name. Specifically it allows the caller to assert that * the MARK will/will not be changing under the lock, and for devices and * clients, that the value in the xarray is still a valid pointer. Change of * the MARK is linked to the object state, so holding the lock and testing the * MARK also asserts that the contained object is in a certain state. * * This is used to build a two stage register/unregister flow where objects * can continue to be in the xarray even though they are still in progress to * register/unregister. * * The xarray itself provides additional locking, and restartable iteration, * which is also relied on. * * Locks should not be nested, with the exception of client_data, which is * allowed to nest under the read side of the other two locks. * * The devices_rwsem also protects the device name list, any change or * assignment of device name must also hold the write side to guarantee unique * names. */ /* * devices contains devices that have had their names assigned. The * devices may not be registered. Users that care about the registration * status need to call ib_device_try_get() on the device to ensure it is * registered, and keep it registered, for the required duration. * */ static DEFINE_XARRAY_FLAGS(devices, XA_FLAGS_ALLOC); static DECLARE_RWSEM(devices_rwsem); #define DEVICE_REGISTERED XA_MARK_1 static u32 highest_client_id; #define CLIENT_REGISTERED XA_MARK_1 static DEFINE_XARRAY_FLAGS(clients, XA_FLAGS_ALLOC); static DECLARE_RWSEM(clients_rwsem); static void ib_client_put(struct ib_client *client) { if (refcount_dec_and_test(&client->uses)) complete(&client->uses_zero); } /* * If client_data is registered then the corresponding client must also still * be registered. */ #define CLIENT_DATA_REGISTERED XA_MARK_1 unsigned int rdma_dev_net_id; /* * A list of net namespaces is maintained in an xarray. This is necessary * because we can't get the locking right using the existing net ns list. We * would require a init_net callback after the list is updated. */ static DEFINE_XARRAY_FLAGS(rdma_nets, XA_FLAGS_ALLOC); /* * rwsem to protect accessing the rdma_nets xarray entries. */ static DECLARE_RWSEM(rdma_nets_rwsem); bool ib_devices_shared_netns = true; module_param_named(netns_mode, ib_devices_shared_netns, bool, 0444); MODULE_PARM_DESC(netns_mode, "Share device among net namespaces; default=1 (shared)"); /** * rdma_dev_access_netns() - Return whether an rdma device can be accessed * from a specified net namespace or not. * @dev: Pointer to rdma device which needs to be checked * @net: Pointer to net namesapce for which access to be checked * * When the rdma device is in shared mode, it ignores the net namespace. * When the rdma device is exclusive to a net namespace, rdma device net * namespace is checked against the specified one. */ bool rdma_dev_access_netns(const struct ib_device *dev, const struct net *net) { return (ib_devices_shared_netns || net_eq(read_pnet(&dev->coredev.rdma_net), net)); } EXPORT_SYMBOL(rdma_dev_access_netns); /* * xarray has this behavior where it won't iterate over NULL values stored in * allocated arrays. So we need our own iterator to see all values stored in * the array. This does the same thing as xa_for_each except that it also * returns NULL valued entries if the array is allocating. Simplified to only * work on simple xarrays. */ static void *xan_find_marked(struct xarray *xa, unsigned long *indexp, xa_mark_t filter) { XA_STATE(xas, xa, *indexp); void *entry; rcu_read_lock(); do { entry = xas_find_marked(&xas, ULONG_MAX, filter); if (xa_is_zero(entry)) break; } while (xas_retry(&xas, entry)); rcu_read_unlock(); if (entry) { *indexp = xas.xa_index; if (xa_is_zero(entry)) return NULL; return entry; } return XA_ERROR(-ENOENT); } #define xan_for_each_marked(xa, index, entry, filter) \ for (index = 0, entry = xan_find_marked(xa, &(index), filter); \ !xa_is_err(entry); \ (index)++, entry = xan_find_marked(xa, &(index), filter)) /* RCU hash table mapping netdevice pointers to struct ib_port_data */ static DEFINE_SPINLOCK(ndev_hash_lock); static DECLARE_HASHTABLE(ndev_hash, 5); static void free_netdevs(struct ib_device *ib_dev); static void ib_unregister_work(struct work_struct *work); static void __ib_unregister_device(struct ib_device *device); static int ib_security_change(struct notifier_block *nb, unsigned long event, void *lsm_data); static void ib_policy_change_task(struct work_struct *work); static DECLARE_WORK(ib_policy_change_work, ib_policy_change_task); static void __ibdev_printk(const char *level, const struct ib_device *ibdev, struct va_format *vaf) { if (ibdev && ibdev->dev.parent) dev_printk_emit(level[1] - '0', ibdev->dev.parent, "%s %s %s: %pV", dev_driver_string(ibdev->dev.parent), dev_name(ibdev->dev.parent), dev_name(&ibdev->dev), vaf); else if (ibdev) printk("%s%s: %pV", level, dev_name(&ibdev->dev), vaf); else printk("%s(NULL ib_device): %pV", level, vaf); } void ibdev_printk(const char *level, const struct ib_device *ibdev, const char *format, ...) { struct va_format vaf; va_list args; va_start(args, format); vaf.fmt = format; vaf.va = &args; __ibdev_printk(level, ibdev, &vaf); va_end(args); } EXPORT_SYMBOL(ibdev_printk); #define define_ibdev_printk_level(func, level) \ void func(const struct ib_device *ibdev, const char *fmt, ...) \ { \ struct va_format vaf; \ va_list args; \ \ va_start(args, fmt); \ \ vaf.fmt = fmt; \ vaf.va = &args; \ \ __ibdev_printk(level, ibdev, &vaf); \ \ va_end(args); \ } \ EXPORT_SYMBOL(func); define_ibdev_printk_level(ibdev_emerg, KERN_EMERG); define_ibdev_printk_level(ibdev_alert, KERN_ALERT); define_ibdev_printk_level(ibdev_crit, KERN_CRIT); define_ibdev_printk_level(ibdev_err, KERN_ERR); define_ibdev_printk_level(ibdev_warn, KERN_WARNING); define_ibdev_printk_level(ibdev_notice, KERN_NOTICE); define_ibdev_printk_level(ibdev_info, KERN_INFO); static struct notifier_block ibdev_lsm_nb = { .notifier_call = ib_security_change, }; static int rdma_dev_change_netns(struct ib_device *device, struct net *cur_net, struct net *net); /* Pointer to the RCU head at the start of the ib_port_data array */ struct ib_port_data_rcu { struct rcu_head rcu_head; struct ib_port_data pdata[]; }; static void ib_device_check_mandatory(struct ib_device *device) { #define IB_MANDATORY_FUNC(x) { offsetof(struct ib_device_ops, x), #x } static const struct { size_t offset; char *name; } mandatory_table[] = { IB_MANDATORY_FUNC(query_device), IB_MANDATORY_FUNC(query_port), IB_MANDATORY_FUNC(alloc_pd), IB_MANDATORY_FUNC(dealloc_pd), IB_MANDATORY_FUNC(create_qp), IB_MANDATORY_FUNC(modify_qp), IB_MANDATORY_FUNC(destroy_qp), IB_MANDATORY_FUNC(post_send), IB_MANDATORY_FUNC(post_recv), IB_MANDATORY_FUNC(create_cq), IB_MANDATORY_FUNC(destroy_cq), IB_MANDATORY_FUNC(poll_cq), IB_MANDATORY_FUNC(req_notify_cq), IB_MANDATORY_FUNC(get_dma_mr), IB_MANDATORY_FUNC(reg_user_mr), IB_MANDATORY_FUNC(dereg_mr), IB_MANDATORY_FUNC(get_port_immutable) }; int i; device->kverbs_provider = true; for (i = 0; i < ARRAY_SIZE(mandatory_table); ++i) { if (!*(void **) ((void *) &device->ops + mandatory_table[i].offset)) { device->kverbs_provider = false; break; } } } /* * Caller must perform ib_device_put() to return the device reference count * when ib_device_get_by_index() returns valid device pointer. */ struct ib_device *ib_device_get_by_index(const struct net *net, u32 index) { struct ib_device *device; down_read(&devices_rwsem); device = xa_load(&devices, index); if (device) { if (!rdma_dev_access_netns(device, net)) { device = NULL; goto out; } if (!ib_device_try_get(device)) device = NULL; } out: up_read(&devices_rwsem); return device; } /** * ib_device_put - Release IB device reference * @device: device whose reference to be released * * ib_device_put() releases reference to the IB device to allow it to be * unregistered and eventually free. */ void ib_device_put(struct ib_device *device) { if (refcount_dec_and_test(&device->refcount)) complete(&device->unreg_completion); } EXPORT_SYMBOL(ib_device_put); static struct ib_device *__ib_device_get_by_name(const char *name) { struct ib_device *device; unsigned long index; xa_for_each (&devices, index, device) if (!strcmp(name, dev_name(&device->dev))) return device; return NULL; } /** * ib_device_get_by_name - Find an IB device by name * @name: The name to look for * @driver_id: The driver ID that must match (RDMA_DRIVER_UNKNOWN matches all) * * Find and hold an ib_device by its name. The caller must call * ib_device_put() on the returned pointer. */ struct ib_device *ib_device_get_by_name(const char *name, enum rdma_driver_id driver_id) { struct ib_device *device; down_read(&devices_rwsem); device = __ib_device_get_by_name(name); if (device && driver_id != RDMA_DRIVER_UNKNOWN && device->ops.driver_id != driver_id) device = NULL; if (device) { if (!ib_device_try_get(device)) device = NULL; } up_read(&devices_rwsem); return device; } EXPORT_SYMBOL(ib_device_get_by_name); static int rename_compat_devs(struct ib_device *device) { struct ib_core_device *cdev; unsigned long index; int ret = 0; mutex_lock(&device->compat_devs_mutex); xa_for_each (&device->compat_devs, index, cdev) { ret = device_rename(&cdev->dev, dev_name(&device->dev)); if (ret) { dev_warn(&cdev->dev, "Fail to rename compatdev to new name %s\n", dev_name(&device->dev)); break; } } mutex_unlock(&device->compat_devs_mutex); return ret; } int ib_device_rename(struct ib_device *ibdev, const char *name) { unsigned long index; void *client_data; int ret; down_write(&devices_rwsem); if (!strcmp(name, dev_name(&ibdev->dev))) { up_write(&devices_rwsem); return 0; } if (__ib_device_get_by_name(name)) { up_write(&devices_rwsem); return -EEXIST; } ret = device_rename(&ibdev->dev, name); if (ret) { up_write(&devices_rwsem); return ret; } strscpy(ibdev->name, name, IB_DEVICE_NAME_MAX); ret = rename_compat_devs(ibdev); downgrade_write(&devices_rwsem); down_read(&ibdev->client_data_rwsem); xan_for_each_marked(&ibdev->client_data, index, client_data, CLIENT_DATA_REGISTERED) { struct ib_client *client = xa_load(&clients, index); if (!client || !client->rename) continue; client->rename(ibdev, client_data); } up_read(&ibdev->client_data_rwsem); rdma_nl_notify_event(ibdev, 0, RDMA_RENAME_EVENT); up_read(&devices_rwsem); return 0; } int ib_device_set_dim(struct ib_device *ibdev, u8 use_dim) { if (use_dim > 1) return -EINVAL; ibdev->use_cq_dim = use_dim; return 0; } static int alloc_name(struct ib_device *ibdev, const char *name) { struct ib_device *device; unsigned long index; struct ida inuse; int rc; int i; lockdep_assert_held_write(&devices_rwsem); ida_init(&inuse); xa_for_each (&devices, index, device) { char buf[IB_DEVICE_NAME_MAX]; if (sscanf(dev_name(&device->dev), name, &i) != 1) continue; if (i < 0 || i >= INT_MAX) continue; snprintf(buf, sizeof buf, name, i); if (strcmp(buf, dev_name(&device->dev)) != 0) continue; rc = ida_alloc_range(&inuse, i, i, GFP_KERNEL); if (rc < 0) goto out; } rc = ida_alloc(&inuse, GFP_KERNEL); if (rc < 0) goto out; rc = dev_set_name(&ibdev->dev, name, rc); out: ida_destroy(&inuse); return rc; } static void ib_device_release(struct device *device) { struct ib_device *dev = container_of(device, struct ib_device, dev); free_netdevs(dev); WARN_ON(refcount_read(&dev->refcount)); if (dev->hw_stats_data) ib_device_release_hw_stats(dev->hw_stats_data); if (dev->port_data) { ib_cache_release_one(dev); ib_security_release_port_pkey_list(dev); rdma_counter_release(dev); kfree_rcu(container_of(dev->port_data, struct ib_port_data_rcu, pdata[0]), rcu_head); } mutex_destroy(&dev->subdev_lock); mutex_destroy(&dev->unregistration_lock); mutex_destroy(&dev->compat_devs_mutex); xa_destroy(&dev->compat_devs); xa_destroy(&dev->client_data); kfree_rcu(dev, rcu_head); } static int ib_device_uevent(const struct device *device, struct kobj_uevent_env *env) { if (add_uevent_var(env, "NAME=%s", dev_name(device))) return -ENOMEM; /* * It would be nice to pass the node GUID with the event... */ return 0; } static const void *net_namespace(const struct device *d) { const struct ib_core_device *coredev = container_of(d, struct ib_core_device, dev); return read_pnet(&coredev->rdma_net); } static struct class ib_class = { .name = "infiniband", .dev_release = ib_device_release, .dev_uevent = ib_device_uevent, .ns_type = &net_ns_type_operations, .namespace = net_namespace, }; static void rdma_init_coredev(struct ib_core_device *coredev, struct ib_device *dev, struct net *net) { /* This BUILD_BUG_ON is intended to catch layout change * of union of ib_core_device and device. * dev must be the first element as ib_core and providers * driver uses it. Adding anything in ib_core_device before * device will break this assumption. */ BUILD_BUG_ON(offsetof(struct ib_device, coredev.dev) != offsetof(struct ib_device, dev)); coredev->dev.class = &ib_class; coredev->dev.groups = dev->groups; device_initialize(&coredev->dev); coredev->owner = dev; INIT_LIST_HEAD(&coredev->port_list); write_pnet(&coredev->rdma_net, net); } /** * _ib_alloc_device - allocate an IB device struct * @size:size of structure to allocate * * Low-level drivers should use ib_alloc_device() to allocate &struct * ib_device. @size is the size of the structure to be allocated, * including any private data used by the low-level driver. * ib_dealloc_device() must be used to free structures allocated with * ib_alloc_device(). */ struct ib_device *_ib_alloc_device(size_t size) { struct ib_device *device; unsigned int i; if (WARN_ON(size < sizeof(struct ib_device))) return NULL; device = kzalloc(size, GFP_KERNEL); if (!device) return NULL; if (rdma_restrack_init(device)) { kfree(device); return NULL; } rdma_init_coredev(&device->coredev, device, &init_net); INIT_LIST_HEAD(&device->event_handler_list); spin_lock_init(&device->qp_open_list_lock); init_rwsem(&device->event_handler_rwsem); mutex_init(&device->unregistration_lock); /* * client_data needs to be alloc because we don't want our mark to be * destroyed if the user stores NULL in the client data. */ xa_init_flags(&device->client_data, XA_FLAGS_ALLOC); init_rwsem(&device->client_data_rwsem); xa_init_flags(&device->compat_devs, XA_FLAGS_ALLOC); mutex_init(&device->compat_devs_mutex); init_completion(&device->unreg_completion); INIT_WORK(&device->unregistration_work, ib_unregister_work); spin_lock_init(&device->cq_pools_lock); for (i = 0; i < ARRAY_SIZE(device->cq_pools); i++) INIT_LIST_HEAD(&device->cq_pools[i]); rwlock_init(&device->cache_lock); device->uverbs_cmd_mask = BIT_ULL(IB_USER_VERBS_CMD_ALLOC_MW) | BIT_ULL(IB_USER_VERBS_CMD_ALLOC_PD) | BIT_ULL(IB_USER_VERBS_CMD_ATTACH_MCAST) | BIT_ULL(IB_USER_VERBS_CMD_CLOSE_XRCD) | BIT_ULL(IB_USER_VERBS_CMD_CREATE_AH) | BIT_ULL(IB_USER_VERBS_CMD_CREATE_COMP_CHANNEL) | BIT_ULL(IB_USER_VERBS_CMD_CREATE_CQ) | BIT_ULL(IB_USER_VERBS_CMD_CREATE_QP) | BIT_ULL(IB_USER_VERBS_CMD_CREATE_SRQ) | BIT_ULL(IB_USER_VERBS_CMD_CREATE_XSRQ) | BIT_ULL(IB_USER_VERBS_CMD_DEALLOC_MW) | BIT_ULL(IB_USER_VERBS_CMD_DEALLOC_PD) | BIT_ULL(IB_USER_VERBS_CMD_DEREG_MR) | BIT_ULL(IB_USER_VERBS_CMD_DESTROY_AH) | BIT_ULL(IB_USER_VERBS_CMD_DESTROY_CQ) | BIT_ULL(IB_USER_VERBS_CMD_DESTROY_QP) | BIT_ULL(IB_USER_VERBS_CMD_DESTROY_SRQ) | BIT_ULL(IB_USER_VERBS_CMD_DETACH_MCAST) | BIT_ULL(IB_USER_VERBS_CMD_GET_CONTEXT) | BIT_ULL(IB_USER_VERBS_CMD_MODIFY_QP) | BIT_ULL(IB_USER_VERBS_CMD_MODIFY_SRQ) | BIT_ULL(IB_USER_VERBS_CMD_OPEN_QP) | BIT_ULL(IB_USER_VERBS_CMD_OPEN_XRCD) | BIT_ULL(IB_USER_VERBS_CMD_QUERY_DEVICE) | BIT_ULL(IB_USER_VERBS_CMD_QUERY_PORT) | BIT_ULL(IB_USER_VERBS_CMD_QUERY_QP) | BIT_ULL(IB_USER_VERBS_CMD_QUERY_SRQ) | BIT_ULL(IB_USER_VERBS_CMD_REG_MR) | BIT_ULL(IB_USER_VERBS_CMD_REREG_MR) | BIT_ULL(IB_USER_VERBS_CMD_RESIZE_CQ); mutex_init(&device->subdev_lock); INIT_LIST_HEAD(&device->subdev_list_head); INIT_LIST_HEAD(&device->subdev_list); return device; } EXPORT_SYMBOL(_ib_alloc_device); /** * ib_dealloc_device - free an IB device struct * @device:structure to free * * Free a structure allocated with ib_alloc_device(). */ void ib_dealloc_device(struct ib_device *device) { if (device->ops.dealloc_driver) device->ops.dealloc_driver(device); /* * ib_unregister_driver() requires all devices to remain in the xarray * while their ops are callable. The last op we call is dealloc_driver * above. This is needed to create a fence on op callbacks prior to * allowing the driver module to unload. */ down_write(&devices_rwsem); if (xa_load(&devices, device->index) == device) xa_erase(&devices, device->index); up_write(&devices_rwsem); /* Expedite releasing netdev references */ free_netdevs(device); WARN_ON(!xa_empty(&device->compat_devs)); WARN_ON(!xa_empty(&device->client_data)); WARN_ON(refcount_read(&device->refcount)); rdma_restrack_clean(device); /* Balances with device_initialize */ put_device(&device->dev); } EXPORT_SYMBOL(ib_dealloc_device); /* * add_client_context() and remove_client_context() must be safe against * parallel calls on the same device - registration/unregistration of both the * device and client can be occurring in parallel. * * The routines need to be a fence, any caller must not return until the add * or remove is fully completed. */ static int add_client_context(struct ib_device *device, struct ib_client *client) { int ret = 0; if (!device->kverbs_provider && !client->no_kverbs_req) return 0; down_write(&device->client_data_rwsem); /* * So long as the client is registered hold both the client and device * unregistration locks. */ if (!refcount_inc_not_zero(&client->uses)) goto out_unlock; refcount_inc(&device->refcount); /* * Another caller to add_client_context got here first and has already * completely initialized context. */ if (xa_get_mark(&device->client_data, client->client_id, CLIENT_DATA_REGISTERED)) goto out; ret = xa_err(xa_store(&device->client_data, client->client_id, NULL, GFP_KERNEL)); if (ret) goto out; downgrade_write(&device->client_data_rwsem); if (client->add) { if (client->add(device)) { /* * If a client fails to add then the error code is * ignored, but we won't call any more ops on this * client. */ xa_erase(&device->client_data, client->client_id); up_read(&device->client_data_rwsem); ib_device_put(device); ib_client_put(client); return 0; } } /* Readers shall not see a client until add has been completed */ xa_set_mark(&device->client_data, client->client_id, CLIENT_DATA_REGISTERED); up_read(&device->client_data_rwsem); return 0; out: ib_device_put(device); ib_client_put(client); out_unlock: up_write(&device->client_data_rwsem); return ret; } static void remove_client_context(struct ib_device *device, unsigned int client_id) { struct ib_client *client; void *client_data; down_write(&device->client_data_rwsem); if (!xa_get_mark(&device->client_data, client_id, CLIENT_DATA_REGISTERED)) { up_write(&device->client_data_rwsem); return; } client_data = xa_load(&device->client_data, client_id); xa_clear_mark(&device->client_data, client_id, CLIENT_DATA_REGISTERED); client = xa_load(&clients, client_id); up_write(&device->client_data_rwsem); /* * Notice we cannot be holding any exclusive locks when calling the * remove callback as the remove callback can recurse back into any * public functions in this module and thus try for any locks those * functions take. * * For this reason clients and drivers should not call the * unregistration functions will holdling any locks. */ if (client->remove) client->remove(device, client_data); xa_erase(&device->client_data, client_id); ib_device_put(device); ib_client_put(client); } static int alloc_port_data(struct ib_device *device) { struct ib_port_data_rcu *pdata_rcu; u32 port; if (device->port_data) return 0; /* This can only be called once the physical port range is defined */ if (WARN_ON(!device->phys_port_cnt)) return -EINVAL; /* Reserve U32_MAX so the logic to go over all the ports is sane */ if (WARN_ON(device->phys_port_cnt == U32_MAX)) return -EINVAL; /* * device->port_data is indexed directly by the port number to make * access to this data as efficient as possible. * * Therefore port_data is declared as a 1 based array with potential * empty slots at the beginning. */ pdata_rcu = kzalloc(struct_size(pdata_rcu, pdata, size_add(rdma_end_port(device), 1)), GFP_KERNEL); if (!pdata_rcu) return -ENOMEM; /* * The rcu_head is put in front of the port data array and the stored * pointer is adjusted since we never need to see that member until * kfree_rcu. */ device->port_data = pdata_rcu->pdata; rdma_for_each_port (device, port) { struct ib_port_data *pdata = &device->port_data[port]; pdata->ib_dev = device; spin_lock_init(&pdata->pkey_list_lock); INIT_LIST_HEAD(&pdata->pkey_list); spin_lock_init(&pdata->netdev_lock); INIT_HLIST_NODE(&pdata->ndev_hash_link); } return 0; } static int verify_immutable(const struct ib_device *dev, u32 port) { return WARN_ON(!rdma_cap_ib_mad(dev, port) && rdma_max_mad_size(dev, port) != 0); } static int setup_port_data(struct ib_device *device) { u32 port; int ret; ret = alloc_port_data(device); if (ret) return ret; rdma_for_each_port (device, port) { struct ib_port_data *pdata = &device->port_data[port]; ret = device->ops.get_port_immutable(device, port, &pdata->immutable); if (ret) return ret; if (verify_immutable(device, port)) return -EINVAL; } return 0; } /** * ib_port_immutable_read() - Read rdma port's immutable data * @dev: IB device * @port: port number whose immutable data to read. It starts with index 1 and * valid upto including rdma_end_port(). */ const struct ib_port_immutable* ib_port_immutable_read(struct ib_device *dev, unsigned int port) { WARN_ON(!rdma_is_port_valid(dev, port)); return &dev->port_data[port].immutable; } EXPORT_SYMBOL(ib_port_immutable_read); void ib_get_device_fw_str(struct ib_device *dev, char *str) { if (dev->ops.get_dev_fw_str) dev->ops.get_dev_fw_str(dev, str); else str[0] = '\0'; } EXPORT_SYMBOL(ib_get_device_fw_str); static void ib_policy_change_task(struct work_struct *work) { struct ib_device *dev; unsigned long index; down_read(&devices_rwsem); xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED) { unsigned int i; rdma_for_each_port (dev, i) { u64 sp; ib_get_cached_subnet_prefix(dev, i, &sp); ib_security_cache_change(dev, i, sp); } } up_read(&devices_rwsem); } static int ib_security_change(struct notifier_block *nb, unsigned long event, void *lsm_data) { if (event != LSM_POLICY_CHANGE) return NOTIFY_DONE; schedule_work(&ib_policy_change_work); ib_mad_agent_security_change(); return NOTIFY_OK; } static void compatdev_release(struct device *dev) { struct ib_core_device *cdev = container_of(dev, struct ib_core_device, dev); kfree(cdev); } static int add_one_compat_dev(struct ib_device *device, struct rdma_dev_net *rnet) { struct ib_core_device *cdev; int ret; lockdep_assert_held(&rdma_nets_rwsem); if (!ib_devices_shared_netns) return 0; /* * Create and add compat device in all namespaces other than where it * is currently bound to. */ if (net_eq(read_pnet(&rnet->net), read_pnet(&device->coredev.rdma_net))) return 0; /* * The first of init_net() or ib_register_device() to take the * compat_devs_mutex wins and gets to add the device. Others will wait * for completion here. */ mutex_lock(&device->compat_devs_mutex); cdev = xa_load(&device->compat_devs, rnet->id); if (cdev) { ret = 0; goto done; } ret = xa_reserve(&device->compat_devs, rnet->id, GFP_KERNEL); if (ret) goto done; cdev = kzalloc(sizeof(*cdev), GFP_KERNEL); if (!cdev) { ret = -ENOMEM; goto cdev_err; } cdev->dev.parent = device->dev.parent; rdma_init_coredev(cdev, device, read_pnet(&rnet->net)); cdev->dev.release = compatdev_release; ret = dev_set_name(&cdev->dev, "%s", dev_name(&device->dev)); if (ret) goto add_err; ret = device_add(&cdev->dev); if (ret) goto add_err; ret = ib_setup_port_attrs(cdev); if (ret) goto port_err; ret = xa_err(xa_store(&device->compat_devs, rnet->id, cdev, GFP_KERNEL)); if (ret) goto insert_err; mutex_unlock(&device->compat_devs_mutex); return 0; insert_err: ib_free_port_attrs(cdev); port_err: device_del(&cdev->dev); add_err: put_device(&cdev->dev); cdev_err: xa_release(&device->compat_devs, rnet->id); done: mutex_unlock(&device->compat_devs_mutex); return ret; } static void remove_one_compat_dev(struct ib_device *device, u32 id) { struct ib_core_device *cdev; mutex_lock(&device->compat_devs_mutex); cdev = xa_erase(&device->compat_devs, id); mutex_unlock(&device->compat_devs_mutex); if (cdev) { ib_free_port_attrs(cdev); device_del(&cdev->dev); put_device(&cdev->dev); } } static void remove_compat_devs(struct ib_device *device) { struct ib_core_device *cdev; unsigned long index; xa_for_each (&device->compat_devs, index, cdev) remove_one_compat_dev(device, index); } static int add_compat_devs(struct ib_device *device) { struct rdma_dev_net *rnet; unsigned long index; int ret = 0; lockdep_assert_held(&devices_rwsem); down_read(&rdma_nets_rwsem); xa_for_each (&rdma_nets, index, rnet) { ret = add_one_compat_dev(device, rnet); if (ret) break; } up_read(&rdma_nets_rwsem); return ret; } static void remove_all_compat_devs(void) { struct ib_compat_device *cdev; struct ib_device *dev; unsigned long index; down_read(&devices_rwsem); xa_for_each (&devices, index, dev) { unsigned long c_index = 0; /* Hold nets_rwsem so that any other thread modifying this * system param can sync with this thread. */ down_read(&rdma_nets_rwsem); xa_for_each (&dev->compat_devs, c_index, cdev) remove_one_compat_dev(dev, c_index); up_read(&rdma_nets_rwsem); } up_read(&devices_rwsem); } static int add_all_compat_devs(void) { struct rdma_dev_net *rnet; struct ib_device *dev; unsigned long index; int ret = 0; down_read(&devices_rwsem); xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED) { unsigned long net_index = 0; /* Hold nets_rwsem so that any other thread modifying this * system param can sync with this thread. */ down_read(&rdma_nets_rwsem); xa_for_each (&rdma_nets, net_index, rnet) { ret = add_one_compat_dev(dev, rnet); if (ret) break; } up_read(&rdma_nets_rwsem); } up_read(&devices_rwsem); if (ret) remove_all_compat_devs(); return ret; } int rdma_compatdev_set(u8 enable) { struct rdma_dev_net *rnet; unsigned long index; int ret = 0; down_write(&rdma_nets_rwsem); if (ib_devices_shared_netns == enable) { up_write(&rdma_nets_rwsem); return 0; } /* enable/disable of compat devices is not supported * when more than default init_net exists. */ xa_for_each (&rdma_nets, index, rnet) { ret++; break; } if (!ret) ib_devices_shared_netns = enable; up_write(&rdma_nets_rwsem); if (ret) return -EBUSY; if (enable) ret = add_all_compat_devs(); else remove_all_compat_devs(); return ret; } static void rdma_dev_exit_net(struct net *net) { struct rdma_dev_net *rnet = rdma_net_to_dev_net(net); struct ib_device *dev; unsigned long index; int ret; down_write(&rdma_nets_rwsem); /* * Prevent the ID from being re-used and hide the id from xa_for_each. */ ret = xa_err(xa_store(&rdma_nets, rnet->id, NULL, GFP_KERNEL)); WARN_ON(ret); up_write(&rdma_nets_rwsem); down_read(&devices_rwsem); xa_for_each (&devices, index, dev) { get_device(&dev->dev); /* * Release the devices_rwsem so that pontentially blocking * device_del, doesn't hold the devices_rwsem for too long. */ up_read(&devices_rwsem); remove_one_compat_dev(dev, rnet->id); /* * If the real device is in the NS then move it back to init. */ rdma_dev_change_netns(dev, net, &init_net); put_device(&dev->dev); down_read(&devices_rwsem); } up_read(&devices_rwsem); rdma_nl_net_exit(rnet); xa_erase(&rdma_nets, rnet->id); } static __net_init int rdma_dev_init_net(struct net *net) { struct rdma_dev_net *rnet = rdma_net_to_dev_net(net); unsigned long index; struct ib_device *dev; int ret; write_pnet(&rnet->net, net); ret = rdma_nl_net_init(rnet); if (ret) return ret; /* No need to create any compat devices in default init_net. */ if (net_eq(net, &init_net)) return 0; ret = xa_alloc(&rdma_nets, &rnet->id, rnet, xa_limit_32b, GFP_KERNEL); if (ret) { rdma_nl_net_exit(rnet); return ret; } down_read(&devices_rwsem); xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED) { /* Hold nets_rwsem so that netlink command cannot change * system configuration for device sharing mode. */ down_read(&rdma_nets_rwsem); ret = add_one_compat_dev(dev, rnet); up_read(&rdma_nets_rwsem); if (ret) break; } up_read(&devices_rwsem); if (ret) rdma_dev_exit_net(net); return ret; } /* * Assign the unique string device name and the unique device index. This is * undone by ib_dealloc_device. */ static int assign_name(struct ib_device *device, const char *name) { static u32 last_id; int ret; down_write(&devices_rwsem); /* Assign a unique name to the device */ if (strchr(name, '%')) ret = alloc_name(device, name); else ret = dev_set_name(&device->dev, name); if (ret) goto out; if (__ib_device_get_by_name(dev_name(&device->dev))) { ret = -ENFILE; goto out; } strscpy(device->name, dev_name(&device->dev), IB_DEVICE_NAME_MAX); ret = xa_alloc_cyclic(&devices, &device->index, device, xa_limit_31b, &last_id, GFP_KERNEL); if (ret > 0) ret = 0; out: up_write(&devices_rwsem); return ret; } /* * setup_device() allocates memory and sets up data that requires calling the * device ops, this is the only reason these actions are not done during * ib_alloc_device. It is undone by ib_dealloc_device(). */ static int setup_device(struct ib_device *device) { struct ib_udata uhw = {.outlen = 0, .inlen = 0}; int ret; ib_device_check_mandatory(device); ret = setup_port_data(device); if (ret) { dev_warn(&device->dev, "Couldn't create per-port data\n"); return ret; } memset(&device->attrs, 0, sizeof(device->attrs)); ret = device->ops.query_device(device, &device->attrs, &uhw); if (ret) { dev_warn(&device->dev, "Couldn't query the device attributes\n"); return ret; } return 0; } static void disable_device(struct ib_device *device) { u32 cid; WARN_ON(!refcount_read(&device->refcount)); down_write(&devices_rwsem); xa_clear_mark(&devices, device->index, DEVICE_REGISTERED); up_write(&devices_rwsem); /* * Remove clients in LIFO order, see assign_client_id. This could be * more efficient if xarray learns to reverse iterate. Since no new * clients can be added to this ib_device past this point we only need * the maximum possible client_id value here. */ down_read(&clients_rwsem); cid = highest_client_id; up_read(&clients_rwsem); while (cid) { cid--; remove_client_context(device, cid); } ib_cq_pool_cleanup(device); /* Pairs with refcount_set in enable_device */ ib_device_put(device); wait_for_completion(&device->unreg_completion); /* * compat devices must be removed after device refcount drops to zero. * Otherwise init_net() may add more compatdevs after removing compat * devices and before device is disabled. */ remove_compat_devs(device); } /* * An enabled device is visible to all clients and to all the public facing * APIs that return a device pointer. This always returns with a new get, even * if it fails. */ static int enable_device_and_get(struct ib_device *device) { struct ib_client *client; unsigned long index; int ret = 0; /* * One ref belongs to the xa and the other belongs to this * thread. This is needed to guard against parallel unregistration. */ refcount_set(&device->refcount, 2); down_write(&devices_rwsem); xa_set_mark(&devices, device->index, DEVICE_REGISTERED); /* * By using downgrade_write() we ensure that no other thread can clear * DEVICE_REGISTERED while we are completing the client setup. */ downgrade_write(&devices_rwsem); if (device->ops.enable_driver) { ret = device->ops.enable_driver(device); if (ret) goto out; } down_read(&clients_rwsem); xa_for_each_marked (&clients, index, client, CLIENT_REGISTERED) { ret = add_client_context(device, client); if (ret) break; } up_read(&clients_rwsem); if (!ret) ret = add_compat_devs(device); out: up_read(&devices_rwsem); return ret; } static void prevent_dealloc_device(struct ib_device *ib_dev) { } static void ib_device_notify_register(struct ib_device *device) { struct net_device *netdev; u32 port; int ret; ret = rdma_nl_notify_event(device, 0, RDMA_REGISTER_EVENT); if (ret) return; rdma_for_each_port(device, port) { netdev = ib_device_get_netdev(device, port); if (!netdev) continue; ret = rdma_nl_notify_event(device, port, RDMA_NETDEV_ATTACH_EVENT); dev_put(netdev); if (ret) return; } } /** * ib_register_device - Register an IB device with IB core * @device: Device to register * @name: unique string device name. This may include a '%' which will * cause a unique index to be added to the passed device name. * @dma_device: pointer to a DMA-capable device. If %NULL, then the IB * device will be used. In this case the caller should fully * setup the ibdev for DMA. This usually means using dma_virt_ops. * * Low-level drivers use ib_register_device() to register their * devices with the IB core. All registered clients will receive a * callback for each device that is added. @device must be allocated * with ib_alloc_device(). * * If the driver uses ops.dealloc_driver and calls any ib_unregister_device() * asynchronously then the device pointer may become freed as soon as this * function returns. */ int ib_register_device(struct ib_device *device, const char *name, struct device *dma_device) { int ret; ret = assign_name(device, name); if (ret) return ret; /* * If the caller does not provide a DMA capable device then the IB core * will set up ib_sge and scatterlist structures that stash the kernel * virtual address into the address field. */ WARN_ON(dma_device && !dma_device->dma_parms); device->dma_device = dma_device; ret = setup_device(device); if (ret) return ret; ret = ib_cache_setup_one(device); if (ret) { dev_warn(&device->dev, "Couldn't set up InfiniBand P_Key/GID cache\n"); return ret; } device->groups[0] = &ib_dev_attr_group; device->groups[1] = device->ops.device_group; ret = ib_setup_device_attrs(device); if (ret) goto cache_cleanup; ib_device_register_rdmacg(device); rdma_counter_init(device); /* * Ensure that ADD uevent is not fired because it * is too early amd device is not initialized yet. */ dev_set_uevent_suppress(&device->dev, true); ret = device_add(&device->dev); if (ret) goto cg_cleanup; ret = ib_setup_port_attrs(&device->coredev); if (ret) { dev_warn(&device->dev, "Couldn't register device with driver model\n"); goto dev_cleanup; } ret = enable_device_and_get(device); if (ret) { void (*dealloc_fn)(struct ib_device *); /* * If we hit this error flow then we don't want to * automatically dealloc the device since the caller is * expected to call ib_dealloc_device() after * ib_register_device() fails. This is tricky due to the * possibility for a parallel unregistration along with this * error flow. Since we have a refcount here we know any * parallel flow is stopped in disable_device and will see the * special dealloc_driver pointer, causing the responsibility to * ib_dealloc_device() to revert back to this thread. */ dealloc_fn = device->ops.dealloc_driver; device->ops.dealloc_driver = prevent_dealloc_device; ib_device_put(device); __ib_unregister_device(device); device->ops.dealloc_driver = dealloc_fn; dev_set_uevent_suppress(&device->dev, false); return ret; } dev_set_uevent_suppress(&device->dev, false); /* Mark for userspace that device is ready */ kobject_uevent(&device->dev.kobj, KOBJ_ADD); ib_device_notify_register(device); ib_device_put(device); return 0; dev_cleanup: device_del(&device->dev); cg_cleanup: dev_set_uevent_suppress(&device->dev, false); ib_device_unregister_rdmacg(device); cache_cleanup: ib_cache_cleanup_one(device); return ret; } EXPORT_SYMBOL(ib_register_device); /* Callers must hold a get on the device. */ static void __ib_unregister_device(struct ib_device *ib_dev) { struct ib_device *sub, *tmp; mutex_lock(&ib_dev->subdev_lock); list_for_each_entry_safe_reverse(sub, tmp, &ib_dev->subdev_list_head, subdev_list) { list_del(&sub->subdev_list); ib_dev->ops.del_sub_dev(sub); ib_device_put(ib_dev); } mutex_unlock(&ib_dev->subdev_lock); /* * We have a registration lock so that all the calls to unregister are * fully fenced, once any unregister returns the device is truely * unregistered even if multiple callers are unregistering it at the * same time. This also interacts with the registration flow and * provides sane semantics if register and unregister are racing. */ mutex_lock(&ib_dev->unregistration_lock); if (!refcount_read(&ib_dev->refcount)) goto out; disable_device(ib_dev); rdma_nl_notify_event(ib_dev, 0, RDMA_UNREGISTER_EVENT); /* Expedite removing unregistered pointers from the hash table */ free_netdevs(ib_dev); ib_free_port_attrs(&ib_dev->coredev); device_del(&ib_dev->dev); ib_device_unregister_rdmacg(ib_dev); ib_cache_cleanup_one(ib_dev); /* * Drivers using the new flow may not call ib_dealloc_device except * in error unwind prior to registration success. */ if (ib_dev->ops.dealloc_driver && ib_dev->ops.dealloc_driver != prevent_dealloc_device) { WARN_ON(kref_read(&ib_dev->dev.kobj.kref) <= 1); ib_dealloc_device(ib_dev); } out: mutex_unlock(&ib_dev->unregistration_lock); } /** * ib_unregister_device - Unregister an IB device * @ib_dev: The device to unregister * * Unregister an IB device. All clients will receive a remove callback. * * Callers should call this routine only once, and protect against races with * registration. Typically it should only be called as part of a remove * callback in an implementation of driver core's struct device_driver and * related. * * If ops.dealloc_driver is used then ib_dev will be freed upon return from * this function. */ void ib_unregister_device(struct ib_device *ib_dev) { get_device(&ib_dev->dev); __ib_unregister_device(ib_dev); put_device(&ib_dev->dev); } EXPORT_SYMBOL(ib_unregister_device); /** * ib_unregister_device_and_put - Unregister a device while holding a 'get' * @ib_dev: The device to unregister * * This is the same as ib_unregister_device(), except it includes an internal * ib_device_put() that should match a 'get' obtained by the caller. * * It is safe to call this routine concurrently from multiple threads while * holding the 'get'. When the function returns the device is fully * unregistered. * * Drivers using this flow MUST use the driver_unregister callback to clean up * their resources associated with the device and dealloc it. */ void ib_unregister_device_and_put(struct ib_device *ib_dev) { WARN_ON(!ib_dev->ops.dealloc_driver); get_device(&ib_dev->dev); ib_device_put(ib_dev); __ib_unregister_device(ib_dev); put_device(&ib_dev->dev); } EXPORT_SYMBOL(ib_unregister_device_and_put); /** * ib_unregister_driver - Unregister all IB devices for a driver * @driver_id: The driver to unregister * * This implements a fence for device unregistration. It only returns once all * devices associated with the driver_id have fully completed their * unregistration and returned from ib_unregister_device*(). * * If device's are not yet unregistered it goes ahead and starts unregistering * them. * * This does not block creation of new devices with the given driver_id, that * is the responsibility of the caller. */ void ib_unregister_driver(enum rdma_driver_id driver_id) { struct ib_device *ib_dev; unsigned long index; down_read(&devices_rwsem); xa_for_each (&devices, index, ib_dev) { if (ib_dev->ops.driver_id != driver_id) continue; get_device(&ib_dev->dev); up_read(&devices_rwsem); WARN_ON(!ib_dev->ops.dealloc_driver); __ib_unregister_device(ib_dev); put_device(&ib_dev->dev); down_read(&devices_rwsem); } up_read(&devices_rwsem); } EXPORT_SYMBOL(ib_unregister_driver); static void ib_unregister_work(struct work_struct *work) { struct ib_device *ib_dev = container_of(work, struct ib_device, unregistration_work); __ib_unregister_device(ib_dev); put_device(&ib_dev->dev); } /** * ib_unregister_device_queued - Unregister a device using a work queue * @ib_dev: The device to unregister * * This schedules an asynchronous unregistration using a WQ for the device. A * driver should use this to avoid holding locks while doing unregistration, * such as holding the RTNL lock. * * Drivers using this API must use ib_unregister_driver before module unload * to ensure that all scheduled unregistrations have completed. */ void ib_unregister_device_queued(struct ib_device *ib_dev) { WARN_ON(!refcount_read(&ib_dev->refcount)); WARN_ON(!ib_dev->ops.dealloc_driver); get_device(&ib_dev->dev); if (!queue_work(ib_unreg_wq, &ib_dev->unregistration_work)) put_device(&ib_dev->dev); } EXPORT_SYMBOL(ib_unregister_device_queued); /* * The caller must pass in a device that has the kref held and the refcount * released. If the device is in cur_net and still registered then it is moved * into net. */ static int rdma_dev_change_netns(struct ib_device *device, struct net *cur_net, struct net *net) { int ret2 = -EINVAL; int ret; mutex_lock(&device->unregistration_lock); /* * If a device not under ib_device_get() or if the unregistration_lock * is not held, the namespace can be changed, or it can be unregistered. * Check again under the lock. */ if (refcount_read(&device->refcount) == 0 || !net_eq(cur_net, read_pnet(&device->coredev.rdma_net))) { ret = -ENODEV; goto out; } kobject_uevent(&device->dev.kobj, KOBJ_REMOVE); disable_device(device); /* * At this point no one can be using the device, so it is safe to * change the namespace. */ write_pnet(&device->coredev.rdma_net, net); down_read(&devices_rwsem); /* * Currently rdma devices are system wide unique. So the device name * is guaranteed free in the new namespace. Publish the new namespace * at the sysfs level. */ ret = device_rename(&device->dev, dev_name(&device->dev)); up_read(&devices_rwsem); if (ret) { dev_warn(&device->dev, "%s: Couldn't rename device after namespace change\n", __func__); /* Try and put things back and re-enable the device */ write_pnet(&device->coredev.rdma_net, cur_net); } ret2 = enable_device_and_get(device); if (ret2) { /* * This shouldn't really happen, but if it does, let the user * retry at later point. So don't disable the device. */ dev_warn(&device->dev, "%s: Couldn't re-enable device after namespace change\n", __func__); } kobject_uevent(&device->dev.kobj, KOBJ_ADD); ib_device_put(device); out: mutex_unlock(&device->unregistration_lock); if (ret) return ret; return ret2; } int ib_device_set_netns_put(struct sk_buff *skb, struct ib_device *dev, u32 ns_fd) { struct net *net; int ret; net = get_net_ns_by_fd(ns_fd); if (IS_ERR(net)) { ret = PTR_ERR(net); goto net_err; } if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { ret = -EPERM; goto ns_err; } /* * All the ib_clients, including uverbs, are reset when the namespace is * changed and this cannot be blocked waiting for userspace to do * something, so disassociation is mandatory. */ if (!dev->ops.disassociate_ucontext || ib_devices_shared_netns) { ret = -EOPNOTSUPP; goto ns_err; } get_device(&dev->dev); ib_device_put(dev); ret = rdma_dev_change_netns(dev, current->nsproxy->net_ns, net); put_device(&dev->dev); put_net(net); return ret; ns_err: put_net(net); net_err: ib_device_put(dev); return ret; } static struct pernet_operations rdma_dev_net_ops = { .init = rdma_dev_init_net, .exit = rdma_dev_exit_net, .id = &rdma_dev_net_id, .size = sizeof(struct rdma_dev_net), }; static int assign_client_id(struct ib_client *client) { int ret; lockdep_assert_held(&clients_rwsem); /* * The add/remove callbacks must be called in FIFO/LIFO order. To * achieve this we assign client_ids so they are sorted in * registration order. */ client->client_id = highest_client_id; ret = xa_insert(&clients, client->client_id, client, GFP_KERNEL); if (ret) return ret; highest_client_id++; xa_set_mark(&clients, client->client_id, CLIENT_REGISTERED); return 0; } static void remove_client_id(struct ib_client *client) { down_write(&clients_rwsem); xa_erase(&clients, client->client_id); for (; highest_client_id; highest_client_id--) if (xa_load(&clients, highest_client_id - 1)) break; up_write(&clients_rwsem); } /** * ib_register_client - Register an IB client * @client:Client to register * * Upper level users of the IB drivers can use ib_register_client() to * register callbacks for IB device addition and removal. When an IB * device is added, each registered client's add method will be called * (in the order the clients were registered), and when a device is * removed, each client's remove method will be called (in the reverse * order that clients were registered). In addition, when * ib_register_client() is called, the client will receive an add * callback for all devices already registered. */ int ib_register_client(struct ib_client *client) { struct ib_device *device; unsigned long index; bool need_unreg = false; int ret; refcount_set(&client->uses, 1); init_completion(&client->uses_zero); /* * The devices_rwsem is held in write mode to ensure that a racing * ib_register_device() sees a consisent view of clients and devices. */ down_write(&devices_rwsem); down_write(&clients_rwsem); ret = assign_client_id(client); if (ret) goto out; need_unreg = true; xa_for_each_marked (&devices, index, device, DEVICE_REGISTERED) { ret = add_client_context(device, client); if (ret) goto out; } ret = 0; out: up_write(&clients_rwsem); up_write(&devices_rwsem); if (need_unreg && ret) ib_unregister_client(client); return ret; } EXPORT_SYMBOL(ib_register_client); /** * ib_unregister_client - Unregister an IB client * @client:Client to unregister * * Upper level users use ib_unregister_client() to remove their client * registration. When ib_unregister_client() is called, the client * will receive a remove callback for each IB device still registered. * * This is a full fence, once it returns no client callbacks will be called, * or are running in another thread. */ void ib_unregister_client(struct ib_client *client) { struct ib_device *device; unsigned long index; down_write(&clients_rwsem); ib_client_put(client); xa_clear_mark(&clients, client->client_id, CLIENT_REGISTERED); up_write(&clients_rwsem); /* We do not want to have locks while calling client->remove() */ rcu_read_lock(); xa_for_each (&devices, index, device) { if (!ib_device_try_get(device)) continue; rcu_read_unlock(); remove_client_context(device, client->client_id); ib_device_put(device); rcu_read_lock(); } rcu_read_unlock(); /* * remove_client_context() is not a fence, it can return even though a * removal is ongoing. Wait until all removals are completed. */ wait_for_completion(&client->uses_zero); remove_client_id(client); } EXPORT_SYMBOL(ib_unregister_client); static int __ib_get_global_client_nl_info(const char *client_name, struct ib_client_nl_info *res) { struct ib_client *client; unsigned long index; int ret = -ENOENT; down_read(&clients_rwsem); xa_for_each_marked (&clients, index, client, CLIENT_REGISTERED) { if (strcmp(client->name, client_name) != 0) continue; if (!client->get_global_nl_info) { ret = -EOPNOTSUPP; break; } ret = client->get_global_nl_info(res); if (WARN_ON(ret == -ENOENT)) ret = -EINVAL; if (!ret && res->cdev) get_device(res->cdev); break; } up_read(&clients_rwsem); return ret; } static int __ib_get_client_nl_info(struct ib_device *ibdev, const char *client_name, struct ib_client_nl_info *res) { unsigned long index; void *client_data; int ret = -ENOENT; down_read(&ibdev->client_data_rwsem); xan_for_each_marked (&ibdev->client_data, index, client_data, CLIENT_DATA_REGISTERED) { struct ib_client *client = xa_load(&clients, index); if (!client || strcmp(client->name, client_name) != 0) continue; if (!client->get_nl_info) { ret = -EOPNOTSUPP; break; } ret = client->get_nl_info(ibdev, client_data, res); if (WARN_ON(ret == -ENOENT)) ret = -EINVAL; /* * The cdev is guaranteed valid as long as we are inside the * client_data_rwsem as remove_one can't be called. Keep it * valid for the caller. */ if (!ret && res->cdev) get_device(res->cdev); break; } up_read(&ibdev->client_data_rwsem); return ret; } /** * ib_get_client_nl_info - Fetch the nl_info from a client * @ibdev: IB device * @client_name: Name of the client * @res: Result of the query */ int ib_get_client_nl_info(struct ib_device *ibdev, const char *client_name, struct ib_client_nl_info *res) { int ret; if (ibdev) ret = __ib_get_client_nl_info(ibdev, client_name, res); else ret = __ib_get_global_client_nl_info(client_name, res); #ifdef CONFIG_MODULES if (ret == -ENOENT) { request_module("rdma-client-%s", client_name); if (ibdev) ret = __ib_get_client_nl_info(ibdev, client_name, res); else ret = __ib_get_global_client_nl_info(client_name, res); } #endif if (ret) { if (ret == -ENOENT) return -EOPNOTSUPP; return ret; } if (WARN_ON(!res->cdev)) return -EINVAL; return 0; } /** * ib_set_client_data - Set IB client context * @device:Device to set context for * @client:Client to set context for * @data:Context to set * * ib_set_client_data() sets client context data that can be retrieved with * ib_get_client_data(). This can only be called while the client is * registered to the device, once the ib_client remove() callback returns this * cannot be called. */ void ib_set_client_data(struct ib_device *device, struct ib_client *client, void *data) { void *rc; if (WARN_ON(IS_ERR(data))) data = NULL; rc = xa_store(&device->client_data, client->client_id, data, GFP_KERNEL); WARN_ON(xa_is_err(rc)); } EXPORT_SYMBOL(ib_set_client_data); /** * ib_register_event_handler - Register an IB event handler * @event_handler:Handler to register * * ib_register_event_handler() registers an event handler that will be * called back when asynchronous IB events occur (as defined in * chapter 11 of the InfiniBand Architecture Specification). This * callback occurs in workqueue context. */ void ib_register_event_handler(struct ib_event_handler *event_handler) { down_write(&event_handler->device->event_handler_rwsem); list_add_tail(&event_handler->list, &event_handler->device->event_handler_list); up_write(&event_handler->device->event_handler_rwsem); } EXPORT_SYMBOL(ib_register_event_handler); /** * ib_unregister_event_handler - Unregister an event handler * @event_handler:Handler to unregister * * Unregister an event handler registered with * ib_register_event_handler(). */ void ib_unregister_event_handler(struct ib_event_handler *event_handler) { down_write(&event_handler->device->event_handler_rwsem); list_del(&event_handler->list); up_write(&event_handler->device->event_handler_rwsem); } EXPORT_SYMBOL(ib_unregister_event_handler); void ib_dispatch_event_clients(struct ib_event *event) { struct ib_event_handler *handler; down_read(&event->device->event_handler_rwsem); list_for_each_entry(handler, &event->device->event_handler_list, list) handler->handler(handler, event); up_read(&event->device->event_handler_rwsem); } static int iw_query_port(struct ib_device *device, u32 port_num, struct ib_port_attr *port_attr) { struct in_device *inetdev; struct net_device *netdev; memset(port_attr, 0, sizeof(*port_attr)); netdev = ib_device_get_netdev(device, port_num); if (!netdev) return -ENODEV; port_attr->max_mtu = IB_MTU_4096; port_attr->active_mtu = ib_mtu_int_to_enum(netdev->mtu); if (!netif_carrier_ok(netdev)) { port_attr->state = IB_PORT_DOWN; port_attr->phys_state = IB_PORT_PHYS_STATE_DISABLED; } else { rcu_read_lock(); inetdev = __in_dev_get_rcu(netdev); if (inetdev && inetdev->ifa_list) { port_attr->state = IB_PORT_ACTIVE; port_attr->phys_state = IB_PORT_PHYS_STATE_LINK_UP; } else { port_attr->state = IB_PORT_INIT; port_attr->phys_state = IB_PORT_PHYS_STATE_PORT_CONFIGURATION_TRAINING; } rcu_read_unlock(); } dev_put(netdev); return device->ops.query_port(device, port_num, port_attr); } static int __ib_query_port(struct ib_device *device, u32 port_num, struct ib_port_attr *port_attr) { int err; memset(port_attr, 0, sizeof(*port_attr)); err = device->ops.query_port(device, port_num, port_attr); if (err || port_attr->subnet_prefix) return err; if (rdma_port_get_link_layer(device, port_num) != IB_LINK_LAYER_INFINIBAND) return 0; ib_get_cached_subnet_prefix(device, port_num, &port_attr->subnet_prefix); return 0; } /** * ib_query_port - Query IB port attributes * @device:Device to query * @port_num:Port number to query * @port_attr:Port attributes * * ib_query_port() returns the attributes of a port through the * @port_attr pointer. */ int ib_query_port(struct ib_device *device, u32 port_num, struct ib_port_attr *port_attr) { if (!rdma_is_port_valid(device, port_num)) return -EINVAL; if (rdma_protocol_iwarp(device, port_num)) return iw_query_port(device, port_num, port_attr); else return __ib_query_port(device, port_num, port_attr); } EXPORT_SYMBOL(ib_query_port); static void add_ndev_hash(struct ib_port_data *pdata) { unsigned long flags; might_sleep(); spin_lock_irqsave(&ndev_hash_lock, flags); if (hash_hashed(&pdata->ndev_hash_link)) { hash_del_rcu(&pdata->ndev_hash_link); spin_unlock_irqrestore(&ndev_hash_lock, flags); /* * We cannot do hash_add_rcu after a hash_del_rcu until the * grace period */ synchronize_rcu(); spin_lock_irqsave(&ndev_hash_lock, flags); } if (pdata->netdev) hash_add_rcu(ndev_hash, &pdata->ndev_hash_link, (uintptr_t)pdata->netdev); spin_unlock_irqrestore(&ndev_hash_lock, flags); } /** * ib_device_set_netdev - Associate the ib_dev with an underlying net_device * @ib_dev: Device to modify * @ndev: net_device to affiliate, may be NULL * @port: IB port the net_device is connected to * * Drivers should use this to link the ib_device to a netdev so the netdev * shows up in interfaces like ib_enum_roce_netdev. Only one netdev may be * affiliated with any port. * * The caller must ensure that the given ndev is not unregistered or * unregistering, and that either the ib_device is unregistered or * ib_device_set_netdev() is called with NULL when the ndev sends a * NETDEV_UNREGISTER event. */ int ib_device_set_netdev(struct ib_device *ib_dev, struct net_device *ndev, u32 port) { enum rdma_nl_notify_event_type etype; struct net_device *old_ndev; struct ib_port_data *pdata; unsigned long flags; int ret; if (!rdma_is_port_valid(ib_dev, port)) return -EINVAL; /* * Drivers wish to call this before ib_register_driver, so we have to * setup the port data early. */ ret = alloc_port_data(ib_dev); if (ret) return ret; pdata = &ib_dev->port_data[port]; spin_lock_irqsave(&pdata->netdev_lock, flags); old_ndev = rcu_dereference_protected( pdata->netdev, lockdep_is_held(&pdata->netdev_lock)); if (old_ndev == ndev) { spin_unlock_irqrestore(&pdata->netdev_lock, flags); return 0; } rcu_assign_pointer(pdata->netdev, ndev); netdev_put(old_ndev, &pdata->netdev_tracker); netdev_hold(ndev, &pdata->netdev_tracker, GFP_ATOMIC); spin_unlock_irqrestore(&pdata->netdev_lock, flags); add_ndev_hash(pdata); /* Make sure that the device is registered before we send events */ if (xa_load(&devices, ib_dev->index) != ib_dev) return 0; etype = ndev ? RDMA_NETDEV_ATTACH_EVENT : RDMA_NETDEV_DETACH_EVENT; rdma_nl_notify_event(ib_dev, port, etype); return 0; } EXPORT_SYMBOL(ib_device_set_netdev); static void free_netdevs(struct ib_device *ib_dev) { unsigned long flags; u32 port; if (!ib_dev->port_data) return; rdma_for_each_port (ib_dev, port) { struct ib_port_data *pdata = &ib_dev->port_data[port]; struct net_device *ndev; spin_lock_irqsave(&pdata->netdev_lock, flags); ndev = rcu_dereference_protected( pdata->netdev, lockdep_is_held(&pdata->netdev_lock)); if (ndev) { spin_lock(&ndev_hash_lock); hash_del_rcu(&pdata->ndev_hash_link); spin_unlock(&ndev_hash_lock); /* * If this is the last dev_put there is still a * synchronize_rcu before the netdev is kfreed, so we * can continue to rely on unlocked pointer * comparisons after the put */ rcu_assign_pointer(pdata->netdev, NULL); netdev_put(ndev, &pdata->netdev_tracker); } spin_unlock_irqrestore(&pdata->netdev_lock, flags); } } struct net_device *ib_device_get_netdev(struct ib_device *ib_dev, u32 port) { struct ib_port_data *pdata; struct net_device *res; if (!rdma_is_port_valid(ib_dev, port)) return NULL; if (!ib_dev->port_data) return NULL; pdata = &ib_dev->port_data[port]; /* * New drivers should use ib_device_set_netdev() not the legacy * get_netdev(). */ if (ib_dev->ops.get_netdev) res = ib_dev->ops.get_netdev(ib_dev, port); else { spin_lock(&pdata->netdev_lock); res = rcu_dereference_protected( pdata->netdev, lockdep_is_held(&pdata->netdev_lock)); dev_hold(res); spin_unlock(&pdata->netdev_lock); } return res; } EXPORT_SYMBOL(ib_device_get_netdev); /** * ib_device_get_by_netdev - Find an IB device associated with a netdev * @ndev: netdev to locate * @driver_id: The driver ID that must match (RDMA_DRIVER_UNKNOWN matches all) * * Find and hold an ib_device that is associated with a netdev via * ib_device_set_netdev(). The caller must call ib_device_put() on the * returned pointer. */ struct ib_device *ib_device_get_by_netdev(struct net_device *ndev, enum rdma_driver_id driver_id) { struct ib_device *res = NULL; struct ib_port_data *cur; rcu_read_lock(); hash_for_each_possible_rcu (ndev_hash, cur, ndev_hash_link, (uintptr_t)ndev) { if (rcu_access_pointer(cur->netdev) == ndev && (driver_id == RDMA_DRIVER_UNKNOWN || cur->ib_dev->ops.driver_id == driver_id) && ib_device_try_get(cur->ib_dev)) { res = cur->ib_dev; break; } } rcu_read_unlock(); return res; } EXPORT_SYMBOL(ib_device_get_by_netdev); /** * ib_enum_roce_netdev - enumerate all RoCE ports * @ib_dev : IB device we want to query * @filter: Should we call the callback? * @filter_cookie: Cookie passed to filter * @cb: Callback to call for each found RoCE ports * @cookie: Cookie passed back to the callback * * Enumerates all of the physical RoCE ports of ib_dev * which are related to netdevice and calls callback() on each * device for which filter() function returns non zero. */ void ib_enum_roce_netdev(struct ib_device *ib_dev, roce_netdev_filter filter, void *filter_cookie, roce_netdev_callback cb, void *cookie) { u32 port; rdma_for_each_port (ib_dev, port) if (rdma_protocol_roce(ib_dev, port)) { struct net_device *idev = ib_device_get_netdev(ib_dev, port); if (filter(ib_dev, port, idev, filter_cookie)) cb(ib_dev, port, idev, cookie); dev_put(idev); } } /** * ib_enum_all_roce_netdevs - enumerate all RoCE devices * @filter: Should we call the callback? * @filter_cookie: Cookie passed to filter * @cb: Callback to call for each found RoCE ports * @cookie: Cookie passed back to the callback * * Enumerates all RoCE devices' physical ports which are related * to netdevices and calls callback() on each device for which * filter() function returns non zero. */ void ib_enum_all_roce_netdevs(roce_netdev_filter filter, void *filter_cookie, roce_netdev_callback cb, void *cookie) { struct ib_device *dev; unsigned long index; down_read(&devices_rwsem); xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED) ib_enum_roce_netdev(dev, filter, filter_cookie, cb, cookie); up_read(&devices_rwsem); } /* * ib_enum_all_devs - enumerate all ib_devices * @cb: Callback to call for each found ib_device * * Enumerates all ib_devices and calls callback() on each device. */ int ib_enum_all_devs(nldev_callback nldev_cb, struct sk_buff *skb, struct netlink_callback *cb) { unsigned long index; struct ib_device *dev; unsigned int idx = 0; int ret = 0; down_read(&devices_rwsem); xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED) { if (!rdma_dev_access_netns(dev, sock_net(skb->sk))) continue; ret = nldev_cb(dev, skb, cb, idx); if (ret) break; idx++; } up_read(&devices_rwsem); return ret; } /** * ib_query_pkey - Get P_Key table entry * @device:Device to query * @port_num:Port number to query * @index:P_Key table index to query * @pkey:Returned P_Key * * ib_query_pkey() fetches the specified P_Key table entry. */ int ib_query_pkey(struct ib_device *device, u32 port_num, u16 index, u16 *pkey) { if (!rdma_is_port_valid(device, port_num)) return -EINVAL; if (!device->ops.query_pkey) return -EOPNOTSUPP; return device->ops.query_pkey(device, port_num, index, pkey); } EXPORT_SYMBOL(ib_query_pkey); /** * ib_modify_device - Change IB device attributes * @device:Device to modify * @device_modify_mask:Mask of attributes to change * @device_modify:New attribute values * * ib_modify_device() changes a device's attributes as specified by * the @device_modify_mask and @device_modify structure. */ int ib_modify_device(struct ib_device *device, int device_modify_mask, struct ib_device_modify *device_modify) { if (!device->ops.modify_device) return -EOPNOTSUPP; return device->ops.modify_device(device, device_modify_mask, device_modify); } EXPORT_SYMBOL(ib_modify_device); /** * ib_modify_port - Modifies the attributes for the specified port. * @device: The device to modify. * @port_num: The number of the port to modify. * @port_modify_mask: Mask used to specify which attributes of the port * to change. * @port_modify: New attribute values for the port. * * ib_modify_port() changes a port's attributes as specified by the * @port_modify_mask and @port_modify structure. */ int ib_modify_port(struct ib_device *device, u32 port_num, int port_modify_mask, struct ib_port_modify *port_modify) { int rc; if (!rdma_is_port_valid(device, port_num)) return -EINVAL; if (device->ops.modify_port) rc = device->ops.modify_port(device, port_num, port_modify_mask, port_modify); else if (rdma_protocol_roce(device, port_num) && ((port_modify->set_port_cap_mask & ~IB_PORT_CM_SUP) == 0 || (port_modify->clr_port_cap_mask & ~IB_PORT_CM_SUP) == 0)) rc = 0; else rc = -EOPNOTSUPP; return rc; } EXPORT_SYMBOL(ib_modify_port); /** * ib_find_gid - Returns the port number and GID table index where * a specified GID value occurs. Its searches only for IB link layer. * @device: The device to query. * @gid: The GID value to search for. * @port_num: The port number of the device where the GID value was found. * @index: The index into the GID table where the GID was found. This * parameter may be NULL. */ int ib_find_gid(struct ib_device *device, union ib_gid *gid, u32 *port_num, u16 *index) { union ib_gid tmp_gid; u32 port; int ret, i; rdma_for_each_port (device, port) { if (!rdma_protocol_ib(device, port)) continue; for (i = 0; i < device->port_data[port].immutable.gid_tbl_len; ++i) { ret = rdma_query_gid(device, port, i, &tmp_gid); if (ret) continue; if (!memcmp(&tmp_gid, gid, sizeof *gid)) { *port_num = port; if (index) *index = i; return 0; } } } return -ENOENT; } EXPORT_SYMBOL(ib_find_gid); /** * ib_find_pkey - Returns the PKey table index where a specified * PKey value occurs. * @device: The device to query. * @port_num: The port number of the device to search for the PKey. * @pkey: The PKey value to search for. * @index: The index into the PKey table where the PKey was found. */ int ib_find_pkey(struct ib_device *device, u32 port_num, u16 pkey, u16 *index) { int ret, i; u16 tmp_pkey; int partial_ix = -1; for (i = 0; i < device->port_data[port_num].immutable.pkey_tbl_len; ++i) { ret = ib_query_pkey(device, port_num, i, &tmp_pkey); if (ret) return ret; if ((pkey & 0x7fff) == (tmp_pkey & 0x7fff)) { /* if there is full-member pkey take it.*/ if (tmp_pkey & 0x8000) { *index = i; return 0; } if (partial_ix < 0) partial_ix = i; } } /*no full-member, if exists take the limited*/ if (partial_ix >= 0) { *index = partial_ix; return 0; } return -ENOENT; } EXPORT_SYMBOL(ib_find_pkey); /** * ib_get_net_dev_by_params() - Return the appropriate net_dev * for a received CM request * @dev: An RDMA device on which the request has been received. * @port: Port number on the RDMA device. * @pkey: The Pkey the request came on. * @gid: A GID that the net_dev uses to communicate. * @addr: Contains the IP address that the request specified as its * destination. * */ struct net_device *ib_get_net_dev_by_params(struct ib_device *dev, u32 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr) { struct net_device *net_dev = NULL; unsigned long index; void *client_data; if (!rdma_protocol_ib(dev, port)) return NULL; /* * Holding the read side guarantees that the client will not become * unregistered while we are calling get_net_dev_by_params() */ down_read(&dev->client_data_rwsem); xan_for_each_marked (&dev->client_data, index, client_data, CLIENT_DATA_REGISTERED) { struct ib_client *client = xa_load(&clients, index); if (!client || !client->get_net_dev_by_params) continue; net_dev = client->get_net_dev_by_params(dev, port, pkey, gid, addr, client_data); if (net_dev) break; } up_read(&dev->client_data_rwsem); return net_dev; } EXPORT_SYMBOL(ib_get_net_dev_by_params); void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops) { struct ib_device_ops *dev_ops = &dev->ops; #define SET_DEVICE_OP(ptr, name) \ do { \ if (ops->name) \ if (!((ptr)->name)) \ (ptr)->name = ops->name; \ } while (0) #define SET_OBJ_SIZE(ptr, name) SET_DEVICE_OP(ptr, size_##name) if (ops->driver_id != RDMA_DRIVER_UNKNOWN) { WARN_ON(dev_ops->driver_id != RDMA_DRIVER_UNKNOWN && dev_ops->driver_id != ops->driver_id); dev_ops->driver_id = ops->driver_id; } if (ops->owner) { WARN_ON(dev_ops->owner && dev_ops->owner != ops->owner); dev_ops->owner = ops->owner; } if (ops->uverbs_abi_ver) dev_ops->uverbs_abi_ver = ops->uverbs_abi_ver; dev_ops->uverbs_no_driver_id_binding |= ops->uverbs_no_driver_id_binding; SET_DEVICE_OP(dev_ops, add_gid); SET_DEVICE_OP(dev_ops, add_sub_dev); SET_DEVICE_OP(dev_ops, advise_mr); SET_DEVICE_OP(dev_ops, alloc_dm); SET_DEVICE_OP(dev_ops, alloc_hw_device_stats); SET_DEVICE_OP(dev_ops, alloc_hw_port_stats); SET_DEVICE_OP(dev_ops, alloc_mr); SET_DEVICE_OP(dev_ops, alloc_mr_integrity); SET_DEVICE_OP(dev_ops, alloc_mw); SET_DEVICE_OP(dev_ops, alloc_pd); SET_DEVICE_OP(dev_ops, alloc_rdma_netdev); SET_DEVICE_OP(dev_ops, alloc_ucontext); SET_DEVICE_OP(dev_ops, alloc_xrcd); SET_DEVICE_OP(dev_ops, attach_mcast); SET_DEVICE_OP(dev_ops, check_mr_status); SET_DEVICE_OP(dev_ops, counter_alloc_stats); SET_DEVICE_OP(dev_ops, counter_bind_qp); SET_DEVICE_OP(dev_ops, counter_dealloc); SET_DEVICE_OP(dev_ops, counter_unbind_qp); SET_DEVICE_OP(dev_ops, counter_update_stats); SET_DEVICE_OP(dev_ops, create_ah); SET_DEVICE_OP(dev_ops, create_counters); SET_DEVICE_OP(dev_ops, create_cq); SET_DEVICE_OP(dev_ops, create_flow); SET_DEVICE_OP(dev_ops, create_qp); SET_DEVICE_OP(dev_ops, create_rwq_ind_table); SET_DEVICE_OP(dev_ops, create_srq); SET_DEVICE_OP(dev_ops, create_user_ah); SET_DEVICE_OP(dev_ops, create_wq); SET_DEVICE_OP(dev_ops, dealloc_dm); SET_DEVICE_OP(dev_ops, dealloc_driver); SET_DEVICE_OP(dev_ops, dealloc_mw); SET_DEVICE_OP(dev_ops, dealloc_pd); SET_DEVICE_OP(dev_ops, dealloc_ucontext); SET_DEVICE_OP(dev_ops, dealloc_xrcd); SET_DEVICE_OP(dev_ops, del_gid); SET_DEVICE_OP(dev_ops, del_sub_dev); SET_DEVICE_OP(dev_ops, dereg_mr); SET_DEVICE_OP(dev_ops, destroy_ah); SET_DEVICE_OP(dev_ops, destroy_counters); SET_DEVICE_OP(dev_ops, destroy_cq); SET_DEVICE_OP(dev_ops, destroy_flow); SET_DEVICE_OP(dev_ops, destroy_flow_action); SET_DEVICE_OP(dev_ops, destroy_qp); SET_DEVICE_OP(dev_ops, destroy_rwq_ind_table); SET_DEVICE_OP(dev_ops, destroy_srq); SET_DEVICE_OP(dev_ops, destroy_wq); SET_DEVICE_OP(dev_ops, device_group); SET_DEVICE_OP(dev_ops, detach_mcast); SET_DEVICE_OP(dev_ops, disassociate_ucontext); SET_DEVICE_OP(dev_ops, drain_rq); SET_DEVICE_OP(dev_ops, drain_sq); SET_DEVICE_OP(dev_ops, enable_driver); SET_DEVICE_OP(dev_ops, fill_res_cm_id_entry); SET_DEVICE_OP(dev_ops, fill_res_cq_entry); SET_DEVICE_OP(dev_ops, fill_res_cq_entry_raw); SET_DEVICE_OP(dev_ops, fill_res_mr_entry); SET_DEVICE_OP(dev_ops, fill_res_mr_entry_raw); SET_DEVICE_OP(dev_ops, fill_res_qp_entry); SET_DEVICE_OP(dev_ops, fill_res_qp_entry_raw); SET_DEVICE_OP(dev_ops, fill_res_srq_entry); SET_DEVICE_OP(dev_ops, fill_res_srq_entry_raw); SET_DEVICE_OP(dev_ops, fill_stat_mr_entry); SET_DEVICE_OP(dev_ops, get_dev_fw_str); SET_DEVICE_OP(dev_ops, get_dma_mr); SET_DEVICE_OP(dev_ops, get_hw_stats); SET_DEVICE_OP(dev_ops, get_link_layer); SET_DEVICE_OP(dev_ops, get_netdev); SET_DEVICE_OP(dev_ops, get_numa_node); SET_DEVICE_OP(dev_ops, get_port_immutable); SET_DEVICE_OP(dev_ops, get_vector_affinity); SET_DEVICE_OP(dev_ops, get_vf_config); SET_DEVICE_OP(dev_ops, get_vf_guid); SET_DEVICE_OP(dev_ops, get_vf_stats); SET_DEVICE_OP(dev_ops, iw_accept); SET_DEVICE_OP(dev_ops, iw_add_ref); SET_DEVICE_OP(dev_ops, iw_connect); SET_DEVICE_OP(dev_ops, iw_create_listen); SET_DEVICE_OP(dev_ops, iw_destroy_listen); SET_DEVICE_OP(dev_ops, iw_get_qp); SET_DEVICE_OP(dev_ops, iw_reject); SET_DEVICE_OP(dev_ops, iw_rem_ref); SET_DEVICE_OP(dev_ops, map_mr_sg); SET_DEVICE_OP(dev_ops, map_mr_sg_pi); SET_DEVICE_OP(dev_ops, mmap); SET_DEVICE_OP(dev_ops, mmap_free); SET_DEVICE_OP(dev_ops, modify_ah); SET_DEVICE_OP(dev_ops, modify_cq); SET_DEVICE_OP(dev_ops, modify_device); SET_DEVICE_OP(dev_ops, modify_hw_stat); SET_DEVICE_OP(dev_ops, modify_port); SET_DEVICE_OP(dev_ops, modify_qp); SET_DEVICE_OP(dev_ops, modify_srq); SET_DEVICE_OP(dev_ops, modify_wq); SET_DEVICE_OP(dev_ops, peek_cq); SET_DEVICE_OP(dev_ops, poll_cq); SET_DEVICE_OP(dev_ops, port_groups); SET_DEVICE_OP(dev_ops, post_recv); SET_DEVICE_OP(dev_ops, post_send); SET_DEVICE_OP(dev_ops, post_srq_recv); SET_DEVICE_OP(dev_ops, process_mad); SET_DEVICE_OP(dev_ops, query_ah); SET_DEVICE_OP(dev_ops, query_device); SET_DEVICE_OP(dev_ops, query_gid); SET_DEVICE_OP(dev_ops, query_pkey); SET_DEVICE_OP(dev_ops, query_port); SET_DEVICE_OP(dev_ops, query_qp); SET_DEVICE_OP(dev_ops, query_srq); SET_DEVICE_OP(dev_ops, query_ucontext); SET_DEVICE_OP(dev_ops, rdma_netdev_get_params); SET_DEVICE_OP(dev_ops, read_counters); SET_DEVICE_OP(dev_ops, reg_dm_mr); SET_DEVICE_OP(dev_ops, reg_user_mr); SET_DEVICE_OP(dev_ops, reg_user_mr_dmabuf); SET_DEVICE_OP(dev_ops, req_notify_cq); SET_DEVICE_OP(dev_ops, rereg_user_mr); SET_DEVICE_OP(dev_ops, resize_cq); SET_DEVICE_OP(dev_ops, set_vf_guid); SET_DEVICE_OP(dev_ops, set_vf_link_state); SET_DEVICE_OP(dev_ops, ufile_hw_cleanup); SET_OBJ_SIZE(dev_ops, ib_ah); SET_OBJ_SIZE(dev_ops, ib_counters); SET_OBJ_SIZE(dev_ops, ib_cq); SET_OBJ_SIZE(dev_ops, ib_mw); SET_OBJ_SIZE(dev_ops, ib_pd); SET_OBJ_SIZE(dev_ops, ib_qp); SET_OBJ_SIZE(dev_ops, ib_rwq_ind_table); SET_OBJ_SIZE(dev_ops, ib_srq); SET_OBJ_SIZE(dev_ops, ib_ucontext); SET_OBJ_SIZE(dev_ops, ib_xrcd); } EXPORT_SYMBOL(ib_set_device_ops); int ib_add_sub_device(struct ib_device *parent, enum rdma_nl_dev_type type, const char *name) { struct ib_device *sub; int ret = 0; if (!parent->ops.add_sub_dev || !parent->ops.del_sub_dev) return -EOPNOTSUPP; if (!ib_device_try_get(parent)) return -EINVAL; sub = parent->ops.add_sub_dev(parent, type, name); if (IS_ERR(sub)) { ib_device_put(parent); return PTR_ERR(sub); } sub->type = type; sub->parent = parent; mutex_lock(&parent->subdev_lock); list_add_tail(&parent->subdev_list_head, &sub->subdev_list); mutex_unlock(&parent->subdev_lock); return ret; } EXPORT_SYMBOL(ib_add_sub_device); int ib_del_sub_device_and_put(struct ib_device *sub) { struct ib_device *parent = sub->parent; if (!parent) return -EOPNOTSUPP; mutex_lock(&parent->subdev_lock); list_del(&sub->subdev_list); mutex_unlock(&parent->subdev_lock); ib_device_put(sub); parent->ops.del_sub_dev(sub); ib_device_put(parent); return 0; } EXPORT_SYMBOL(ib_del_sub_device_and_put); #ifdef CONFIG_INFINIBAND_VIRT_DMA int ib_dma_virt_map_sg(struct ib_device *dev, struct scatterlist *sg, int nents) { struct scatterlist *s; int i; for_each_sg(sg, s, nents, i) { sg_dma_address(s) = (uintptr_t)sg_virt(s); sg_dma_len(s) = s->length; } return nents; } EXPORT_SYMBOL(ib_dma_virt_map_sg); #endif /* CONFIG_INFINIBAND_VIRT_DMA */ static const struct rdma_nl_cbs ibnl_ls_cb_table[RDMA_NL_LS_NUM_OPS] = { [RDMA_NL_LS_OP_RESOLVE] = { .doit = ib_nl_handle_resolve_resp, .flags = RDMA_NL_ADMIN_PERM, }, [RDMA_NL_LS_OP_SET_TIMEOUT] = { .doit = ib_nl_handle_set_timeout, .flags = RDMA_NL_ADMIN_PERM, }, [RDMA_NL_LS_OP_IP_RESOLVE] = { .doit = ib_nl_handle_ip_res_resp, .flags = RDMA_NL_ADMIN_PERM, }, }; static int ib_netdevice_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *ndev = netdev_notifier_info_to_dev(ptr); struct net_device *ib_ndev; struct ib_device *ibdev; u32 port; switch (event) { case NETDEV_CHANGENAME: ibdev = ib_device_get_by_netdev(ndev, RDMA_DRIVER_UNKNOWN); if (!ibdev) return NOTIFY_DONE; rdma_for_each_port(ibdev, port) { ib_ndev = ib_device_get_netdev(ibdev, port); if (ndev == ib_ndev) rdma_nl_notify_event(ibdev, port, RDMA_NETDEV_RENAME_EVENT); dev_put(ib_ndev); } ib_device_put(ibdev); break; default: break; } return NOTIFY_DONE; } static struct notifier_block nb_netdevice = { .notifier_call = ib_netdevice_event, }; static int __init ib_core_init(void) { int ret = -ENOMEM; ib_wq = alloc_workqueue("infiniband", 0, 0); if (!ib_wq) return -ENOMEM; ib_unreg_wq = alloc_workqueue("ib-unreg-wq", WQ_UNBOUND, WQ_UNBOUND_MAX_ACTIVE); if (!ib_unreg_wq) goto err; ib_comp_wq = alloc_workqueue("ib-comp-wq", WQ_HIGHPRI | WQ_MEM_RECLAIM | WQ_SYSFS, 0); if (!ib_comp_wq) goto err_unbound; ib_comp_unbound_wq = alloc_workqueue("ib-comp-unb-wq", WQ_UNBOUND | WQ_HIGHPRI | WQ_MEM_RECLAIM | WQ_SYSFS, WQ_UNBOUND_MAX_ACTIVE); if (!ib_comp_unbound_wq) goto err_comp; ret = class_register(&ib_class); if (ret) { pr_warn("Couldn't create InfiniBand device class\n"); goto err_comp_unbound; } rdma_nl_init(); ret = addr_init(); if (ret) { pr_warn("Couldn't init IB address resolution\n"); goto err_ibnl; } ret = ib_mad_init(); if (ret) { pr_warn("Couldn't init IB MAD\n"); goto err_addr; } ret = ib_sa_init(); if (ret) { pr_warn("Couldn't init SA\n"); goto err_mad; } ret = register_blocking_lsm_notifier(&ibdev_lsm_nb); if (ret) { pr_warn("Couldn't register LSM notifier. ret %d\n", ret); goto err_sa; } ret = register_pernet_device(&rdma_dev_net_ops); if (ret) { pr_warn("Couldn't init compat dev. ret %d\n", ret); goto err_compat; } nldev_init(); rdma_nl_register(RDMA_NL_LS, ibnl_ls_cb_table); ret = roce_gid_mgmt_init(); if (ret) { pr_warn("Couldn't init RoCE GID management\n"); goto err_parent; } register_netdevice_notifier(&nb_netdevice); return 0; err_parent: rdma_nl_unregister(RDMA_NL_LS); nldev_exit(); unregister_pernet_device(&rdma_dev_net_ops); err_compat: unregister_blocking_lsm_notifier(&ibdev_lsm_nb); err_sa: ib_sa_cleanup(); err_mad: ib_mad_cleanup(); err_addr: addr_cleanup(); err_ibnl: class_unregister(&ib_class); err_comp_unbound: destroy_workqueue(ib_comp_unbound_wq); err_comp: destroy_workqueue(ib_comp_wq); err_unbound: destroy_workqueue(ib_unreg_wq); err: destroy_workqueue(ib_wq); return ret; } static void __exit ib_core_cleanup(void) { unregister_netdevice_notifier(&nb_netdevice); roce_gid_mgmt_cleanup(); rdma_nl_unregister(RDMA_NL_LS); nldev_exit(); unregister_pernet_device(&rdma_dev_net_ops); unregister_blocking_lsm_notifier(&ibdev_lsm_nb); ib_sa_cleanup(); ib_mad_cleanup(); addr_cleanup(); rdma_nl_exit(); class_unregister(&ib_class); destroy_workqueue(ib_comp_unbound_wq); destroy_workqueue(ib_comp_wq); /* Make sure that any pending umem accounting work is done. */ destroy_workqueue(ib_wq); destroy_workqueue(ib_unreg_wq); WARN_ON(!xa_empty(&clients)); WARN_ON(!xa_empty(&devices)); } MODULE_ALIAS_RDMA_NETLINK(RDMA_NL_LS, 4); /* ib core relies on netdev stack to first register net_ns_type_operations * ns kobject type before ib_core initialization. */ fs_initcall(ib_core_init); module_exit(ib_core_cleanup); |
| 8 6 2 6 2 6 1 1 5 2 4 3 1 3 2 2 4 2 1 1 4 2 2 2 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> #include <net/ip.h> #include <net/tcp.h> #include <net/netlink.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_synproxy.h> #include <net/netfilter/nf_synproxy.h> #include <linux/netfilter/nf_tables.h> #include <linux/netfilter/nf_synproxy.h> struct nft_synproxy { struct nf_synproxy_info info; }; static const struct nla_policy nft_synproxy_policy[NFTA_SYNPROXY_MAX + 1] = { [NFTA_SYNPROXY_MSS] = { .type = NLA_U16 }, [NFTA_SYNPROXY_WSCALE] = { .type = NLA_U8 }, [NFTA_SYNPROXY_FLAGS] = { .type = NLA_U32 }, }; static void nft_synproxy_tcp_options(struct synproxy_options *opts, const struct tcphdr *tcp, struct synproxy_net *snet, struct nf_synproxy_info *info, const struct nft_synproxy *priv) { this_cpu_inc(snet->stats->syn_received); if (tcp->ece && tcp->cwr) opts->options |= NF_SYNPROXY_OPT_ECN; opts->options &= priv->info.options; opts->mss_encode = opts->mss_option; opts->mss_option = info->mss; if (opts->options & NF_SYNPROXY_OPT_TIMESTAMP) synproxy_init_timestamp_cookie(info, opts); else opts->options &= ~(NF_SYNPROXY_OPT_WSCALE | NF_SYNPROXY_OPT_SACK_PERM | NF_SYNPROXY_OPT_ECN); } static void nft_synproxy_eval_v4(const struct nft_synproxy *priv, struct nft_regs *regs, const struct nft_pktinfo *pkt, const struct tcphdr *tcp, struct tcphdr *_tcph, struct synproxy_options *opts) { struct nf_synproxy_info info = priv->info; struct net *net = nft_net(pkt); struct synproxy_net *snet = synproxy_pernet(net); struct sk_buff *skb = pkt->skb; if (tcp->syn) { /* Initial SYN from client */ nft_synproxy_tcp_options(opts, tcp, snet, &info, priv); synproxy_send_client_synack(net, skb, tcp, opts); consume_skb(skb); regs->verdict.code = NF_STOLEN; } else if (tcp->ack) { /* ACK from client */ if (synproxy_recv_client_ack(net, skb, tcp, opts, ntohl(tcp->seq))) { consume_skb(skb); regs->verdict.code = NF_STOLEN; } else { regs->verdict.code = NF_DROP; } } } #if IS_ENABLED(CONFIG_NF_TABLES_IPV6) static void nft_synproxy_eval_v6(const struct nft_synproxy *priv, struct nft_regs *regs, const struct nft_pktinfo *pkt, const struct tcphdr *tcp, struct tcphdr *_tcph, struct synproxy_options *opts) { struct nf_synproxy_info info = priv->info; struct net *net = nft_net(pkt); struct synproxy_net *snet = synproxy_pernet(net); struct sk_buff *skb = pkt->skb; if (tcp->syn) { /* Initial SYN from client */ nft_synproxy_tcp_options(opts, tcp, snet, &info, priv); synproxy_send_client_synack_ipv6(net, skb, tcp, opts); consume_skb(skb); regs->verdict.code = NF_STOLEN; } else if (tcp->ack) { /* ACK from client */ if (synproxy_recv_client_ack_ipv6(net, skb, tcp, opts, ntohl(tcp->seq))) { consume_skb(skb); regs->verdict.code = NF_STOLEN; } else { regs->verdict.code = NF_DROP; } } } #endif /* CONFIG_NF_TABLES_IPV6*/ static void nft_synproxy_do_eval(const struct nft_synproxy *priv, struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct synproxy_options opts = {}; struct sk_buff *skb = pkt->skb; int thoff = nft_thoff(pkt); const struct tcphdr *tcp; struct tcphdr _tcph; if (pkt->tprot != IPPROTO_TCP) { regs->verdict.code = NFT_BREAK; return; } if (nf_ip_checksum(skb, nft_hook(pkt), thoff, IPPROTO_TCP)) { regs->verdict.code = NF_DROP; return; } tcp = skb_header_pointer(skb, thoff, sizeof(struct tcphdr), &_tcph); if (!tcp) { regs->verdict.code = NF_DROP; return; } if (!synproxy_parse_options(skb, thoff, tcp, &opts)) { regs->verdict.code = NF_DROP; return; } switch (skb->protocol) { case htons(ETH_P_IP): nft_synproxy_eval_v4(priv, regs, pkt, tcp, &_tcph, &opts); return; #if IS_ENABLED(CONFIG_NF_TABLES_IPV6) case htons(ETH_P_IPV6): nft_synproxy_eval_v6(priv, regs, pkt, tcp, &_tcph, &opts); return; #endif } regs->verdict.code = NFT_BREAK; } static int nft_synproxy_do_init(const struct nft_ctx *ctx, const struct nlattr * const tb[], struct nft_synproxy *priv) { struct synproxy_net *snet = synproxy_pernet(ctx->net); u32 flags; int err; if (tb[NFTA_SYNPROXY_MSS]) priv->info.mss = ntohs(nla_get_be16(tb[NFTA_SYNPROXY_MSS])); if (tb[NFTA_SYNPROXY_WSCALE]) priv->info.wscale = nla_get_u8(tb[NFTA_SYNPROXY_WSCALE]); if (tb[NFTA_SYNPROXY_FLAGS]) { flags = ntohl(nla_get_be32(tb[NFTA_SYNPROXY_FLAGS])); if (flags & ~NF_SYNPROXY_OPT_MASK) return -EOPNOTSUPP; priv->info.options = flags; } err = nf_ct_netns_get(ctx->net, ctx->family); if (err) return err; switch (ctx->family) { case NFPROTO_IPV4: err = nf_synproxy_ipv4_init(snet, ctx->net); if (err) goto nf_ct_failure; break; #if IS_ENABLED(CONFIG_NF_TABLES_IPV6) case NFPROTO_IPV6: err = nf_synproxy_ipv6_init(snet, ctx->net); if (err) goto nf_ct_failure; break; #endif case NFPROTO_INET: err = nf_synproxy_ipv4_init(snet, ctx->net); if (err) goto nf_ct_failure; err = nf_synproxy_ipv6_init(snet, ctx->net); if (err) { nf_synproxy_ipv4_fini(snet, ctx->net); goto nf_ct_failure; } break; } return 0; nf_ct_failure: nf_ct_netns_put(ctx->net, ctx->family); return err; } static void nft_synproxy_do_destroy(const struct nft_ctx *ctx) { struct synproxy_net *snet = synproxy_pernet(ctx->net); switch (ctx->family) { case NFPROTO_IPV4: nf_synproxy_ipv4_fini(snet, ctx->net); break; #if IS_ENABLED(CONFIG_NF_TABLES_IPV6) case NFPROTO_IPV6: nf_synproxy_ipv6_fini(snet, ctx->net); break; #endif case NFPROTO_INET: nf_synproxy_ipv4_fini(snet, ctx->net); nf_synproxy_ipv6_fini(snet, ctx->net); break; } nf_ct_netns_put(ctx->net, ctx->family); } static int nft_synproxy_do_dump(struct sk_buff *skb, struct nft_synproxy *priv) { if (nla_put_be16(skb, NFTA_SYNPROXY_MSS, htons(priv->info.mss)) || nla_put_u8(skb, NFTA_SYNPROXY_WSCALE, priv->info.wscale) || nla_put_be32(skb, NFTA_SYNPROXY_FLAGS, htonl(priv->info.options))) goto nla_put_failure; return 0; nla_put_failure: return -1; } static void nft_synproxy_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_synproxy *priv = nft_expr_priv(expr); nft_synproxy_do_eval(priv, regs, pkt); } static int nft_synproxy_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { if (ctx->family != NFPROTO_IPV4 && ctx->family != NFPROTO_IPV6 && ctx->family != NFPROTO_INET) return -EOPNOTSUPP; return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD)); } static int nft_synproxy_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_synproxy *priv = nft_expr_priv(expr); return nft_synproxy_do_init(ctx, tb, priv); } static void nft_synproxy_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { nft_synproxy_do_destroy(ctx); } static int nft_synproxy_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { struct nft_synproxy *priv = nft_expr_priv(expr); return nft_synproxy_do_dump(skb, priv); } static struct nft_expr_type nft_synproxy_type; static const struct nft_expr_ops nft_synproxy_ops = { .eval = nft_synproxy_eval, .size = NFT_EXPR_SIZE(sizeof(struct nft_synproxy)), .init = nft_synproxy_init, .destroy = nft_synproxy_destroy, .dump = nft_synproxy_dump, .type = &nft_synproxy_type, .validate = nft_synproxy_validate, .reduce = NFT_REDUCE_READONLY, }; static struct nft_expr_type nft_synproxy_type __read_mostly = { .ops = &nft_synproxy_ops, .name = "synproxy", .owner = THIS_MODULE, .policy = nft_synproxy_policy, .maxattr = NFTA_SYNPROXY_MAX, }; static int nft_synproxy_obj_init(const struct nft_ctx *ctx, const struct nlattr * const tb[], struct nft_object *obj) { struct nft_synproxy *priv = nft_obj_data(obj); return nft_synproxy_do_init(ctx, tb, priv); } static void nft_synproxy_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj) { nft_synproxy_do_destroy(ctx); } static int nft_synproxy_obj_dump(struct sk_buff *skb, struct nft_object *obj, bool reset) { struct nft_synproxy *priv = nft_obj_data(obj); return nft_synproxy_do_dump(skb, priv); } static void nft_synproxy_obj_eval(struct nft_object *obj, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_synproxy *priv = nft_obj_data(obj); nft_synproxy_do_eval(priv, regs, pkt); } static void nft_synproxy_obj_update(struct nft_object *obj, struct nft_object *newobj) { struct nft_synproxy *newpriv = nft_obj_data(newobj); struct nft_synproxy *priv = nft_obj_data(obj); priv->info = newpriv->info; } static struct nft_object_type nft_synproxy_obj_type; static const struct nft_object_ops nft_synproxy_obj_ops = { .type = &nft_synproxy_obj_type, .size = sizeof(struct nft_synproxy), .init = nft_synproxy_obj_init, .destroy = nft_synproxy_obj_destroy, .dump = nft_synproxy_obj_dump, .eval = nft_synproxy_obj_eval, .update = nft_synproxy_obj_update, }; static struct nft_object_type nft_synproxy_obj_type __read_mostly = { .type = NFT_OBJECT_SYNPROXY, .ops = &nft_synproxy_obj_ops, .maxattr = NFTA_SYNPROXY_MAX, .policy = nft_synproxy_policy, .owner = THIS_MODULE, }; static int __init nft_synproxy_module_init(void) { int err; err = nft_register_obj(&nft_synproxy_obj_type); if (err < 0) return err; err = nft_register_expr(&nft_synproxy_type); if (err < 0) goto err; return 0; err: nft_unregister_obj(&nft_synproxy_obj_type); return err; } static void __exit nft_synproxy_module_exit(void) { nft_unregister_expr(&nft_synproxy_type); nft_unregister_obj(&nft_synproxy_obj_type); } module_init(nft_synproxy_module_init); module_exit(nft_synproxy_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Fernando Fernandez <ffmancera@riseup.net>"); MODULE_ALIAS_NFT_EXPR("synproxy"); MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_SYNPROXY); MODULE_DESCRIPTION("nftables SYNPROXY expression support"); |
| 373 2374 44 339 2016 3 1 3 269 123 264 13 501 9 2 2 28 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (c) 2020 Christoph Hellwig. * * Support for "universal" pointers that can point to either kernel or userspace * memory. */ #ifndef _LINUX_SOCKPTR_H #define _LINUX_SOCKPTR_H #include <linux/slab.h> #include <linux/uaccess.h> typedef struct { union { void *kernel; void __user *user; }; bool is_kernel : 1; } sockptr_t; static inline bool sockptr_is_kernel(sockptr_t sockptr) { return sockptr.is_kernel; } static inline sockptr_t KERNEL_SOCKPTR(void *p) { return (sockptr_t) { .kernel = p, .is_kernel = true }; } static inline sockptr_t USER_SOCKPTR(void __user *p) { return (sockptr_t) { .user = p }; } static inline bool sockptr_is_null(sockptr_t sockptr) { if (sockptr_is_kernel(sockptr)) return !sockptr.kernel; return !sockptr.user; } static inline int copy_from_sockptr_offset(void *dst, sockptr_t src, size_t offset, size_t size) { if (!sockptr_is_kernel(src)) return copy_from_user(dst, src.user + offset, size); memcpy(dst, src.kernel + offset, size); return 0; } /* Deprecated. * This is unsafe, unless caller checked user provided optlen. * Prefer copy_safe_from_sockptr() instead. * * Returns 0 for success, or number of bytes not copied on error. */ static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size) { return copy_from_sockptr_offset(dst, src, 0, size); } /** * copy_safe_from_sockptr: copy a struct from sockptr * @dst: Destination address, in kernel space. This buffer must be @ksize * bytes long. * @ksize: Size of @dst struct. * @optval: Source address. (in user or kernel space) * @optlen: Size of @optval data. * * Returns: * * -EINVAL: @optlen < @ksize * * -EFAULT: access to userspace failed. * * 0 : @ksize bytes were copied */ static inline int copy_safe_from_sockptr(void *dst, size_t ksize, sockptr_t optval, unsigned int optlen) { if (optlen < ksize) return -EINVAL; if (copy_from_sockptr(dst, optval, ksize)) return -EFAULT; return 0; } static inline int copy_struct_from_sockptr(void *dst, size_t ksize, sockptr_t src, size_t usize) { size_t size = min(ksize, usize); size_t rest = max(ksize, usize) - size; if (!sockptr_is_kernel(src)) return copy_struct_from_user(dst, ksize, src.user, size); if (usize < ksize) { memset(dst + size, 0, rest); } else if (usize > ksize) { char *p = src.kernel; while (rest--) { if (*p++) return -E2BIG; } } memcpy(dst, src.kernel, size); return 0; } static inline int copy_to_sockptr_offset(sockptr_t dst, size_t offset, const void *src, size_t size) { if (!sockptr_is_kernel(dst)) return copy_to_user(dst.user + offset, src, size); memcpy(dst.kernel + offset, src, size); return 0; } static inline int copy_to_sockptr(sockptr_t dst, const void *src, size_t size) { return copy_to_sockptr_offset(dst, 0, src, size); } static inline void *memdup_sockptr_noprof(sockptr_t src, size_t len) { void *p = kmalloc_track_caller_noprof(len, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_sockptr(p, src, len)) { kfree(p); return ERR_PTR(-EFAULT); } return p; } #define memdup_sockptr(...) alloc_hooks(memdup_sockptr_noprof(__VA_ARGS__)) static inline void *memdup_sockptr_nul_noprof(sockptr_t src, size_t len) { char *p = kmalloc_track_caller_noprof(len + 1, GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_sockptr(p, src, len)) { kfree(p); return ERR_PTR(-EFAULT); } p[len] = '\0'; return p; } #define memdup_sockptr_nul(...) alloc_hooks(memdup_sockptr_nul_noprof(__VA_ARGS__)) static inline long strncpy_from_sockptr(char *dst, sockptr_t src, size_t count) { if (sockptr_is_kernel(src)) { size_t len = min(strnlen(src.kernel, count - 1) + 1, count); memcpy(dst, src.kernel, len); return len; } return strncpy_from_user(dst, src.user, count); } static inline int check_zeroed_sockptr(sockptr_t src, size_t offset, size_t size) { if (!sockptr_is_kernel(src)) return check_zeroed_user(src.user + offset, size); return memchr_inv(src.kernel + offset, 0, size) == NULL; } #endif /* _LINUX_SOCKPTR_H */ |
| 1 8 8 43 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/export.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/fs.h> #include <linux/path.h> #include <linux/slab.h> #include <linux/fs_struct.h> #include "internal.h" /* * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values. * It can block. */ void set_fs_root(struct fs_struct *fs, const struct path *path) { struct path old_root; path_get(path); spin_lock(&fs->lock); write_seqcount_begin(&fs->seq); old_root = fs->root; fs->root = *path; write_seqcount_end(&fs->seq); spin_unlock(&fs->lock); if (old_root.dentry) path_put(&old_root); } /* * Replace the fs->{pwdmnt,pwd} with {mnt,dentry}. Put the old values. * It can block. */ void set_fs_pwd(struct fs_struct *fs, const struct path *path) { struct path old_pwd; path_get(path); spin_lock(&fs->lock); write_seqcount_begin(&fs->seq); old_pwd = fs->pwd; fs->pwd = *path; write_seqcount_end(&fs->seq); spin_unlock(&fs->lock); if (old_pwd.dentry) path_put(&old_pwd); } static inline int replace_path(struct path *p, const struct path *old, const struct path *new) { if (likely(p->dentry != old->dentry || p->mnt != old->mnt)) return 0; *p = *new; return 1; } void chroot_fs_refs(const struct path *old_root, const struct path *new_root) { struct task_struct *g, *p; struct fs_struct *fs; int count = 0; read_lock(&tasklist_lock); for_each_process_thread(g, p) { task_lock(p); fs = p->fs; if (fs) { int hits = 0; spin_lock(&fs->lock); write_seqcount_begin(&fs->seq); hits += replace_path(&fs->root, old_root, new_root); hits += replace_path(&fs->pwd, old_root, new_root); write_seqcount_end(&fs->seq); while (hits--) { count++; path_get(new_root); } spin_unlock(&fs->lock); } task_unlock(p); } read_unlock(&tasklist_lock); while (count--) path_put(old_root); } void free_fs_struct(struct fs_struct *fs) { path_put(&fs->root); path_put(&fs->pwd); kmem_cache_free(fs_cachep, fs); } void exit_fs(struct task_struct *tsk) { struct fs_struct *fs = tsk->fs; if (fs) { int kill; task_lock(tsk); spin_lock(&fs->lock); tsk->fs = NULL; kill = !--fs->users; spin_unlock(&fs->lock); task_unlock(tsk); if (kill) free_fs_struct(fs); } } struct fs_struct *copy_fs_struct(struct fs_struct *old) { struct fs_struct *fs = kmem_cache_alloc(fs_cachep, GFP_KERNEL); /* We don't need to lock fs - think why ;-) */ if (fs) { fs->users = 1; fs->in_exec = 0; spin_lock_init(&fs->lock); seqcount_spinlock_init(&fs->seq, &fs->lock); fs->umask = old->umask; spin_lock(&old->lock); fs->root = old->root; path_get(&fs->root); fs->pwd = old->pwd; path_get(&fs->pwd); spin_unlock(&old->lock); } return fs; } int unshare_fs_struct(void) { struct fs_struct *fs = current->fs; struct fs_struct *new_fs = copy_fs_struct(fs); int kill; if (!new_fs) return -ENOMEM; task_lock(current); spin_lock(&fs->lock); kill = !--fs->users; current->fs = new_fs; spin_unlock(&fs->lock); task_unlock(current); if (kill) free_fs_struct(fs); return 0; } EXPORT_SYMBOL_GPL(unshare_fs_struct); int current_umask(void) { return current->fs->umask; } EXPORT_SYMBOL(current_umask); /* to be mentioned only in INIT_TASK */ struct fs_struct init_fs = { .users = 1, .lock = __SPIN_LOCK_UNLOCKED(init_fs.lock), .seq = SEQCNT_SPINLOCK_ZERO(init_fs.seq, &init_fs.lock), .umask = 0022, }; |
| 7452 6897 2014 7980 35 3 793 2193 387 55 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_SEQLOCK_H #define __LINUX_SEQLOCK_H /* * seqcount_t / seqlock_t - a reader-writer consistency mechanism with * lockless readers (read-only retry loops), and no writer starvation. * * See Documentation/locking/seqlock.rst * * Copyrights: * - Based on x86_64 vsyscall gettimeofday: Keith Owens, Andrea Arcangeli * - Sequence counters with associated locks, (C) 2020 Linutronix GmbH */ #include <linux/compiler.h> #include <linux/kcsan-checks.h> #include <linux/lockdep.h> #include <linux/mutex.h> #include <linux/preempt.h> #include <linux/seqlock_types.h> #include <linux/spinlock.h> #include <asm/processor.h> /* * The seqlock seqcount_t interface does not prescribe a precise sequence of * read begin/retry/end. For readers, typically there is a call to * read_seqcount_begin() and read_seqcount_retry(), however, there are more * esoteric cases which do not follow this pattern. * * As a consequence, we take the following best-effort approach for raw usage * via seqcount_t under KCSAN: upon beginning a seq-reader critical section, * pessimistically mark the next KCSAN_SEQLOCK_REGION_MAX memory accesses as * atomics; if there is a matching read_seqcount_retry() call, no following * memory operations are considered atomic. Usage of the seqlock_t interface * is not affected. */ #define KCSAN_SEQLOCK_REGION_MAX 1000 static inline void __seqcount_init(seqcount_t *s, const char *name, struct lock_class_key *key) { /* * Make sure we are not reinitializing a held lock: */ lockdep_init_map(&s->dep_map, name, key, 0); s->sequence = 0; } #ifdef CONFIG_DEBUG_LOCK_ALLOC # define SEQCOUNT_DEP_MAP_INIT(lockname) \ .dep_map = { .name = #lockname } /** * seqcount_init() - runtime initializer for seqcount_t * @s: Pointer to the seqcount_t instance */ # define seqcount_init(s) \ do { \ static struct lock_class_key __key; \ __seqcount_init((s), #s, &__key); \ } while (0) static inline void seqcount_lockdep_reader_access(const seqcount_t *s) { seqcount_t *l = (seqcount_t *)s; unsigned long flags; local_irq_save(flags); seqcount_acquire_read(&l->dep_map, 0, 0, _RET_IP_); seqcount_release(&l->dep_map, _RET_IP_); local_irq_restore(flags); } #else # define SEQCOUNT_DEP_MAP_INIT(lockname) # define seqcount_init(s) __seqcount_init(s, NULL, NULL) # define seqcount_lockdep_reader_access(x) #endif /** * SEQCNT_ZERO() - static initializer for seqcount_t * @name: Name of the seqcount_t instance */ #define SEQCNT_ZERO(name) { .sequence = 0, SEQCOUNT_DEP_MAP_INIT(name) } /* * Sequence counters with associated locks (seqcount_LOCKNAME_t) * * A sequence counter which associates the lock used for writer * serialization at initialization time. This enables lockdep to validate * that the write side critical section is properly serialized. * * For associated locks which do not implicitly disable preemption, * preemption protection is enforced in the write side function. * * Lockdep is never used in any for the raw write variants. * * See Documentation/locking/seqlock.rst */ /* * typedef seqcount_LOCKNAME_t - sequence counter with LOCKNAME associated * @seqcount: The real sequence counter * @lock: Pointer to the associated lock * * A plain sequence counter with external writer synchronization by * LOCKNAME @lock. The lock is associated to the sequence counter in the * static initializer or init function. This enables lockdep to validate * that the write side critical section is properly serialized. * * LOCKNAME: raw_spinlock, spinlock, rwlock or mutex */ /* * seqcount_LOCKNAME_init() - runtime initializer for seqcount_LOCKNAME_t * @s: Pointer to the seqcount_LOCKNAME_t instance * @lock: Pointer to the associated lock */ #define seqcount_LOCKNAME_init(s, _lock, lockname) \ do { \ seqcount_##lockname##_t *____s = (s); \ seqcount_init(&____s->seqcount); \ __SEQ_LOCK(____s->lock = (_lock)); \ } while (0) #define seqcount_raw_spinlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, raw_spinlock) #define seqcount_spinlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, spinlock) #define seqcount_rwlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, rwlock) #define seqcount_mutex_init(s, lock) seqcount_LOCKNAME_init(s, lock, mutex) /* * SEQCOUNT_LOCKNAME() - Instantiate seqcount_LOCKNAME_t and helpers * seqprop_LOCKNAME_*() - Property accessors for seqcount_LOCKNAME_t * * @lockname: "LOCKNAME" part of seqcount_LOCKNAME_t * @locktype: LOCKNAME canonical C data type * @preemptible: preemptibility of above locktype * @lockbase: prefix for associated lock/unlock */ #define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockbase) \ static __always_inline seqcount_t * \ __seqprop_##lockname##_ptr(seqcount_##lockname##_t *s) \ { \ return &s->seqcount; \ } \ \ static __always_inline const seqcount_t * \ __seqprop_##lockname##_const_ptr(const seqcount_##lockname##_t *s) \ { \ return &s->seqcount; \ } \ \ static __always_inline unsigned \ __seqprop_##lockname##_sequence(const seqcount_##lockname##_t *s) \ { \ unsigned seq = smp_load_acquire(&s->seqcount.sequence); \ \ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \ return seq; \ \ if (preemptible && unlikely(seq & 1)) { \ __SEQ_LOCK(lockbase##_lock(s->lock)); \ __SEQ_LOCK(lockbase##_unlock(s->lock)); \ \ /* \ * Re-read the sequence counter since the (possibly \ * preempted) writer made progress. \ */ \ seq = smp_load_acquire(&s->seqcount.sequence); \ } \ \ return seq; \ } \ \ static __always_inline bool \ __seqprop_##lockname##_preemptible(const seqcount_##lockname##_t *s) \ { \ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \ return preemptible; \ \ /* PREEMPT_RT relies on the above LOCK+UNLOCK */ \ return false; \ } \ \ static __always_inline void \ __seqprop_##lockname##_assert(const seqcount_##lockname##_t *s) \ { \ __SEQ_LOCK(lockdep_assert_held(s->lock)); \ } /* * __seqprop() for seqcount_t */ static inline seqcount_t *__seqprop_ptr(seqcount_t *s) { return s; } static inline const seqcount_t *__seqprop_const_ptr(const seqcount_t *s) { return s; } static inline unsigned __seqprop_sequence(const seqcount_t *s) { return smp_load_acquire(&s->sequence); } static inline bool __seqprop_preemptible(const seqcount_t *s) { return false; } static inline void __seqprop_assert(const seqcount_t *s) { lockdep_assert_preemption_disabled(); } #define __SEQ_RT IS_ENABLED(CONFIG_PREEMPT_RT) SEQCOUNT_LOCKNAME(raw_spinlock, raw_spinlock_t, false, raw_spin) SEQCOUNT_LOCKNAME(spinlock, spinlock_t, __SEQ_RT, spin) SEQCOUNT_LOCKNAME(rwlock, rwlock_t, __SEQ_RT, read) SEQCOUNT_LOCKNAME(mutex, struct mutex, true, mutex) #undef SEQCOUNT_LOCKNAME /* * SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t * @name: Name of the seqcount_LOCKNAME_t instance * @lock: Pointer to the associated LOCKNAME */ #define SEQCOUNT_LOCKNAME_ZERO(seq_name, assoc_lock) { \ .seqcount = SEQCNT_ZERO(seq_name.seqcount), \ __SEQ_LOCK(.lock = (assoc_lock)) \ } #define SEQCNT_RAW_SPINLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_SPINLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_RWLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_MUTEX_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_WW_MUTEX_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define __seqprop_case(s, lockname, prop) \ seqcount_##lockname##_t: __seqprop_##lockname##_##prop #define __seqprop(s, prop) _Generic(*(s), \ seqcount_t: __seqprop_##prop, \ __seqprop_case((s), raw_spinlock, prop), \ __seqprop_case((s), spinlock, prop), \ __seqprop_case((s), rwlock, prop), \ __seqprop_case((s), mutex, prop)) #define seqprop_ptr(s) __seqprop(s, ptr)(s) #define seqprop_const_ptr(s) __seqprop(s, const_ptr)(s) #define seqprop_sequence(s) __seqprop(s, sequence)(s) #define seqprop_preemptible(s) __seqprop(s, preemptible)(s) #define seqprop_assert(s) __seqprop(s, assert)(s) /** * __read_seqcount_begin() - begin a seqcount_t read section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Return: count to be passed to read_seqcount_retry() */ #define __read_seqcount_begin(s) \ ({ \ unsigned __seq; \ \ while ((__seq = seqprop_sequence(s)) & 1) \ cpu_relax(); \ \ kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); \ __seq; \ }) /** * raw_read_seqcount_begin() - begin a seqcount_t read section w/o lockdep * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Return: count to be passed to read_seqcount_retry() */ #define raw_read_seqcount_begin(s) __read_seqcount_begin(s) /** * read_seqcount_begin() - begin a seqcount_t read critical section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Return: count to be passed to read_seqcount_retry() */ #define read_seqcount_begin(s) \ ({ \ seqcount_lockdep_reader_access(seqprop_const_ptr(s)); \ raw_read_seqcount_begin(s); \ }) /** * raw_read_seqcount() - read the raw seqcount_t counter value * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * raw_read_seqcount opens a read critical section of the given * seqcount_t, without any lockdep checking, and without checking or * masking the sequence counter LSB. Calling code is responsible for * handling that. * * Return: count to be passed to read_seqcount_retry() */ #define raw_read_seqcount(s) \ ({ \ unsigned __seq = seqprop_sequence(s); \ \ kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); \ __seq; \ }) /** * raw_seqcount_begin() - begin a seqcount_t read critical section w/o * lockdep and w/o counter stabilization * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * raw_seqcount_begin opens a read critical section of the given * seqcount_t. Unlike read_seqcount_begin(), this function will not wait * for the count to stabilize. If a writer is active when it begins, it * will fail the read_seqcount_retry() at the end of the read critical * section instead of stabilizing at the beginning of it. * * Use this only in special kernel hot paths where the read section is * small and has a high probability of success through other external * means. It will save a single branching instruction. * * Return: count to be passed to read_seqcount_retry() */ #define raw_seqcount_begin(s) \ ({ \ /* \ * If the counter is odd, let read_seqcount_retry() fail \ * by decrementing the counter. \ */ \ raw_read_seqcount(s) & ~1; \ }) /** * __read_seqcount_retry() - end a seqcount_t read section w/o barrier * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * @start: count, from read_seqcount_begin() * * __read_seqcount_retry is like read_seqcount_retry, but has no smp_rmb() * barrier. Callers should ensure that smp_rmb() or equivalent ordering is * provided before actually loading any of the variables that are to be * protected in this critical section. * * Use carefully, only in critical code, and comment how the barrier is * provided. * * Return: true if a read section retry is required, else false */ #define __read_seqcount_retry(s, start) \ do___read_seqcount_retry(seqprop_const_ptr(s), start) static inline int do___read_seqcount_retry(const seqcount_t *s, unsigned start) { kcsan_atomic_next(0); return unlikely(READ_ONCE(s->sequence) != start); } /** * read_seqcount_retry() - end a seqcount_t read critical section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * @start: count, from read_seqcount_begin() * * read_seqcount_retry closes the read critical section of given * seqcount_t. If the critical section was invalid, it must be ignored * (and typically retried). * * Return: true if a read section retry is required, else false */ #define read_seqcount_retry(s, start) \ do_read_seqcount_retry(seqprop_const_ptr(s), start) static inline int do_read_seqcount_retry(const seqcount_t *s, unsigned start) { smp_rmb(); return do___read_seqcount_retry(s, start); } /** * raw_write_seqcount_begin() - start a seqcount_t write section w/o lockdep * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Context: check write_seqcount_begin() */ #define raw_write_seqcount_begin(s) \ do { \ if (seqprop_preemptible(s)) \ preempt_disable(); \ \ do_raw_write_seqcount_begin(seqprop_ptr(s)); \ } while (0) static inline void do_raw_write_seqcount_begin(seqcount_t *s) { kcsan_nestable_atomic_begin(); s->sequence++; smp_wmb(); } /** * raw_write_seqcount_end() - end a seqcount_t write section w/o lockdep * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Context: check write_seqcount_end() */ #define raw_write_seqcount_end(s) \ do { \ do_raw_write_seqcount_end(seqprop_ptr(s)); \ \ if (seqprop_preemptible(s)) \ preempt_enable(); \ } while (0) static inline void do_raw_write_seqcount_end(seqcount_t *s) { smp_wmb(); s->sequence++; kcsan_nestable_atomic_end(); } /** * write_seqcount_begin_nested() - start a seqcount_t write section with * custom lockdep nesting level * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * @subclass: lockdep nesting level * * See Documentation/locking/lockdep-design.rst * Context: check write_seqcount_begin() */ #define write_seqcount_begin_nested(s, subclass) \ do { \ seqprop_assert(s); \ \ if (seqprop_preemptible(s)) \ preempt_disable(); \ \ do_write_seqcount_begin_nested(seqprop_ptr(s), subclass); \ } while (0) static inline void do_write_seqcount_begin_nested(seqcount_t *s, int subclass) { seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_); do_raw_write_seqcount_begin(s); } /** * write_seqcount_begin() - start a seqcount_t write side critical section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Context: sequence counter write side sections must be serialized and * non-preemptible. Preemption will be automatically disabled if and * only if the seqcount write serialization lock is associated, and * preemptible. If readers can be invoked from hardirq or softirq * context, interrupts or bottom halves must be respectively disabled. */ #define write_seqcount_begin(s) \ do { \ seqprop_assert(s); \ \ if (seqprop_preemptible(s)) \ preempt_disable(); \ \ do_write_seqcount_begin(seqprop_ptr(s)); \ } while (0) static inline void do_write_seqcount_begin(seqcount_t *s) { do_write_seqcount_begin_nested(s, 0); } /** * write_seqcount_end() - end a seqcount_t write side critical section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Context: Preemption will be automatically re-enabled if and only if * the seqcount write serialization lock is associated, and preemptible. */ #define write_seqcount_end(s) \ do { \ do_write_seqcount_end(seqprop_ptr(s)); \ \ if (seqprop_preemptible(s)) \ preempt_enable(); \ } while (0) static inline void do_write_seqcount_end(seqcount_t *s) { seqcount_release(&s->dep_map, _RET_IP_); do_raw_write_seqcount_end(s); } /** * raw_write_seqcount_barrier() - do a seqcount_t write barrier * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * This can be used to provide an ordering guarantee instead of the usual * consistency guarantee. It is one wmb cheaper, because it can collapse * the two back-to-back wmb()s. * * Note that writes surrounding the barrier should be declared atomic (e.g. * via WRITE_ONCE): a) to ensure the writes become visible to other threads * atomically, avoiding compiler optimizations; b) to document which writes are * meant to propagate to the reader critical section. This is necessary because * neither writes before nor after the barrier are enclosed in a seq-writer * critical section that would ensure readers are aware of ongoing writes:: * * seqcount_t seq; * bool X = true, Y = false; * * void read(void) * { * bool x, y; * * do { * int s = read_seqcount_begin(&seq); * * x = X; y = Y; * * } while (read_seqcount_retry(&seq, s)); * * BUG_ON(!x && !y); * } * * void write(void) * { * WRITE_ONCE(Y, true); * * raw_write_seqcount_barrier(seq); * * WRITE_ONCE(X, false); * } */ #define raw_write_seqcount_barrier(s) \ do_raw_write_seqcount_barrier(seqprop_ptr(s)) static inline void do_raw_write_seqcount_barrier(seqcount_t *s) { kcsan_nestable_atomic_begin(); s->sequence++; smp_wmb(); s->sequence++; kcsan_nestable_atomic_end(); } /** * write_seqcount_invalidate() - invalidate in-progress seqcount_t read * side operations * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * After write_seqcount_invalidate, no seqcount_t read side operations * will complete successfully and see data older than this. */ #define write_seqcount_invalidate(s) \ do_write_seqcount_invalidate(seqprop_ptr(s)) static inline void do_write_seqcount_invalidate(seqcount_t *s) { smp_wmb(); kcsan_nestable_atomic_begin(); s->sequence+=2; kcsan_nestable_atomic_end(); } /* * Latch sequence counters (seqcount_latch_t) * * A sequence counter variant where the counter even/odd value is used to * switch between two copies of protected data. This allows the read path, * typically NMIs, to safely interrupt the write side critical section. * * As the write sections are fully preemptible, no special handling for * PREEMPT_RT is needed. */ typedef struct { seqcount_t seqcount; } seqcount_latch_t; /** * SEQCNT_LATCH_ZERO() - static initializer for seqcount_latch_t * @seq_name: Name of the seqcount_latch_t instance */ #define SEQCNT_LATCH_ZERO(seq_name) { \ .seqcount = SEQCNT_ZERO(seq_name.seqcount), \ } /** * seqcount_latch_init() - runtime initializer for seqcount_latch_t * @s: Pointer to the seqcount_latch_t instance */ #define seqcount_latch_init(s) seqcount_init(&(s)->seqcount) /** * raw_read_seqcount_latch() - pick even/odd latch data copy * @s: Pointer to seqcount_latch_t * * See raw_write_seqcount_latch() for details and a full reader/writer * usage example. * * Return: sequence counter raw value. Use the lowest bit as an index for * picking which data copy to read. The full counter must then be checked * with raw_read_seqcount_latch_retry(). */ static __always_inline unsigned raw_read_seqcount_latch(const seqcount_latch_t *s) { /* * Pairs with the first smp_wmb() in raw_write_seqcount_latch(). * Due to the dependent load, a full smp_rmb() is not needed. */ return READ_ONCE(s->seqcount.sequence); } /** * read_seqcount_latch() - pick even/odd latch data copy * @s: Pointer to seqcount_latch_t * * See write_seqcount_latch() for details and a full reader/writer usage * example. * * Return: sequence counter raw value. Use the lowest bit as an index for * picking which data copy to read. The full counter must then be checked * with read_seqcount_latch_retry(). */ static __always_inline unsigned read_seqcount_latch(const seqcount_latch_t *s) { kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); return raw_read_seqcount_latch(s); } /** * raw_read_seqcount_latch_retry() - end a seqcount_latch_t read section * @s: Pointer to seqcount_latch_t * @start: count, from raw_read_seqcount_latch() * * Return: true if a read section retry is required, else false */ static __always_inline int raw_read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start) { smp_rmb(); return unlikely(READ_ONCE(s->seqcount.sequence) != start); } /** * read_seqcount_latch_retry() - end a seqcount_latch_t read section * @s: Pointer to seqcount_latch_t * @start: count, from read_seqcount_latch() * * Return: true if a read section retry is required, else false */ static __always_inline int read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start) { kcsan_atomic_next(0); return raw_read_seqcount_latch_retry(s, start); } /** * raw_write_seqcount_latch() - redirect latch readers to even/odd copy * @s: Pointer to seqcount_latch_t */ static __always_inline void raw_write_seqcount_latch(seqcount_latch_t *s) { smp_wmb(); /* prior stores before incrementing "sequence" */ s->seqcount.sequence++; smp_wmb(); /* increment "sequence" before following stores */ } /** * write_seqcount_latch_begin() - redirect latch readers to odd copy * @s: Pointer to seqcount_latch_t * * The latch technique is a multiversion concurrency control method that allows * queries during non-atomic modifications. If you can guarantee queries never * interrupt the modification -- e.g. the concurrency is strictly between CPUs * -- you most likely do not need this. * * Where the traditional RCU/lockless data structures rely on atomic * modifications to ensure queries observe either the old or the new state the * latch allows the same for non-atomic updates. The trade-off is doubling the * cost of storage; we have to maintain two copies of the entire data * structure. * * Very simply put: we first modify one copy and then the other. This ensures * there is always one copy in a stable state, ready to give us an answer. * * The basic form is a data structure like:: * * struct latch_struct { * seqcount_latch_t seq; * struct data_struct data[2]; * }; * * Where a modification, which is assumed to be externally serialized, does the * following:: * * void latch_modify(struct latch_struct *latch, ...) * { * write_seqcount_latch_begin(&latch->seq); * modify(latch->data[0], ...); * write_seqcount_latch(&latch->seq); * modify(latch->data[1], ...); * write_seqcount_latch_end(&latch->seq); * } * * The query will have a form like:: * * struct entry *latch_query(struct latch_struct *latch, ...) * { * struct entry *entry; * unsigned seq, idx; * * do { * seq = read_seqcount_latch(&latch->seq); * * idx = seq & 0x01; * entry = data_query(latch->data[idx], ...); * * // This includes needed smp_rmb() * } while (read_seqcount_latch_retry(&latch->seq, seq)); * * return entry; * } * * So during the modification, queries are first redirected to data[1]. Then we * modify data[0]. When that is complete, we redirect queries back to data[0] * and we can modify data[1]. * * NOTE: * * The non-requirement for atomic modifications does _NOT_ include * the publishing of new entries in the case where data is a dynamic * data structure. * * An iteration might start in data[0] and get suspended long enough * to miss an entire modification sequence, once it resumes it might * observe the new entry. * * NOTE2: * * When data is a dynamic data structure; one should use regular RCU * patterns to manage the lifetimes of the objects within. */ static __always_inline void write_seqcount_latch_begin(seqcount_latch_t *s) { kcsan_nestable_atomic_begin(); raw_write_seqcount_latch(s); } /** * write_seqcount_latch() - redirect latch readers to even copy * @s: Pointer to seqcount_latch_t */ static __always_inline void write_seqcount_latch(seqcount_latch_t *s) { raw_write_seqcount_latch(s); } /** * write_seqcount_latch_end() - end a seqcount_latch_t write section * @s: Pointer to seqcount_latch_t * * Marks the end of a seqcount_latch_t writer section, after all copies of the * latch-protected data have been updated. */ static __always_inline void write_seqcount_latch_end(seqcount_latch_t *s) { kcsan_nestable_atomic_end(); } #define __SEQLOCK_UNLOCKED(lockname) \ { \ .seqcount = SEQCNT_SPINLOCK_ZERO(lockname, &(lockname).lock), \ .lock = __SPIN_LOCK_UNLOCKED(lockname) \ } /** * seqlock_init() - dynamic initializer for seqlock_t * @sl: Pointer to the seqlock_t instance */ #define seqlock_init(sl) \ do { \ spin_lock_init(&(sl)->lock); \ seqcount_spinlock_init(&(sl)->seqcount, &(sl)->lock); \ } while (0) /** * DEFINE_SEQLOCK(sl) - Define a statically allocated seqlock_t * @sl: Name of the seqlock_t instance */ #define DEFINE_SEQLOCK(sl) \ seqlock_t sl = __SEQLOCK_UNLOCKED(sl) /** * read_seqbegin() - start a seqlock_t read side critical section * @sl: Pointer to seqlock_t * * Return: count, to be passed to read_seqretry() */ static inline unsigned read_seqbegin(const seqlock_t *sl) { return read_seqcount_begin(&sl->seqcount); } /** * read_seqretry() - end a seqlock_t read side section * @sl: Pointer to seqlock_t * @start: count, from read_seqbegin() * * read_seqretry closes the read side critical section of given seqlock_t. * If the critical section was invalid, it must be ignored (and typically * retried). * * Return: true if a read section retry is required, else false */ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) { return read_seqcount_retry(&sl->seqcount, start); } /* * For all seqlock_t write side functions, use the internal * do_write_seqcount_begin() instead of generic write_seqcount_begin(). * This way, no redundant lockdep_assert_held() checks are added. */ /** * write_seqlock() - start a seqlock_t write side critical section * @sl: Pointer to seqlock_t * * write_seqlock opens a write side critical section for the given * seqlock_t. It also implicitly acquires the spinlock_t embedded inside * that sequential lock. All seqlock_t write side sections are thus * automatically serialized and non-preemptible. * * Context: if the seqlock_t read section, or other write side critical * sections, can be invoked from hardirq or softirq contexts, use the * _irqsave or _bh variants of this function instead. */ static inline void write_seqlock(seqlock_t *sl) { spin_lock(&sl->lock); do_write_seqcount_begin(&sl->seqcount.seqcount); } /** * write_sequnlock() - end a seqlock_t write side critical section * @sl: Pointer to seqlock_t * * write_sequnlock closes the (serialized and non-preemptible) write side * critical section of given seqlock_t. */ static inline void write_sequnlock(seqlock_t *sl) { do_write_seqcount_end(&sl->seqcount.seqcount); spin_unlock(&sl->lock); } /** * write_seqlock_bh() - start a softirqs-disabled seqlock_t write section * @sl: Pointer to seqlock_t * * _bh variant of write_seqlock(). Use only if the read side section, or * other write side sections, can be invoked from softirq contexts. */ static inline void write_seqlock_bh(seqlock_t *sl) { spin_lock_bh(&sl->lock); do_write_seqcount_begin(&sl->seqcount.seqcount); } /** * write_sequnlock_bh() - end a softirqs-disabled seqlock_t write section * @sl: Pointer to seqlock_t * * write_sequnlock_bh closes the serialized, non-preemptible, and * softirqs-disabled, seqlock_t write side critical section opened with * write_seqlock_bh(). */ static inline void write_sequnlock_bh(seqlock_t *sl) { do_write_seqcount_end(&sl->seqcount.seqcount); spin_unlock_bh(&sl->lock); } /** * write_seqlock_irq() - start a non-interruptible seqlock_t write section * @sl: Pointer to seqlock_t * * _irq variant of write_seqlock(). Use only if the read side section, or * other write sections, can be invoked from hardirq contexts. */ static inline void write_seqlock_irq(seqlock_t *sl) { spin_lock_irq(&sl->lock); do_write_seqcount_begin(&sl->seqcount.seqcount); } /** * write_sequnlock_irq() - end a non-interruptible seqlock_t write section * @sl: Pointer to seqlock_t * * write_sequnlock_irq closes the serialized and non-interruptible * seqlock_t write side section opened with write_seqlock_irq(). */ static inline void write_sequnlock_irq(seqlock_t *sl) { do_write_seqcount_end(&sl->seqcount.seqcount); spin_unlock_irq(&sl->lock); } static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl) { unsigned long flags; spin_lock_irqsave(&sl->lock, flags); do_write_seqcount_begin(&sl->seqcount.seqcount); return flags; } /** * write_seqlock_irqsave() - start a non-interruptible seqlock_t write * section * @lock: Pointer to seqlock_t * @flags: Stack-allocated storage for saving caller's local interrupt * state, to be passed to write_sequnlock_irqrestore(). * * _irqsave variant of write_seqlock(). Use it only if the read side * section, or other write sections, can be invoked from hardirq context. */ #define write_seqlock_irqsave(lock, flags) \ do { flags = __write_seqlock_irqsave(lock); } while (0) /** * write_sequnlock_irqrestore() - end non-interruptible seqlock_t write * section * @sl: Pointer to seqlock_t * @flags: Caller's saved interrupt state, from write_seqlock_irqsave() * * write_sequnlock_irqrestore closes the serialized and non-interruptible * seqlock_t write section previously opened with write_seqlock_irqsave(). */ static inline void write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags) { do_write_seqcount_end(&sl->seqcount.seqcount); spin_unlock_irqrestore(&sl->lock, flags); } /** * read_seqlock_excl() - begin a seqlock_t locking reader section * @sl: Pointer to seqlock_t * * read_seqlock_excl opens a seqlock_t locking reader critical section. A * locking reader exclusively locks out *both* other writers *and* other * locking readers, but it does not update the embedded sequence number. * * Locking readers act like a normal spin_lock()/spin_unlock(). * * Context: if the seqlock_t write section, *or other read sections*, can * be invoked from hardirq or softirq contexts, use the _irqsave or _bh * variant of this function instead. * * The opened read section must be closed with read_sequnlock_excl(). */ static inline void read_seqlock_excl(seqlock_t *sl) { spin_lock(&sl->lock); } /** * read_sequnlock_excl() - end a seqlock_t locking reader critical section * @sl: Pointer to seqlock_t */ static inline void read_sequnlock_excl(seqlock_t *sl) { spin_unlock(&sl->lock); } /** * read_seqlock_excl_bh() - start a seqlock_t locking reader section with * softirqs disabled * @sl: Pointer to seqlock_t * * _bh variant of read_seqlock_excl(). Use this variant only if the * seqlock_t write side section, *or other read sections*, can be invoked * from softirq contexts. */ static inline void read_seqlock_excl_bh(seqlock_t *sl) { spin_lock_bh(&sl->lock); } /** * read_sequnlock_excl_bh() - stop a seqlock_t softirq-disabled locking * reader section * @sl: Pointer to seqlock_t */ static inline void read_sequnlock_excl_bh(seqlock_t *sl) { spin_unlock_bh(&sl->lock); } /** * read_seqlock_excl_irq() - start a non-interruptible seqlock_t locking * reader section * @sl: Pointer to seqlock_t * * _irq variant of read_seqlock_excl(). Use this only if the seqlock_t * write side section, *or other read sections*, can be invoked from a * hardirq context. */ static inline void read_seqlock_excl_irq(seqlock_t *sl) { spin_lock_irq(&sl->lock); } /** * read_sequnlock_excl_irq() - end an interrupts-disabled seqlock_t * locking reader section * @sl: Pointer to seqlock_t */ static inline void read_sequnlock_excl_irq(seqlock_t *sl) { spin_unlock_irq(&sl->lock); } static inline unsigned long __read_seqlock_excl_irqsave(seqlock_t *sl) { unsigned long flags; spin_lock_irqsave(&sl->lock, flags); return flags; } /** * read_seqlock_excl_irqsave() - start a non-interruptible seqlock_t * locking reader section * @lock: Pointer to seqlock_t * @flags: Stack-allocated storage for saving caller's local interrupt * state, to be passed to read_sequnlock_excl_irqrestore(). * * _irqsave variant of read_seqlock_excl(). Use this only if the seqlock_t * write side section, *or other read sections*, can be invoked from a * hardirq context. */ #define read_seqlock_excl_irqsave(lock, flags) \ do { flags = __read_seqlock_excl_irqsave(lock); } while (0) /** * read_sequnlock_excl_irqrestore() - end non-interruptible seqlock_t * locking reader section * @sl: Pointer to seqlock_t * @flags: Caller saved interrupt state, from read_seqlock_excl_irqsave() */ static inline void read_sequnlock_excl_irqrestore(seqlock_t *sl, unsigned long flags) { spin_unlock_irqrestore(&sl->lock, flags); } /** * read_seqbegin_or_lock() - begin a seqlock_t lockless or locking reader * @lock: Pointer to seqlock_t * @seq : Marker and return parameter. If the passed value is even, the * reader will become a *lockless* seqlock_t reader as in read_seqbegin(). * If the passed value is odd, the reader will become a *locking* reader * as in read_seqlock_excl(). In the first call to this function, the * caller *must* initialize and pass an even value to @seq; this way, a * lockless read can be optimistically tried first. * * read_seqbegin_or_lock is an API designed to optimistically try a normal * lockless seqlock_t read section first. If an odd counter is found, the * lockless read trial has failed, and the next read iteration transforms * itself into a full seqlock_t locking reader. * * This is typically used to avoid seqlock_t lockless readers starvation * (too much retry loops) in the case of a sharp spike in write side * activity. * * Context: if the seqlock_t write section, *or other read sections*, can * be invoked from hardirq or softirq contexts, use the _irqsave or _bh * variant of this function instead. * * Check Documentation/locking/seqlock.rst for template example code. * * Return: the encountered sequence counter value, through the @seq * parameter, which is overloaded as a return parameter. This returned * value must be checked with need_seqretry(). If the read section need to * be retried, this returned value must also be passed as the @seq * parameter of the next read_seqbegin_or_lock() iteration. */ static inline void read_seqbegin_or_lock(seqlock_t *lock, int *seq) { if (!(*seq & 1)) /* Even */ *seq = read_seqbegin(lock); else /* Odd */ read_seqlock_excl(lock); } /** * need_seqretry() - validate seqlock_t "locking or lockless" read section * @lock: Pointer to seqlock_t * @seq: sequence count, from read_seqbegin_or_lock() * * Return: true if a read section retry is required, false otherwise */ static inline int need_seqretry(seqlock_t *lock, int seq) { return !(seq & 1) && read_seqretry(lock, seq); } /** * done_seqretry() - end seqlock_t "locking or lockless" reader section * @lock: Pointer to seqlock_t * @seq: count, from read_seqbegin_or_lock() * * done_seqretry finishes the seqlock_t read side critical section started * with read_seqbegin_or_lock() and validated by need_seqretry(). */ static inline void done_seqretry(seqlock_t *lock, int seq) { if (seq & 1) read_sequnlock_excl(lock); } /** * read_seqbegin_or_lock_irqsave() - begin a seqlock_t lockless reader, or * a non-interruptible locking reader * @lock: Pointer to seqlock_t * @seq: Marker and return parameter. Check read_seqbegin_or_lock(). * * This is the _irqsave variant of read_seqbegin_or_lock(). Use it only if * the seqlock_t write section, *or other read sections*, can be invoked * from hardirq context. * * Note: Interrupts will be disabled only for "locking reader" mode. * * Return: * * 1. The saved local interrupts state in case of a locking reader, to * be passed to done_seqretry_irqrestore(). * * 2. The encountered sequence counter value, returned through @seq * overloaded as a return parameter. Check read_seqbegin_or_lock(). */ static inline unsigned long read_seqbegin_or_lock_irqsave(seqlock_t *lock, int *seq) { unsigned long flags = 0; if (!(*seq & 1)) /* Even */ *seq = read_seqbegin(lock); else /* Odd */ read_seqlock_excl_irqsave(lock, flags); return flags; } /** * done_seqretry_irqrestore() - end a seqlock_t lockless reader, or a * non-interruptible locking reader section * @lock: Pointer to seqlock_t * @seq: Count, from read_seqbegin_or_lock_irqsave() * @flags: Caller's saved local interrupt state in case of a locking * reader, also from read_seqbegin_or_lock_irqsave() * * This is the _irqrestore variant of done_seqretry(). The read section * must've been opened with read_seqbegin_or_lock_irqsave(), and validated * by need_seqretry(). */ static inline void done_seqretry_irqrestore(seqlock_t *lock, int seq, unsigned long flags) { if (seq & 1) read_sequnlock_excl_irqrestore(lock, flags); } #endif /* __LINUX_SEQLOCK_H */ |
| 8509 8509 8574 1110 721 59 1023 30 719 59 1023 719 30 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM net #if !defined(_TRACE_NET_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_NET_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/if_vlan.h> #include <linux/ip.h> #include <linux/tracepoint.h> TRACE_EVENT(net_dev_start_xmit, TP_PROTO(const struct sk_buff *skb, const struct net_device *dev), TP_ARGS(skb, dev), TP_STRUCT__entry( __string( name, dev->name ) __field( u16, queue_mapping ) __field( const void *, skbaddr ) __field( bool, vlan_tagged ) __field( u16, vlan_proto ) __field( u16, vlan_tci ) __field( u16, protocol ) __field( u8, ip_summed ) __field( unsigned int, len ) __field( unsigned int, data_len ) __field( int, network_offset ) __field( bool, transport_offset_valid) __field( int, transport_offset) __field( u8, tx_flags ) __field( u16, gso_size ) __field( u16, gso_segs ) __field( u16, gso_type ) ), TP_fast_assign( __assign_str(name); __entry->queue_mapping = skb->queue_mapping; __entry->skbaddr = skb; __entry->vlan_tagged = skb_vlan_tag_present(skb); __entry->vlan_proto = ntohs(skb->vlan_proto); __entry->vlan_tci = skb_vlan_tag_get(skb); __entry->protocol = ntohs(skb->protocol); __entry->ip_summed = skb->ip_summed; __entry->len = skb->len; __entry->data_len = skb->data_len; __entry->network_offset = skb_network_offset(skb); __entry->transport_offset_valid = skb_transport_header_was_set(skb); __entry->transport_offset = skb_transport_header_was_set(skb) ? skb_transport_offset(skb) : 0; __entry->tx_flags = skb_shinfo(skb)->tx_flags; __entry->gso_size = skb_shinfo(skb)->gso_size; __entry->gso_segs = skb_shinfo(skb)->gso_segs; __entry->gso_type = skb_shinfo(skb)->gso_type; ), TP_printk("dev=%s queue_mapping=%u skbaddr=%p vlan_tagged=%d vlan_proto=0x%04x vlan_tci=0x%04x protocol=0x%04x ip_summed=%d len=%u data_len=%u network_offset=%d transport_offset_valid=%d transport_offset=%d tx_flags=%d gso_size=%d gso_segs=%d gso_type=%#x", __get_str(name), __entry->queue_mapping, __entry->skbaddr, __entry->vlan_tagged, __entry->vlan_proto, __entry->vlan_tci, __entry->protocol, __entry->ip_summed, __entry->len, __entry->data_len, __entry->network_offset, __entry->transport_offset_valid, __entry->transport_offset, __entry->tx_flags, __entry->gso_size, __entry->gso_segs, __entry->gso_type) ); TRACE_EVENT(net_dev_xmit, TP_PROTO(struct sk_buff *skb, int rc, struct net_device *dev, unsigned int skb_len), TP_ARGS(skb, rc, dev, skb_len), TP_STRUCT__entry( __field( void *, skbaddr ) __field( unsigned int, len ) __field( int, rc ) __string( name, dev->name ) ), TP_fast_assign( __entry->skbaddr = skb; __entry->len = skb_len; __entry->rc = rc; __assign_str(name); ), TP_printk("dev=%s skbaddr=%p len=%u rc=%d", __get_str(name), __entry->skbaddr, __entry->len, __entry->rc) ); TRACE_EVENT(net_dev_xmit_timeout, TP_PROTO(struct net_device *dev, int queue_index), TP_ARGS(dev, queue_index), TP_STRUCT__entry( __string( name, dev->name ) __string( driver, netdev_drivername(dev)) __field( int, queue_index ) ), TP_fast_assign( __assign_str(name); __assign_str(driver); __entry->queue_index = queue_index; ), TP_printk("dev=%s driver=%s queue=%d", __get_str(name), __get_str(driver), __entry->queue_index) ); DECLARE_EVENT_CLASS(net_dev_template, TP_PROTO(struct sk_buff *skb), TP_ARGS(skb), TP_STRUCT__entry( __field( void *, skbaddr ) __field( unsigned int, len ) __string( name, skb->dev->name ) ), TP_fast_assign( __entry->skbaddr = skb; __entry->len = skb->len; __assign_str(name); ), TP_printk("dev=%s skbaddr=%p len=%u", __get_str(name), __entry->skbaddr, __entry->len) ) DEFINE_EVENT(net_dev_template, net_dev_queue, TP_PROTO(struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_template, netif_receive_skb, TP_PROTO(struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_template, netif_rx, TP_PROTO(struct sk_buff *skb), TP_ARGS(skb) ); DECLARE_EVENT_CLASS(net_dev_rx_verbose_template, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb), TP_STRUCT__entry( __string( name, skb->dev->name ) __field( unsigned int, napi_id ) __field( u16, queue_mapping ) __field( const void *, skbaddr ) __field( bool, vlan_tagged ) __field( u16, vlan_proto ) __field( u16, vlan_tci ) __field( u16, protocol ) __field( u8, ip_summed ) __field( u32, hash ) __field( bool, l4_hash ) __field( unsigned int, len ) __field( unsigned int, data_len ) __field( unsigned int, truesize ) __field( bool, mac_header_valid) __field( int, mac_header ) __field( unsigned char, nr_frags ) __field( u16, gso_size ) __field( u16, gso_type ) ), TP_fast_assign( __assign_str(name); #ifdef CONFIG_NET_RX_BUSY_POLL __entry->napi_id = skb->napi_id; #else __entry->napi_id = 0; #endif __entry->queue_mapping = skb->queue_mapping; __entry->skbaddr = skb; __entry->vlan_tagged = skb_vlan_tag_present(skb); __entry->vlan_proto = ntohs(skb->vlan_proto); __entry->vlan_tci = skb_vlan_tag_get(skb); __entry->protocol = ntohs(skb->protocol); __entry->ip_summed = skb->ip_summed; __entry->hash = skb->hash; __entry->l4_hash = skb->l4_hash; __entry->len = skb->len; __entry->data_len = skb->data_len; __entry->truesize = skb->truesize; __entry->mac_header_valid = skb_mac_header_was_set(skb); __entry->mac_header = skb_mac_header(skb) - skb->data; __entry->nr_frags = skb_shinfo(skb)->nr_frags; __entry->gso_size = skb_shinfo(skb)->gso_size; __entry->gso_type = skb_shinfo(skb)->gso_type; ), TP_printk("dev=%s napi_id=%#x queue_mapping=%u skbaddr=%p vlan_tagged=%d vlan_proto=0x%04x vlan_tci=0x%04x protocol=0x%04x ip_summed=%d hash=0x%08x l4_hash=%d len=%u data_len=%u truesize=%u mac_header_valid=%d mac_header=%d nr_frags=%d gso_size=%d gso_type=%#x", __get_str(name), __entry->napi_id, __entry->queue_mapping, __entry->skbaddr, __entry->vlan_tagged, __entry->vlan_proto, __entry->vlan_tci, __entry->protocol, __entry->ip_summed, __entry->hash, __entry->l4_hash, __entry->len, __entry->data_len, __entry->truesize, __entry->mac_header_valid, __entry->mac_header, __entry->nr_frags, __entry->gso_size, __entry->gso_type) ); DEFINE_EVENT(net_dev_rx_verbose_template, napi_gro_frags_entry, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_rx_verbose_template, napi_gro_receive_entry, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_rx_verbose_template, netif_receive_skb_entry, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_rx_verbose_template, netif_receive_skb_list_entry, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_rx_verbose_template, netif_rx_entry, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb) ); DECLARE_EVENT_CLASS(net_dev_rx_exit_template, TP_PROTO(int ret), TP_ARGS(ret), TP_STRUCT__entry( __field(int, ret) ), TP_fast_assign( __entry->ret = ret; ), TP_printk("ret=%d", __entry->ret) ); DEFINE_EVENT(net_dev_rx_exit_template, napi_gro_frags_exit, TP_PROTO(int ret), TP_ARGS(ret) ); DEFINE_EVENT(net_dev_rx_exit_template, napi_gro_receive_exit, TP_PROTO(int ret), TP_ARGS(ret) ); DEFINE_EVENT(net_dev_rx_exit_template, netif_receive_skb_exit, TP_PROTO(int ret), TP_ARGS(ret) ); DEFINE_EVENT(net_dev_rx_exit_template, netif_rx_exit, TP_PROTO(int ret), TP_ARGS(ret) ); DEFINE_EVENT(net_dev_rx_exit_template, netif_receive_skb_list_exit, TP_PROTO(int ret), TP_ARGS(ret) ); #endif /* _TRACE_NET_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 33 33 81 1080 2 1 72 16 9 134 9 143 1 103 74 73 73 64 24 25 43 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_SIGNAL_H #define _LINUX_SCHED_SIGNAL_H #include <linux/rculist.h> #include <linux/signal.h> #include <linux/sched.h> #include <linux/sched/jobctl.h> #include <linux/sched/task.h> #include <linux/cred.h> #include <linux/refcount.h> #include <linux/pid.h> #include <linux/posix-timers.h> #include <linux/mm_types.h> #include <asm/ptrace.h> /* * Types defining task->signal and task->sighand and APIs using them: */ struct sighand_struct { spinlock_t siglock; refcount_t count; wait_queue_head_t signalfd_wqh; struct k_sigaction action[_NSIG]; }; /* * Per-process accounting stats: */ struct pacct_struct { int ac_flag; long ac_exitcode; unsigned long ac_mem; u64 ac_utime, ac_stime; unsigned long ac_minflt, ac_majflt; }; struct cpu_itimer { u64 expires; u64 incr; }; /* * This is the atomic variant of task_cputime, which can be used for * storing and updating task_cputime statistics without locking. */ struct task_cputime_atomic { atomic64_t utime; atomic64_t stime; atomic64_t sum_exec_runtime; }; #define INIT_CPUTIME_ATOMIC \ (struct task_cputime_atomic) { \ .utime = ATOMIC64_INIT(0), \ .stime = ATOMIC64_INIT(0), \ .sum_exec_runtime = ATOMIC64_INIT(0), \ } /** * struct thread_group_cputimer - thread group interval timer counts * @cputime_atomic: atomic thread group interval timers. * * This structure contains the version of task_cputime, above, that is * used for thread group CPU timer calculations. */ struct thread_group_cputimer { struct task_cputime_atomic cputime_atomic; }; struct multiprocess_signals { sigset_t signal; struct hlist_node node; }; struct core_thread { struct task_struct *task; struct core_thread *next; }; struct core_state { atomic_t nr_threads; struct core_thread dumper; struct completion startup; }; /* * NOTE! "signal_struct" does not have its own * locking, because a shared signal_struct always * implies a shared sighand_struct, so locking * sighand_struct is always a proper superset of * the locking of signal_struct. */ struct signal_struct { refcount_t sigcnt; atomic_t live; int nr_threads; int quick_threads; struct list_head thread_head; wait_queue_head_t wait_chldexit; /* for wait4() */ /* current thread group signal load-balancing target: */ struct task_struct *curr_target; /* shared signal handling: */ struct sigpending shared_pending; /* For collecting multiprocess signals during fork */ struct hlist_head multiprocess; /* thread group exit support */ int group_exit_code; /* notify group_exec_task when notify_count is less or equal to 0 */ int notify_count; struct task_struct *group_exec_task; /* thread group stop support, overloads group_exit_code too */ int group_stop_count; unsigned int flags; /* see SIGNAL_* flags below */ struct core_state *core_state; /* coredumping support */ /* * PR_SET_CHILD_SUBREAPER marks a process, like a service * manager, to re-parent orphan (double-forking) child processes * to this process instead of 'init'. The service manager is * able to receive SIGCHLD signals and is able to investigate * the process until it calls wait(). All children of this * process will inherit a flag if they should look for a * child_subreaper process at exit. */ unsigned int is_child_subreaper:1; unsigned int has_child_subreaper:1; #ifdef CONFIG_POSIX_TIMERS /* POSIX.1b Interval Timers */ unsigned int next_posix_timer_id; struct hlist_head posix_timers; struct hlist_head ignored_posix_timers; /* ITIMER_REAL timer for the process */ struct hrtimer real_timer; ktime_t it_real_incr; /* * ITIMER_PROF and ITIMER_VIRTUAL timers for the process, we use * CPUCLOCK_PROF and CPUCLOCK_VIRT for indexing array as these * values are defined to 0 and 1 respectively */ struct cpu_itimer it[2]; /* * Thread group totals for process CPU timers. * See thread_group_cputimer(), et al, for details. */ struct thread_group_cputimer cputimer; #endif /* Empty if CONFIG_POSIX_TIMERS=n */ struct posix_cputimers posix_cputimers; /* PID/PID hash table linkage. */ struct pid *pids[PIDTYPE_MAX]; #ifdef CONFIG_NO_HZ_FULL atomic_t tick_dep_mask; #endif struct pid *tty_old_pgrp; /* boolean value for session group leader */ int leader; struct tty_struct *tty; /* NULL if no tty */ #ifdef CONFIG_SCHED_AUTOGROUP struct autogroup *autogroup; #endif /* * Cumulative resource counters for dead threads in the group, * and for reaped dead child processes forked by this group. * Live threads maintain their own counters and add to these * in __exit_signal, except for the group leader. */ seqlock_t stats_lock; u64 utime, stime, cutime, cstime; u64 gtime; u64 cgtime; struct prev_cputime prev_cputime; unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt; unsigned long inblock, oublock, cinblock, coublock; unsigned long maxrss, cmaxrss; struct task_io_accounting ioac; /* * Cumulative ns of schedule CPU time fo dead threads in the * group, not including a zombie group leader, (This only differs * from jiffies_to_ns(utime + stime) if sched_clock uses something * other than jiffies.) */ unsigned long long sum_sched_runtime; /* * We don't bother to synchronize most readers of this at all, * because there is no reader checking a limit that actually needs * to get both rlim_cur and rlim_max atomically, and either one * alone is a single word that can safely be read normally. * getrlimit/setrlimit use task_lock(current->group_leader) to * protect this instead of the siglock, because they really * have no need to disable irqs. */ struct rlimit rlim[RLIM_NLIMITS]; #ifdef CONFIG_BSD_PROCESS_ACCT struct pacct_struct pacct; /* per-process accounting information */ #endif #ifdef CONFIG_TASKSTATS struct taskstats *stats; #endif #ifdef CONFIG_AUDIT unsigned audit_tty; struct tty_audit_buf *tty_audit_buf; #endif /* * Thread is the potential origin of an oom condition; kill first on * oom */ bool oom_flag_origin; short oom_score_adj; /* OOM kill score adjustment */ short oom_score_adj_min; /* OOM kill score adjustment min value. * Only settable by CAP_SYS_RESOURCE. */ struct mm_struct *oom_mm; /* recorded mm when the thread group got * killed by the oom killer */ struct mutex cred_guard_mutex; /* guard against foreign influences on * credential calculations * (notably. ptrace) * Deprecated do not use in new code. * Use exec_update_lock instead. */ struct rw_semaphore exec_update_lock; /* Held while task_struct is * being updated during exec, * and may have inconsistent * permissions. */ } __randomize_layout; /* * Bits in flags field of signal_struct. */ #define SIGNAL_STOP_STOPPED 0x00000001 /* job control stop in effect */ #define SIGNAL_STOP_CONTINUED 0x00000002 /* SIGCONT since WCONTINUED reap */ #define SIGNAL_GROUP_EXIT 0x00000004 /* group exit in progress */ /* * Pending notifications to parent. */ #define SIGNAL_CLD_STOPPED 0x00000010 #define SIGNAL_CLD_CONTINUED 0x00000020 #define SIGNAL_CLD_MASK (SIGNAL_CLD_STOPPED|SIGNAL_CLD_CONTINUED) #define SIGNAL_UNKILLABLE 0x00000040 /* for init: ignore fatal signals */ #define SIGNAL_STOP_MASK (SIGNAL_CLD_MASK | SIGNAL_STOP_STOPPED | \ SIGNAL_STOP_CONTINUED) static inline void signal_set_stop_flags(struct signal_struct *sig, unsigned int flags) { WARN_ON(sig->flags & SIGNAL_GROUP_EXIT); sig->flags = (sig->flags & ~SIGNAL_STOP_MASK) | flags; } extern void flush_signals(struct task_struct *); extern void ignore_signals(struct task_struct *); extern void flush_signal_handlers(struct task_struct *, int force_default); extern int dequeue_signal(sigset_t *mask, kernel_siginfo_t *info, enum pid_type *type); static inline int kernel_dequeue_signal(void) { struct task_struct *task = current; kernel_siginfo_t __info; enum pid_type __type; int ret; spin_lock_irq(&task->sighand->siglock); ret = dequeue_signal(&task->blocked, &__info, &__type); spin_unlock_irq(&task->sighand->siglock); return ret; } static inline void kernel_signal_stop(void) { spin_lock_irq(¤t->sighand->siglock); if (current->jobctl & JOBCTL_STOP_DEQUEUED) { current->jobctl |= JOBCTL_STOPPED; set_special_state(TASK_STOPPED); } spin_unlock_irq(¤t->sighand->siglock); schedule(); } int force_sig_fault_to_task(int sig, int code, void __user *addr, struct task_struct *t); int force_sig_fault(int sig, int code, void __user *addr); int send_sig_fault(int sig, int code, void __user *addr, struct task_struct *t); int force_sig_mceerr(int code, void __user *, short); int send_sig_mceerr(int code, void __user *, short, struct task_struct *); int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper); int force_sig_pkuerr(void __user *addr, u32 pkey); int send_sig_perf(void __user *addr, u32 type, u64 sig_data); int force_sig_ptrace_errno_trap(int errno, void __user *addr); int force_sig_fault_trapno(int sig, int code, void __user *addr, int trapno); int send_sig_fault_trapno(int sig, int code, void __user *addr, int trapno, struct task_struct *t); int force_sig_seccomp(int syscall, int reason, bool force_coredump); extern int send_sig_info(int, struct kernel_siginfo *, struct task_struct *); extern void force_sigsegv(int sig); extern int force_sig_info(struct kernel_siginfo *); extern int __kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp); extern int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid); extern int kill_pid_usb_asyncio(int sig, int errno, sigval_t addr, struct pid *, const struct cred *); extern int kill_pgrp(struct pid *pid, int sig, int priv); extern int kill_pid(struct pid *pid, int sig, int priv); extern __must_check bool do_notify_parent(struct task_struct *, int); extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent); extern void force_sig(int); extern void force_fatal_sig(int); extern void force_exit_sig(int); extern int send_sig(int, struct task_struct *, int); extern int zap_other_threads(struct task_struct *p); extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *); static inline void clear_notify_signal(void) { clear_thread_flag(TIF_NOTIFY_SIGNAL); smp_mb__after_atomic(); } /* * Returns 'true' if kick_process() is needed to force a transition from * user -> kernel to guarantee expedient run of TWA_SIGNAL based task_work. */ static inline bool __set_notify_signal(struct task_struct *task) { return !test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && !wake_up_state(task, TASK_INTERRUPTIBLE); } /* * Called to break out of interruptible wait loops, and enter the * exit_to_user_mode_loop(). */ static inline void set_notify_signal(struct task_struct *task) { if (__set_notify_signal(task)) kick_process(task); } static inline int restart_syscall(void) { set_tsk_thread_flag(current, TIF_SIGPENDING); return -ERESTARTNOINTR; } static inline int task_sigpending(struct task_struct *p) { return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING)); } static inline int signal_pending(struct task_struct *p) { /* * TIF_NOTIFY_SIGNAL isn't really a signal, but it requires the same * behavior in terms of ensuring that we break out of wait loops * so that notify signal callbacks can be processed. */ if (unlikely(test_tsk_thread_flag(p, TIF_NOTIFY_SIGNAL))) return 1; return task_sigpending(p); } static inline int __fatal_signal_pending(struct task_struct *p) { return unlikely(sigismember(&p->pending.signal, SIGKILL)); } static inline int fatal_signal_pending(struct task_struct *p) { return task_sigpending(p) && __fatal_signal_pending(p); } static inline int signal_pending_state(unsigned int state, struct task_struct *p) { if (!(state & (TASK_INTERRUPTIBLE | TASK_WAKEKILL))) return 0; if (!signal_pending(p)) return 0; return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); } /* * This should only be used in fault handlers to decide whether we * should stop the current fault routine to handle the signals * instead, especially with the case where we've got interrupted with * a VM_FAULT_RETRY. */ static inline bool fault_signal_pending(vm_fault_t fault_flags, struct pt_regs *regs) { return unlikely((fault_flags & VM_FAULT_RETRY) && (fatal_signal_pending(current) || (user_mode(regs) && signal_pending(current)))); } /* * Reevaluate whether the task has signals pending delivery. * Wake the task if so. * This is required every time the blocked sigset_t changes. * callers must hold sighand->siglock. */ extern void recalc_sigpending(void); extern void calculate_sigpending(void); extern void signal_wake_up_state(struct task_struct *t, unsigned int state); static inline void signal_wake_up(struct task_struct *t, bool fatal) { unsigned int state = 0; if (fatal && !(t->jobctl & JOBCTL_PTRACE_FROZEN)) { t->jobctl &= ~(JOBCTL_STOPPED | JOBCTL_TRACED); state = TASK_WAKEKILL | __TASK_TRACED; } signal_wake_up_state(t, state); } static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume) { unsigned int state = 0; if (resume) { t->jobctl &= ~JOBCTL_TRACED; state = __TASK_TRACED; } signal_wake_up_state(t, state); } void task_join_group_stop(struct task_struct *task); #ifdef TIF_RESTORE_SIGMASK /* * Legacy restore_sigmask accessors. These are inefficient on * SMP architectures because they require atomic operations. */ /** * set_restore_sigmask() - make sure saved_sigmask processing gets done * * This sets TIF_RESTORE_SIGMASK and ensures that the arch signal code * will run before returning to user mode, to process the flag. For * all callers, TIF_SIGPENDING is already set or it's no harm to set * it. TIF_RESTORE_SIGMASK need not be in the set of bits that the * arch code will notice on return to user mode, in case those bits * are scarce. We set TIF_SIGPENDING here to ensure that the arch * signal code always gets run when TIF_RESTORE_SIGMASK is set. */ static inline void set_restore_sigmask(void) { set_thread_flag(TIF_RESTORE_SIGMASK); } static inline void clear_tsk_restore_sigmask(struct task_struct *task) { clear_tsk_thread_flag(task, TIF_RESTORE_SIGMASK); } static inline void clear_restore_sigmask(void) { clear_thread_flag(TIF_RESTORE_SIGMASK); } static inline bool test_tsk_restore_sigmask(struct task_struct *task) { return test_tsk_thread_flag(task, TIF_RESTORE_SIGMASK); } static inline bool test_restore_sigmask(void) { return test_thread_flag(TIF_RESTORE_SIGMASK); } static inline bool test_and_clear_restore_sigmask(void) { return test_and_clear_thread_flag(TIF_RESTORE_SIGMASK); } #else /* TIF_RESTORE_SIGMASK */ /* Higher-quality implementation, used if TIF_RESTORE_SIGMASK doesn't exist. */ static inline void set_restore_sigmask(void) { current->restore_sigmask = true; } static inline void clear_tsk_restore_sigmask(struct task_struct *task) { task->restore_sigmask = false; } static inline void clear_restore_sigmask(void) { current->restore_sigmask = false; } static inline bool test_restore_sigmask(void) { return current->restore_sigmask; } static inline bool test_tsk_restore_sigmask(struct task_struct *task) { return task->restore_sigmask; } static inline bool test_and_clear_restore_sigmask(void) { if (!current->restore_sigmask) return false; current->restore_sigmask = false; return true; } #endif static inline void restore_saved_sigmask(void) { if (test_and_clear_restore_sigmask()) __set_current_blocked(¤t->saved_sigmask); } extern int set_user_sigmask(const sigset_t __user *umask, size_t sigsetsize); static inline void restore_saved_sigmask_unless(bool interrupted) { if (interrupted) WARN_ON(!signal_pending(current)); else restore_saved_sigmask(); } static inline sigset_t *sigmask_to_save(void) { sigset_t *res = ¤t->blocked; if (unlikely(test_restore_sigmask())) res = ¤t->saved_sigmask; return res; } static inline int kill_cad_pid(int sig, int priv) { return kill_pid(cad_pid, sig, priv); } /* These can be the second arg to send_sig_info/send_group_sig_info. */ #define SEND_SIG_NOINFO ((struct kernel_siginfo *) 0) #define SEND_SIG_PRIV ((struct kernel_siginfo *) 1) static inline int __on_sig_stack(unsigned long sp) { #ifdef CONFIG_STACK_GROWSUP return sp >= current->sas_ss_sp && sp - current->sas_ss_sp < current->sas_ss_size; #else return sp > current->sas_ss_sp && sp - current->sas_ss_sp <= current->sas_ss_size; #endif } /* * True if we are on the alternate signal stack. */ static inline int on_sig_stack(unsigned long sp) { /* * If the signal stack is SS_AUTODISARM then, by construction, we * can't be on the signal stack unless user code deliberately set * SS_AUTODISARM when we were already on it. * * This improves reliability: if user state gets corrupted such that * the stack pointer points very close to the end of the signal stack, * then this check will enable the signal to be handled anyway. */ if (current->sas_ss_flags & SS_AUTODISARM) return 0; return __on_sig_stack(sp); } static inline int sas_ss_flags(unsigned long sp) { if (!current->sas_ss_size) return SS_DISABLE; return on_sig_stack(sp) ? SS_ONSTACK : 0; } static inline void sas_ss_reset(struct task_struct *p) { p->sas_ss_sp = 0; p->sas_ss_size = 0; p->sas_ss_flags = SS_DISABLE; } static inline unsigned long sigsp(unsigned long sp, struct ksignal *ksig) { if (unlikely((ksig->ka.sa.sa_flags & SA_ONSTACK)) && ! sas_ss_flags(sp)) #ifdef CONFIG_STACK_GROWSUP return current->sas_ss_sp; #else return current->sas_ss_sp + current->sas_ss_size; #endif return sp; } extern void __cleanup_sighand(struct sighand_struct *); extern void flush_itimer_signals(void); #define tasklist_empty() \ list_empty(&init_task.tasks) #define next_task(p) \ list_entry_rcu((p)->tasks.next, struct task_struct, tasks) #define for_each_process(p) \ for (p = &init_task ; (p = next_task(p)) != &init_task ; ) extern bool current_is_single_threaded(void); /* * Without tasklist/siglock it is only rcu-safe if g can't exit/exec, * otherwise next_thread(t) will never reach g after list_del_rcu(g). */ #define while_each_thread(g, t) \ while ((t = next_thread(t)) != g) #define for_other_threads(p, t) \ for (t = p; (t = next_thread(t)) != p; ) #define __for_each_thread(signal, t) \ list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node, \ lockdep_is_held(&tasklist_lock)) #define for_each_thread(p, t) \ __for_each_thread((p)->signal, t) /* Careful: this is a double loop, 'break' won't work as expected. */ #define for_each_process_thread(p, t) \ for_each_process(p) for_each_thread(p, t) typedef int (*proc_visitor)(struct task_struct *p, void *data); void walk_process_tree(struct task_struct *top, proc_visitor, void *); static inline struct pid *task_pid_type(struct task_struct *task, enum pid_type type) { struct pid *pid; if (type == PIDTYPE_PID) pid = task_pid(task); else pid = task->signal->pids[type]; return pid; } static inline struct pid *task_tgid(struct task_struct *task) { return task->signal->pids[PIDTYPE_TGID]; } /* * Without tasklist or RCU lock it is not safe to dereference * the result of task_pgrp/task_session even if task == current, * we can race with another thread doing sys_setsid/sys_setpgid. */ static inline struct pid *task_pgrp(struct task_struct *task) { return task->signal->pids[PIDTYPE_PGID]; } static inline struct pid *task_session(struct task_struct *task) { return task->signal->pids[PIDTYPE_SID]; } static inline int get_nr_threads(struct task_struct *task) { return task->signal->nr_threads; } static inline bool thread_group_leader(struct task_struct *p) { return p->exit_signal >= 0; } static inline bool same_thread_group(struct task_struct *p1, struct task_struct *p2) { return p1->signal == p2->signal; } /* * returns NULL if p is the last thread in the thread group */ static inline struct task_struct *__next_thread(struct task_struct *p) { return list_next_or_null_rcu(&p->signal->thread_head, &p->thread_node, struct task_struct, thread_node); } static inline struct task_struct *next_thread(struct task_struct *p) { return __next_thread(p) ?: p->group_leader; } static inline int thread_group_empty(struct task_struct *p) { return thread_group_leader(p) && list_is_last(&p->thread_node, &p->signal->thread_head); } #define delay_group_leader(p) \ (thread_group_leader(p) && !thread_group_empty(p)) extern struct sighand_struct *__lock_task_sighand(struct task_struct *task, unsigned long *flags); static inline struct sighand_struct *lock_task_sighand(struct task_struct *task, unsigned long *flags) { struct sighand_struct *ret; ret = __lock_task_sighand(task, flags); (void)__cond_lock(&task->sighand->siglock, ret); return ret; } static inline void unlock_task_sighand(struct task_struct *task, unsigned long *flags) { spin_unlock_irqrestore(&task->sighand->siglock, *flags); } #ifdef CONFIG_LOCKDEP extern void lockdep_assert_task_sighand_held(struct task_struct *task); #else static inline void lockdep_assert_task_sighand_held(struct task_struct *task) { } #endif static inline unsigned long task_rlimit(const struct task_struct *task, unsigned int limit) { return READ_ONCE(task->signal->rlim[limit].rlim_cur); } static inline unsigned long task_rlimit_max(const struct task_struct *task, unsigned int limit) { return READ_ONCE(task->signal->rlim[limit].rlim_max); } static inline unsigned long rlimit(unsigned int limit) { return task_rlimit(current, limit); } static inline unsigned long rlimit_max(unsigned int limit) { return task_rlimit_max(current, limit); } #endif /* _LINUX_SCHED_SIGNAL_H */ |
| 23 506 54 473 517 141 499 514 512 511 21 39 607 609 606 608 607 610 444 486 189 211 508 470 483 490 510 514 511 479 511 1 437 536 537 513 481 481 468 466 23 23 23 1 1 1 1 221 222 203 196 221 198 200 817 445 811 812 5 5 226 225 201 203 223 5 222 226 796 225 792 803 16 15 57 56 57 56 433 438 178 180 180 179 434 435 432 438 610 593 608 639 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * kobject.c - library routines for handling generic kernel objects * * Copyright (c) 2002-2003 Patrick Mochel <mochel@osdl.org> * Copyright (c) 2006-2007 Greg Kroah-Hartman <greg@kroah.com> * Copyright (c) 2006-2007 Novell Inc. * * Please see the file Documentation/core-api/kobject.rst for critical information * about using the kobject interface. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kobject.h> #include <linux/string.h> #include <linux/export.h> #include <linux/stat.h> #include <linux/slab.h> #include <linux/random.h> /** * kobject_namespace() - Return @kobj's namespace tag. * @kobj: kobject in question * * Returns namespace tag of @kobj if its parent has namespace ops enabled * and thus @kobj should have a namespace tag associated with it. Returns * %NULL otherwise. */ const void *kobject_namespace(const struct kobject *kobj) { const struct kobj_ns_type_operations *ns_ops = kobj_ns_ops(kobj); if (!ns_ops || ns_ops->type == KOBJ_NS_TYPE_NONE) return NULL; return kobj->ktype->namespace(kobj); } /** * kobject_get_ownership() - Get sysfs ownership data for @kobj. * @kobj: kobject in question * @uid: kernel user ID for sysfs objects * @gid: kernel group ID for sysfs objects * * Returns initial uid/gid pair that should be used when creating sysfs * representation of given kobject. Normally used to adjust ownership of * objects in a container. */ void kobject_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid) { *uid = GLOBAL_ROOT_UID; *gid = GLOBAL_ROOT_GID; if (kobj->ktype->get_ownership) kobj->ktype->get_ownership(kobj, uid, gid); } static bool kobj_ns_type_is_valid(enum kobj_ns_type type) { if ((type <= KOBJ_NS_TYPE_NONE) || (type >= KOBJ_NS_TYPES)) return false; return true; } static int create_dir(struct kobject *kobj) { const struct kobj_type *ktype = get_ktype(kobj); const struct kobj_ns_type_operations *ops; int error; error = sysfs_create_dir_ns(kobj, kobject_namespace(kobj)); if (error) return error; if (ktype) { error = sysfs_create_groups(kobj, ktype->default_groups); if (error) { sysfs_remove_dir(kobj); return error; } } /* * @kobj->sd may be deleted by an ancestor going away. Hold an * extra reference so that it stays until @kobj is gone. */ sysfs_get(kobj->sd); /* * If @kobj has ns_ops, its children need to be filtered based on * their namespace tags. Enable namespace support on @kobj->sd. */ ops = kobj_child_ns_ops(kobj); if (ops) { BUG_ON(!kobj_ns_type_is_valid(ops->type)); BUG_ON(!kobj_ns_type_registered(ops->type)); sysfs_enable_ns(kobj->sd); } return 0; } static int get_kobj_path_length(const struct kobject *kobj) { int length = 1; const struct kobject *parent = kobj; /* walk up the ancestors until we hit the one pointing to the * root. * Add 1 to strlen for leading '/' of each level. */ do { if (kobject_name(parent) == NULL) return 0; length += strlen(kobject_name(parent)) + 1; parent = parent->parent; } while (parent); return length; } static int fill_kobj_path(const struct kobject *kobj, char *path, int length) { const struct kobject *parent; --length; for (parent = kobj; parent; parent = parent->parent) { int cur = strlen(kobject_name(parent)); /* back up enough to print this name with '/' */ length -= cur; if (length <= 0) return -EINVAL; memcpy(path + length, kobject_name(parent), cur); *(path + --length) = '/'; } pr_debug("'%s' (%p): %s: path = '%s'\n", kobject_name(kobj), kobj, __func__, path); return 0; } /** * kobject_get_path() - Allocate memory and fill in the path for @kobj. * @kobj: kobject in question, with which to build the path * @gfp_mask: the allocation type used to allocate the path * * Return: The newly allocated memory, caller must free with kfree(). */ char *kobject_get_path(const struct kobject *kobj, gfp_t gfp_mask) { char *path; int len; retry: len = get_kobj_path_length(kobj); if (len == 0) return NULL; path = kzalloc(len, gfp_mask); if (!path) return NULL; if (fill_kobj_path(kobj, path, len)) { kfree(path); goto retry; } return path; } EXPORT_SYMBOL_GPL(kobject_get_path); /* add the kobject to its kset's list */ static void kobj_kset_join(struct kobject *kobj) { if (!kobj->kset) return; kset_get(kobj->kset); spin_lock(&kobj->kset->list_lock); list_add_tail(&kobj->entry, &kobj->kset->list); spin_unlock(&kobj->kset->list_lock); } /* remove the kobject from its kset's list */ static void kobj_kset_leave(struct kobject *kobj) { if (!kobj->kset) return; spin_lock(&kobj->kset->list_lock); list_del_init(&kobj->entry); spin_unlock(&kobj->kset->list_lock); kset_put(kobj->kset); } static void kobject_init_internal(struct kobject *kobj) { if (!kobj) return; kref_init(&kobj->kref); INIT_LIST_HEAD(&kobj->entry); kobj->state_in_sysfs = 0; kobj->state_add_uevent_sent = 0; kobj->state_remove_uevent_sent = 0; kobj->state_initialized = 1; } static int kobject_add_internal(struct kobject *kobj) { int error = 0; struct kobject *parent; if (!kobj) return -ENOENT; if (!kobj->name || !kobj->name[0]) { WARN(1, "kobject: (%p): attempted to be registered with empty name!\n", kobj); return -EINVAL; } parent = kobject_get(kobj->parent); /* join kset if set, use it as parent if we do not already have one */ if (kobj->kset) { if (!parent) parent = kobject_get(&kobj->kset->kobj); kobj_kset_join(kobj); kobj->parent = parent; } pr_debug("'%s' (%p): %s: parent: '%s', set: '%s'\n", kobject_name(kobj), kobj, __func__, parent ? kobject_name(parent) : "<NULL>", kobj->kset ? kobject_name(&kobj->kset->kobj) : "<NULL>"); error = create_dir(kobj); if (error) { kobj_kset_leave(kobj); kobject_put(parent); kobj->parent = NULL; /* be noisy on error issues */ if (error == -EEXIST) pr_err("%s failed for %s with -EEXIST, don't try to register things with the same name in the same directory.\n", __func__, kobject_name(kobj)); else pr_err("%s failed for %s (error: %d parent: %s)\n", __func__, kobject_name(kobj), error, parent ? kobject_name(parent) : "'none'"); } else kobj->state_in_sysfs = 1; return error; } /** * kobject_set_name_vargs() - Set the name of a kobject. * @kobj: struct kobject to set the name of * @fmt: format string used to build the name * @vargs: vargs to format the string. */ int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, va_list vargs) { const char *s; if (kobj->name && !fmt) return 0; s = kvasprintf_const(GFP_KERNEL, fmt, vargs); if (!s) return -ENOMEM; /* * ewww... some of these buggers have '/' in the name ... If * that's the case, we need to make sure we have an actual * allocated copy to modify, since kvasprintf_const may have * returned something from .rodata. */ if (strchr(s, '/')) { char *t; t = kstrdup(s, GFP_KERNEL); kfree_const(s); if (!t) return -ENOMEM; s = strreplace(t, '/', '!'); } kfree_const(kobj->name); kobj->name = s; return 0; } /** * kobject_set_name() - Set the name of a kobject. * @kobj: struct kobject to set the name of * @fmt: format string used to build the name * * This sets the name of the kobject. If you have already added the * kobject to the system, you must call kobject_rename() in order to * change the name of the kobject. */ int kobject_set_name(struct kobject *kobj, const char *fmt, ...) { va_list vargs; int retval; va_start(vargs, fmt); retval = kobject_set_name_vargs(kobj, fmt, vargs); va_end(vargs); return retval; } EXPORT_SYMBOL(kobject_set_name); /** * kobject_init() - Initialize a kobject structure. * @kobj: pointer to the kobject to initialize * @ktype: pointer to the ktype for this kobject. * * This function will properly initialize a kobject such that it can then * be passed to the kobject_add() call. * * After this function is called, the kobject MUST be cleaned up by a call * to kobject_put(), not by a call to kfree directly to ensure that all of * the memory is cleaned up properly. */ void kobject_init(struct kobject *kobj, const struct kobj_type *ktype) { char *err_str; if (!kobj) { err_str = "invalid kobject pointer!"; goto error; } if (!ktype) { err_str = "must have a ktype to be initialized properly!\n"; goto error; } if (kobj->state_initialized) { /* do not error out as sometimes we can recover */ pr_err("kobject (%p): tried to init an initialized object, something is seriously wrong.\n", kobj); dump_stack_lvl(KERN_ERR); } kobject_init_internal(kobj); kobj->ktype = ktype; return; error: pr_err("kobject (%p): %s\n", kobj, err_str); dump_stack_lvl(KERN_ERR); } EXPORT_SYMBOL(kobject_init); static __printf(3, 0) int kobject_add_varg(struct kobject *kobj, struct kobject *parent, const char *fmt, va_list vargs) { int retval; retval = kobject_set_name_vargs(kobj, fmt, vargs); if (retval) { pr_err("can not set name properly!\n"); return retval; } kobj->parent = parent; return kobject_add_internal(kobj); } /** * kobject_add() - The main kobject add function. * @kobj: the kobject to add * @parent: pointer to the parent of the kobject. * @fmt: format to name the kobject with. * * The kobject name is set and added to the kobject hierarchy in this * function. * * If @parent is set, then the parent of the @kobj will be set to it. * If @parent is NULL, then the parent of the @kobj will be set to the * kobject associated with the kset assigned to this kobject. If no kset * is assigned to the kobject, then the kobject will be located in the * root of the sysfs tree. * * Note, no "add" uevent will be created with this call, the caller should set * up all of the necessary sysfs files for the object and then call * kobject_uevent() with the UEVENT_ADD parameter to ensure that * userspace is properly notified of this kobject's creation. * * Return: If this function returns an error, kobject_put() must be * called to properly clean up the memory associated with the * object. Under no instance should the kobject that is passed * to this function be directly freed with a call to kfree(), * that can leak memory. * * If this function returns success, kobject_put() must also be called * in order to properly clean up the memory associated with the object. * * In short, once this function is called, kobject_put() MUST be called * when the use of the object is finished in order to properly free * everything. */ int kobject_add(struct kobject *kobj, struct kobject *parent, const char *fmt, ...) { va_list args; int retval; if (!kobj) return -EINVAL; if (!kobj->state_initialized) { pr_err("kobject '%s' (%p): tried to add an uninitialized object, something is seriously wrong.\n", kobject_name(kobj), kobj); dump_stack_lvl(KERN_ERR); return -EINVAL; } va_start(args, fmt); retval = kobject_add_varg(kobj, parent, fmt, args); va_end(args); return retval; } EXPORT_SYMBOL(kobject_add); /** * kobject_init_and_add() - Initialize a kobject structure and add it to * the kobject hierarchy. * @kobj: pointer to the kobject to initialize * @ktype: pointer to the ktype for this kobject. * @parent: pointer to the parent of this kobject. * @fmt: the name of the kobject. * * This function combines the call to kobject_init() and kobject_add(). * * If this function returns an error, kobject_put() must be called to * properly clean up the memory associated with the object. This is the * same type of error handling after a call to kobject_add() and kobject * lifetime rules are the same here. */ int kobject_init_and_add(struct kobject *kobj, const struct kobj_type *ktype, struct kobject *parent, const char *fmt, ...) { va_list args; int retval; kobject_init(kobj, ktype); va_start(args, fmt); retval = kobject_add_varg(kobj, parent, fmt, args); va_end(args); return retval; } EXPORT_SYMBOL_GPL(kobject_init_and_add); /** * kobject_rename() - Change the name of an object. * @kobj: object in question. * @new_name: object's new name * * It is the responsibility of the caller to provide mutual * exclusion between two different calls of kobject_rename * on the same kobject and to ensure that new_name is valid and * won't conflict with other kobjects. */ int kobject_rename(struct kobject *kobj, const char *new_name) { int error = 0; const char *devpath = NULL; const char *dup_name = NULL, *name; char *devpath_string = NULL; char *envp[2]; kobj = kobject_get(kobj); if (!kobj) return -EINVAL; if (!kobj->parent) { kobject_put(kobj); return -EINVAL; } devpath = kobject_get_path(kobj, GFP_KERNEL); if (!devpath) { error = -ENOMEM; goto out; } devpath_string = kmalloc(strlen(devpath) + 15, GFP_KERNEL); if (!devpath_string) { error = -ENOMEM; goto out; } sprintf(devpath_string, "DEVPATH_OLD=%s", devpath); envp[0] = devpath_string; envp[1] = NULL; name = dup_name = kstrdup_const(new_name, GFP_KERNEL); if (!name) { error = -ENOMEM; goto out; } error = sysfs_rename_dir_ns(kobj, new_name, kobject_namespace(kobj)); if (error) goto out; /* Install the new kobject name */ dup_name = kobj->name; kobj->name = name; /* This function is mostly/only used for network interface. * Some hotplug package track interfaces by their name and * therefore want to know when the name is changed by the user. */ kobject_uevent_env(kobj, KOBJ_MOVE, envp); out: kfree_const(dup_name); kfree(devpath_string); kfree(devpath); kobject_put(kobj); return error; } EXPORT_SYMBOL_GPL(kobject_rename); /** * kobject_move() - Move object to another parent. * @kobj: object in question. * @new_parent: object's new parent (can be NULL) */ int kobject_move(struct kobject *kobj, struct kobject *new_parent) { int error; struct kobject *old_parent; const char *devpath = NULL; char *devpath_string = NULL; char *envp[2]; kobj = kobject_get(kobj); if (!kobj) return -EINVAL; new_parent = kobject_get(new_parent); if (!new_parent) { if (kobj->kset) new_parent = kobject_get(&kobj->kset->kobj); } /* old object path */ devpath = kobject_get_path(kobj, GFP_KERNEL); if (!devpath) { error = -ENOMEM; goto out; } devpath_string = kmalloc(strlen(devpath) + 15, GFP_KERNEL); if (!devpath_string) { error = -ENOMEM; goto out; } sprintf(devpath_string, "DEVPATH_OLD=%s", devpath); envp[0] = devpath_string; envp[1] = NULL; error = sysfs_move_dir_ns(kobj, new_parent, kobject_namespace(kobj)); if (error) goto out; old_parent = kobj->parent; kobj->parent = new_parent; new_parent = NULL; kobject_put(old_parent); kobject_uevent_env(kobj, KOBJ_MOVE, envp); out: kobject_put(new_parent); kobject_put(kobj); kfree(devpath_string); kfree(devpath); return error; } EXPORT_SYMBOL_GPL(kobject_move); static void __kobject_del(struct kobject *kobj) { struct kernfs_node *sd; const struct kobj_type *ktype; sd = kobj->sd; ktype = get_ktype(kobj); if (ktype) sysfs_remove_groups(kobj, ktype->default_groups); /* send "remove" if the caller did not do it but sent "add" */ if (kobj->state_add_uevent_sent && !kobj->state_remove_uevent_sent) { pr_debug("'%s' (%p): auto cleanup 'remove' event\n", kobject_name(kobj), kobj); kobject_uevent(kobj, KOBJ_REMOVE); } sysfs_remove_dir(kobj); sysfs_put(sd); kobj->state_in_sysfs = 0; kobj_kset_leave(kobj); kobj->parent = NULL; } /** * kobject_del() - Unlink kobject from hierarchy. * @kobj: object. * * This is the function that should be called to delete an object * successfully added via kobject_add(). */ void kobject_del(struct kobject *kobj) { struct kobject *parent; if (!kobj) return; parent = kobj->parent; __kobject_del(kobj); kobject_put(parent); } EXPORT_SYMBOL(kobject_del); /** * kobject_get() - Increment refcount for object. * @kobj: object. */ struct kobject *kobject_get(struct kobject *kobj) { if (kobj) { if (!kobj->state_initialized) WARN(1, KERN_WARNING "kobject: '%s' (%p): is not initialized, yet kobject_get() is being called.\n", kobject_name(kobj), kobj); kref_get(&kobj->kref); } return kobj; } EXPORT_SYMBOL(kobject_get); struct kobject * __must_check kobject_get_unless_zero(struct kobject *kobj) { if (!kobj) return NULL; if (!kref_get_unless_zero(&kobj->kref)) kobj = NULL; return kobj; } EXPORT_SYMBOL(kobject_get_unless_zero); /* * kobject_cleanup - free kobject resources. * @kobj: object to cleanup */ static void kobject_cleanup(struct kobject *kobj) { struct kobject *parent = kobj->parent; const struct kobj_type *t = get_ktype(kobj); const char *name = kobj->name; pr_debug("'%s' (%p): %s, parent %p\n", kobject_name(kobj), kobj, __func__, kobj->parent); if (t && !t->release) pr_debug("'%s' (%p): does not have a release() function, it is broken and must be fixed. See Documentation/core-api/kobject.rst.\n", kobject_name(kobj), kobj); /* remove from sysfs if the caller did not do it */ if (kobj->state_in_sysfs) { pr_debug("'%s' (%p): auto cleanup kobject_del\n", kobject_name(kobj), kobj); __kobject_del(kobj); } else { /* avoid dropping the parent reference unnecessarily */ parent = NULL; } if (t && t->release) { pr_debug("'%s' (%p): calling ktype release\n", kobject_name(kobj), kobj); t->release(kobj); } /* free name if we allocated it */ if (name) { pr_debug("'%s': free name\n", name); kfree_const(name); } kobject_put(parent); } #ifdef CONFIG_DEBUG_KOBJECT_RELEASE static void kobject_delayed_cleanup(struct work_struct *work) { kobject_cleanup(container_of(to_delayed_work(work), struct kobject, release)); } #endif static void kobject_release(struct kref *kref) { struct kobject *kobj = container_of(kref, struct kobject, kref); #ifdef CONFIG_DEBUG_KOBJECT_RELEASE unsigned long delay = HZ + HZ * get_random_u32_below(4); pr_info("'%s' (%p): %s, parent %p (delayed %ld)\n", kobject_name(kobj), kobj, __func__, kobj->parent, delay); INIT_DELAYED_WORK(&kobj->release, kobject_delayed_cleanup); schedule_delayed_work(&kobj->release, delay); #else kobject_cleanup(kobj); #endif } /** * kobject_put() - Decrement refcount for object. * @kobj: object. * * Decrement the refcount, and if 0, call kobject_cleanup(). */ void kobject_put(struct kobject *kobj) { if (kobj) { if (!kobj->state_initialized) WARN(1, KERN_WARNING "kobject: '%s' (%p): is not initialized, yet kobject_put() is being called.\n", kobject_name(kobj), kobj); kref_put(&kobj->kref, kobject_release); } } EXPORT_SYMBOL(kobject_put); static void dynamic_kobj_release(struct kobject *kobj) { pr_debug("(%p): %s\n", kobj, __func__); kfree(kobj); } static const struct kobj_type dynamic_kobj_ktype = { .release = dynamic_kobj_release, .sysfs_ops = &kobj_sysfs_ops, }; /** * kobject_create() - Create a struct kobject dynamically. * * This function creates a kobject structure dynamically and sets it up * to be a "dynamic" kobject with a default release function set up. * * If the kobject was not able to be created, NULL will be returned. * The kobject structure returned from here must be cleaned up with a * call to kobject_put() and not kfree(), as kobject_init() has * already been called on this structure. */ static struct kobject *kobject_create(void) { struct kobject *kobj; kobj = kzalloc(sizeof(*kobj), GFP_KERNEL); if (!kobj) return NULL; kobject_init(kobj, &dynamic_kobj_ktype); return kobj; } /** * kobject_create_and_add() - Create a struct kobject dynamically and * register it with sysfs. * @name: the name for the kobject * @parent: the parent kobject of this kobject, if any. * * This function creates a kobject structure dynamically and registers it * with sysfs. When you are finished with this structure, call * kobject_put() and the structure will be dynamically freed when * it is no longer being used. * * If the kobject was not able to be created, NULL will be returned. */ struct kobject *kobject_create_and_add(const char *name, struct kobject *parent) { struct kobject *kobj; int retval; kobj = kobject_create(); if (!kobj) return NULL; retval = kobject_add(kobj, parent, "%s", name); if (retval) { pr_warn("%s: kobject_add error: %d\n", __func__, retval); kobject_put(kobj); kobj = NULL; } return kobj; } EXPORT_SYMBOL_GPL(kobject_create_and_add); /** * kset_init() - Initialize a kset for use. * @k: kset */ void kset_init(struct kset *k) { kobject_init_internal(&k->kobj); INIT_LIST_HEAD(&k->list); spin_lock_init(&k->list_lock); } /* default kobject attribute operations */ static ssize_t kobj_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { struct kobj_attribute *kattr; ssize_t ret = -EIO; kattr = container_of(attr, struct kobj_attribute, attr); if (kattr->show) ret = kattr->show(kobj, kattr, buf); return ret; } static ssize_t kobj_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { struct kobj_attribute *kattr; ssize_t ret = -EIO; kattr = container_of(attr, struct kobj_attribute, attr); if (kattr->store) ret = kattr->store(kobj, kattr, buf, count); return ret; } const struct sysfs_ops kobj_sysfs_ops = { .show = kobj_attr_show, .store = kobj_attr_store, }; EXPORT_SYMBOL_GPL(kobj_sysfs_ops); /** * kset_register() - Initialize and add a kset. * @k: kset. * * NOTE: On error, the kset.kobj.name allocated by() kobj_set_name() * is freed, it can not be used any more. */ int kset_register(struct kset *k) { int err; if (!k) return -EINVAL; if (!k->kobj.ktype) { pr_err("must have a ktype to be initialized properly!\n"); return -EINVAL; } kset_init(k); err = kobject_add_internal(&k->kobj); if (err) { kfree_const(k->kobj.name); /* Set it to NULL to avoid accessing bad pointer in callers. */ k->kobj.name = NULL; return err; } kobject_uevent(&k->kobj, KOBJ_ADD); return 0; } EXPORT_SYMBOL(kset_register); /** * kset_unregister() - Remove a kset. * @k: kset. */ void kset_unregister(struct kset *k) { if (!k) return; kobject_del(&k->kobj); kobject_put(&k->kobj); } EXPORT_SYMBOL(kset_unregister); /** * kset_find_obj() - Search for object in kset. * @kset: kset we're looking in. * @name: object's name. * * Lock kset via @kset->subsys, and iterate over @kset->list, * looking for a matching kobject. If matching object is found * take a reference and return the object. */ struct kobject *kset_find_obj(struct kset *kset, const char *name) { struct kobject *k; struct kobject *ret = NULL; spin_lock(&kset->list_lock); list_for_each_entry(k, &kset->list, entry) { if (kobject_name(k) && !strcmp(kobject_name(k), name)) { ret = kobject_get_unless_zero(k); break; } } spin_unlock(&kset->list_lock); return ret; } EXPORT_SYMBOL_GPL(kset_find_obj); static void kset_release(struct kobject *kobj) { struct kset *kset = container_of(kobj, struct kset, kobj); pr_debug("'%s' (%p): %s\n", kobject_name(kobj), kobj, __func__); kfree(kset); } static void kset_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid) { if (kobj->parent) kobject_get_ownership(kobj->parent, uid, gid); } static const struct kobj_type kset_ktype = { .sysfs_ops = &kobj_sysfs_ops, .release = kset_release, .get_ownership = kset_get_ownership, }; /** * kset_create() - Create a struct kset dynamically. * * @name: the name for the kset * @uevent_ops: a struct kset_uevent_ops for the kset * @parent_kobj: the parent kobject of this kset, if any. * * This function creates a kset structure dynamically. This structure can * then be registered with the system and show up in sysfs with a call to * kset_register(). When you are finished with this structure, if * kset_register() has been called, call kset_unregister() and the * structure will be dynamically freed when it is no longer being used. * * If the kset was not able to be created, NULL will be returned. */ static struct kset *kset_create(const char *name, const struct kset_uevent_ops *uevent_ops, struct kobject *parent_kobj) { struct kset *kset; int retval; kset = kzalloc(sizeof(*kset), GFP_KERNEL); if (!kset) return NULL; retval = kobject_set_name(&kset->kobj, "%s", name); if (retval) { kfree(kset); return NULL; } kset->uevent_ops = uevent_ops; kset->kobj.parent = parent_kobj; /* * The kobject of this kset will have a type of kset_ktype and belong to * no kset itself. That way we can properly free it when it is * finished being used. */ kset->kobj.ktype = &kset_ktype; kset->kobj.kset = NULL; return kset; } /** * kset_create_and_add() - Create a struct kset dynamically and add it to sysfs. * * @name: the name for the kset * @uevent_ops: a struct kset_uevent_ops for the kset * @parent_kobj: the parent kobject of this kset, if any. * * This function creates a kset structure dynamically and registers it * with sysfs. When you are finished with this structure, call * kset_unregister() and the structure will be dynamically freed when it * is no longer being used. * * If the kset was not able to be created, NULL will be returned. */ struct kset *kset_create_and_add(const char *name, const struct kset_uevent_ops *uevent_ops, struct kobject *parent_kobj) { struct kset *kset; int error; kset = kset_create(name, uevent_ops, parent_kobj); if (!kset) return NULL; error = kset_register(kset); if (error) { kfree(kset); return NULL; } return kset; } EXPORT_SYMBOL_GPL(kset_create_and_add); static DEFINE_SPINLOCK(kobj_ns_type_lock); static const struct kobj_ns_type_operations *kobj_ns_ops_tbl[KOBJ_NS_TYPES]; int kobj_ns_type_register(const struct kobj_ns_type_operations *ops) { enum kobj_ns_type type = ops->type; int error; spin_lock(&kobj_ns_type_lock); error = -EINVAL; if (!kobj_ns_type_is_valid(type)) goto out; error = -EBUSY; if (kobj_ns_ops_tbl[type]) goto out; error = 0; kobj_ns_ops_tbl[type] = ops; out: spin_unlock(&kobj_ns_type_lock); return error; } int kobj_ns_type_registered(enum kobj_ns_type type) { int registered = 0; spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type)) registered = kobj_ns_ops_tbl[type] != NULL; spin_unlock(&kobj_ns_type_lock); return registered; } const struct kobj_ns_type_operations *kobj_child_ns_ops(const struct kobject *parent) { const struct kobj_ns_type_operations *ops = NULL; if (parent && parent->ktype && parent->ktype->child_ns_type) ops = parent->ktype->child_ns_type(parent); return ops; } const struct kobj_ns_type_operations *kobj_ns_ops(const struct kobject *kobj) { return kobj_child_ns_ops(kobj->parent); } bool kobj_ns_current_may_mount(enum kobj_ns_type type) { bool may_mount = true; spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type]) may_mount = kobj_ns_ops_tbl[type]->current_may_mount(); spin_unlock(&kobj_ns_type_lock); return may_mount; } void *kobj_ns_grab_current(enum kobj_ns_type type) { void *ns = NULL; spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type]) ns = kobj_ns_ops_tbl[type]->grab_current_ns(); spin_unlock(&kobj_ns_type_lock); return ns; } EXPORT_SYMBOL_GPL(kobj_ns_grab_current); const void *kobj_ns_netlink(enum kobj_ns_type type, struct sock *sk) { const void *ns = NULL; spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type]) ns = kobj_ns_ops_tbl[type]->netlink_ns(sk); spin_unlock(&kobj_ns_type_lock); return ns; } const void *kobj_ns_initial(enum kobj_ns_type type) { const void *ns = NULL; spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type]) ns = kobj_ns_ops_tbl[type]->initial_ns(); spin_unlock(&kobj_ns_type_lock); return ns; } void kobj_ns_drop(enum kobj_ns_type type, void *ns) { spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type] && kobj_ns_ops_tbl[type]->drop_ns) kobj_ns_ops_tbl[type]->drop_ns(ns); spin_unlock(&kobj_ns_type_lock); } EXPORT_SYMBOL_GPL(kobj_ns_drop); |
| 128 3 3 3 13 13 13 21 1 1 1 17 1 1 1 1 1 1 2 1 1 9 4 13 1 13 1 5 5 4 1 5 5 5 880 882 883 182 124 1 9 9 13 13 13 4 9 13 13 13 13 2 7 2 2 2 7 2 2 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/act_mirred.c packet mirroring and redirect actions * * Authors: Jamal Hadi Salim (2002-4) * * TODO: Add ingress support (and socket redirect support) */ #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/module.h> #include <linux/init.h> #include <linux/gfp.h> #include <linux/if_arp.h> #include <net/net_namespace.h> #include <net/netlink.h> #include <net/dst.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <linux/tc_act/tc_mirred.h> #include <net/tc_act/tc_mirred.h> #include <net/tc_wrapper.h> static LIST_HEAD(mirred_list); static DEFINE_SPINLOCK(mirred_list_lock); #define MIRRED_NEST_LIMIT 4 static DEFINE_PER_CPU(unsigned int, mirred_nest_level); static bool tcf_mirred_is_act_redirect(int action) { return action == TCA_EGRESS_REDIR || action == TCA_INGRESS_REDIR; } static bool tcf_mirred_act_wants_ingress(int action) { switch (action) { case TCA_EGRESS_REDIR: case TCA_EGRESS_MIRROR: return false; case TCA_INGRESS_REDIR: case TCA_INGRESS_MIRROR: return true; default: BUG(); } } static bool tcf_mirred_can_reinsert(int action) { switch (action) { case TC_ACT_SHOT: case TC_ACT_STOLEN: case TC_ACT_QUEUED: case TC_ACT_TRAP: return true; } return false; } static struct net_device *tcf_mirred_dev_dereference(struct tcf_mirred *m) { return rcu_dereference_protected(m->tcfm_dev, lockdep_is_held(&m->tcf_lock)); } static void tcf_mirred_release(struct tc_action *a) { struct tcf_mirred *m = to_mirred(a); struct net_device *dev; spin_lock(&mirred_list_lock); list_del(&m->tcfm_list); spin_unlock(&mirred_list_lock); /* last reference to action, no need to lock */ dev = rcu_dereference_protected(m->tcfm_dev, 1); netdev_put(dev, &m->tcfm_dev_tracker); } static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = { [TCA_MIRRED_PARMS] = { .len = sizeof(struct tc_mirred) }, [TCA_MIRRED_BLOCKID] = NLA_POLICY_MIN(NLA_U32, 1), }; static struct tc_action_ops act_mirred_ops; static void tcf_mirred_replace_dev(struct tcf_mirred *m, struct net_device *ndev) { struct net_device *odev; odev = rcu_replace_pointer(m->tcfm_dev, ndev, lockdep_is_held(&m->tcf_lock)); netdev_put(odev, &m->tcfm_dev_tracker); } static int tcf_mirred_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, act_mirred_ops.net_id); bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_MIRRED_MAX + 1]; struct tcf_chain *goto_ch = NULL; bool mac_header_xmit = false; struct tc_mirred *parm; struct tcf_mirred *m; bool exists = false; int ret, err; u32 index; if (!nla) { NL_SET_ERR_MSG_MOD(extack, "Mirred requires attributes to be passed"); return -EINVAL; } ret = nla_parse_nested_deprecated(tb, TCA_MIRRED_MAX, nla, mirred_policy, extack); if (ret < 0) return ret; if (!tb[TCA_MIRRED_PARMS]) { NL_SET_ERR_MSG_MOD(extack, "Missing required mirred parameters"); return -EINVAL; } parm = nla_data(tb[TCA_MIRRED_PARMS]); index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; if (exists && bind) return ACT_P_BOUND; if (tb[TCA_MIRRED_BLOCKID] && parm->ifindex) { NL_SET_ERR_MSG_MOD(extack, "Cannot specify Block ID and dev simultaneously"); if (exists) tcf_idr_release(*a, bind); else tcf_idr_cleanup(tn, index); return -EINVAL; } switch (parm->eaction) { case TCA_EGRESS_MIRROR: case TCA_EGRESS_REDIR: case TCA_INGRESS_REDIR: case TCA_INGRESS_MIRROR: break; default: if (exists) tcf_idr_release(*a, bind); else tcf_idr_cleanup(tn, index); NL_SET_ERR_MSG_MOD(extack, "Unknown mirred option"); return -EINVAL; } if (!exists) { if (!parm->ifindex && !tb[TCA_MIRRED_BLOCKID]) { tcf_idr_cleanup(tn, index); NL_SET_ERR_MSG_MOD(extack, "Must specify device or block"); return -EINVAL; } ret = tcf_idr_create_from_flags(tn, index, est, a, &act_mirred_ops, bind, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } m = to_mirred(*a); if (ret == ACT_P_CREATED) INIT_LIST_HEAD(&m->tcfm_list); err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; spin_lock_bh(&m->tcf_lock); if (parm->ifindex) { struct net_device *ndev; ndev = dev_get_by_index(net, parm->ifindex); if (!ndev) { spin_unlock_bh(&m->tcf_lock); err = -ENODEV; goto put_chain; } mac_header_xmit = dev_is_mac_header_xmit(ndev); tcf_mirred_replace_dev(m, ndev); netdev_tracker_alloc(ndev, &m->tcfm_dev_tracker, GFP_ATOMIC); m->tcfm_mac_header_xmit = mac_header_xmit; m->tcfm_blockid = 0; } else if (tb[TCA_MIRRED_BLOCKID]) { tcf_mirred_replace_dev(m, NULL); m->tcfm_mac_header_xmit = false; m->tcfm_blockid = nla_get_u32(tb[TCA_MIRRED_BLOCKID]); } goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); m->tcfm_eaction = parm->eaction; spin_unlock_bh(&m->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); if (ret == ACT_P_CREATED) { spin_lock(&mirred_list_lock); list_add(&m->tcfm_list, &mirred_list); spin_unlock(&mirred_list_lock); } return ret; put_chain: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: tcf_idr_release(*a, bind); return err; } static int tcf_mirred_forward(bool at_ingress, bool want_ingress, struct sk_buff *skb) { int err; if (!want_ingress) err = tcf_dev_queue_xmit(skb, dev_queue_xmit); else if (!at_ingress) err = netif_rx(skb); else err = netif_receive_skb(skb); return err; } static int tcf_mirred_to_dev(struct sk_buff *skb, struct tcf_mirred *m, struct net_device *dev, const bool m_mac_header_xmit, int m_eaction, int retval) { struct sk_buff *skb_to_send = skb; bool want_ingress; bool is_redirect; bool expects_nh; bool at_ingress; bool dont_clone; int mac_len; bool at_nh; int err; is_redirect = tcf_mirred_is_act_redirect(m_eaction); if (unlikely(!(dev->flags & IFF_UP)) || !netif_carrier_ok(dev)) { net_notice_ratelimited("tc mirred to Houston: device %s is down\n", dev->name); goto err_cant_do; } /* we could easily avoid the clone only if called by ingress and clsact; * since we can't easily detect the clsact caller, skip clone only for * ingress - that covers the TC S/W datapath. */ at_ingress = skb_at_tc_ingress(skb); dont_clone = skb_at_tc_ingress(skb) && is_redirect && tcf_mirred_can_reinsert(retval); if (!dont_clone) { skb_to_send = skb_clone(skb, GFP_ATOMIC); if (!skb_to_send) goto err_cant_do; } want_ingress = tcf_mirred_act_wants_ingress(m_eaction); /* All mirred/redirected skbs should clear previous ct info */ nf_reset_ct(skb_to_send); if (want_ingress && !at_ingress) /* drop dst for egress -> ingress */ skb_dst_drop(skb_to_send); expects_nh = want_ingress || !m_mac_header_xmit; at_nh = skb->data == skb_network_header(skb); if (at_nh != expects_nh) { mac_len = at_ingress ? skb->mac_len : skb_network_offset(skb); if (expects_nh) { /* target device/action expect data at nh */ skb_pull_rcsum(skb_to_send, mac_len); } else { /* target device/action expect data at mac */ skb_push_rcsum(skb_to_send, mac_len); } } skb_to_send->skb_iif = skb->dev->ifindex; skb_to_send->dev = dev; if (is_redirect) { if (skb == skb_to_send) retval = TC_ACT_CONSUMED; skb_set_redirected(skb_to_send, skb_to_send->tc_at_ingress); err = tcf_mirred_forward(at_ingress, want_ingress, skb_to_send); } else { err = tcf_mirred_forward(at_ingress, want_ingress, skb_to_send); } if (err) tcf_action_inc_overlimit_qstats(&m->common); return retval; err_cant_do: if (is_redirect) retval = TC_ACT_SHOT; tcf_action_inc_overlimit_qstats(&m->common); return retval; } static int tcf_blockcast_redir(struct sk_buff *skb, struct tcf_mirred *m, struct tcf_block *block, int m_eaction, const u32 exception_ifindex, int retval) { struct net_device *dev_prev = NULL; struct net_device *dev = NULL; unsigned long index; int mirred_eaction; mirred_eaction = tcf_mirred_act_wants_ingress(m_eaction) ? TCA_INGRESS_MIRROR : TCA_EGRESS_MIRROR; xa_for_each(&block->ports, index, dev) { if (index == exception_ifindex) continue; if (!dev_prev) goto assign_prev; tcf_mirred_to_dev(skb, m, dev_prev, dev_is_mac_header_xmit(dev), mirred_eaction, retval); assign_prev: dev_prev = dev; } if (dev_prev) return tcf_mirred_to_dev(skb, m, dev_prev, dev_is_mac_header_xmit(dev_prev), m_eaction, retval); return retval; } static int tcf_blockcast_mirror(struct sk_buff *skb, struct tcf_mirred *m, struct tcf_block *block, int m_eaction, const u32 exception_ifindex, int retval) { struct net_device *dev = NULL; unsigned long index; xa_for_each(&block->ports, index, dev) { if (index == exception_ifindex) continue; tcf_mirred_to_dev(skb, m, dev, dev_is_mac_header_xmit(dev), m_eaction, retval); } return retval; } static int tcf_blockcast(struct sk_buff *skb, struct tcf_mirred *m, const u32 blockid, struct tcf_result *res, int retval) { const u32 exception_ifindex = skb->dev->ifindex; struct tcf_block *block; bool is_redirect; int m_eaction; m_eaction = READ_ONCE(m->tcfm_eaction); is_redirect = tcf_mirred_is_act_redirect(m_eaction); /* we are already under rcu protection, so can call block lookup * directly. */ block = tcf_block_lookup(dev_net(skb->dev), blockid); if (!block || xa_empty(&block->ports)) { tcf_action_inc_overlimit_qstats(&m->common); return retval; } if (is_redirect) return tcf_blockcast_redir(skb, m, block, m_eaction, exception_ifindex, retval); /* If it's not redirect, it is mirror */ return tcf_blockcast_mirror(skb, m, block, m_eaction, exception_ifindex, retval); } TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_mirred *m = to_mirred(a); int retval = READ_ONCE(m->tcf_action); unsigned int nest_level; bool m_mac_header_xmit; struct net_device *dev; int m_eaction; u32 blockid; nest_level = __this_cpu_inc_return(mirred_nest_level); if (unlikely(nest_level > MIRRED_NEST_LIMIT)) { net_warn_ratelimited("Packet exceeded mirred recursion limit on dev %s\n", netdev_name(skb->dev)); retval = TC_ACT_SHOT; goto dec_nest_level; } tcf_lastuse_update(&m->tcf_tm); tcf_action_update_bstats(&m->common, skb); blockid = READ_ONCE(m->tcfm_blockid); if (blockid) { retval = tcf_blockcast(skb, m, blockid, res, retval); goto dec_nest_level; } dev = rcu_dereference_bh(m->tcfm_dev); if (unlikely(!dev)) { pr_notice_once("tc mirred: target device is gone\n"); tcf_action_inc_overlimit_qstats(&m->common); goto dec_nest_level; } m_mac_header_xmit = READ_ONCE(m->tcfm_mac_header_xmit); m_eaction = READ_ONCE(m->tcfm_eaction); retval = tcf_mirred_to_dev(skb, m, dev, m_mac_header_xmit, m_eaction, retval); dec_nest_level: __this_cpu_dec(mirred_nest_level); return retval; } static void tcf_stats_update(struct tc_action *a, u64 bytes, u64 packets, u64 drops, u64 lastuse, bool hw) { struct tcf_mirred *m = to_mirred(a); struct tcf_t *tm = &m->tcf_tm; tcf_action_update_stats(a, bytes, packets, drops, hw); tm->lastuse = max_t(u64, tm->lastuse, lastuse); } static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_mirred *m = to_mirred(a); struct tc_mirred opt = { .index = m->tcf_index, .refcnt = refcount_read(&m->tcf_refcnt) - ref, .bindcnt = atomic_read(&m->tcf_bindcnt) - bind, }; struct net_device *dev; struct tcf_t t; u32 blockid; spin_lock_bh(&m->tcf_lock); opt.action = m->tcf_action; opt.eaction = m->tcfm_eaction; dev = tcf_mirred_dev_dereference(m); if (dev) opt.ifindex = dev->ifindex; if (nla_put(skb, TCA_MIRRED_PARMS, sizeof(opt), &opt)) goto nla_put_failure; blockid = m->tcfm_blockid; if (blockid && nla_put_u32(skb, TCA_MIRRED_BLOCKID, blockid)) goto nla_put_failure; tcf_tm_dump(&t, &m->tcf_tm); if (nla_put_64bit(skb, TCA_MIRRED_TM, sizeof(t), &t, TCA_MIRRED_PAD)) goto nla_put_failure; spin_unlock_bh(&m->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&m->tcf_lock); nlmsg_trim(skb, b); return -1; } static int mirred_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct tcf_mirred *m; ASSERT_RTNL(); if (event == NETDEV_UNREGISTER) { spin_lock(&mirred_list_lock); list_for_each_entry(m, &mirred_list, tcfm_list) { spin_lock_bh(&m->tcf_lock); if (tcf_mirred_dev_dereference(m) == dev) { netdev_put(dev, &m->tcfm_dev_tracker); /* Note : no rcu grace period necessary, as * net_device are already rcu protected. */ RCU_INIT_POINTER(m->tcfm_dev, NULL); } spin_unlock_bh(&m->tcf_lock); } spin_unlock(&mirred_list_lock); } return NOTIFY_DONE; } static struct notifier_block mirred_device_notifier = { .notifier_call = mirred_device_event, }; static void tcf_mirred_dev_put(void *priv) { struct net_device *dev = priv; dev_put(dev); } static struct net_device * tcf_mirred_get_dev(const struct tc_action *a, tc_action_priv_destructor *destructor) { struct tcf_mirred *m = to_mirred(a); struct net_device *dev; rcu_read_lock(); dev = rcu_dereference(m->tcfm_dev); if (dev) { dev_hold(dev); *destructor = tcf_mirred_dev_put; } rcu_read_unlock(); return dev; } static size_t tcf_mirred_get_fill_size(const struct tc_action *act) { return nla_total_size(sizeof(struct tc_mirred)); } static void tcf_offload_mirred_get_dev(struct flow_action_entry *entry, const struct tc_action *act) { entry->dev = act->ops->get_dev(act, &entry->destructor); if (!entry->dev) return; entry->destructor_priv = entry->dev; } static int tcf_mirred_offload_act_setup(struct tc_action *act, void *entry_data, u32 *index_inc, bool bind, struct netlink_ext_ack *extack) { if (bind) { struct flow_action_entry *entry = entry_data; if (is_tcf_mirred_egress_redirect(act)) { entry->id = FLOW_ACTION_REDIRECT; tcf_offload_mirred_get_dev(entry, act); } else if (is_tcf_mirred_egress_mirror(act)) { entry->id = FLOW_ACTION_MIRRED; tcf_offload_mirred_get_dev(entry, act); } else if (is_tcf_mirred_ingress_redirect(act)) { entry->id = FLOW_ACTION_REDIRECT_INGRESS; tcf_offload_mirred_get_dev(entry, act); } else if (is_tcf_mirred_ingress_mirror(act)) { entry->id = FLOW_ACTION_MIRRED_INGRESS; tcf_offload_mirred_get_dev(entry, act); } else { NL_SET_ERR_MSG_MOD(extack, "Unsupported mirred offload"); return -EOPNOTSUPP; } *index_inc = 1; } else { struct flow_offload_action *fl_action = entry_data; if (is_tcf_mirred_egress_redirect(act)) fl_action->id = FLOW_ACTION_REDIRECT; else if (is_tcf_mirred_egress_mirror(act)) fl_action->id = FLOW_ACTION_MIRRED; else if (is_tcf_mirred_ingress_redirect(act)) fl_action->id = FLOW_ACTION_REDIRECT_INGRESS; else if (is_tcf_mirred_ingress_mirror(act)) fl_action->id = FLOW_ACTION_MIRRED_INGRESS; else return -EOPNOTSUPP; } return 0; } static struct tc_action_ops act_mirred_ops = { .kind = "mirred", .id = TCA_ID_MIRRED, .owner = THIS_MODULE, .act = tcf_mirred_act, .stats_update = tcf_stats_update, .dump = tcf_mirred_dump, .cleanup = tcf_mirred_release, .init = tcf_mirred_init, .get_fill_size = tcf_mirred_get_fill_size, .offload_act_setup = tcf_mirred_offload_act_setup, .size = sizeof(struct tcf_mirred), .get_dev = tcf_mirred_get_dev, }; MODULE_ALIAS_NET_ACT("mirred"); static __net_init int mirred_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, act_mirred_ops.net_id); return tc_action_net_init(net, tn, &act_mirred_ops); } static void __net_exit mirred_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_mirred_ops.net_id); } static struct pernet_operations mirred_net_ops = { .init = mirred_init_net, .exit_batch = mirred_exit_net, .id = &act_mirred_ops.net_id, .size = sizeof(struct tc_action_net), }; MODULE_AUTHOR("Jamal Hadi Salim(2002)"); MODULE_DESCRIPTION("Device Mirror/redirect actions"); MODULE_LICENSE("GPL"); static int __init mirred_init_module(void) { int err = register_netdevice_notifier(&mirred_device_notifier); if (err) return err; pr_info("Mirror/redirect action on\n"); err = tcf_register_action(&act_mirred_ops, &mirred_net_ops); if (err) unregister_netdevice_notifier(&mirred_device_notifier); return err; } static void __exit mirred_cleanup_module(void) { tcf_unregister_action(&act_mirred_ops, &mirred_net_ops); unregister_netdevice_notifier(&mirred_device_notifier); } module_init(mirred_init_module); module_exit(mirred_cleanup_module); |
| 10 4 2 366 365 363 364 367 367 364 31 31 12 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RMAP_H #define _LINUX_RMAP_H /* * Declarations for Reverse Mapping functions in mm/rmap.c */ #include <linux/list.h> #include <linux/slab.h> #include <linux/mm.h> #include <linux/rwsem.h> #include <linux/memcontrol.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/memremap.h> /* * The anon_vma heads a list of private "related" vmas, to scan if * an anonymous page pointing to this anon_vma needs to be unmapped: * the vmas on the list will be related by forking, or by splitting. * * Since vmas come and go as they are split and merged (particularly * in mprotect), the mapping field of an anonymous page cannot point * directly to a vma: instead it points to an anon_vma, on whose list * the related vmas can be easily linked or unlinked. * * After unlinking the last vma on the list, we must garbage collect * the anon_vma object itself: we're guaranteed no page can be * pointing to this anon_vma once its vma list is empty. */ struct anon_vma { struct anon_vma *root; /* Root of this anon_vma tree */ struct rw_semaphore rwsem; /* W: modification, R: walking the list */ /* * The refcount is taken on an anon_vma when there is no * guarantee that the vma of page tables will exist for * the duration of the operation. A caller that takes * the reference is responsible for clearing up the * anon_vma if they are the last user on release */ atomic_t refcount; /* * Count of child anon_vmas. Equals to the count of all anon_vmas that * have ->parent pointing to this one, including itself. * * This counter is used for making decision about reusing anon_vma * instead of forking new one. See comments in function anon_vma_clone. */ unsigned long num_children; /* Count of VMAs whose ->anon_vma pointer points to this object. */ unsigned long num_active_vmas; struct anon_vma *parent; /* Parent of this anon_vma */ /* * NOTE: the LSB of the rb_root.rb_node is set by * mm_take_all_locks() _after_ taking the above lock. So the * rb_root must only be read/written after taking the above lock * to be sure to see a valid next pointer. The LSB bit itself * is serialized by a system wide lock only visible to * mm_take_all_locks() (mm_all_locks_mutex). */ /* Interval tree of private "related" vmas */ struct rb_root_cached rb_root; }; /* * The copy-on-write semantics of fork mean that an anon_vma * can become associated with multiple processes. Furthermore, * each child process will have its own anon_vma, where new * pages for that process are instantiated. * * This structure allows us to find the anon_vmas associated * with a VMA, or the VMAs associated with an anon_vma. * The "same_vma" list contains the anon_vma_chains linking * all the anon_vmas associated with this VMA. * The "rb" field indexes on an interval tree the anon_vma_chains * which link all the VMAs associated with this anon_vma. */ struct anon_vma_chain { struct vm_area_struct *vma; struct anon_vma *anon_vma; struct list_head same_vma; /* locked by mmap_lock & page_table_lock */ struct rb_node rb; /* locked by anon_vma->rwsem */ unsigned long rb_subtree_last; #ifdef CONFIG_DEBUG_VM_RB unsigned long cached_vma_start, cached_vma_last; #endif }; enum ttu_flags { TTU_SPLIT_HUGE_PMD = 0x4, /* split huge PMD if any */ TTU_IGNORE_MLOCK = 0x8, /* ignore mlock */ TTU_SYNC = 0x10, /* avoid racy checks with PVMW_SYNC */ TTU_HWPOISON = 0x20, /* do convert pte to hwpoison entry */ TTU_BATCH_FLUSH = 0x40, /* Batch TLB flushes where possible * and caller guarantees they will * do a final flush if necessary */ TTU_RMAP_LOCKED = 0x80, /* do not grab rmap lock: * caller holds it */ }; #ifdef CONFIG_MMU static inline void get_anon_vma(struct anon_vma *anon_vma) { atomic_inc(&anon_vma->refcount); } void __put_anon_vma(struct anon_vma *anon_vma); static inline void put_anon_vma(struct anon_vma *anon_vma) { if (atomic_dec_and_test(&anon_vma->refcount)) __put_anon_vma(anon_vma); } static inline void anon_vma_lock_write(struct anon_vma *anon_vma) { down_write(&anon_vma->root->rwsem); } static inline int anon_vma_trylock_write(struct anon_vma *anon_vma) { return down_write_trylock(&anon_vma->root->rwsem); } static inline void anon_vma_unlock_write(struct anon_vma *anon_vma) { up_write(&anon_vma->root->rwsem); } static inline void anon_vma_lock_read(struct anon_vma *anon_vma) { down_read(&anon_vma->root->rwsem); } static inline int anon_vma_trylock_read(struct anon_vma *anon_vma) { return down_read_trylock(&anon_vma->root->rwsem); } static inline void anon_vma_unlock_read(struct anon_vma *anon_vma) { up_read(&anon_vma->root->rwsem); } /* * anon_vma helper functions. */ void anon_vma_init(void); /* create anon_vma_cachep */ int __anon_vma_prepare(struct vm_area_struct *); void unlink_anon_vmas(struct vm_area_struct *); int anon_vma_clone(struct vm_area_struct *, struct vm_area_struct *); int anon_vma_fork(struct vm_area_struct *, struct vm_area_struct *); static inline int anon_vma_prepare(struct vm_area_struct *vma) { if (likely(vma->anon_vma)) return 0; return __anon_vma_prepare(vma); } static inline void anon_vma_merge(struct vm_area_struct *vma, struct vm_area_struct *next) { VM_BUG_ON_VMA(vma->anon_vma != next->anon_vma, vma); unlink_anon_vmas(next); } struct anon_vma *folio_get_anon_vma(const struct folio *folio); /* RMAP flags, currently only relevant for some anon rmap operations. */ typedef int __bitwise rmap_t; /* * No special request: A mapped anonymous (sub)page is possibly shared between * processes. */ #define RMAP_NONE ((__force rmap_t)0) /* The anonymous (sub)page is exclusive to a single process. */ #define RMAP_EXCLUSIVE ((__force rmap_t)BIT(0)) /* * Internally, we're using an enum to specify the granularity. We make the * compiler emit specialized code for each granularity. */ enum rmap_level { RMAP_LEVEL_PTE = 0, RMAP_LEVEL_PMD, }; static inline void __folio_rmap_sanity_checks(const struct folio *folio, const struct page *page, int nr_pages, enum rmap_level level) { /* hugetlb folios are handled separately. */ VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); /* When (un)mapping zeropages, we should never touch ref+mapcount. */ VM_WARN_ON_FOLIO(is_zero_folio(folio), folio); /* * TODO: we get driver-allocated folios that have nothing to do with * the rmap using vm_insert_page(); therefore, we cannot assume that * folio_test_large_rmappable() holds for large folios. We should * handle any desired mapcount+stats accounting for these folios in * VM_MIXEDMAP VMAs separately, and then sanity-check here that * we really only get rmappable folios. */ VM_WARN_ON_ONCE(nr_pages <= 0); VM_WARN_ON_FOLIO(page_folio(page) != folio, folio); VM_WARN_ON_FOLIO(page_folio(page + nr_pages - 1) != folio, folio); switch (level) { case RMAP_LEVEL_PTE: break; case RMAP_LEVEL_PMD: /* * We don't support folios larger than a single PMD yet. So * when RMAP_LEVEL_PMD is set, we assume that we are creating * a single "entire" mapping of the folio. */ VM_WARN_ON_FOLIO(folio_nr_pages(folio) != HPAGE_PMD_NR, folio); VM_WARN_ON_FOLIO(nr_pages != HPAGE_PMD_NR, folio); break; default: VM_WARN_ON_ONCE(true); } } /* * rmap interfaces called when adding or removing pte of page */ void folio_move_anon_rmap(struct folio *, struct vm_area_struct *); void folio_add_anon_rmap_ptes(struct folio *, struct page *, int nr_pages, struct vm_area_struct *, unsigned long address, rmap_t flags); #define folio_add_anon_rmap_pte(folio, page, vma, address, flags) \ folio_add_anon_rmap_ptes(folio, page, 1, vma, address, flags) void folio_add_anon_rmap_pmd(struct folio *, struct page *, struct vm_area_struct *, unsigned long address, rmap_t flags); void folio_add_new_anon_rmap(struct folio *, struct vm_area_struct *, unsigned long address, rmap_t flags); void folio_add_file_rmap_ptes(struct folio *, struct page *, int nr_pages, struct vm_area_struct *); #define folio_add_file_rmap_pte(folio, page, vma) \ folio_add_file_rmap_ptes(folio, page, 1, vma) void folio_add_file_rmap_pmd(struct folio *, struct page *, struct vm_area_struct *); void folio_remove_rmap_ptes(struct folio *, struct page *, int nr_pages, struct vm_area_struct *); #define folio_remove_rmap_pte(folio, page, vma) \ folio_remove_rmap_ptes(folio, page, 1, vma) void folio_remove_rmap_pmd(struct folio *, struct page *, struct vm_area_struct *); void hugetlb_add_anon_rmap(struct folio *, struct vm_area_struct *, unsigned long address, rmap_t flags); void hugetlb_add_new_anon_rmap(struct folio *, struct vm_area_struct *, unsigned long address); /* See folio_try_dup_anon_rmap_*() */ static inline int hugetlb_try_dup_anon_rmap(struct folio *folio, struct vm_area_struct *vma) { VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); if (PageAnonExclusive(&folio->page)) { if (unlikely(folio_needs_cow_for_dma(vma, folio))) return -EBUSY; ClearPageAnonExclusive(&folio->page); } atomic_inc(&folio->_entire_mapcount); atomic_inc(&folio->_large_mapcount); return 0; } /* See folio_try_share_anon_rmap_*() */ static inline int hugetlb_try_share_anon_rmap(struct folio *folio) { VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); VM_WARN_ON_FOLIO(!PageAnonExclusive(&folio->page), folio); /* Paired with the memory barrier in try_grab_folio(). */ if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_mb(); if (unlikely(folio_maybe_dma_pinned(folio))) return -EBUSY; ClearPageAnonExclusive(&folio->page); /* * This is conceptually a smp_wmb() paired with the smp_rmb() in * gup_must_unshare(). */ if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_mb__after_atomic(); return 0; } static inline void hugetlb_add_file_rmap(struct folio *folio) { VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); VM_WARN_ON_FOLIO(folio_test_anon(folio), folio); atomic_inc(&folio->_entire_mapcount); atomic_inc(&folio->_large_mapcount); } static inline void hugetlb_remove_rmap(struct folio *folio) { VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); atomic_dec(&folio->_entire_mapcount); atomic_dec(&folio->_large_mapcount); } static __always_inline void __folio_dup_file_rmap(struct folio *folio, struct page *page, int nr_pages, enum rmap_level level) { const int orig_nr_pages = nr_pages; __folio_rmap_sanity_checks(folio, page, nr_pages, level); switch (level) { case RMAP_LEVEL_PTE: if (!folio_test_large(folio)) { atomic_inc(&folio->_mapcount); break; } do { atomic_inc(&page->_mapcount); } while (page++, --nr_pages > 0); atomic_add(orig_nr_pages, &folio->_large_mapcount); break; case RMAP_LEVEL_PMD: atomic_inc(&folio->_entire_mapcount); atomic_inc(&folio->_large_mapcount); break; } } /** * folio_dup_file_rmap_ptes - duplicate PTE mappings of a page range of a folio * @folio: The folio to duplicate the mappings of * @page: The first page to duplicate the mappings of * @nr_pages: The number of pages of which the mapping will be duplicated * * The page range of the folio is defined by [page, page + nr_pages) * * The caller needs to hold the page table lock. */ static inline void folio_dup_file_rmap_ptes(struct folio *folio, struct page *page, int nr_pages) { __folio_dup_file_rmap(folio, page, nr_pages, RMAP_LEVEL_PTE); } static __always_inline void folio_dup_file_rmap_pte(struct folio *folio, struct page *page) { __folio_dup_file_rmap(folio, page, 1, RMAP_LEVEL_PTE); } /** * folio_dup_file_rmap_pmd - duplicate a PMD mapping of a page range of a folio * @folio: The folio to duplicate the mapping of * @page: The first page to duplicate the mapping of * * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock. */ static inline void folio_dup_file_rmap_pmd(struct folio *folio, struct page *page) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE __folio_dup_file_rmap(folio, page, HPAGE_PMD_NR, RMAP_LEVEL_PTE); #else WARN_ON_ONCE(true); #endif } static __always_inline int __folio_try_dup_anon_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *src_vma, enum rmap_level level) { const int orig_nr_pages = nr_pages; bool maybe_pinned; int i; VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); __folio_rmap_sanity_checks(folio, page, nr_pages, level); /* * If this folio may have been pinned by the parent process, * don't allow to duplicate the mappings but instead require to e.g., * copy the subpage immediately for the child so that we'll always * guarantee the pinned folio won't be randomly replaced in the * future on write faults. */ maybe_pinned = likely(!folio_is_device_private(folio)) && unlikely(folio_needs_cow_for_dma(src_vma, folio)); /* * No need to check+clear for already shared PTEs/PMDs of the * folio. But if any page is PageAnonExclusive, we must fallback to * copying if the folio maybe pinned. */ switch (level) { case RMAP_LEVEL_PTE: if (unlikely(maybe_pinned)) { for (i = 0; i < nr_pages; i++) if (PageAnonExclusive(page + i)) return -EBUSY; } if (!folio_test_large(folio)) { if (PageAnonExclusive(page)) ClearPageAnonExclusive(page); atomic_inc(&folio->_mapcount); break; } do { if (PageAnonExclusive(page)) ClearPageAnonExclusive(page); atomic_inc(&page->_mapcount); } while (page++, --nr_pages > 0); atomic_add(orig_nr_pages, &folio->_large_mapcount); break; case RMAP_LEVEL_PMD: if (PageAnonExclusive(page)) { if (unlikely(maybe_pinned)) return -EBUSY; ClearPageAnonExclusive(page); } atomic_inc(&folio->_entire_mapcount); atomic_inc(&folio->_large_mapcount); break; } return 0; } /** * folio_try_dup_anon_rmap_ptes - try duplicating PTE mappings of a page range * of a folio * @folio: The folio to duplicate the mappings of * @page: The first page to duplicate the mappings of * @nr_pages: The number of pages of which the mapping will be duplicated * @src_vma: The vm area from which the mappings are duplicated * * The page range of the folio is defined by [page, page + nr_pages) * * The caller needs to hold the page table lock and the * vma->vma_mm->write_protect_seq. * * Duplicating the mappings can only fail if the folio may be pinned; device * private folios cannot get pinned and consequently this function cannot fail * for them. * * If duplicating the mappings succeeded, the duplicated PTEs have to be R/O in * the parent and the child. They must *not* be writable after this call * succeeded. * * Returns 0 if duplicating the mappings succeeded. Returns -EBUSY otherwise. */ static inline int folio_try_dup_anon_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *src_vma) { return __folio_try_dup_anon_rmap(folio, page, nr_pages, src_vma, RMAP_LEVEL_PTE); } static __always_inline int folio_try_dup_anon_rmap_pte(struct folio *folio, struct page *page, struct vm_area_struct *src_vma) { return __folio_try_dup_anon_rmap(folio, page, 1, src_vma, RMAP_LEVEL_PTE); } /** * folio_try_dup_anon_rmap_pmd - try duplicating a PMD mapping of a page range * of a folio * @folio: The folio to duplicate the mapping of * @page: The first page to duplicate the mapping of * @src_vma: The vm area from which the mapping is duplicated * * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock and the * vma->vma_mm->write_protect_seq. * * Duplicating the mapping can only fail if the folio may be pinned; device * private folios cannot get pinned and consequently this function cannot fail * for them. * * If duplicating the mapping succeeds, the duplicated PMD has to be R/O in * the parent and the child. They must *not* be writable after this call * succeeded. * * Returns 0 if duplicating the mapping succeeded. Returns -EBUSY otherwise. */ static inline int folio_try_dup_anon_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *src_vma) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE return __folio_try_dup_anon_rmap(folio, page, HPAGE_PMD_NR, src_vma, RMAP_LEVEL_PMD); #else WARN_ON_ONCE(true); return -EBUSY; #endif } static __always_inline int __folio_try_share_anon_rmap(struct folio *folio, struct page *page, int nr_pages, enum rmap_level level) { VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); VM_WARN_ON_FOLIO(!PageAnonExclusive(page), folio); __folio_rmap_sanity_checks(folio, page, nr_pages, level); /* device private folios cannot get pinned via GUP. */ if (unlikely(folio_is_device_private(folio))) { ClearPageAnonExclusive(page); return 0; } /* * We have to make sure that when we clear PageAnonExclusive, that * the page is not pinned and that concurrent GUP-fast won't succeed in * concurrently pinning the page. * * Conceptually, PageAnonExclusive clearing consists of: * (A1) Clear PTE * (A2) Check if the page is pinned; back off if so. * (A3) Clear PageAnonExclusive * (A4) Restore PTE (optional, but certainly not writable) * * When clearing PageAnonExclusive, we cannot possibly map the page * writable again, because anon pages that may be shared must never * be writable. So in any case, if the PTE was writable it cannot * be writable anymore afterwards and there would be a PTE change. Only * if the PTE wasn't writable, there might not be a PTE change. * * Conceptually, GUP-fast pinning of an anon page consists of: * (B1) Read the PTE * (B2) FOLL_WRITE: check if the PTE is not writable; back off if so. * (B3) Pin the mapped page * (B4) Check if the PTE changed by re-reading it; back off if so. * (B5) If the original PTE is not writable, check if * PageAnonExclusive is not set; back off if so. * * If the PTE was writable, we only have to make sure that GUP-fast * observes a PTE change and properly backs off. * * If the PTE was not writable, we have to make sure that GUP-fast either * detects a (temporary) PTE change or that PageAnonExclusive is cleared * and properly backs off. * * Consequently, when clearing PageAnonExclusive(), we have to make * sure that (A1), (A2)/(A3) and (A4) happen in the right memory * order. In GUP-fast pinning code, we have to make sure that (B3),(B4) * and (B5) happen in the right memory order. * * We assume that there might not be a memory barrier after * clearing/invalidating the PTE (A1) and before restoring the PTE (A4), * so we use explicit ones here. */ /* Paired with the memory barrier in try_grab_folio(). */ if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_mb(); if (unlikely(folio_maybe_dma_pinned(folio))) return -EBUSY; ClearPageAnonExclusive(page); /* * This is conceptually a smp_wmb() paired with the smp_rmb() in * gup_must_unshare(). */ if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_mb__after_atomic(); return 0; } /** * folio_try_share_anon_rmap_pte - try marking an exclusive anonymous page * mapped by a PTE possibly shared to prepare * for KSM or temporary unmapping * @folio: The folio to share a mapping of * @page: The mapped exclusive page * * The caller needs to hold the page table lock and has to have the page table * entries cleared/invalidated. * * This is similar to folio_try_dup_anon_rmap_pte(), however, not used during * fork() to duplicate mappings, but instead to prepare for KSM or temporarily * unmapping parts of a folio (swap, migration) via folio_remove_rmap_pte(). * * Marking the mapped page shared can only fail if the folio maybe pinned; * device private folios cannot get pinned and consequently this function cannot * fail. * * Returns 0 if marking the mapped page possibly shared succeeded. Returns * -EBUSY otherwise. */ static inline int folio_try_share_anon_rmap_pte(struct folio *folio, struct page *page) { return __folio_try_share_anon_rmap(folio, page, 1, RMAP_LEVEL_PTE); } /** * folio_try_share_anon_rmap_pmd - try marking an exclusive anonymous page * range mapped by a PMD possibly shared to * prepare for temporary unmapping * @folio: The folio to share the mapping of * @page: The first page to share the mapping of * * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock and has to have the page table * entries cleared/invalidated. * * This is similar to folio_try_dup_anon_rmap_pmd(), however, not used during * fork() to duplicate a mapping, but instead to prepare for temporarily * unmapping parts of a folio (swap, migration) via folio_remove_rmap_pmd(). * * Marking the mapped pages shared can only fail if the folio maybe pinned; * device private folios cannot get pinned and consequently this function cannot * fail. * * Returns 0 if marking the mapped pages possibly shared succeeded. Returns * -EBUSY otherwise. */ static inline int folio_try_share_anon_rmap_pmd(struct folio *folio, struct page *page) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE return __folio_try_share_anon_rmap(folio, page, HPAGE_PMD_NR, RMAP_LEVEL_PMD); #else WARN_ON_ONCE(true); return -EBUSY; #endif } /* * Called from mm/vmscan.c to handle paging out */ int folio_referenced(struct folio *, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags); void try_to_migrate(struct folio *folio, enum ttu_flags flags); void try_to_unmap(struct folio *, enum ttu_flags flags); int make_device_exclusive_range(struct mm_struct *mm, unsigned long start, unsigned long end, struct page **pages, void *arg); /* Avoid racy checks */ #define PVMW_SYNC (1 << 0) /* Look for migration entries rather than present PTEs */ #define PVMW_MIGRATION (1 << 1) struct page_vma_mapped_walk { unsigned long pfn; unsigned long nr_pages; pgoff_t pgoff; struct vm_area_struct *vma; unsigned long address; pmd_t *pmd; pte_t *pte; spinlock_t *ptl; unsigned int flags; }; #define DEFINE_FOLIO_VMA_WALK(name, _folio, _vma, _address, _flags) \ struct page_vma_mapped_walk name = { \ .pfn = folio_pfn(_folio), \ .nr_pages = folio_nr_pages(_folio), \ .pgoff = folio_pgoff(_folio), \ .vma = _vma, \ .address = _address, \ .flags = _flags, \ } static inline void page_vma_mapped_walk_done(struct page_vma_mapped_walk *pvmw) { /* HugeTLB pte is set to the relevant page table entry without pte_mapped. */ if (pvmw->pte && !is_vm_hugetlb_page(pvmw->vma)) pte_unmap(pvmw->pte); if (pvmw->ptl) spin_unlock(pvmw->ptl); } /** * page_vma_mapped_walk_restart - Restart the page table walk. * @pvmw: Pointer to struct page_vma_mapped_walk. * * It restarts the page table walk when changes occur in the page * table, such as splitting a PMD. Ensures that the PTL held during * the previous walk is released and resets the state to allow for * a new walk starting at the current address stored in pvmw->address. */ static inline void page_vma_mapped_walk_restart(struct page_vma_mapped_walk *pvmw) { WARN_ON_ONCE(!pvmw->pmd && !pvmw->pte); if (likely(pvmw->ptl)) spin_unlock(pvmw->ptl); else WARN_ON_ONCE(1); pvmw->ptl = NULL; pvmw->pmd = NULL; pvmw->pte = NULL; } bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw); unsigned long page_address_in_vma(const struct folio *folio, const struct page *, const struct vm_area_struct *); /* * Cleans the PTEs of shared mappings. * (and since clean PTEs should also be readonly, write protects them too) * * returns the number of cleaned PTEs. */ int folio_mkclean(struct folio *); int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, struct vm_area_struct *vma); enum rmp_flags { RMP_LOCKED = 1 << 0, RMP_USE_SHARED_ZEROPAGE = 1 << 1, }; void remove_migration_ptes(struct folio *src, struct folio *dst, int flags); /* * rmap_walk_control: To control rmap traversing for specific needs * * arg: passed to rmap_one() and invalid_vma() * try_lock: bail out if the rmap lock is contended * contended: indicate the rmap traversal bailed out due to lock contention * rmap_one: executed on each vma where page is mapped * done: for checking traversing termination condition * anon_lock: for getting anon_lock by optimized way rather than default * invalid_vma: for skipping uninterested vma */ struct rmap_walk_control { void *arg; bool try_lock; bool contended; /* * Return false if page table scanning in rmap_walk should be stopped. * Otherwise, return true. */ bool (*rmap_one)(struct folio *folio, struct vm_area_struct *vma, unsigned long addr, void *arg); int (*done)(struct folio *folio); struct anon_vma *(*anon_lock)(const struct folio *folio, struct rmap_walk_control *rwc); bool (*invalid_vma)(struct vm_area_struct *vma, void *arg); }; void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc); void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc); struct anon_vma *folio_lock_anon_vma_read(const struct folio *folio, struct rmap_walk_control *rwc); #else /* !CONFIG_MMU */ #define anon_vma_init() do {} while (0) #define anon_vma_prepare(vma) (0) static inline int folio_referenced(struct folio *folio, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags) { *vm_flags = 0; return 0; } static inline void try_to_unmap(struct folio *folio, enum ttu_flags flags) { } static inline int folio_mkclean(struct folio *folio) { return 0; } #endif /* CONFIG_MMU */ #endif /* _LINUX_RMAP_H */ |
| 345 7 341 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/uaccess.h> #include <linux/kernel.h> #include <asm/vsyscall.h> #ifdef CONFIG_X86_64 bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) { unsigned long vaddr = (unsigned long)unsafe_src; /* * Do not allow userspace addresses. This disallows * normal userspace and the userspace guard page: */ if (vaddr < TASK_SIZE_MAX + PAGE_SIZE) return false; /* * Reading from the vsyscall page may cause an unhandled fault in * certain cases. Though it is at an address above TASK_SIZE_MAX, it is * usually considered as a user space address. */ if (is_vsyscall_vaddr(vaddr)) return false; /* * Allow everything during early boot before 'x86_virt_bits' * is initialized. Needed for instruction decoding in early * exception handlers. */ if (!boot_cpu_data.x86_virt_bits) return true; return __is_canonical_address(vaddr, boot_cpu_data.x86_virt_bits); } #else bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) { return (unsigned long)unsafe_src >= TASK_SIZE_MAX; } #endif |
| 80 80 1 80 1 81 81 80 81 81 80 10 10 9 10 5 9 8 8 1 3 9 1 5 5 3 3 1 2 2 19 30 28 30 8 18 5 35 1 32 32 1 29 30 2 1 9 11 6 8 6 3 1 1 2 1 1 1 2 1 1 1 1 1 3 1 1 39 1 1 1 32 3 2 1 1 1 1 1 44 40 4 14 4 5 2 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Packet matching code for ARP packets. * * Based heavily, if not almost entirely, upon ip_tables.c framework. * * Some ARP specific bits are: * * Copyright (C) 2002 David S. Miller (davem@redhat.com) * Copyright (C) 2006-2009 Patrick McHardy <kaber@trash.net> * */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/capability.h> #include <linux/if_arp.h> #include <linux/kmod.h> #include <linux/vmalloc.h> #include <linux/proc_fs.h> #include <linux/module.h> #include <linux/init.h> #include <linux/mutex.h> #include <linux/err.h> #include <net/compat.h> #include <net/sock.h> #include <linux/uaccess.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_arp/arp_tables.h> #include "../../netfilter/xt_repldata.h" MODULE_LICENSE("GPL"); MODULE_AUTHOR("David S. Miller <davem@redhat.com>"); MODULE_DESCRIPTION("arptables core"); void *arpt_alloc_initial_table(const struct xt_table *info) { return xt_alloc_initial_table(arpt, ARPT); } EXPORT_SYMBOL_GPL(arpt_alloc_initial_table); static inline int arp_devaddr_compare(const struct arpt_devaddr_info *ap, const char *hdr_addr, int len) { int i, ret; if (len > ARPT_DEV_ADDR_LEN_MAX) len = ARPT_DEV_ADDR_LEN_MAX; ret = 0; for (i = 0; i < len; i++) ret |= (hdr_addr[i] ^ ap->addr[i]) & ap->mask[i]; return ret != 0; } /* * Unfortunately, _b and _mask are not aligned to an int (or long int) * Some arches dont care, unrolling the loop is a win on them. * For other arches, we only have a 16bit alignement. */ static unsigned long ifname_compare(const char *_a, const char *_b, const char *_mask) { #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS unsigned long ret = ifname_compare_aligned(_a, _b, _mask); #else unsigned long ret = 0; const u16 *a = (const u16 *)_a; const u16 *b = (const u16 *)_b; const u16 *mask = (const u16 *)_mask; int i; for (i = 0; i < IFNAMSIZ/sizeof(u16); i++) ret |= (a[i] ^ b[i]) & mask[i]; #endif return ret; } /* Returns whether packet matches rule or not. */ static inline int arp_packet_match(const struct arphdr *arphdr, struct net_device *dev, const char *indev, const char *outdev, const struct arpt_arp *arpinfo) { const char *arpptr = (char *)(arphdr + 1); const char *src_devaddr, *tgt_devaddr; __be32 src_ipaddr, tgt_ipaddr; long ret; if (NF_INVF(arpinfo, ARPT_INV_ARPOP, (arphdr->ar_op & arpinfo->arpop_mask) != arpinfo->arpop)) return 0; if (NF_INVF(arpinfo, ARPT_INV_ARPHRD, (arphdr->ar_hrd & arpinfo->arhrd_mask) != arpinfo->arhrd)) return 0; if (NF_INVF(arpinfo, ARPT_INV_ARPPRO, (arphdr->ar_pro & arpinfo->arpro_mask) != arpinfo->arpro)) return 0; if (NF_INVF(arpinfo, ARPT_INV_ARPHLN, (arphdr->ar_hln & arpinfo->arhln_mask) != arpinfo->arhln)) return 0; src_devaddr = arpptr; arpptr += dev->addr_len; memcpy(&src_ipaddr, arpptr, sizeof(u32)); arpptr += sizeof(u32); tgt_devaddr = arpptr; arpptr += dev->addr_len; memcpy(&tgt_ipaddr, arpptr, sizeof(u32)); if (NF_INVF(arpinfo, ARPT_INV_SRCDEVADDR, arp_devaddr_compare(&arpinfo->src_devaddr, src_devaddr, dev->addr_len)) || NF_INVF(arpinfo, ARPT_INV_TGTDEVADDR, arp_devaddr_compare(&arpinfo->tgt_devaddr, tgt_devaddr, dev->addr_len))) return 0; if (NF_INVF(arpinfo, ARPT_INV_SRCIP, (src_ipaddr & arpinfo->smsk.s_addr) != arpinfo->src.s_addr) || NF_INVF(arpinfo, ARPT_INV_TGTIP, (tgt_ipaddr & arpinfo->tmsk.s_addr) != arpinfo->tgt.s_addr)) return 0; /* Look for ifname matches. */ ret = ifname_compare(indev, arpinfo->iniface, arpinfo->iniface_mask); if (NF_INVF(arpinfo, ARPT_INV_VIA_IN, ret != 0)) return 0; ret = ifname_compare(outdev, arpinfo->outiface, arpinfo->outiface_mask); if (NF_INVF(arpinfo, ARPT_INV_VIA_OUT, ret != 0)) return 0; return 1; } static inline int arp_checkentry(const struct arpt_arp *arp) { if (arp->flags & ~ARPT_F_MASK) return 0; if (arp->invflags & ~ARPT_INV_MASK) return 0; return 1; } static unsigned int arpt_error(struct sk_buff *skb, const struct xt_action_param *par) { net_err_ratelimited("arp_tables: error: '%s'\n", (const char *)par->targinfo); return NF_DROP; } static inline const struct xt_entry_target * arpt_get_target_c(const struct arpt_entry *e) { return arpt_get_target((struct arpt_entry *)e); } static inline struct arpt_entry * get_entry(const void *base, unsigned int offset) { return (struct arpt_entry *)(base + offset); } static inline struct arpt_entry *arpt_next_entry(const struct arpt_entry *entry) { return (void *)entry + entry->next_offset; } unsigned int arpt_do_table(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { const struct xt_table *table = priv; unsigned int hook = state->hook; static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); unsigned int verdict = NF_DROP; const struct arphdr *arp; struct arpt_entry *e, **jumpstack; const char *indev, *outdev; const void *table_base; unsigned int cpu, stackidx = 0; const struct xt_table_info *private; struct xt_action_param acpar; unsigned int addend; if (!pskb_may_pull(skb, arp_hdr_len(skb->dev))) return NF_DROP; indev = state->in ? state->in->name : nulldevname; outdev = state->out ? state->out->name : nulldevname; local_bh_disable(); addend = xt_write_recseq_begin(); private = READ_ONCE(table->private); /* Address dependency. */ cpu = smp_processor_id(); table_base = private->entries; jumpstack = (struct arpt_entry **)private->jumpstack[cpu]; /* No TEE support for arptables, so no need to switch to alternate * stack. All targets that reenter must return absolute verdicts. */ e = get_entry(table_base, private->hook_entry[hook]); acpar.state = state; acpar.hotdrop = false; arp = arp_hdr(skb); do { const struct xt_entry_target *t; struct xt_counters *counter; if (!arp_packet_match(arp, skb->dev, indev, outdev, &e->arp)) { e = arpt_next_entry(e); continue; } counter = xt_get_this_cpu_counter(&e->counters); ADD_COUNTER(*counter, arp_hdr_len(skb->dev), 1); t = arpt_get_target_c(e); /* Standard target? */ if (!t->u.kernel.target->target) { int v; v = ((struct xt_standard_target *)t)->verdict; if (v < 0) { /* Pop from stack? */ if (v != XT_RETURN) { verdict = (unsigned int)(-v) - 1; break; } if (stackidx == 0) { e = get_entry(table_base, private->underflow[hook]); } else { e = jumpstack[--stackidx]; e = arpt_next_entry(e); } continue; } if (table_base + v != arpt_next_entry(e)) { if (unlikely(stackidx >= private->stacksize)) { verdict = NF_DROP; break; } jumpstack[stackidx++] = e; } e = get_entry(table_base, v); continue; } acpar.target = t->u.kernel.target; acpar.targinfo = t->data; verdict = t->u.kernel.target->target(skb, &acpar); if (verdict == XT_CONTINUE) { /* Target might have changed stuff. */ arp = arp_hdr(skb); e = arpt_next_entry(e); } else { /* Verdict */ break; } } while (!acpar.hotdrop); xt_write_recseq_end(addend); local_bh_enable(); if (acpar.hotdrop) return NF_DROP; else return verdict; } /* All zeroes == unconditional rule. */ static inline bool unconditional(const struct arpt_entry *e) { static const struct arpt_arp uncond; return e->target_offset == sizeof(struct arpt_entry) && memcmp(&e->arp, &uncond, sizeof(uncond)) == 0; } /* Figures out from what hook each rule can be called: returns 0 if * there are loops. Puts hook bitmask in comefrom. */ static int mark_source_chains(const struct xt_table_info *newinfo, unsigned int valid_hooks, void *entry0, unsigned int *offsets) { unsigned int hook; /* No recursion; use packet counter to save back ptrs (reset * to 0 as we leave), and comefrom to save source hook bitmask. */ for (hook = 0; hook < NF_ARP_NUMHOOKS; hook++) { unsigned int pos = newinfo->hook_entry[hook]; struct arpt_entry *e = entry0 + pos; if (!(valid_hooks & (1 << hook))) continue; /* Set initial back pointer. */ e->counters.pcnt = pos; for (;;) { const struct xt_standard_target *t = (void *)arpt_get_target_c(e); int visited = e->comefrom & (1 << hook); if (e->comefrom & (1 << NF_ARP_NUMHOOKS)) return 0; e->comefrom |= ((1 << hook) | (1 << NF_ARP_NUMHOOKS)); /* Unconditional return/END. */ if ((unconditional(e) && (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0) && t->verdict < 0) || visited) { unsigned int oldpos, size; /* Return: backtrack through the last * big jump. */ do { e->comefrom ^= (1<<NF_ARP_NUMHOOKS); oldpos = pos; pos = e->counters.pcnt; e->counters.pcnt = 0; /* We're at the start. */ if (pos == oldpos) goto next; e = entry0 + pos; } while (oldpos == pos + e->next_offset); /* Move along one */ size = e->next_offset; e = entry0 + pos + size; if (pos + size >= newinfo->size) return 0; e->counters.pcnt = pos; pos += size; } else { int newpos = t->verdict; if (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0 && newpos >= 0) { /* This a jump; chase it. */ if (!xt_find_jump_offset(offsets, newpos, newinfo->number)) return 0; } else { /* ... this is a fallthru */ newpos = pos + e->next_offset; if (newpos >= newinfo->size) return 0; } e = entry0 + newpos; e->counters.pcnt = pos; pos = newpos; } } next: ; } return 1; } static int check_target(struct arpt_entry *e, struct net *net, const char *name) { struct xt_entry_target *t = arpt_get_target(e); struct xt_tgchk_param par = { .net = net, .table = name, .entryinfo = e, .target = t->u.kernel.target, .targinfo = t->data, .hook_mask = e->comefrom, .family = NFPROTO_ARP, }; return xt_check_target(&par, t->u.target_size - sizeof(*t), 0, false); } static int find_check_entry(struct arpt_entry *e, struct net *net, const char *name, unsigned int size, struct xt_percpu_counter_alloc_state *alloc_state) { struct xt_entry_target *t; struct xt_target *target; int ret; if (!xt_percpu_counter_alloc(alloc_state, &e->counters)) return -ENOMEM; t = arpt_get_target(e); target = xt_request_find_target(NFPROTO_ARP, t->u.user.name, t->u.user.revision); if (IS_ERR(target)) { ret = PTR_ERR(target); goto out; } t->u.kernel.target = target; ret = check_target(e, net, name); if (ret) goto err; return 0; err: module_put(t->u.kernel.target->me); out: xt_percpu_counter_free(&e->counters); return ret; } static bool check_underflow(const struct arpt_entry *e) { const struct xt_entry_target *t; unsigned int verdict; if (!unconditional(e)) return false; t = arpt_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) return false; verdict = ((struct xt_standard_target *)t)->verdict; verdict = -verdict - 1; return verdict == NF_DROP || verdict == NF_ACCEPT; } static inline int check_entry_size_and_hooks(struct arpt_entry *e, struct xt_table_info *newinfo, const unsigned char *base, const unsigned char *limit, const unsigned int *hook_entries, const unsigned int *underflows, unsigned int valid_hooks) { unsigned int h; int err; if ((unsigned long)e % __alignof__(struct arpt_entry) != 0 || (unsigned char *)e + sizeof(struct arpt_entry) >= limit || (unsigned char *)e + e->next_offset > limit) return -EINVAL; if (e->next_offset < sizeof(struct arpt_entry) + sizeof(struct xt_entry_target)) return -EINVAL; if (!arp_checkentry(&e->arp)) return -EINVAL; err = xt_check_entry_offsets(e, e->elems, e->target_offset, e->next_offset); if (err) return err; /* Check hooks & underflows */ for (h = 0; h < NF_ARP_NUMHOOKS; h++) { if (!(valid_hooks & (1 << h))) continue; if ((unsigned char *)e - base == hook_entries[h]) newinfo->hook_entry[h] = hook_entries[h]; if ((unsigned char *)e - base == underflows[h]) { if (!check_underflow(e)) return -EINVAL; newinfo->underflow[h] = underflows[h]; } } /* Clear counters and comefrom */ e->counters = ((struct xt_counters) { 0, 0 }); e->comefrom = 0; return 0; } static void cleanup_entry(struct arpt_entry *e, struct net *net) { struct xt_tgdtor_param par; struct xt_entry_target *t; t = arpt_get_target(e); par.net = net; par.target = t->u.kernel.target; par.targinfo = t->data; par.family = NFPROTO_ARP; if (par.target->destroy != NULL) par.target->destroy(&par); module_put(par.target->me); xt_percpu_counter_free(&e->counters); } /* Checks and translates the user-supplied table segment (held in * newinfo). */ static int translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, const struct arpt_replace *repl) { struct xt_percpu_counter_alloc_state alloc_state = { 0 }; struct arpt_entry *iter; unsigned int *offsets; unsigned int i; int ret = 0; newinfo->size = repl->size; newinfo->number = repl->num_entries; /* Init all hooks to impossible value. */ for (i = 0; i < NF_ARP_NUMHOOKS; i++) { newinfo->hook_entry[i] = 0xFFFFFFFF; newinfo->underflow[i] = 0xFFFFFFFF; } offsets = xt_alloc_entry_offsets(newinfo->number); if (!offsets) return -ENOMEM; i = 0; /* Walk through entries, checking offsets. */ xt_entry_foreach(iter, entry0, newinfo->size) { ret = check_entry_size_and_hooks(iter, newinfo, entry0, entry0 + repl->size, repl->hook_entry, repl->underflow, repl->valid_hooks); if (ret != 0) goto out_free; if (i < repl->num_entries) offsets[i] = (void *)iter - entry0; ++i; if (strcmp(arpt_get_target(iter)->u.user.name, XT_ERROR_TARGET) == 0) ++newinfo->stacksize; } ret = -EINVAL; if (i != repl->num_entries) goto out_free; ret = xt_check_table_hooks(newinfo, repl->valid_hooks); if (ret) goto out_free; if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) { ret = -ELOOP; goto out_free; } kvfree(offsets); /* Finally, each sanity check must pass */ i = 0; xt_entry_foreach(iter, entry0, newinfo->size) { ret = find_check_entry(iter, net, repl->name, repl->size, &alloc_state); if (ret != 0) break; ++i; } if (ret != 0) { xt_entry_foreach(iter, entry0, newinfo->size) { if (i-- == 0) break; cleanup_entry(iter, net); } return ret; } return ret; out_free: kvfree(offsets); return ret; } static void get_counters(const struct xt_table_info *t, struct xt_counters counters[]) { struct arpt_entry *iter; unsigned int cpu; unsigned int i; for_each_possible_cpu(cpu) { seqcount_t *s = &per_cpu(xt_recseq, cpu); i = 0; xt_entry_foreach(iter, t->entries, t->size) { struct xt_counters *tmp; u64 bcnt, pcnt; unsigned int start; tmp = xt_get_per_cpu_counter(&iter->counters, cpu); do { start = read_seqcount_begin(s); bcnt = tmp->bcnt; pcnt = tmp->pcnt; } while (read_seqcount_retry(s, start)); ADD_COUNTER(counters[i], bcnt, pcnt); ++i; cond_resched(); } } } static void get_old_counters(const struct xt_table_info *t, struct xt_counters counters[]) { struct arpt_entry *iter; unsigned int cpu, i; for_each_possible_cpu(cpu) { i = 0; xt_entry_foreach(iter, t->entries, t->size) { struct xt_counters *tmp; tmp = xt_get_per_cpu_counter(&iter->counters, cpu); ADD_COUNTER(counters[i], tmp->bcnt, tmp->pcnt); ++i; } cond_resched(); } } static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; const struct xt_table_info *private = table->private; /* We need atomic snapshot of counters: rest doesn't change * (other than comefrom, which userspace doesn't care * about). */ countersize = sizeof(struct xt_counters) * private->number; counters = vzalloc(countersize); if (counters == NULL) return ERR_PTR(-ENOMEM); get_counters(private, counters); return counters; } static int copy_entries_to_user(unsigned int total_size, const struct xt_table *table, void __user *userptr) { unsigned int off, num; const struct arpt_entry *e; struct xt_counters *counters; struct xt_table_info *private = table->private; int ret = 0; void *loc_cpu_entry; counters = alloc_counters(table); if (IS_ERR(counters)) return PTR_ERR(counters); loc_cpu_entry = private->entries; /* FIXME: use iterator macros --RR */ /* ... then go back and fix counters and names */ for (off = 0, num = 0; off < total_size; off += e->next_offset, num++){ const struct xt_entry_target *t; e = loc_cpu_entry + off; if (copy_to_user(userptr + off, e, sizeof(*e))) { ret = -EFAULT; goto free_counters; } if (copy_to_user(userptr + off + offsetof(struct arpt_entry, counters), &counters[num], sizeof(counters[num])) != 0) { ret = -EFAULT; goto free_counters; } t = arpt_get_target_c(e); if (xt_target_to_user(t, userptr + off + e->target_offset)) { ret = -EFAULT; goto free_counters; } } free_counters: vfree(counters); return ret; } #ifdef CONFIG_NETFILTER_XTABLES_COMPAT static void compat_standard_from_user(void *dst, const void *src) { int v = *(compat_int_t *)src; if (v > 0) v += xt_compat_calc_jump(NFPROTO_ARP, v); memcpy(dst, &v, sizeof(v)); } static int compat_standard_to_user(void __user *dst, const void *src) { compat_int_t cv = *(int *)src; if (cv > 0) cv -= xt_compat_calc_jump(NFPROTO_ARP, cv); return copy_to_user(dst, &cv, sizeof(cv)) ? -EFAULT : 0; } static int compat_calc_entry(const struct arpt_entry *e, const struct xt_table_info *info, const void *base, struct xt_table_info *newinfo) { const struct xt_entry_target *t; unsigned int entry_offset; int off, i, ret; off = sizeof(struct arpt_entry) - sizeof(struct compat_arpt_entry); entry_offset = (void *)e - base; t = arpt_get_target_c(e); off += xt_compat_target_offset(t->u.kernel.target); newinfo->size -= off; ret = xt_compat_add_offset(NFPROTO_ARP, entry_offset, off); if (ret) return ret; for (i = 0; i < NF_ARP_NUMHOOKS; i++) { if (info->hook_entry[i] && (e < (struct arpt_entry *)(base + info->hook_entry[i]))) newinfo->hook_entry[i] -= off; if (info->underflow[i] && (e < (struct arpt_entry *)(base + info->underflow[i]))) newinfo->underflow[i] -= off; } return 0; } static int compat_table_info(const struct xt_table_info *info, struct xt_table_info *newinfo) { struct arpt_entry *iter; const void *loc_cpu_entry; int ret; if (!newinfo || !info) return -EINVAL; /* we dont care about newinfo->entries */ memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); newinfo->initial_entries = 0; loc_cpu_entry = info->entries; ret = xt_compat_init_offsets(NFPROTO_ARP, info->number); if (ret) return ret; xt_entry_foreach(iter, loc_cpu_entry, info->size) { ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo); if (ret != 0) return ret; } return 0; } #endif static int get_info(struct net *net, void __user *user, const int *len) { char name[XT_TABLE_MAXNAMELEN]; struct xt_table *t; int ret; if (*len != sizeof(struct arpt_getinfo)) return -EINVAL; if (copy_from_user(name, user, sizeof(name)) != 0) return -EFAULT; name[XT_TABLE_MAXNAMELEN-1] = '\0'; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) xt_compat_lock(NFPROTO_ARP); #endif t = xt_request_find_table_lock(net, NFPROTO_ARP, name); if (!IS_ERR(t)) { struct arpt_getinfo info; const struct xt_table_info *private = t->private; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT struct xt_table_info tmp; if (in_compat_syscall()) { ret = compat_table_info(private, &tmp); xt_compat_flush_offsets(NFPROTO_ARP); private = &tmp; } #endif memset(&info, 0, sizeof(info)); info.valid_hooks = t->valid_hooks; memcpy(info.hook_entry, private->hook_entry, sizeof(info.hook_entry)); memcpy(info.underflow, private->underflow, sizeof(info.underflow)); info.num_entries = private->number; info.size = private->size; strscpy(info.name, name); if (copy_to_user(user, &info, *len) != 0) ret = -EFAULT; else ret = 0; xt_table_unlock(t); module_put(t->me); } else ret = PTR_ERR(t); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) xt_compat_unlock(NFPROTO_ARP); #endif return ret; } static int get_entries(struct net *net, struct arpt_get_entries __user *uptr, const int *len) { int ret; struct arpt_get_entries get; struct xt_table *t; if (*len < sizeof(get)) return -EINVAL; if (copy_from_user(&get, uptr, sizeof(get)) != 0) return -EFAULT; if (*len != sizeof(struct arpt_get_entries) + get.size) return -EINVAL; get.name[sizeof(get.name) - 1] = '\0'; t = xt_find_table_lock(net, NFPROTO_ARP, get.name); if (!IS_ERR(t)) { const struct xt_table_info *private = t->private; if (get.size == private->size) ret = copy_entries_to_user(private->size, t, uptr->entrytable); else ret = -EAGAIN; module_put(t->me); xt_table_unlock(t); } else ret = PTR_ERR(t); return ret; } static int __do_replace(struct net *net, const char *name, unsigned int valid_hooks, struct xt_table_info *newinfo, unsigned int num_counters, void __user *counters_ptr) { int ret; struct xt_table *t; struct xt_table_info *oldinfo; struct xt_counters *counters; void *loc_cpu_old_entry; struct arpt_entry *iter; ret = 0; counters = xt_counters_alloc(num_counters); if (!counters) { ret = -ENOMEM; goto out; } t = xt_request_find_table_lock(net, NFPROTO_ARP, name); if (IS_ERR(t)) { ret = PTR_ERR(t); goto free_newinfo_counters_untrans; } /* You lied! */ if (valid_hooks != t->valid_hooks) { ret = -EINVAL; goto put_module; } oldinfo = xt_replace_table(t, num_counters, newinfo, &ret); if (!oldinfo) goto put_module; /* Update module usage count based on number of rules */ if ((oldinfo->number > oldinfo->initial_entries) || (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); if ((oldinfo->number > oldinfo->initial_entries) && (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); xt_table_unlock(t); get_old_counters(oldinfo, counters); /* Decrease module usage counts and free resource */ loc_cpu_old_entry = oldinfo->entries; xt_entry_foreach(iter, loc_cpu_old_entry, oldinfo->size) cleanup_entry(iter, net); xt_free_table_info(oldinfo); if (copy_to_user(counters_ptr, counters, sizeof(struct xt_counters) * num_counters) != 0) { /* Silent error, can't fail, new table is already in place */ net_warn_ratelimited("arptables: counters copy to user failed while replacing table\n"); } vfree(counters); return ret; put_module: module_put(t->me); xt_table_unlock(t); free_newinfo_counters_untrans: vfree(counters); out: return ret; } static int do_replace(struct net *net, sockptr_t arg, unsigned int len) { int ret; struct arpt_replace tmp; struct xt_table_info *newinfo; void *loc_cpu_entry; struct arpt_entry *iter; if (len < sizeof(tmp)) return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; if ((u64)len < (u64)tmp.size + sizeof(tmp)) return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; } ret = translate_table(net, newinfo, loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo, tmp.num_counters, tmp.counters); if (ret) goto free_newinfo_untrans; return 0; free_newinfo_untrans: xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); free_newinfo: xt_free_table_info(newinfo); return ret; } static int do_add_counters(struct net *net, sockptr_t arg, unsigned int len) { unsigned int i; struct xt_counters_info tmp; struct xt_counters *paddc; struct xt_table *t; const struct xt_table_info *private; int ret = 0; struct arpt_entry *iter; unsigned int addend; paddc = xt_copy_counters(arg, len, &tmp); if (IS_ERR(paddc)) return PTR_ERR(paddc); t = xt_find_table_lock(net, NFPROTO_ARP, tmp.name); if (IS_ERR(t)) { ret = PTR_ERR(t); goto free; } local_bh_disable(); private = t->private; if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; } i = 0; addend = xt_write_recseq_begin(); xt_entry_foreach(iter, private->entries, private->size) { struct xt_counters *tmp; tmp = xt_get_this_cpu_counter(&iter->counters); ADD_COUNTER(*tmp, paddc[i].bcnt, paddc[i].pcnt); ++i; } xt_write_recseq_end(addend); unlock_up_free: local_bh_enable(); xt_table_unlock(t); module_put(t->me); free: vfree(paddc); return ret; } #ifdef CONFIG_NETFILTER_XTABLES_COMPAT struct compat_arpt_replace { char name[XT_TABLE_MAXNAMELEN]; u32 valid_hooks; u32 num_entries; u32 size; u32 hook_entry[NF_ARP_NUMHOOKS]; u32 underflow[NF_ARP_NUMHOOKS]; u32 num_counters; compat_uptr_t counters; struct compat_arpt_entry entries[]; }; static inline void compat_release_entry(struct compat_arpt_entry *e) { struct xt_entry_target *t; t = compat_arpt_get_target(e); module_put(t->u.kernel.target->me); } static int check_compat_entry_size_and_hooks(struct compat_arpt_entry *e, struct xt_table_info *newinfo, unsigned int *size, const unsigned char *base, const unsigned char *limit) { struct xt_entry_target *t; struct xt_target *target; unsigned int entry_offset; int ret, off; if ((unsigned long)e % __alignof__(struct compat_arpt_entry) != 0 || (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit || (unsigned char *)e + e->next_offset > limit) return -EINVAL; if (e->next_offset < sizeof(struct compat_arpt_entry) + sizeof(struct compat_xt_entry_target)) return -EINVAL; if (!arp_checkentry(&e->arp)) return -EINVAL; ret = xt_compat_check_entry_offsets(e, e->elems, e->target_offset, e->next_offset); if (ret) return ret; off = sizeof(struct arpt_entry) - sizeof(struct compat_arpt_entry); entry_offset = (void *)e - (void *)base; t = compat_arpt_get_target(e); target = xt_request_find_target(NFPROTO_ARP, t->u.user.name, t->u.user.revision); if (IS_ERR(target)) { ret = PTR_ERR(target); goto out; } t->u.kernel.target = target; off += xt_compat_target_offset(target); *size += off; ret = xt_compat_add_offset(NFPROTO_ARP, entry_offset, off); if (ret) goto release_target; return 0; release_target: module_put(t->u.kernel.target->me); out: return ret; } static void compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr, unsigned int *size, struct xt_table_info *newinfo, unsigned char *base) { struct xt_entry_target *t; struct arpt_entry *de; unsigned int origsize; int h; origsize = *size; de = *dstptr; memcpy(de, e, sizeof(struct arpt_entry)); memcpy(&de->counters, &e->counters, sizeof(e->counters)); *dstptr += sizeof(struct arpt_entry); *size += sizeof(struct arpt_entry) - sizeof(struct compat_arpt_entry); de->target_offset = e->target_offset - (origsize - *size); t = compat_arpt_get_target(e); xt_compat_target_from_user(t, dstptr, size); de->next_offset = e->next_offset - (origsize - *size); for (h = 0; h < NF_ARP_NUMHOOKS; h++) { if ((unsigned char *)de - base < newinfo->hook_entry[h]) newinfo->hook_entry[h] -= origsize - *size; if ((unsigned char *)de - base < newinfo->underflow[h]) newinfo->underflow[h] -= origsize - *size; } } static int translate_compat_table(struct net *net, struct xt_table_info **pinfo, void **pentry0, const struct compat_arpt_replace *compatr) { unsigned int i, j; struct xt_table_info *newinfo, *info; void *pos, *entry0, *entry1; struct compat_arpt_entry *iter0; struct arpt_replace repl; unsigned int size; int ret; info = *pinfo; entry0 = *pentry0; size = compatr->size; info->number = compatr->num_entries; j = 0; xt_compat_lock(NFPROTO_ARP); ret = xt_compat_init_offsets(NFPROTO_ARP, compatr->num_entries); if (ret) goto out_unlock; /* Walk through entries, checking offsets. */ xt_entry_foreach(iter0, entry0, compatr->size) { ret = check_compat_entry_size_and_hooks(iter0, info, &size, entry0, entry0 + compatr->size); if (ret != 0) goto out_unlock; ++j; } ret = -EINVAL; if (j != compatr->num_entries) goto out_unlock; ret = -ENOMEM; newinfo = xt_alloc_table_info(size); if (!newinfo) goto out_unlock; memset(newinfo->entries, 0, size); newinfo->number = compatr->num_entries; for (i = 0; i < NF_ARP_NUMHOOKS; i++) { newinfo->hook_entry[i] = compatr->hook_entry[i]; newinfo->underflow[i] = compatr->underflow[i]; } entry1 = newinfo->entries; pos = entry1; size = compatr->size; xt_entry_foreach(iter0, entry0, compatr->size) compat_copy_entry_from_user(iter0, &pos, &size, newinfo, entry1); /* all module references in entry0 are now gone */ xt_compat_flush_offsets(NFPROTO_ARP); xt_compat_unlock(NFPROTO_ARP); memcpy(&repl, compatr, sizeof(*compatr)); for (i = 0; i < NF_ARP_NUMHOOKS; i++) { repl.hook_entry[i] = newinfo->hook_entry[i]; repl.underflow[i] = newinfo->underflow[i]; } repl.num_counters = 0; repl.counters = NULL; repl.size = newinfo->size; ret = translate_table(net, newinfo, entry1, &repl); if (ret) goto free_newinfo; *pinfo = newinfo; *pentry0 = entry1; xt_free_table_info(info); return 0; free_newinfo: xt_free_table_info(newinfo); return ret; out_unlock: xt_compat_flush_offsets(NFPROTO_ARP); xt_compat_unlock(NFPROTO_ARP); xt_entry_foreach(iter0, entry0, compatr->size) { if (j-- == 0) break; compat_release_entry(iter0); } return ret; } static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) { int ret; struct compat_arpt_replace tmp; struct xt_table_info *newinfo; void *loc_cpu_entry; struct arpt_entry *iter; if (len < sizeof(tmp)) return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; if ((u64)len < (u64)tmp.size + sizeof(tmp)) return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; } ret = translate_compat_table(net, &newinfo, &loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo, tmp.num_counters, compat_ptr(tmp.counters)); if (ret) goto free_newinfo_untrans; return 0; free_newinfo_untrans: xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); free_newinfo: xt_free_table_info(newinfo); return ret; } static int compat_copy_entry_to_user(struct arpt_entry *e, void __user **dstptr, compat_uint_t *size, struct xt_counters *counters, unsigned int i) { struct xt_entry_target *t; struct compat_arpt_entry __user *ce; u_int16_t target_offset, next_offset; compat_uint_t origsize; int ret; origsize = *size; ce = *dstptr; if (copy_to_user(ce, e, sizeof(struct arpt_entry)) != 0 || copy_to_user(&ce->counters, &counters[i], sizeof(counters[i])) != 0) return -EFAULT; *dstptr += sizeof(struct compat_arpt_entry); *size -= sizeof(struct arpt_entry) - sizeof(struct compat_arpt_entry); target_offset = e->target_offset - (origsize - *size); t = arpt_get_target(e); ret = xt_compat_target_to_user(t, dstptr, size); if (ret) return ret; next_offset = e->next_offset - (origsize - *size); if (put_user(target_offset, &ce->target_offset) != 0 || put_user(next_offset, &ce->next_offset) != 0) return -EFAULT; return 0; } static int compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table, void __user *userptr) { struct xt_counters *counters; const struct xt_table_info *private = table->private; void __user *pos; unsigned int size; int ret = 0; unsigned int i = 0; struct arpt_entry *iter; counters = alloc_counters(table); if (IS_ERR(counters)) return PTR_ERR(counters); pos = userptr; size = total_size; xt_entry_foreach(iter, private->entries, total_size) { ret = compat_copy_entry_to_user(iter, &pos, &size, counters, i++); if (ret != 0) break; } vfree(counters); return ret; } struct compat_arpt_get_entries { char name[XT_TABLE_MAXNAMELEN]; compat_uint_t size; struct compat_arpt_entry entrytable[]; }; static int compat_get_entries(struct net *net, struct compat_arpt_get_entries __user *uptr, int *len) { int ret; struct compat_arpt_get_entries get; struct xt_table *t; if (*len < sizeof(get)) return -EINVAL; if (copy_from_user(&get, uptr, sizeof(get)) != 0) return -EFAULT; if (*len != sizeof(struct compat_arpt_get_entries) + get.size) return -EINVAL; get.name[sizeof(get.name) - 1] = '\0'; xt_compat_lock(NFPROTO_ARP); t = xt_find_table_lock(net, NFPROTO_ARP, get.name); if (!IS_ERR(t)) { const struct xt_table_info *private = t->private; struct xt_table_info info; ret = compat_table_info(private, &info); if (!ret && get.size == info.size) { ret = compat_copy_entries_to_user(private->size, t, uptr->entrytable); } else if (!ret) ret = -EAGAIN; xt_compat_flush_offsets(NFPROTO_ARP); module_put(t->me); xt_table_unlock(t); } else ret = PTR_ERR(t); xt_compat_unlock(NFPROTO_ARP); return ret; } #endif static int do_arpt_set_ctl(struct sock *sk, int cmd, sockptr_t arg, unsigned int len) { int ret; if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { case ARPT_SO_SET_REPLACE: #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) ret = compat_do_replace(sock_net(sk), arg, len); else #endif ret = do_replace(sock_net(sk), arg, len); break; case ARPT_SO_SET_ADD_COUNTERS: ret = do_add_counters(sock_net(sk), arg, len); break; default: ret = -EINVAL; } return ret; } static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { int ret; if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { case ARPT_SO_GET_INFO: ret = get_info(sock_net(sk), user, len); break; case ARPT_SO_GET_ENTRIES: #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) ret = compat_get_entries(sock_net(sk), user, len); else #endif ret = get_entries(sock_net(sk), user, len); break; case ARPT_SO_GET_REVISION_TARGET: { struct xt_get_revision rev; if (*len != sizeof(rev)) { ret = -EINVAL; break; } if (copy_from_user(&rev, user, sizeof(rev)) != 0) { ret = -EFAULT; break; } rev.name[sizeof(rev.name)-1] = 0; try_then_request_module(xt_find_revision(NFPROTO_ARP, rev.name, rev.revision, 1, &ret), "arpt_%s", rev.name); break; } default: ret = -EINVAL; } return ret; } static void __arpt_unregister_table(struct net *net, struct xt_table *table) { struct xt_table_info *private; void *loc_cpu_entry; struct module *table_owner = table->me; struct arpt_entry *iter; private = xt_unregister_table(table); /* Decrease module usage counts and free resources */ loc_cpu_entry = private->entries; xt_entry_foreach(iter, loc_cpu_entry, private->size) cleanup_entry(iter, net); if (private->number > private->initial_entries) module_put(table_owner); xt_free_table_info(private); } int arpt_register_table(struct net *net, const struct xt_table *table, const struct arpt_replace *repl, const struct nf_hook_ops *template_ops) { struct nf_hook_ops *ops; unsigned int num_ops; int ret, i; struct xt_table_info *newinfo; struct xt_table_info bootstrap = {0}; void *loc_cpu_entry; struct xt_table *new_table; newinfo = xt_alloc_table_info(repl->size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; memcpy(loc_cpu_entry, repl->entries, repl->size); ret = translate_table(net, newinfo, loc_cpu_entry, repl); if (ret != 0) { xt_free_table_info(newinfo); return ret; } new_table = xt_register_table(net, table, &bootstrap, newinfo); if (IS_ERR(new_table)) { struct arpt_entry *iter; xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); xt_free_table_info(newinfo); return PTR_ERR(new_table); } num_ops = hweight32(table->valid_hooks); if (num_ops == 0) { ret = -EINVAL; goto out_free; } ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL); if (!ops) { ret = -ENOMEM; goto out_free; } for (i = 0; i < num_ops; i++) ops[i].priv = new_table; new_table->ops = ops; ret = nf_register_net_hooks(net, ops, num_ops); if (ret != 0) goto out_free; return ret; out_free: __arpt_unregister_table(net, new_table); return ret; } void arpt_unregister_table_pre_exit(struct net *net, const char *name) { struct xt_table *table = xt_find_table(net, NFPROTO_ARP, name); if (table) nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks)); } EXPORT_SYMBOL(arpt_unregister_table_pre_exit); void arpt_unregister_table(struct net *net, const char *name) { struct xt_table *table = xt_find_table(net, NFPROTO_ARP, name); if (table) __arpt_unregister_table(net, table); } /* The built-in targets: standard (NULL) and error. */ static struct xt_target arpt_builtin_tg[] __read_mostly = { { .name = XT_STANDARD_TARGET, .targetsize = sizeof(int), .family = NFPROTO_ARP, #ifdef CONFIG_NETFILTER_XTABLES_COMPAT .compatsize = sizeof(compat_int_t), .compat_from_user = compat_standard_from_user, .compat_to_user = compat_standard_to_user, #endif }, { .name = XT_ERROR_TARGET, .target = arpt_error, .targetsize = XT_FUNCTION_MAXNAMELEN, .family = NFPROTO_ARP, }, }; static struct nf_sockopt_ops arpt_sockopts = { .pf = PF_INET, .set_optmin = ARPT_BASE_CTL, .set_optmax = ARPT_SO_SET_MAX+1, .set = do_arpt_set_ctl, .get_optmin = ARPT_BASE_CTL, .get_optmax = ARPT_SO_GET_MAX+1, .get = do_arpt_get_ctl, .owner = THIS_MODULE, }; static int __net_init arp_tables_net_init(struct net *net) { return xt_proto_init(net, NFPROTO_ARP); } static void __net_exit arp_tables_net_exit(struct net *net) { xt_proto_fini(net, NFPROTO_ARP); } static struct pernet_operations arp_tables_net_ops = { .init = arp_tables_net_init, .exit = arp_tables_net_exit, }; static int __init arp_tables_init(void) { int ret; ret = register_pernet_subsys(&arp_tables_net_ops); if (ret < 0) goto err1; /* No one else will be downing sem now, so we won't sleep */ ret = xt_register_targets(arpt_builtin_tg, ARRAY_SIZE(arpt_builtin_tg)); if (ret < 0) goto err2; /* Register setsockopt */ ret = nf_register_sockopt(&arpt_sockopts); if (ret < 0) goto err4; return 0; err4: xt_unregister_targets(arpt_builtin_tg, ARRAY_SIZE(arpt_builtin_tg)); err2: unregister_pernet_subsys(&arp_tables_net_ops); err1: return ret; } static void __exit arp_tables_fini(void) { nf_unregister_sockopt(&arpt_sockopts); xt_unregister_targets(arpt_builtin_tg, ARRAY_SIZE(arpt_builtin_tg)); unregister_pernet_subsys(&arp_tables_net_ops); } EXPORT_SYMBOL(arpt_register_table); EXPORT_SYMBOL(arpt_unregister_table); EXPORT_SYMBOL(arpt_do_table); module_init(arp_tables_init); module_exit(arp_tables_fini); |
| 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 | // SPDX-License-Identifier: GPL-2.0+ /* * ext4_jbd2.h * * Written by Stephen C. Tweedie <sct@redhat.com>, 1999 * * Copyright 1998--1999 Red Hat corp --- All Rights Reserved * * Ext4-specific journaling extensions. */ #ifndef _EXT4_JBD2_H #define _EXT4_JBD2_H #include <linux/fs.h> #include <linux/jbd2.h> #include "ext4.h" #define EXT4_JOURNAL(inode) (EXT4_SB((inode)->i_sb)->s_journal) /* Define the number of blocks we need to account to a transaction to * modify one block of data. * * We may have to touch one inode, one bitmap buffer, up to three * indirection blocks, the group and superblock summaries, and the data * block to complete the transaction. * * For extents-enabled fs we may have to allocate and modify up to * 5 levels of tree, data block (for each of these we need bitmap + group * summaries), root which is stored in the inode, sb */ #define EXT4_SINGLEDATA_TRANS_BLOCKS(sb) \ (ext4_has_feature_extents(sb) ? 20U : 8U) /* Extended attribute operations touch at most two data buffers, * two bitmap buffers, and two group summaries, in addition to the inode * and the superblock, which are already accounted for. */ #define EXT4_XATTR_TRANS_BLOCKS 6U /* Define the minimum size for a transaction which modifies data. This * needs to take into account the fact that we may end up modifying two * quota files too (one for the group, one for the user quota). The * superblock only gets updated once, of course, so don't bother * counting that again for the quota updates. */ #define EXT4_DATA_TRANS_BLOCKS(sb) (EXT4_SINGLEDATA_TRANS_BLOCKS(sb) + \ EXT4_XATTR_TRANS_BLOCKS - 2 + \ EXT4_MAXQUOTAS_TRANS_BLOCKS(sb)) /* * Define the number of metadata blocks we need to account to modify data. * * This include super block, inode block, quota blocks and xattr blocks */ #define EXT4_META_TRANS_BLOCKS(sb) (EXT4_XATTR_TRANS_BLOCKS + \ EXT4_MAXQUOTAS_TRANS_BLOCKS(sb)) /* Define an arbitrary limit for the amount of data we will anticipate * writing to any given transaction. For unbounded transactions such as * write(2) and truncate(2) we can write more than this, but we always * start off at the maximum transaction size and grow the transaction * optimistically as we go. */ #define EXT4_MAX_TRANS_DATA 64U /* We break up a large truncate or write transaction once the handle's * buffer credits gets this low, we need either to extend the * transaction or to start a new one. Reserve enough space here for * inode, bitmap, superblock, group and indirection updates for at least * one block, plus two quota updates. Quota allocations are not * needed. */ #define EXT4_RESERVE_TRANS_BLOCKS 12U /* * Number of credits needed if we need to insert an entry into a * directory. For each new index block, we need 4 blocks (old index * block, new index block, bitmap block, bg summary). For normal * htree directories there are 2 levels; if the largedir feature * enabled it's 3 levels. */ #define EXT4_INDEX_EXTRA_TRANS_BLOCKS 12U #ifdef CONFIG_QUOTA /* Amount of blocks needed for quota update - we know that the structure was * allocated so we need to update only data block */ #define EXT4_QUOTA_TRANS_BLOCKS(sb) ((ext4_quota_capable(sb)) ? 1 : 0) /* Amount of blocks needed for quota insert/delete - we do some block writes * but inode, sb and group updates are done only once */ #define EXT4_QUOTA_INIT_BLOCKS(sb) ((ext4_quota_capable(sb)) ?\ (DQUOT_INIT_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\ +3+DQUOT_INIT_REWRITE) : 0) #define EXT4_QUOTA_DEL_BLOCKS(sb) ((ext4_quota_capable(sb)) ?\ (DQUOT_DEL_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\ +3+DQUOT_DEL_REWRITE) : 0) #else #define EXT4_QUOTA_TRANS_BLOCKS(sb) 0 #define EXT4_QUOTA_INIT_BLOCKS(sb) 0 #define EXT4_QUOTA_DEL_BLOCKS(sb) 0 #endif #define EXT4_MAXQUOTAS_TRANS_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_TRANS_BLOCKS(sb)) #define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb)) #define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb)) /* * Ext4 handle operation types -- for logging purposes */ #define EXT4_HT_MISC 0 #define EXT4_HT_INODE 1 #define EXT4_HT_WRITE_PAGE 2 #define EXT4_HT_MAP_BLOCKS 3 #define EXT4_HT_DIR 4 #define EXT4_HT_TRUNCATE 5 #define EXT4_HT_QUOTA 6 #define EXT4_HT_RESIZE 7 #define EXT4_HT_MIGRATE 8 #define EXT4_HT_MOVE_EXTENTS 9 #define EXT4_HT_XATTR 10 #define EXT4_HT_EXT_CONVERT 11 #define EXT4_HT_MAX 12 /** * struct ext4_journal_cb_entry - Base structure for callback information. * * This struct is a 'seed' structure for a using with your own callback * structs. If you are using callbacks you must allocate one of these * or another struct of your own definition which has this struct * as it's first element and pass it to ext4_journal_callback_add(). */ struct ext4_journal_cb_entry { /* list information for other callbacks attached to the same handle */ struct list_head jce_list; /* Function to call with this callback structure */ void (*jce_func)(struct super_block *sb, struct ext4_journal_cb_entry *jce, int error); /* user data goes here */ }; /** * ext4_journal_callback_add: add a function to call after transaction commit * @handle: active journal transaction handle to register callback on * @func: callback function to call after the transaction has committed: * @sb: superblock of current filesystem for transaction * @jce: returned journal callback data * @rc: journal state at commit (0 = transaction committed properly) * @jce: journal callback data (internal and function private data struct) * * The registered function will be called in the context of the journal thread * after the transaction for which the handle was created has completed. * * No locks are held when the callback function is called, so it is safe to * call blocking functions from within the callback, but the callback should * not block or run for too long, or the filesystem will be blocked waiting for * the next transaction to commit. No journaling functions can be used, or * there is a risk of deadlock. * * There is no guaranteed calling order of multiple registered callbacks on * the same transaction. */ static inline void _ext4_journal_callback_add(handle_t *handle, struct ext4_journal_cb_entry *jce) { /* Add the jce to transaction's private list */ list_add_tail(&jce->jce_list, &handle->h_transaction->t_private_list); } static inline void ext4_journal_callback_add(handle_t *handle, void (*func)(struct super_block *sb, struct ext4_journal_cb_entry *jce, int rc), struct ext4_journal_cb_entry *jce) { struct ext4_sb_info *sbi = EXT4_SB(handle->h_transaction->t_journal->j_private); /* Add the jce to transaction's private list */ jce->jce_func = func; spin_lock(&sbi->s_md_lock); _ext4_journal_callback_add(handle, jce); spin_unlock(&sbi->s_md_lock); } /** * ext4_journal_callback_del: delete a registered callback * @handle: active journal transaction handle on which callback was registered * @jce: registered journal callback entry to unregister * Return true if object was successfully removed */ static inline bool ext4_journal_callback_try_del(handle_t *handle, struct ext4_journal_cb_entry *jce) { bool deleted; struct ext4_sb_info *sbi = EXT4_SB(handle->h_transaction->t_journal->j_private); spin_lock(&sbi->s_md_lock); deleted = !list_empty(&jce->jce_list); list_del_init(&jce->jce_list); spin_unlock(&sbi->s_md_lock); return deleted; } int ext4_mark_iloc_dirty(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc); /* * On success, We end up with an outstanding reference count against * iloc->bh. This _must_ be cleaned up later. */ int ext4_reserve_inode_write(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc); #define ext4_mark_inode_dirty(__h, __i) \ __ext4_mark_inode_dirty((__h), (__i), __func__, __LINE__) int __ext4_mark_inode_dirty(handle_t *handle, struct inode *inode, const char *func, unsigned int line); int ext4_expand_extra_isize(struct inode *inode, unsigned int new_extra_isize, struct ext4_iloc *iloc); /* * Wrapper functions with which ext4 calls into JBD. */ int __ext4_journal_get_write_access(const char *where, unsigned int line, handle_t *handle, struct super_block *sb, struct buffer_head *bh, enum ext4_journal_trigger_type trigger_type); int __ext4_forget(const char *where, unsigned int line, handle_t *handle, int is_metadata, struct inode *inode, struct buffer_head *bh, ext4_fsblk_t blocknr); int __ext4_journal_get_create_access(const char *where, unsigned int line, handle_t *handle, struct super_block *sb, struct buffer_head *bh, enum ext4_journal_trigger_type trigger_type); int __ext4_handle_dirty_metadata(const char *where, unsigned int line, handle_t *handle, struct inode *inode, struct buffer_head *bh); #define ext4_journal_get_write_access(handle, sb, bh, trigger_type) \ __ext4_journal_get_write_access(__func__, __LINE__, (handle), (sb), \ (bh), (trigger_type)) #define ext4_forget(handle, is_metadata, inode, bh, block_nr) \ __ext4_forget(__func__, __LINE__, (handle), (is_metadata), (inode), \ (bh), (block_nr)) #define ext4_journal_get_create_access(handle, sb, bh, trigger_type) \ __ext4_journal_get_create_access(__func__, __LINE__, (handle), (sb), \ (bh), (trigger_type)) #define ext4_handle_dirty_metadata(handle, inode, bh) \ __ext4_handle_dirty_metadata(__func__, __LINE__, (handle), (inode), \ (bh)) handle_t *__ext4_journal_start_sb(struct inode *inode, struct super_block *sb, unsigned int line, int type, int blocks, int rsv_blocks, int revoke_creds); int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle); #define EXT4_NOJOURNAL_MAX_REF_COUNT ((unsigned long) 4096) /* Note: Do not use this for NULL handles. This is only to determine if * a properly allocated handle is using a journal or not. */ static inline int ext4_handle_valid(handle_t *handle) { if ((unsigned long)handle < EXT4_NOJOURNAL_MAX_REF_COUNT) return 0; return 1; } static inline void ext4_handle_sync(handle_t *handle) { if (ext4_handle_valid(handle)) handle->h_sync = 1; } static inline int ext4_handle_is_aborted(handle_t *handle) { if (ext4_handle_valid(handle)) return is_handle_aborted(handle); return 0; } static inline int ext4_free_metadata_revoke_credits(struct super_block *sb, int blocks) { /* Freeing each metadata block can result in freeing one cluster */ return blocks * EXT4_SB(sb)->s_cluster_ratio; } static inline int ext4_trans_default_revoke_credits(struct super_block *sb) { return ext4_free_metadata_revoke_credits(sb, 8); } #define ext4_journal_start_sb(sb, type, nblocks) \ __ext4_journal_start_sb(NULL, (sb), __LINE__, (type), (nblocks), 0,\ ext4_trans_default_revoke_credits(sb)) #define ext4_journal_start(inode, type, nblocks) \ __ext4_journal_start((inode), __LINE__, (type), (nblocks), 0, \ ext4_trans_default_revoke_credits((inode)->i_sb)) #define ext4_journal_start_with_reserve(inode, type, blocks, rsv_blocks)\ __ext4_journal_start((inode), __LINE__, (type), (blocks), (rsv_blocks),\ ext4_trans_default_revoke_credits((inode)->i_sb)) #define ext4_journal_start_with_revoke(inode, type, blocks, revoke_creds) \ __ext4_journal_start((inode), __LINE__, (type), (blocks), 0, \ (revoke_creds)) static inline handle_t *__ext4_journal_start(struct inode *inode, unsigned int line, int type, int blocks, int rsv_blocks, int revoke_creds) { return __ext4_journal_start_sb(inode, inode->i_sb, line, type, blocks, rsv_blocks, revoke_creds); } #define ext4_journal_stop(handle) \ __ext4_journal_stop(__func__, __LINE__, (handle)) #define ext4_journal_start_reserved(handle, type) \ __ext4_journal_start_reserved((handle), __LINE__, (type)) handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line, int type); static inline handle_t *ext4_journal_current_handle(void) { return journal_current_handle(); } static inline int ext4_journal_extend(handle_t *handle, int nblocks, int revoke) { if (ext4_handle_valid(handle)) return jbd2_journal_extend(handle, nblocks, revoke); return 0; } static inline int ext4_journal_restart(handle_t *handle, int nblocks, int revoke) { if (ext4_handle_valid(handle)) return jbd2__journal_restart(handle, nblocks, revoke, GFP_NOFS); return 0; } int __ext4_journal_ensure_credits(handle_t *handle, int check_cred, int extend_cred, int revoke_cred); /* * Ensure @handle has at least @check_creds credits available. If not, * transaction will be extended or restarted to contain at least @extend_cred * credits. Before restarting transaction @fn is executed to allow for cleanup * before the transaction is restarted. * * The return value is < 0 in case of error, 0 in case the handle has enough * credits or transaction extension succeeded, 1 in case transaction had to be * restarted. */ #define ext4_journal_ensure_credits_fn(handle, check_cred, extend_cred, \ revoke_cred, fn) \ ({ \ __label__ __ensure_end; \ int err = __ext4_journal_ensure_credits((handle), (check_cred), \ (extend_cred), (revoke_cred)); \ \ if (err <= 0) \ goto __ensure_end; \ err = (fn); \ if (err < 0) \ goto __ensure_end; \ err = ext4_journal_restart((handle), (extend_cred), (revoke_cred)); \ if (err == 0) \ err = 1; \ __ensure_end: \ err; \ }) /* * Ensure given handle has at least requested amount of credits available, * possibly restarting transaction if needed. We also make sure the transaction * has space for at least ext4_trans_default_revoke_credits(sb) revoke records * as freeing one or two blocks is very common pattern and requesting this is * very cheap. */ static inline int ext4_journal_ensure_credits(handle_t *handle, int credits, int revoke_creds) { return ext4_journal_ensure_credits_fn(handle, credits, credits, revoke_creds, 0); } static inline int ext4_journal_blocks_per_page(struct inode *inode) { if (EXT4_JOURNAL(inode) != NULL) return jbd2_journal_blocks_per_page(inode); return 0; } static inline int ext4_journal_force_commit(journal_t *journal) { if (journal) return jbd2_journal_force_commit(journal); return 0; } static inline int ext4_jbd2_inode_add_write(handle_t *handle, struct inode *inode, loff_t start_byte, loff_t length) { if (ext4_handle_valid(handle)) return jbd2_journal_inode_ranged_write(handle, EXT4_I(inode)->jinode, start_byte, length); return 0; } static inline int ext4_jbd2_inode_add_wait(handle_t *handle, struct inode *inode, loff_t start_byte, loff_t length) { if (ext4_handle_valid(handle)) return jbd2_journal_inode_ranged_wait(handle, EXT4_I(inode)->jinode, start_byte, length); return 0; } static inline void ext4_update_inode_fsync_trans(handle_t *handle, struct inode *inode, int datasync) { struct ext4_inode_info *ei = EXT4_I(inode); if (ext4_handle_valid(handle) && !is_handle_aborted(handle)) { ei->i_sync_tid = handle->h_transaction->t_tid; if (datasync) ei->i_datasync_tid = handle->h_transaction->t_tid; } } /* super.c */ int ext4_force_commit(struct super_block *sb); /* * Ext4 inode journal modes */ #define EXT4_INODE_JOURNAL_DATA_MODE 0x01 /* journal data mode */ #define EXT4_INODE_ORDERED_DATA_MODE 0x02 /* ordered data mode */ #define EXT4_INODE_WRITEBACK_DATA_MODE 0x04 /* writeback data mode */ int ext4_inode_journal_mode(struct inode *inode); static inline int ext4_should_journal_data(struct inode *inode) { return ext4_inode_journal_mode(inode) & EXT4_INODE_JOURNAL_DATA_MODE; } static inline int ext4_should_order_data(struct inode *inode) { return ext4_inode_journal_mode(inode) & EXT4_INODE_ORDERED_DATA_MODE; } static inline int ext4_should_writeback_data(struct inode *inode) { return ext4_inode_journal_mode(inode) & EXT4_INODE_WRITEBACK_DATA_MODE; } static inline int ext4_free_data_revoke_credits(struct inode *inode, int blocks) { if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) return 0; if (!ext4_should_journal_data(inode)) return 0; /* * Data blocks in one extent are contiguous, just account for partial * clusters at extent boundaries */ return blocks + 2*(EXT4_SB(inode->i_sb)->s_cluster_ratio - 1); } /* * This function controls whether or not we should try to go down the * dioread_nolock code paths, which makes it safe to avoid taking * i_rwsem for direct I/O reads. This only works for extent-based * files, and it doesn't work if data journaling is enabled, since the * dioread_nolock code uses b_private to pass information back to the * I/O completion handler, and this conflicts with the jbd's use of * b_private. */ static inline int ext4_should_dioread_nolock(struct inode *inode) { if (!test_opt(inode->i_sb, DIOREAD_NOLOCK)) return 0; if (!S_ISREG(inode->i_mode)) return 0; if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) return 0; if (ext4_should_journal_data(inode)) return 0; /* temporary fix to prevent generic/422 test failures */ if (!test_opt(inode->i_sb, DELALLOC)) return 0; return 1; } #endif /* _EXT4_JBD2_H */ |
| 5 5 5 5 5 5 5 5 5 5 5 5 5 4 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 16 16 16 17 17 17 16 10 6 16 15 6 16 16 16 7 5 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * AppArmor security module * * This file contains AppArmor label definitions * * Copyright 2017 Canonical Ltd. */ #include <linux/audit.h> #include <linux/seq_file.h> #include <linux/sort.h> #include "include/apparmor.h" #include "include/cred.h" #include "include/label.h" #include "include/policy.h" #include "include/secid.h" /* * the aa_label represents the set of profiles confining an object * * Labels maintain a reference count to the set of pointers they reference * Labels are ref counted by * tasks and object via the security field/security context off the field * code - will take a ref count on a label if it needs the label * beyond what is possible with an rcu_read_lock. * profiles - each profile is a label * secids - a pinned secid will keep a refcount of the label it is * referencing * objects - inode, files, sockets, ... * * Labels are not ref counted by the label set, so they maybe removed and * freed when no longer in use. * */ #define PROXY_POISON 97 #define LABEL_POISON 100 static void free_proxy(struct aa_proxy *proxy) { if (proxy) { /* p->label will not updated any more as p is dead */ aa_put_label(rcu_dereference_protected(proxy->label, true)); memset(proxy, 0, sizeof(*proxy)); RCU_INIT_POINTER(proxy->label, (struct aa_label *)PROXY_POISON); kfree(proxy); } } void aa_proxy_kref(struct kref *kref) { struct aa_proxy *proxy = container_of(kref, struct aa_proxy, count); free_proxy(proxy); } struct aa_proxy *aa_alloc_proxy(struct aa_label *label, gfp_t gfp) { struct aa_proxy *new; new = kzalloc(sizeof(struct aa_proxy), gfp); if (new) { kref_init(&new->count); rcu_assign_pointer(new->label, aa_get_label(label)); } return new; } /* requires profile list write lock held */ void __aa_proxy_redirect(struct aa_label *orig, struct aa_label *new) { struct aa_label *tmp; AA_BUG(!orig); AA_BUG(!new); lockdep_assert_held_write(&labels_set(orig)->lock); tmp = rcu_dereference_protected(orig->proxy->label, &labels_ns(orig)->lock); rcu_assign_pointer(orig->proxy->label, aa_get_label(new)); orig->flags |= FLAG_STALE; aa_put_label(tmp); } static void __proxy_share(struct aa_label *old, struct aa_label *new) { struct aa_proxy *proxy = new->proxy; new->proxy = aa_get_proxy(old->proxy); __aa_proxy_redirect(old, new); aa_put_proxy(proxy); } /** * ns_cmp - compare ns for label set ordering * @a: ns to compare (NOT NULL) * @b: ns to compare (NOT NULL) * * Returns: <0 if a < b * ==0 if a == b * >0 if a > b */ static int ns_cmp(struct aa_ns *a, struct aa_ns *b) { int res; AA_BUG(!a); AA_BUG(!b); AA_BUG(!a->base.hname); AA_BUG(!b->base.hname); if (a == b) return 0; res = a->level - b->level; if (res) return res; return strcmp(a->base.hname, b->base.hname); } /** * profile_cmp - profile comparison for set ordering * @a: profile to compare (NOT NULL) * @b: profile to compare (NOT NULL) * * Returns: <0 if a < b * ==0 if a == b * >0 if a > b */ static int profile_cmp(struct aa_profile *a, struct aa_profile *b) { int res; AA_BUG(!a); AA_BUG(!b); AA_BUG(!a->ns); AA_BUG(!b->ns); AA_BUG(!a->base.hname); AA_BUG(!b->base.hname); if (a == b || a->base.hname == b->base.hname) return 0; res = ns_cmp(a->ns, b->ns); if (res) return res; return strcmp(a->base.hname, b->base.hname); } /** * vec_cmp - label comparison for set ordering * @a: aa_profile to compare (NOT NULL) * @an: length of @a * @b: aa_profile to compare (NOT NULL) * @bn: length of @b * * Returns: <0 if @a < @b * ==0 if @a == @b * >0 if @a > @b */ static int vec_cmp(struct aa_profile **a, int an, struct aa_profile **b, int bn) { int i; AA_BUG(!a); AA_BUG(!*a); AA_BUG(!b); AA_BUG(!*b); AA_BUG(an <= 0); AA_BUG(bn <= 0); for (i = 0; i < an && i < bn; i++) { int res = profile_cmp(a[i], b[i]); if (res != 0) return res; } return an - bn; } static bool vec_is_stale(struct aa_profile **vec, int n) { int i; AA_BUG(!vec); for (i = 0; i < n; i++) { if (profile_is_stale(vec[i])) return true; } return false; } static long accum_vec_flags(struct aa_profile **vec, int n) { long u = FLAG_UNCONFINED; int i; AA_BUG(!vec); for (i = 0; i < n; i++) { u |= vec[i]->label.flags & (FLAG_DEBUG1 | FLAG_DEBUG2 | FLAG_STALE); if (!(u & vec[i]->label.flags & FLAG_UNCONFINED)) u &= ~FLAG_UNCONFINED; } return u; } static int sort_cmp(const void *a, const void *b) { return profile_cmp(*(struct aa_profile **)a, *(struct aa_profile **)b); } /* * assumes vec is sorted * Assumes @vec has null terminator at vec[n], and will null terminate * vec[n - dups] */ static inline int unique(struct aa_profile **vec, int n) { int i, pos, dups = 0; AA_BUG(n < 1); AA_BUG(!vec); pos = 0; for (i = 1; i < n; i++) { int res = profile_cmp(vec[pos], vec[i]); AA_BUG(res > 0, "vec not sorted"); if (res == 0) { /* drop duplicate */ aa_put_profile(vec[i]); dups++; continue; } pos++; if (dups) vec[pos] = vec[i]; } AA_BUG(dups < 0); return dups; } /** * aa_vec_unique - canonical sort and unique a list of profiles * @n: number of refcounted profiles in the list (@n > 0) * @vec: list of profiles to sort and merge * @flags: null terminator flags of @vec * * Returns: the number of duplicates eliminated == references put * * If @flags & VEC_FLAG_TERMINATE @vec has null terminator at vec[n], and will * null terminate vec[n - dups] */ int aa_vec_unique(struct aa_profile **vec, int n, int flags) { int i, dups = 0; AA_BUG(n < 1); AA_BUG(!vec); /* vecs are usually small and inorder, have a fallback for larger */ if (n > 8) { sort(vec, n, sizeof(struct aa_profile *), sort_cmp, NULL); dups = unique(vec, n); goto out; } /* insertion sort + unique in one */ for (i = 1; i < n; i++) { struct aa_profile *tmp = vec[i]; int pos, j; for (pos = i - 1 - dups; pos >= 0; pos--) { int res = profile_cmp(vec[pos], tmp); if (res == 0) { /* drop duplicate entry */ aa_put_profile(tmp); dups++; goto continue_outer; } else if (res < 0) break; } /* pos is at entry < tmp, or index -1. Set to insert pos */ pos++; for (j = i - dups; j > pos; j--) vec[j] = vec[j - 1]; vec[pos] = tmp; continue_outer: ; } AA_BUG(dups < 0); out: if (flags & VEC_FLAG_TERMINATE) vec[n - dups] = NULL; return dups; } void aa_label_destroy(struct aa_label *label) { AA_BUG(!label); if (!label_isprofile(label)) { struct aa_profile *profile; struct label_it i; aa_put_str(label->hname); label_for_each(i, label, profile) { aa_put_profile(profile); label->vec[i.i] = (struct aa_profile *) (LABEL_POISON + (long) i.i); } } if (label->proxy) { if (rcu_dereference_protected(label->proxy->label, true) == label) rcu_assign_pointer(label->proxy->label, NULL); aa_put_proxy(label->proxy); } aa_free_secid(label->secid); label->proxy = (struct aa_proxy *) PROXY_POISON + 1; } void aa_label_free(struct aa_label *label) { if (!label) return; aa_label_destroy(label); kfree(label); } static void label_free_switch(struct aa_label *label) { if (label->flags & FLAG_NS_COUNT) aa_free_ns(labels_ns(label)); else if (label_isprofile(label)) aa_free_profile(labels_profile(label)); else aa_label_free(label); } static void label_free_rcu(struct rcu_head *head) { struct aa_label *label = container_of(head, struct aa_label, rcu); if (label->flags & FLAG_IN_TREE) (void) aa_label_remove(label); label_free_switch(label); } void aa_label_kref(struct kref *kref) { struct aa_label *label = container_of(kref, struct aa_label, count); struct aa_ns *ns = labels_ns(label); if (!ns) { /* never live, no rcu callback needed, just using the fn */ label_free_switch(label); return; } /* TODO: update labels_profile macro so it works here */ AA_BUG(label_isprofile(label) && on_list_rcu(&label->vec[0]->base.profiles)); AA_BUG(label_isprofile(label) && on_list_rcu(&label->vec[0]->base.list)); /* TODO: if compound label and not stale add to reclaim cache */ call_rcu(&label->rcu, label_free_rcu); } static void label_free_or_put_new(struct aa_label *label, struct aa_label *new) { if (label != new) /* need to free directly to break circular ref with proxy */ aa_label_free(new); else aa_put_label(new); } bool aa_label_init(struct aa_label *label, int size, gfp_t gfp) { AA_BUG(!label); AA_BUG(size < 1); if (aa_alloc_secid(label, gfp) < 0) return false; label->size = size; /* doesn't include null */ label->vec[size] = NULL; /* null terminate */ kref_init(&label->count); RB_CLEAR_NODE(&label->node); return true; } /** * aa_label_alloc - allocate a label with a profile vector of @size length * @size: size of profile vector in the label * @proxy: proxy to use OR null if to allocate a new one * @gfp: memory allocation type * * Returns: new label * else NULL if failed */ struct aa_label *aa_label_alloc(int size, struct aa_proxy *proxy, gfp_t gfp) { struct aa_label *new; AA_BUG(size < 1); /* + 1 for null terminator entry on vec */ new = kzalloc(struct_size(new, vec, size + 1), gfp); AA_DEBUG("%s (%p)\n", __func__, new); if (!new) goto fail; if (!aa_label_init(new, size, gfp)) goto fail; if (!proxy) { proxy = aa_alloc_proxy(new, gfp); if (!proxy) goto fail; } else aa_get_proxy(proxy); /* just set new's proxy, don't redirect proxy here if it was passed in*/ new->proxy = proxy; return new; fail: kfree(new); return NULL; } /** * label_cmp - label comparison for set ordering * @a: label to compare (NOT NULL) * @b: label to compare (NOT NULL) * * Returns: <0 if a < b * ==0 if a == b * >0 if a > b */ static int label_cmp(struct aa_label *a, struct aa_label *b) { AA_BUG(!b); if (a == b) return 0; return vec_cmp(a->vec, a->size, b->vec, b->size); } /* helper fn for label_for_each_confined */ int aa_label_next_confined(struct aa_label *label, int i) { AA_BUG(!label); AA_BUG(i < 0); for (; i < label->size; i++) { if (!profile_unconfined(label->vec[i])) return i; } return i; } /** * __aa_label_next_not_in_set - return the next profile of @sub not in @set * @I: label iterator * @set: label to test against * @sub: label to if is subset of @set * * Returns: profile in @sub that is not in @set, with iterator set pos after * else NULL if @sub is a subset of @set */ struct aa_profile *__aa_label_next_not_in_set(struct label_it *I, struct aa_label *set, struct aa_label *sub) { AA_BUG(!set); AA_BUG(!I); AA_BUG(I->i < 0); AA_BUG(I->i > set->size); AA_BUG(!sub); AA_BUG(I->j < 0); AA_BUG(I->j > sub->size); while (I->j < sub->size && I->i < set->size) { int res = profile_cmp(sub->vec[I->j], set->vec[I->i]); if (res == 0) { (I->j)++; (I->i)++; } else if (res > 0) (I->i)++; else return sub->vec[(I->j)++]; } if (I->j < sub->size) return sub->vec[(I->j)++]; return NULL; } /** * aa_label_is_subset - test if @sub is a subset of @set * @set: label to test against * @sub: label to test if is subset of @set * * Returns: true if @sub is subset of @set * else false */ bool aa_label_is_subset(struct aa_label *set, struct aa_label *sub) { struct label_it i = { }; AA_BUG(!set); AA_BUG(!sub); if (sub == set) return true; return __aa_label_next_not_in_set(&i, set, sub) == NULL; } /** * aa_label_is_unconfined_subset - test if @sub is a subset of @set * @set: label to test against * @sub: label to test if is subset of @set * * This checks for subset but taking into account unconfined. IF * @sub contains an unconfined profile that does not have a matching * unconfined in @set then this will not cause the test to fail. * Conversely we don't care about an unconfined in @set that is not in * @sub * * Returns: true if @sub is special_subset of @set * else false */ bool aa_label_is_unconfined_subset(struct aa_label *set, struct aa_label *sub) { struct label_it i = { }; struct aa_profile *p; AA_BUG(!set); AA_BUG(!sub); if (sub == set) return true; do { p = __aa_label_next_not_in_set(&i, set, sub); if (p && !profile_unconfined(p)) break; } while (p); return p == NULL; } /** * __label_remove - remove @label from the label set * @label: label to remove * @new: label to redirect to * * Requires: labels_set(@label)->lock write_lock * Returns: true if the label was in the tree and removed */ static bool __label_remove(struct aa_label *label, struct aa_label *new) { struct aa_labelset *ls = labels_set(label); AA_BUG(!ls); AA_BUG(!label); lockdep_assert_held_write(&ls->lock); if (new) __aa_proxy_redirect(label, new); if (!label_is_stale(label)) __label_make_stale(label); if (label->flags & FLAG_IN_TREE) { rb_erase(&label->node, &ls->root); label->flags &= ~FLAG_IN_TREE; return true; } return false; } /** * __label_replace - replace @old with @new in label set * @old: label to remove from label set * @new: label to replace @old with * * Requires: labels_set(@old)->lock write_lock * valid ref count be held on @new * Returns: true if @old was in set and replaced by @new * * Note: current implementation requires label set be order in such a way * that @new directly replaces @old position in the set (ie. * using pointer comparison of the label address would not work) */ static bool __label_replace(struct aa_label *old, struct aa_label *new) { struct aa_labelset *ls = labels_set(old); AA_BUG(!ls); AA_BUG(!old); AA_BUG(!new); lockdep_assert_held_write(&ls->lock); AA_BUG(new->flags & FLAG_IN_TREE); if (!label_is_stale(old)) __label_make_stale(old); if (old->flags & FLAG_IN_TREE) { rb_replace_node(&old->node, &new->node, &ls->root); old->flags &= ~FLAG_IN_TREE; new->flags |= FLAG_IN_TREE; return true; } return false; } /** * __label_insert - attempt to insert @l into a label set * @ls: set of labels to insert @l into (NOT NULL) * @label: new label to insert (NOT NULL) * @replace: whether insertion should replace existing entry that is not stale * * Requires: @ls->lock * caller to hold a valid ref on l * if @replace is true l has a preallocated proxy associated * Returns: @l if successful in inserting @l - with additional refcount * else ref counted equivalent label that is already in the set, * the else condition only happens if @replace is false */ static struct aa_label *__label_insert(struct aa_labelset *ls, struct aa_label *label, bool replace) { struct rb_node **new, *parent = NULL; AA_BUG(!ls); AA_BUG(!label); AA_BUG(labels_set(label) != ls); lockdep_assert_held_write(&ls->lock); AA_BUG(label->flags & FLAG_IN_TREE); /* Figure out where to put new node */ new = &ls->root.rb_node; while (*new) { struct aa_label *this = rb_entry(*new, struct aa_label, node); int result = label_cmp(label, this); parent = *new; if (result == 0) { /* !__aa_get_label means queued for destruction, * so replace in place, however the label has * died before the replacement so do not share * the proxy */ if (!replace && !label_is_stale(this)) { if (__aa_get_label(this)) return this; } else __proxy_share(this, label); AA_BUG(!__label_replace(this, label)); return aa_get_label(label); } else if (result < 0) new = &((*new)->rb_left); else /* (result > 0) */ new = &((*new)->rb_right); } /* Add new node and rebalance tree. */ rb_link_node(&label->node, parent, new); rb_insert_color(&label->node, &ls->root); label->flags |= FLAG_IN_TREE; return aa_get_label(label); } /** * __vec_find - find label that matches @vec in label set * @vec: vec of profiles to find matching label for (NOT NULL) * @n: length of @vec * * Requires: @vec_labelset(vec) lock held * caller to hold a valid ref on l * * Returns: ref counted @label if matching label is in tree * ref counted label that is equiv to @l in tree * else NULL if @vec equiv is not in tree */ static struct aa_label *__vec_find(struct aa_profile **vec, int n) { struct rb_node *node; AA_BUG(!vec); AA_BUG(!*vec); AA_BUG(n <= 0); node = vec_labelset(vec, n)->root.rb_node; while (node) { struct aa_label *this = rb_entry(node, struct aa_label, node); int result = vec_cmp(this->vec, this->size, vec, n); if (result > 0) node = node->rb_left; else if (result < 0) node = node->rb_right; else return __aa_get_label(this); } return NULL; } /** * __label_find - find label @label in label set * @label: label to find (NOT NULL) * * Requires: labels_set(@label)->lock held * caller to hold a valid ref on l * * Returns: ref counted @label if @label is in tree OR * ref counted label that is equiv to @label in tree * else NULL if @label or equiv is not in tree */ static struct aa_label *__label_find(struct aa_label *label) { AA_BUG(!label); return __vec_find(label->vec, label->size); } /** * aa_label_remove - remove a label from the labelset * @label: label to remove * * Returns: true if @label was removed from the tree * else @label was not in tree so it could not be removed */ bool aa_label_remove(struct aa_label *label) { struct aa_labelset *ls = labels_set(label); unsigned long flags; bool res; AA_BUG(!ls); write_lock_irqsave(&ls->lock, flags); res = __label_remove(label, ns_unconfined(labels_ns(label))); write_unlock_irqrestore(&ls->lock, flags); return res; } /** * aa_label_replace - replace a label @old with a new version @new * @old: label to replace * @new: label replacing @old * * Returns: true if @old was in tree and replaced * else @old was not in tree, and @new was not inserted */ bool aa_label_replace(struct aa_label *old, struct aa_label *new) { unsigned long flags; bool res; if (name_is_shared(old, new) && labels_ns(old) == labels_ns(new)) { write_lock_irqsave(&labels_set(old)->lock, flags); if (old->proxy != new->proxy) __proxy_share(old, new); else __aa_proxy_redirect(old, new); res = __label_replace(old, new); write_unlock_irqrestore(&labels_set(old)->lock, flags); } else { struct aa_label *l; struct aa_labelset *ls = labels_set(old); write_lock_irqsave(&ls->lock, flags); res = __label_remove(old, new); if (labels_ns(old) != labels_ns(new)) { write_unlock_irqrestore(&ls->lock, flags); ls = labels_set(new); write_lock_irqsave(&ls->lock, flags); } l = __label_insert(ls, new, true); res = (l == new); write_unlock_irqrestore(&ls->lock, flags); aa_put_label(l); } return res; } /** * vec_find - find label @l in label set * @vec: array of profiles to find equiv label for (NOT NULL) * @n: length of @vec * * Returns: refcounted label if @vec equiv is in tree * else NULL if @vec equiv is not in tree */ static struct aa_label *vec_find(struct aa_profile **vec, int n) { struct aa_labelset *ls; struct aa_label *label; unsigned long flags; AA_BUG(!vec); AA_BUG(!*vec); AA_BUG(n <= 0); ls = vec_labelset(vec, n); read_lock_irqsave(&ls->lock, flags); label = __vec_find(vec, n); read_unlock_irqrestore(&ls->lock, flags); return label; } /* requires sort and merge done first */ static struct aa_label *vec_create_and_insert_label(struct aa_profile **vec, int len, gfp_t gfp) { struct aa_label *label = NULL; struct aa_labelset *ls; unsigned long flags; struct aa_label *new; int i; AA_BUG(!vec); if (len == 1) return aa_get_label(&vec[0]->label); ls = labels_set(&vec[len - 1]->label); /* TODO: enable when read side is lockless * check if label exists before taking locks */ new = aa_label_alloc(len, NULL, gfp); if (!new) return NULL; for (i = 0; i < len; i++) new->vec[i] = aa_get_profile(vec[i]); write_lock_irqsave(&ls->lock, flags); label = __label_insert(ls, new, false); write_unlock_irqrestore(&ls->lock, flags); label_free_or_put_new(label, new); return label; } struct aa_label *aa_vec_find_or_create_label(struct aa_profile **vec, int len, gfp_t gfp) { struct aa_label *label = vec_find(vec, len); if (label) return label; return vec_create_and_insert_label(vec, len, gfp); } /** * aa_label_insert - insert label @label into @ls or return existing label * @ls: labelset to insert @label into * @label: label to insert * * Requires: caller to hold a valid ref on @label * * Returns: ref counted @label if successful in inserting @label * else ref counted equivalent label that is already in the set */ struct aa_label *aa_label_insert(struct aa_labelset *ls, struct aa_label *label) { struct aa_label *l; unsigned long flags; AA_BUG(!ls); AA_BUG(!label); /* check if label exists before taking lock */ if (!label_is_stale(label)) { read_lock_irqsave(&ls->lock, flags); l = __label_find(label); read_unlock_irqrestore(&ls->lock, flags); if (l) return l; } write_lock_irqsave(&ls->lock, flags); l = __label_insert(ls, label, false); write_unlock_irqrestore(&ls->lock, flags); return l; } /** * aa_label_next_in_merge - find the next profile when merging @a and @b * @I: label iterator * @a: label to merge * @b: label to merge * * Returns: next profile * else null if no more profiles */ struct aa_profile *aa_label_next_in_merge(struct label_it *I, struct aa_label *a, struct aa_label *b) { AA_BUG(!a); AA_BUG(!b); AA_BUG(!I); AA_BUG(I->i < 0); AA_BUG(I->i > a->size); AA_BUG(I->j < 0); AA_BUG(I->j > b->size); if (I->i < a->size) { if (I->j < b->size) { int res = profile_cmp(a->vec[I->i], b->vec[I->j]); if (res > 0) return b->vec[(I->j)++]; if (res == 0) (I->j)++; } return a->vec[(I->i)++]; } if (I->j < b->size) return b->vec[(I->j)++]; return NULL; } /** * label_merge_cmp - cmp of @a merging with @b against @z for set ordering * @a: label to merge then compare (NOT NULL) * @b: label to merge then compare (NOT NULL) * @z: label to compare merge against (NOT NULL) * * Assumes: using the most recent versions of @a, @b, and @z * * Returns: <0 if a < b * ==0 if a == b * >0 if a > b */ static int label_merge_cmp(struct aa_label *a, struct aa_label *b, struct aa_label *z) { struct aa_profile *p = NULL; struct label_it i = { }; int k; AA_BUG(!a); AA_BUG(!b); AA_BUG(!z); for (k = 0; k < z->size && (p = aa_label_next_in_merge(&i, a, b)); k++) { int res = profile_cmp(p, z->vec[k]); if (res != 0) return res; } if (p) return 1; else if (k < z->size) return -1; return 0; } /** * label_merge_insert - create a new label by merging @a and @b * @new: preallocated label to merge into (NOT NULL) * @a: label to merge with @b (NOT NULL) * @b: label to merge with @a (NOT NULL) * * Requires: preallocated proxy * * Returns: ref counted label either @new if merge is unique * @a if @b is a subset of @a * @b if @a is a subset of @b * * NOTE: will not use @new if the merge results in @new == @a or @b * * Must be used within labelset write lock to avoid racing with * setting labels stale. */ static struct aa_label *label_merge_insert(struct aa_label *new, struct aa_label *a, struct aa_label *b) { struct aa_label *label; struct aa_labelset *ls; struct aa_profile *next; struct label_it i; unsigned long flags; int k = 0, invcount = 0; bool stale = false; AA_BUG(!a); AA_BUG(a->size < 0); AA_BUG(!b); AA_BUG(b->size < 0); AA_BUG(!new); AA_BUG(new->size < a->size + b->size); label_for_each_in_merge(i, a, b, next) { AA_BUG(!next); if (profile_is_stale(next)) { new->vec[k] = aa_get_newest_profile(next); AA_BUG(!new->vec[k]->label.proxy); AA_BUG(!new->vec[k]->label.proxy->label); if (next->label.proxy != new->vec[k]->label.proxy) invcount++; k++; stale = true; } else new->vec[k++] = aa_get_profile(next); } /* set to actual size which is <= allocated len */ new->size = k; new->vec[k] = NULL; if (invcount) { new->size -= aa_vec_unique(&new->vec[0], new->size, VEC_FLAG_TERMINATE); /* TODO: deal with reference labels */ if (new->size == 1) { label = aa_get_label(&new->vec[0]->label); return label; } } else if (!stale) { /* * merge could be same as a || b, note: it is not possible * for new->size == a->size == b->size unless a == b */ if (k == a->size) return aa_get_label(a); else if (k == b->size) return aa_get_label(b); } new->flags |= accum_vec_flags(new->vec, new->size); ls = labels_set(new); write_lock_irqsave(&ls->lock, flags); label = __label_insert(labels_set(new), new, false); write_unlock_irqrestore(&ls->lock, flags); return label; } /** * labelset_of_merge - find which labelset a merged label should be inserted * @a: label to merge and insert * @b: label to merge and insert * * Returns: labelset that the merged label should be inserted into */ static struct aa_labelset *labelset_of_merge(struct aa_label *a, struct aa_label *b) { struct aa_ns *nsa = labels_ns(a); struct aa_ns *nsb = labels_ns(b); if (ns_cmp(nsa, nsb) <= 0) return &nsa->labels; return &nsb->labels; } /** * __label_find_merge - find label that is equiv to merge of @a and @b * @ls: set of labels to search (NOT NULL) * @a: label to merge with @b (NOT NULL) * @b: label to merge with @a (NOT NULL) * * Requires: ls->lock read_lock held * * Returns: ref counted label that is equiv to merge of @a and @b * else NULL if merge of @a and @b is not in set */ static struct aa_label *__label_find_merge(struct aa_labelset *ls, struct aa_label *a, struct aa_label *b) { struct rb_node *node; AA_BUG(!ls); AA_BUG(!a); AA_BUG(!b); if (a == b) return __label_find(a); node = ls->root.rb_node; while (node) { struct aa_label *this = container_of(node, struct aa_label, node); int result = label_merge_cmp(a, b, this); if (result < 0) node = node->rb_left; else if (result > 0) node = node->rb_right; else return __aa_get_label(this); } return NULL; } /** * aa_label_find_merge - find label that is equiv to merge of @a and @b * @a: label to merge with @b (NOT NULL) * @b: label to merge with @a (NOT NULL) * * Requires: labels be fully constructed with a valid ns * * Returns: ref counted label that is equiv to merge of @a and @b * else NULL if merge of @a and @b is not in set */ struct aa_label *aa_label_find_merge(struct aa_label *a, struct aa_label *b) { struct aa_labelset *ls; struct aa_label *label, *ar = NULL, *br = NULL; unsigned long flags; AA_BUG(!a); AA_BUG(!b); if (label_is_stale(a)) a = ar = aa_get_newest_label(a); if (label_is_stale(b)) b = br = aa_get_newest_label(b); ls = labelset_of_merge(a, b); read_lock_irqsave(&ls->lock, flags); label = __label_find_merge(ls, a, b); read_unlock_irqrestore(&ls->lock, flags); aa_put_label(ar); aa_put_label(br); return label; } /** * aa_label_merge - attempt to insert new merged label of @a and @b * @a: label to merge with @b (NOT NULL) * @b: label to merge with @a (NOT NULL) * @gfp: memory allocation type * * Requires: caller to hold valid refs on @a and @b * labels be fully constructed with a valid ns * * Returns: ref counted new label if successful in inserting merge of a & b * else ref counted equivalent label that is already in the set. * else NULL if could not create label (-ENOMEM) */ struct aa_label *aa_label_merge(struct aa_label *a, struct aa_label *b, gfp_t gfp) { struct aa_label *label = NULL; AA_BUG(!a); AA_BUG(!b); if (a == b) return aa_get_newest_label(a); /* TODO: enable when read side is lockless * check if label exists before taking locks if (!label_is_stale(a) && !label_is_stale(b)) label = aa_label_find_merge(a, b); */ if (!label) { struct aa_label *new; a = aa_get_newest_label(a); b = aa_get_newest_label(b); /* could use label_merge_len(a, b), but requires double * comparison for small savings */ new = aa_label_alloc(a->size + b->size, NULL, gfp); if (!new) goto out; label = label_merge_insert(new, a, b); label_free_or_put_new(label, new); out: aa_put_label(a); aa_put_label(b); } return label; } /* match a profile and its associated ns component if needed * Assumes visibility test has already been done. * If a subns profile is not to be matched should be prescreened with * visibility test. */ static inline aa_state_t match_component(struct aa_profile *profile, struct aa_ruleset *rules, struct aa_profile *tp, aa_state_t state) { const char *ns_name; if (profile->ns == tp->ns) return aa_dfa_match(rules->policy->dfa, state, tp->base.hname); /* try matching with namespace name and then profile */ ns_name = aa_ns_name(profile->ns, tp->ns, true); state = aa_dfa_match_len(rules->policy->dfa, state, ":", 1); state = aa_dfa_match(rules->policy->dfa, state, ns_name); state = aa_dfa_match_len(rules->policy->dfa, state, ":", 1); return aa_dfa_match(rules->policy->dfa, state, tp->base.hname); } /** * label_compound_match - find perms for full compound label * @profile: profile to find perms for * @rules: ruleset to search * @label: label to check access permissions for * @state: state to start match in * @subns: whether to do permission checks on components in a subns * @request: permissions to request * @perms: perms struct to set * * Returns: 0 on success else ERROR * * For the label A//&B//&C this does the perm match for A//&B//&C * @perms should be preinitialized with allperms OR a previous permission * check to be stacked. */ static int label_compound_match(struct aa_profile *profile, struct aa_ruleset *rules, struct aa_label *label, aa_state_t state, bool subns, u32 request, struct aa_perms *perms) { struct aa_profile *tp; struct label_it i; /* find first subcomponent that is visible */ label_for_each(i, label, tp) { if (!aa_ns_visible(profile->ns, tp->ns, subns)) continue; state = match_component(profile, rules, tp, state); if (!state) goto fail; goto next; } /* no component visible */ *perms = allperms; return 0; next: label_for_each_cont(i, label, tp) { if (!aa_ns_visible(profile->ns, tp->ns, subns)) continue; state = aa_dfa_match(rules->policy->dfa, state, "//&"); state = match_component(profile, rules, tp, state); if (!state) goto fail; } *perms = *aa_lookup_perms(rules->policy, state); aa_apply_modes_to_perms(profile, perms); if ((perms->allow & request) != request) return -EACCES; return 0; fail: *perms = nullperms; return state; } /** * label_components_match - find perms for all subcomponents of a label * @profile: profile to find perms for * @rules: ruleset to search * @label: label to check access permissions for * @start: state to start match in * @subns: whether to do permission checks on components in a subns * @request: permissions to request * @perms: an initialized perms struct to add accumulation to * * Returns: 0 on success else ERROR * * For the label A//&B//&C this does the perm match for each of A and B and C * @perms should be preinitialized with allperms OR a previous permission * check to be stacked. */ static int label_components_match(struct aa_profile *profile, struct aa_ruleset *rules, struct aa_label *label, aa_state_t start, bool subns, u32 request, struct aa_perms *perms) { struct aa_profile *tp; struct label_it i; struct aa_perms tmp; aa_state_t state = 0; /* find first subcomponent to test */ label_for_each(i, label, tp) { if (!aa_ns_visible(profile->ns, tp->ns, subns)) continue; state = match_component(profile, rules, tp, start); if (!state) goto fail; goto next; } /* no subcomponents visible - no change in perms */ return 0; next: tmp = *aa_lookup_perms(rules->policy, state); aa_apply_modes_to_perms(profile, &tmp); aa_perms_accum(perms, &tmp); label_for_each_cont(i, label, tp) { if (!aa_ns_visible(profile->ns, tp->ns, subns)) continue; state = match_component(profile, rules, tp, start); if (!state) goto fail; tmp = *aa_lookup_perms(rules->policy, state); aa_apply_modes_to_perms(profile, &tmp); aa_perms_accum(perms, &tmp); } if ((perms->allow & request) != request) return -EACCES; return 0; fail: *perms = nullperms; return -EACCES; } /** * aa_label_match - do a multi-component label match * @profile: profile to match against (NOT NULL) * @rules: ruleset to search * @label: label to match (NOT NULL) * @state: state to start in * @subns: whether to match subns components * @request: permission request * @perms: Returns computed perms (NOT NULL) * * Returns: the state the match finished in, may be the none matching state */ int aa_label_match(struct aa_profile *profile, struct aa_ruleset *rules, struct aa_label *label, aa_state_t state, bool subns, u32 request, struct aa_perms *perms) { int error = label_compound_match(profile, rules, label, state, subns, request, perms); if (!error) return error; *perms = allperms; return label_components_match(profile, rules, label, state, subns, request, perms); } /** * aa_update_label_name - update a label to have a stored name * @ns: ns being viewed from (NOT NULL) * @label: label to update (NOT NULL) * @gfp: type of memory allocation * * Requires: labels_set(label) not locked in caller * * note: only updates the label name if it does not have a name already * and if it is in the labelset */ bool aa_update_label_name(struct aa_ns *ns, struct aa_label *label, gfp_t gfp) { struct aa_labelset *ls; unsigned long flags; char __counted *name; bool res = false; AA_BUG(!ns); AA_BUG(!label); if (label->hname || labels_ns(label) != ns) return res; if (aa_label_acntsxprint(&name, ns, label, FLAGS_NONE, gfp) < 0) return res; ls = labels_set(label); write_lock_irqsave(&ls->lock, flags); if (!label->hname && label->flags & FLAG_IN_TREE) { label->hname = name; res = true; } else aa_put_str(name); write_unlock_irqrestore(&ls->lock, flags); return res; } /* * cached label name is present and visible * @label->hname only exists if label is namespace hierachical */ static inline bool use_label_hname(struct aa_ns *ns, struct aa_label *label, int flags) { if (label->hname && (!ns || labels_ns(label) == ns) && !(flags & ~FLAG_SHOW_MODE)) return true; return false; } /* helper macro for snprint routines */ #define update_for_len(total, len, size, str) \ do { \ size_t ulen = len; \ \ AA_BUG(len < 0); \ total += ulen; \ ulen = min(ulen, size); \ size -= ulen; \ str += ulen; \ } while (0) /** * aa_profile_snxprint - print a profile name to a buffer * @str: buffer to write to. (MAY BE NULL if @size == 0) * @size: size of buffer * @view: namespace profile is being viewed from * @profile: profile to view (NOT NULL) * @flags: whether to include the mode string * @prev_ns: last ns printed when used in compound print * * Returns: size of name written or would be written if larger than * available buffer * * Note: will not print anything if the profile is not visible */ static int aa_profile_snxprint(char *str, size_t size, struct aa_ns *view, struct aa_profile *profile, int flags, struct aa_ns **prev_ns) { const char *ns_name = NULL; AA_BUG(!str && size != 0); AA_BUG(!profile); if (!view) view = profiles_ns(profile); if (view != profile->ns && (!prev_ns || (*prev_ns != profile->ns))) { if (prev_ns) *prev_ns = profile->ns; ns_name = aa_ns_name(view, profile->ns, flags & FLAG_VIEW_SUBNS); if (ns_name == aa_hidden_ns_name) { if (flags & FLAG_HIDDEN_UNCONFINED) return snprintf(str, size, "%s", "unconfined"); return snprintf(str, size, "%s", ns_name); } } if ((flags & FLAG_SHOW_MODE) && profile != profile->ns->unconfined) { const char *modestr = aa_profile_mode_names[profile->mode]; if (ns_name) return snprintf(str, size, ":%s:%s (%s)", ns_name, profile->base.hname, modestr); return snprintf(str, size, "%s (%s)", profile->base.hname, modestr); } if (ns_name) return snprintf(str, size, ":%s:%s", ns_name, profile->base.hname); return snprintf(str, size, "%s", profile->base.hname); } static const char *label_modename(struct aa_ns *ns, struct aa_label *label, int flags) { struct aa_profile *profile; struct label_it i; int mode = -1, count = 0; label_for_each(i, label, profile) { if (aa_ns_visible(ns, profile->ns, flags & FLAG_VIEW_SUBNS)) { count++; if (profile == profile->ns->unconfined) /* special case unconfined so stacks with * unconfined don't report as mixed. ie. * profile_foo//&:ns1:unconfined (mixed) */ continue; if (mode == -1) mode = profile->mode; else if (mode != profile->mode) return "mixed"; } } if (count == 0) return "-"; if (mode == -1) /* everything was unconfined */ mode = APPARMOR_UNCONFINED; return aa_profile_mode_names[mode]; } /* if any visible label is not unconfined the display_mode returns true */ static inline bool display_mode(struct aa_ns *ns, struct aa_label *label, int flags) { if ((flags & FLAG_SHOW_MODE)) { struct aa_profile *profile; struct label_it i; label_for_each(i, label, profile) { if (aa_ns_visible(ns, profile->ns, flags & FLAG_VIEW_SUBNS) && profile != profile->ns->unconfined) return true; } /* only ns->unconfined in set of profiles in ns */ return false; } return false; } /** * aa_label_snxprint - print a label name to a string buffer * @str: buffer to write to. (MAY BE NULL if @size == 0) * @size: size of buffer * @ns: namespace profile is being viewed from * @label: label to view (NOT NULL) * @flags: whether to include the mode string * * Returns: size of name written or would be written if larger than * available buffer * * Note: labels do not have to be strictly hierarchical to the ns as * objects may be shared across different namespaces and thus * pickup labeling from each ns. If a particular part of the * label is not visible it will just be excluded. And if none * of the label is visible "---" will be used. */ int aa_label_snxprint(char *str, size_t size, struct aa_ns *ns, struct aa_label *label, int flags) { struct aa_profile *profile; struct aa_ns *prev_ns = NULL; struct label_it i; int count = 0, total = 0; ssize_t len; AA_BUG(!str && size != 0); AA_BUG(!label); if (AA_DEBUG_LABEL && (flags & FLAG_ABS_ROOT)) { ns = root_ns; len = snprintf(str, size, "_"); update_for_len(total, len, size, str); } else if (!ns) { ns = labels_ns(label); } label_for_each(i, label, profile) { if (aa_ns_visible(ns, profile->ns, flags & FLAG_VIEW_SUBNS)) { if (count > 0) { len = snprintf(str, size, "//&"); update_for_len(total, len, size, str); } len = aa_profile_snxprint(str, size, ns, profile, flags & FLAG_VIEW_SUBNS, &prev_ns); update_for_len(total, len, size, str); count++; } } if (count == 0) { if (flags & FLAG_HIDDEN_UNCONFINED) return snprintf(str, size, "%s", "unconfined"); return snprintf(str, size, "%s", aa_hidden_ns_name); } /* count == 1 && ... is for backwards compat where the mode * is not displayed for 'unconfined' in the current ns */ if (display_mode(ns, label, flags)) { len = snprintf(str, size, " (%s)", label_modename(ns, label, flags)); update_for_len(total, len, size, str); } return total; } #undef update_for_len /** * aa_label_asxprint - allocate a string buffer and print label into it * @strp: Returns - the allocated buffer with the label name. (NOT NULL) * @ns: namespace profile is being viewed from * @label: label to view (NOT NULL) * @flags: flags controlling what label info is printed * @gfp: kernel memory allocation type * * Returns: size of name written or would be written if larger than * available buffer */ int aa_label_asxprint(char **strp, struct aa_ns *ns, struct aa_label *label, int flags, gfp_t gfp) { int size; AA_BUG(!strp); AA_BUG(!label); size = aa_label_snxprint(NULL, 0, ns, label, flags); if (size < 0) return size; *strp = kmalloc(size + 1, gfp); if (!*strp) return -ENOMEM; return aa_label_snxprint(*strp, size + 1, ns, label, flags); } /** * aa_label_acntsxprint - allocate a __counted string buffer and print label * @strp: buffer to write to. * @ns: namespace profile is being viewed from * @label: label to view (NOT NULL) * @flags: flags controlling what label info is printed * @gfp: kernel memory allocation type * * Returns: size of name written or would be written if larger than * available buffer */ int aa_label_acntsxprint(char __counted **strp, struct aa_ns *ns, struct aa_label *label, int flags, gfp_t gfp) { int size; AA_BUG(!strp); AA_BUG(!label); size = aa_label_snxprint(NULL, 0, ns, label, flags); if (size < 0) return size; *strp = aa_str_alloc(size + 1, gfp); if (!*strp) return -ENOMEM; return aa_label_snxprint(*strp, size + 1, ns, label, flags); } void aa_label_xaudit(struct audit_buffer *ab, struct aa_ns *ns, struct aa_label *label, int flags, gfp_t gfp) { const char *str; char *name = NULL; int len; AA_BUG(!ab); AA_BUG(!label); if (!use_label_hname(ns, label, flags) || display_mode(ns, label, flags)) { len = aa_label_asxprint(&name, ns, label, flags, gfp); if (len < 0) { AA_DEBUG("label print error"); return; } str = name; } else { str = (char *) label->hname; len = strlen(str); } if (audit_string_contains_control(str, len)) audit_log_n_hex(ab, str, len); else audit_log_n_string(ab, str, len); kfree(name); } void aa_label_seq_xprint(struct seq_file *f, struct aa_ns *ns, struct aa_label *label, int flags, gfp_t gfp) { AA_BUG(!f); AA_BUG(!label); if (!use_label_hname(ns, label, flags)) { char *str; int len; len = aa_label_asxprint(&str, ns, label, flags, gfp); if (len < 0) { AA_DEBUG("label print error"); return; } seq_puts(f, str); kfree(str); } else if (display_mode(ns, label, flags)) seq_printf(f, "%s (%s)", label->hname, label_modename(ns, label, flags)); else seq_puts(f, label->hname); } void aa_label_xprintk(struct aa_ns *ns, struct aa_label *label, int flags, gfp_t gfp) { AA_BUG(!label); if (!use_label_hname(ns, label, flags)) { char *str; int len; len = aa_label_asxprint(&str, ns, label, flags, gfp); if (len < 0) { AA_DEBUG("label print error"); return; } pr_info("%s", str); kfree(str); } else if (display_mode(ns, label, flags)) pr_info("%s (%s)", label->hname, label_modename(ns, label, flags)); else pr_info("%s", label->hname); } void aa_label_printk(struct aa_label *label, gfp_t gfp) { struct aa_ns *ns = aa_get_current_ns(); aa_label_xprintk(ns, label, FLAG_VIEW_SUBNS, gfp); aa_put_ns(ns); } static int label_count_strn_entries(const char *str, size_t n) { const char *end = str + n; const char *split; int count = 1; AA_BUG(!str); for (split = aa_label_strn_split(str, end - str); split; split = aa_label_strn_split(str, end - str)) { count++; str = split + 3; } return count; } /* * ensure stacks with components like * :ns:A//&B * have :ns: applied to both 'A' and 'B' by making the lookup relative * to the base if the lookup specifies an ns, else making the stacked lookup * relative to the last embedded ns in the string. */ static struct aa_profile *fqlookupn_profile(struct aa_label *base, struct aa_label *currentbase, const char *str, size_t n) { const char *first = skipn_spaces(str, n); if (first && *first == ':') return aa_fqlookupn_profile(base, str, n); return aa_fqlookupn_profile(currentbase, str, n); } /** * aa_label_strn_parse - parse, validate and convert a text string to a label * @base: base label to use for lookups (NOT NULL) * @str: null terminated text string (NOT NULL) * @n: length of str to parse, will stop at \0 if encountered before n * @gfp: allocation type * @create: true if should create compound labels if they don't exist * @force_stack: true if should stack even if no leading & * * Returns: the matching refcounted label if present * else ERRPTR */ struct aa_label *aa_label_strn_parse(struct aa_label *base, const char *str, size_t n, gfp_t gfp, bool create, bool force_stack) { DEFINE_VEC(profile, vec); struct aa_label *label, *currbase = base; int i, len, stack = 0, error; const char *end = str + n; const char *split; AA_BUG(!base); AA_BUG(!str); str = skipn_spaces(str, n); if (str == NULL || (AA_DEBUG_LABEL && *str == '_' && base != &root_ns->unconfined->label)) return ERR_PTR(-EINVAL); len = label_count_strn_entries(str, end - str); if (*str == '&' || force_stack) { /* stack on top of base */ stack = base->size; len += stack; if (*str == '&') str++; } error = vec_setup(profile, vec, len, gfp); if (error) return ERR_PTR(error); for (i = 0; i < stack; i++) vec[i] = aa_get_profile(base->vec[i]); for (split = aa_label_strn_split(str, end - str), i = stack; split && i < len; i++) { vec[i] = fqlookupn_profile(base, currbase, str, split - str); if (!vec[i]) goto fail; /* * if component specified a new ns it becomes the new base * so that subsequent lookups are relative to it */ if (vec[i]->ns != labels_ns(currbase)) currbase = &vec[i]->label; str = split + 3; split = aa_label_strn_split(str, end - str); } /* last element doesn't have a split */ if (i < len) { vec[i] = fqlookupn_profile(base, currbase, str, end - str); if (!vec[i]) goto fail; } if (len == 1) /* no need to free vec as len < LOCAL_VEC_ENTRIES */ return &vec[0]->label; len -= aa_vec_unique(vec, len, VEC_FLAG_TERMINATE); /* TODO: deal with reference labels */ if (len == 1) { label = aa_get_label(&vec[0]->label); goto out; } if (create) label = aa_vec_find_or_create_label(vec, len, gfp); else label = vec_find(vec, len); if (!label) goto fail; out: /* use adjusted len from after vec_unique, not original */ vec_cleanup(profile, vec, len); return label; fail: label = ERR_PTR(-ENOENT); goto out; } struct aa_label *aa_label_parse(struct aa_label *base, const char *str, gfp_t gfp, bool create, bool force_stack) { return aa_label_strn_parse(base, str, strlen(str), gfp, create, force_stack); } /** * aa_labelset_destroy - remove all labels from the label set * @ls: label set to cleanup (NOT NULL) * * Labels that are removed from the set may still exist beyond the set * being destroyed depending on their reference counting */ void aa_labelset_destroy(struct aa_labelset *ls) { struct rb_node *node; unsigned long flags; AA_BUG(!ls); write_lock_irqsave(&ls->lock, flags); for (node = rb_first(&ls->root); node; node = rb_first(&ls->root)) { struct aa_label *this = rb_entry(node, struct aa_label, node); if (labels_ns(this) != root_ns) __label_remove(this, ns_unconfined(labels_ns(this)->parent)); else __label_remove(this, NULL); } write_unlock_irqrestore(&ls->lock, flags); } /* * @ls: labelset to init (NOT NULL) */ void aa_labelset_init(struct aa_labelset *ls) { AA_BUG(!ls); rwlock_init(&ls->lock); ls->root = RB_ROOT; } static struct aa_label *labelset_next_stale(struct aa_labelset *ls) { struct aa_label *label; struct rb_node *node; unsigned long flags; AA_BUG(!ls); read_lock_irqsave(&ls->lock, flags); __labelset_for_each(ls, node) { label = rb_entry(node, struct aa_label, node); if ((label_is_stale(label) || vec_is_stale(label->vec, label->size)) && __aa_get_label(label)) goto out; } label = NULL; out: read_unlock_irqrestore(&ls->lock, flags); return label; } /** * __label_update - insert updated version of @label into labelset * @label: the label to update/replace * * Returns: new label that is up to date * else NULL on failure * * Requires: @ns lock be held * * Note: worst case is the stale @label does not get updated and has * to be updated at a later time. */ static struct aa_label *__label_update(struct aa_label *label) { struct aa_label *new, *tmp; struct aa_labelset *ls; unsigned long flags; int i, invcount = 0; AA_BUG(!label); AA_BUG(!mutex_is_locked(&labels_ns(label)->lock)); new = aa_label_alloc(label->size, label->proxy, GFP_KERNEL); if (!new) return NULL; /* * while holding the ns_lock will stop profile replacement, removal, * and label updates, label merging and removal can be occurring */ ls = labels_set(label); write_lock_irqsave(&ls->lock, flags); for (i = 0; i < label->size; i++) { AA_BUG(!label->vec[i]); new->vec[i] = aa_get_newest_profile(label->vec[i]); AA_BUG(!new->vec[i]); AA_BUG(!new->vec[i]->label.proxy); AA_BUG(!new->vec[i]->label.proxy->label); if (new->vec[i]->label.proxy != label->vec[i]->label.proxy) invcount++; } /* updated stale label by being removed/renamed from labelset */ if (invcount) { new->size -= aa_vec_unique(&new->vec[0], new->size, VEC_FLAG_TERMINATE); /* TODO: deal with reference labels */ if (new->size == 1) { tmp = aa_get_label(&new->vec[0]->label); AA_BUG(tmp == label); goto remove; } if (labels_set(label) != labels_set(new)) { write_unlock_irqrestore(&ls->lock, flags); tmp = aa_label_insert(labels_set(new), new); write_lock_irqsave(&ls->lock, flags); goto remove; } } else AA_BUG(labels_ns(label) != labels_ns(new)); tmp = __label_insert(labels_set(label), new, true); remove: /* ensure label is removed, and redirected correctly */ __label_remove(label, tmp); write_unlock_irqrestore(&ls->lock, flags); label_free_or_put_new(tmp, new); return tmp; } /** * __labelset_update - update labels in @ns * @ns: namespace to update labels in (NOT NULL) * * Requires: @ns lock be held * * Walk the labelset ensuring that all labels are up to date and valid * Any label that has a stale component is marked stale and replaced and * by an updated version. * * If failures happen due to memory pressures then stale labels will * be left in place until the next pass. */ static void __labelset_update(struct aa_ns *ns) { struct aa_label *label; AA_BUG(!ns); AA_BUG(!mutex_is_locked(&ns->lock)); do { label = labelset_next_stale(&ns->labels); if (label) { struct aa_label *l = __label_update(label); aa_put_label(l); aa_put_label(label); } } while (label); } /** * __aa_labelset_update_subtree - update all labels with a stale component * @ns: ns to start update at (NOT NULL) * * Requires: @ns lock be held * * Invalidates labels based on @p in @ns and any children namespaces. */ void __aa_labelset_update_subtree(struct aa_ns *ns) { struct aa_ns *child; AA_BUG(!ns); AA_BUG(!mutex_is_locked(&ns->lock)); __labelset_update(ns); list_for_each_entry(child, &ns->sub_ns, base.list) { mutex_lock_nested(&child->lock, child->level); __aa_labelset_update_subtree(child); mutex_unlock(&child->lock); } } |
| 9 3 9 1 2 5 1 1 4 4 14 14 1 1 3 9 3 2 5 3 3 1 20 1 11 7 19 19 1 20 1 26 8 18 1 5 5 20 15 56 2 4 29 30 25 27 24 26 2 27 17 17 4 15 12 5 15 18 18 17 17 4 2 2 9 9 6 1 2 3 2 5 5 9 8 1 1 8 5 5 4 3 1 1 5 4 1 19 21 1 19 12 8 1 1 2 8 4 20 1 59 5 57 7 3 33 28 19 45 2 7 1 41 6 45 36 1 35 29 25 1 25 1 1 25 24 54 3 48 4 50 1 47 4 47 5 49 3 48 3 43 7 48 3 49 2 51 50 22 25 4 44 5 2 42 5 3 9 13 1 8 4 2 5 2 3 2 46 48 12 13 12 16 57 4 25 25 1 23 16 15 15 7 7 1 3 2 11 11 10 1 6 69 116 1 4 1 1 3 1 2 1 1 2 4 1 1 102 46 76 3 37 66 1 8 72 16 20 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux NET3: GRE over IP protocol decoder. * * Authors: Alexey Kuznetsov (kuznet@ms2.inr.ac.ru) */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/in.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/if_arp.h> #include <linux/if_vlan.h> #include <linux/init.h> #include <linux/in6.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/netfilter_ipv4.h> #include <linux/etherdevice.h> #include <linux/if_ether.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> #include <net/protocol.h> #include <net/ip_tunnels.h> #include <net/arp.h> #include <net/checksum.h> #include <net/dsfield.h> #include <net/inet_ecn.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> #include <net/gre.h> #include <net/dst_metadata.h> #include <net/erspan.h> #include <net/inet_dscp.h> /* Problems & solutions -------------------- 1. The most important issue is detecting local dead loops. They would cause complete host lockup in transmit, which would be "resolved" by stack overflow or, if queueing is enabled, with infinite looping in net_bh. We cannot track such dead loops during route installation, it is infeasible task. The most general solutions would be to keep skb->encapsulation counter (sort of local ttl), and silently drop packet when it expires. It is a good solution, but it supposes maintaining new variable in ALL skb, even if no tunneling is used. Current solution: xmit_recursion breaks dead loops. This is a percpu counter, since when we enter the first ndo_xmit(), cpu migration is forbidden. We force an exit if this counter reaches RECURSION_LIMIT 2. Networking dead loops would not kill routers, but would really kill network. IP hop limit plays role of "t->recursion" in this case, if we copy it from packet being encapsulated to upper header. It is very good solution, but it introduces two problems: - Routing protocols, using packets with ttl=1 (OSPF, RIP2), do not work over tunnels. - traceroute does not work. I planned to relay ICMP from tunnel, so that this problem would be solved and traceroute output would even more informative. This idea appeared to be wrong: only Linux complies to rfc1812 now (yes, guys, Linux is the only true router now :-)), all routers (at least, in neighbourhood of mine) return only 8 bytes of payload. It is the end. Hence, if we want that OSPF worked or traceroute said something reasonable, we should search for another solution. One of them is to parse packet trying to detect inner encapsulation made by our node. It is difficult or even impossible, especially, taking into account fragmentation. TO be short, ttl is not solution at all. Current solution: The solution was UNEXPECTEDLY SIMPLE. We force DF flag on tunnels with preconfigured hop limit, that is ALL. :-) Well, it does not remove the problem completely, but exponential growth of network traffic is changed to linear (branches, that exceed pmtu are pruned) and tunnel mtu rapidly degrades to value <68, where looping stops. Yes, it is not good if there exists a router in the loop, which does not force DF, even when encapsulating packets have DF set. But it is not our problem! Nobody could accuse us, we made all that we could make. Even if it is your gated who injected fatal route to network, even if it were you who configured fatal static route: you are innocent. :-) Alexey Kuznetsov. */ static bool log_ecn_error = true; module_param(log_ecn_error, bool, 0644); MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); static struct rtnl_link_ops ipgre_link_ops __read_mostly; static const struct header_ops ipgre_header_ops; static int ipgre_tunnel_init(struct net_device *dev); static void erspan_build_header(struct sk_buff *skb, u32 id, u32 index, bool truncate, bool is_ipv4); static unsigned int ipgre_net_id __read_mostly; static unsigned int gre_tap_net_id __read_mostly; static unsigned int erspan_net_id __read_mostly; static int ipgre_err(struct sk_buff *skb, u32 info, const struct tnl_ptk_info *tpi) { /* All the routers (except for Linux) return only 8 bytes of packet payload. It means, that precise relaying of ICMP in the real Internet is absolutely infeasible. Moreover, Cisco "wise men" put GRE key to the third word in GRE header. It makes impossible maintaining even soft state for keyed GRE tunnels with enabled checksum. Tell them "thank you". Well, I wonder, rfc1812 was written by Cisco employee, what the hell these idiots break standards established by themselves??? */ struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn; const struct iphdr *iph; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; unsigned int data_len = 0; struct ip_tunnel *t; if (tpi->proto == htons(ETH_P_TEB)) itn = net_generic(net, gre_tap_net_id); else if (tpi->proto == htons(ETH_P_ERSPAN) || tpi->proto == htons(ETH_P_ERSPAN2)) itn = net_generic(net, erspan_net_id); else itn = net_generic(net, ipgre_net_id); iph = (const struct iphdr *)(icmp_hdr(skb) + 1); t = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags, iph->daddr, iph->saddr, tpi->key); if (!t) return -ENOENT; switch (type) { default: case ICMP_PARAMETERPROB: return 0; case ICMP_DEST_UNREACH: switch (code) { case ICMP_SR_FAILED: case ICMP_PORT_UNREACH: /* Impossible event. */ return 0; default: /* All others are translated to HOST_UNREACH. rfc2003 contains "deep thoughts" about NET_UNREACH, I believe they are just ether pollution. --ANK */ break; } break; case ICMP_TIME_EXCEEDED: if (code != ICMP_EXC_TTL) return 0; data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */ break; case ICMP_REDIRECT: break; } #if IS_ENABLED(CONFIG_IPV6) if (tpi->proto == htons(ETH_P_IPV6) && !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4 + tpi->hdr_len, type, data_len)) return 0; #endif if (t->parms.iph.daddr == 0 || ipv4_is_multicast(t->parms.iph.daddr)) return 0; if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED) return 0; if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO)) t->err_count++; else t->err_count = 1; t->err_time = jiffies; return 0; } static void gre_err(struct sk_buff *skb, u32 info) { /* All the routers (except for Linux) return only * 8 bytes of packet payload. It means, that precise relaying of * ICMP in the real Internet is absolutely infeasible. * * Moreover, Cisco "wise men" put GRE key to the third word * in GRE header. It makes impossible maintaining even soft * state for keyed * GRE tunnels with enabled checksum. Tell them "thank you". * * Well, I wonder, rfc1812 was written by Cisco employee, * what the hell these idiots break standards established * by themselves??? */ const struct iphdr *iph = (struct iphdr *)skb->data; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct tnl_ptk_info tpi; if (gre_parse_header(skb, &tpi, NULL, htons(ETH_P_IP), iph->ihl * 4) < 0) return; if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { ipv4_update_pmtu(skb, dev_net(skb->dev), info, skb->dev->ifindex, IPPROTO_GRE); return; } if (type == ICMP_REDIRECT) { ipv4_redirect(skb, dev_net(skb->dev), skb->dev->ifindex, IPPROTO_GRE); return; } ipgre_err(skb, info, &tpi); } static bool is_erspan_type1(int gre_hdr_len) { /* Both ERSPAN type I (version 0) and type II (version 1) use * protocol 0x88BE, but the type I has only 4-byte GRE header, * while type II has 8-byte. */ return gre_hdr_len == 4; } static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, int gre_hdr_len) { struct net *net = dev_net(skb->dev); struct metadata_dst *tun_dst = NULL; struct erspan_base_hdr *ershdr; IP_TUNNEL_DECLARE_FLAGS(flags); struct ip_tunnel_net *itn; struct ip_tunnel *tunnel; const struct iphdr *iph; struct erspan_md2 *md2; int ver; int len; ip_tunnel_flags_copy(flags, tpi->flags); itn = net_generic(net, erspan_net_id); iph = ip_hdr(skb); if (is_erspan_type1(gre_hdr_len)) { ver = 0; __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, iph->daddr, 0); } else { if (unlikely(!pskb_may_pull(skb, gre_hdr_len + sizeof(*ershdr)))) return PACKET_REJECT; ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len); ver = ershdr->ver; iph = ip_hdr(skb); __set_bit(IP_TUNNEL_KEY_BIT, flags); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, iph->daddr, tpi->key); } if (tunnel) { if (is_erspan_type1(gre_hdr_len)) len = gre_hdr_len; else len = gre_hdr_len + erspan_hdr_len(ver); if (unlikely(!pskb_may_pull(skb, len))) return PACKET_REJECT; if (__iptunnel_pull_header(skb, len, htons(ETH_P_TEB), false, false) < 0) goto drop; if (tunnel->collect_md) { struct erspan_metadata *pkt_md, *md; struct ip_tunnel_info *info; unsigned char *gh; __be64 tun_id; __set_bit(IP_TUNNEL_KEY_BIT, tpi->flags); ip_tunnel_flags_copy(flags, tpi->flags); tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ip_tun_rx_dst(skb, flags, tun_id, sizeof(*md)); if (!tun_dst) return PACKET_REJECT; /* skb can be uncloned in __iptunnel_pull_header, so * old pkt_md is no longer valid and we need to reset * it */ gh = skb_network_header(skb) + skb_network_header_len(skb); pkt_md = (struct erspan_metadata *)(gh + gre_hdr_len + sizeof(*ershdr)); md = ip_tunnel_info_opts(&tun_dst->u.tun_info); md->version = ver; md2 = &md->u.md2; memcpy(md2, pkt_md, ver == 1 ? ERSPAN_V1_MDSIZE : ERSPAN_V2_MDSIZE); info = &tun_dst->u.tun_info; __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags); info->options_len = sizeof(*md); } skb_reset_mac_header(skb); ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); return PACKET_RCVD; } return PACKET_REJECT; drop: kfree_skb(skb); return PACKET_RCVD; } static int __ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct ip_tunnel_net *itn, int hdr_len, bool raw_proto) { struct metadata_dst *tun_dst = NULL; const struct iphdr *iph; struct ip_tunnel *tunnel; iph = ip_hdr(skb); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags, iph->saddr, iph->daddr, tpi->key); if (tunnel) { const struct iphdr *tnl_params; if (__iptunnel_pull_header(skb, hdr_len, tpi->proto, raw_proto, false) < 0) goto drop; /* Special case for ipgre_header_parse(), which expects the * mac_header to point to the outer IP header. */ if (tunnel->dev->header_ops == &ipgre_header_ops) skb_pop_mac_header(skb); else skb_reset_mac_header(skb); tnl_params = &tunnel->parms.iph; if (tunnel->collect_md || tnl_params->daddr == 0) { IP_TUNNEL_DECLARE_FLAGS(flags) = { }; __be64 tun_id; __set_bit(IP_TUNNEL_CSUM_BIT, flags); __set_bit(IP_TUNNEL_KEY_BIT, flags); ip_tunnel_flags_and(flags, tpi->flags, flags); tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ip_tun_rx_dst(skb, flags, tun_id, 0); if (!tun_dst) return PACKET_REJECT; } ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); return PACKET_RCVD; } return PACKET_NEXT; drop: kfree_skb(skb); return PACKET_RCVD; } static int ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi, int hdr_len) { struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn; int res; if (tpi->proto == htons(ETH_P_TEB)) itn = net_generic(net, gre_tap_net_id); else itn = net_generic(net, ipgre_net_id); res = __ipgre_rcv(skb, tpi, itn, hdr_len, false); if (res == PACKET_NEXT && tpi->proto == htons(ETH_P_TEB)) { /* ipgre tunnels in collect metadata mode should receive * also ETH_P_TEB traffic. */ itn = net_generic(net, ipgre_net_id); res = __ipgre_rcv(skb, tpi, itn, hdr_len, true); } return res; } static int gre_rcv(struct sk_buff *skb) { struct tnl_ptk_info tpi; bool csum_err = false; int hdr_len; #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(ip_hdr(skb)->daddr)) { /* Looped back packet, drop it! */ if (rt_is_output_route(skb_rtable(skb))) goto drop; } #endif hdr_len = gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IP), 0); if (hdr_len < 0) goto drop; if (unlikely(tpi.proto == htons(ETH_P_ERSPAN) || tpi.proto == htons(ETH_P_ERSPAN2))) { if (erspan_rcv(skb, &tpi, hdr_len) == PACKET_RCVD) return 0; goto out; } if (ipgre_rcv(skb, &tpi, hdr_len) == PACKET_RCVD) return 0; out: icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); drop: kfree_skb(skb); return 0; } static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); IP_TUNNEL_DECLARE_FLAGS(flags); ip_tunnel_flags_copy(flags, tunnel->parms.o_flags); /* Push GRE header. */ gre_build_header(skb, tunnel->tun_hlen, flags, proto, tunnel->parms.o_key, test_bit(IP_TUNNEL_SEQ_BIT, flags) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol); } static int gre_handle_offloads(struct sk_buff *skb, bool csum) { return iptunnel_handle_offloads(skb, csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE); } static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; int tunnel_hlen; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || ip_tunnel_info_af(tun_info) != AF_INET)) goto err_free_skb; key = &tun_info->key; tunnel_hlen = gre_calc_hlen(key->tun_flags); if (skb_cow_head(skb, dev->needed_headroom)) goto err_free_skb; /* Push Tunnel header. */ if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags))) goto err_free_skb; __set_bit(IP_TUNNEL_CSUM_BIT, flags); __set_bit(IP_TUNNEL_KEY_BIT, flags); __set_bit(IP_TUNNEL_SEQ_BIT, flags); ip_tunnel_flags_and(flags, tun_info->key.tun_flags, flags); gre_build_header(skb, tunnel_hlen, flags, proto, tunnel_id_to_key32(tun_info->key.tun_id), test_bit(IP_TUNNEL_SEQ_BIT, flags) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); return; err_free_skb: kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); } static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; struct erspan_metadata *md; bool truncate = false; __be16 proto; int tunnel_hlen; int version; int nhoff; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || ip_tunnel_info_af(tun_info) != AF_INET)) goto err_free_skb; key = &tun_info->key; if (!test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, tun_info->key.tun_flags)) goto err_free_skb; if (tun_info->options_len < sizeof(*md)) goto err_free_skb; md = ip_tunnel_info_opts(tun_info); /* ERSPAN has fixed 8 byte GRE header */ version = md->version; tunnel_hlen = 8 + erspan_hdr_len(version); if (skb_cow_head(skb, dev->needed_headroom)) goto err_free_skb; if (gre_handle_offloads(skb, false)) goto err_free_skb; if (skb->len > dev->mtu + dev->hard_header_len) { if (pskb_trim(skb, dev->mtu + dev->hard_header_len)) goto err_free_skb; truncate = true; } nhoff = skb_network_offset(skb); if (skb->protocol == htons(ETH_P_IP) && (ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff)) truncate = true; if (skb->protocol == htons(ETH_P_IPV6)) { int thoff; if (skb_transport_header_was_set(skb)) thoff = skb_transport_offset(skb); else thoff = nhoff + sizeof(struct ipv6hdr); if (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff) truncate = true; } if (version == 1) { erspan_build_header(skb, ntohl(tunnel_id_to_key32(key->tun_id)), ntohl(md->u.index), truncate, true); proto = htons(ETH_P_ERSPAN); } else if (version == 2) { erspan_build_header_v2(skb, ntohl(tunnel_id_to_key32(key->tun_id)), md->u.md2.dir, get_hwid(&md->u.md2), truncate, true); proto = htons(ETH_P_ERSPAN2); } else { goto err_free_skb; } __set_bit(IP_TUNNEL_SEQ_BIT, flags); gre_build_header(skb, 8, flags, proto, 0, htonl(atomic_fetch_inc(&tunnel->o_seqno))); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); return; err_free_skb: kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); } static int gre_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct ip_tunnel_info *info = skb_tunnel_info(skb); const struct ip_tunnel_key *key; struct rtable *rt; struct flowi4 fl4; if (ip_tunnel_info_af(info) != AF_INET) return -EINVAL; key = &info->key; ip_tunnel_init_flow(&fl4, IPPROTO_GRE, key->u.ipv4.dst, key->u.ipv4.src, tunnel_id_to_key32(key->tun_id), key->tos & ~INET_ECN_MASK, dev_net(dev), 0, skb->mark, skb_get_hash(skb), key->flow_flags); rt = ip_route_output_key(dev_net(dev), &fl4); if (IS_ERR(rt)) return PTR_ERR(rt); ip_rt_put(rt); info->key.u.ipv4.src = fl4.saddr; return 0; } static netdev_tx_t ipgre_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tnl_params; if (!pskb_inet_may_pull(skb)) goto free_skb; if (tunnel->collect_md) { gre_fb_xmit(skb, dev, skb->protocol); return NETDEV_TX_OK; } if (dev->header_ops) { int pull_len = tunnel->hlen + sizeof(struct iphdr); if (skb_cow_head(skb, 0)) goto free_skb; if (!pskb_may_pull(skb, pull_len)) goto free_skb; tnl_params = (const struct iphdr *)skb->data; /* ip_tunnel_xmit() needs skb->data pointing to gre header. */ skb_pull(skb, pull_len); skb_reset_mac_header(skb); if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start(skb) < skb->data) goto free_skb; } else { if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; tnl_params = &tunnel->parms.iph; } if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags))) goto free_skb; __gre_xmit(skb, dev, tnl_params, skb->protocol); return NETDEV_TX_OK; free_skb: kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } static netdev_tx_t erspan_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); bool truncate = false; __be16 proto; if (!pskb_inet_may_pull(skb)) goto free_skb; if (tunnel->collect_md) { erspan_fb_xmit(skb, dev); return NETDEV_TX_OK; } if (gre_handle_offloads(skb, false)) goto free_skb; if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; if (skb->len > dev->mtu + dev->hard_header_len) { if (pskb_trim(skb, dev->mtu + dev->hard_header_len)) goto free_skb; truncate = true; } /* Push ERSPAN header */ if (tunnel->erspan_ver == 0) { proto = htons(ETH_P_ERSPAN); __clear_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.o_flags); } else if (tunnel->erspan_ver == 1) { erspan_build_header(skb, ntohl(tunnel->parms.o_key), tunnel->index, truncate, true); proto = htons(ETH_P_ERSPAN); } else if (tunnel->erspan_ver == 2) { erspan_build_header_v2(skb, ntohl(tunnel->parms.o_key), tunnel->dir, tunnel->hwid, truncate, true); proto = htons(ETH_P_ERSPAN2); } else { goto free_skb; } __clear_bit(IP_TUNNEL_KEY_BIT, tunnel->parms.o_flags); __gre_xmit(skb, dev, &tunnel->parms.iph, proto); return NETDEV_TX_OK; free_skb: kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } static netdev_tx_t gre_tap_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); if (!pskb_inet_may_pull(skb)) goto free_skb; if (tunnel->collect_md) { gre_fb_xmit(skb, dev, htons(ETH_P_TEB)); return NETDEV_TX_OK; } if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags))) goto free_skb; if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; __gre_xmit(skb, dev, &tunnel->parms.iph, htons(ETH_P_TEB)); return NETDEV_TX_OK; free_skb: kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } static void ipgre_link_update(struct net_device *dev, bool set_mtu) { struct ip_tunnel *tunnel = netdev_priv(dev); int len; len = tunnel->tun_hlen; tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags); len = tunnel->tun_hlen - len; tunnel->hlen = tunnel->hlen + len; if (dev->header_ops) dev->hard_header_len += len; else dev->needed_headroom += len; if (set_mtu) WRITE_ONCE(dev->mtu, max_t(int, dev->mtu - len, 68)); if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.o_flags) || (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags) && tunnel->encap.type != TUNNEL_ENCAP_NONE)) { dev->features &= ~NETIF_F_GSO_SOFTWARE; dev->hw_features &= ~NETIF_F_GSO_SOFTWARE; } else { dev->features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_GSO_SOFTWARE; } } static int ipgre_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, int cmd) { __be16 i_flags, o_flags; int err; if (!ip_tunnel_flags_is_be16_compat(p->i_flags) || !ip_tunnel_flags_is_be16_compat(p->o_flags)) return -EOVERFLOW; i_flags = ip_tunnel_flags_to_be16(p->i_flags); o_flags = ip_tunnel_flags_to_be16(p->o_flags); if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { if (p->iph.version != 4 || p->iph.protocol != IPPROTO_GRE || p->iph.ihl != 5 || (p->iph.frag_off & htons(~IP_DF)) || ((i_flags | o_flags) & (GRE_VERSION | GRE_ROUTING))) return -EINVAL; } gre_flags_to_tnl_flags(p->i_flags, i_flags); gre_flags_to_tnl_flags(p->o_flags, o_flags); err = ip_tunnel_ctl(dev, p, cmd); if (err) return err; if (cmd == SIOCCHGTUNNEL) { struct ip_tunnel *t = netdev_priv(dev); ip_tunnel_flags_copy(t->parms.i_flags, p->i_flags); ip_tunnel_flags_copy(t->parms.o_flags, p->o_flags); if (strcmp(dev->rtnl_link_ops->kind, "erspan")) ipgre_link_update(dev, true); } i_flags = gre_tnl_flags_to_gre_flags(p->i_flags); ip_tunnel_flags_from_be16(p->i_flags, i_flags); o_flags = gre_tnl_flags_to_gre_flags(p->o_flags); ip_tunnel_flags_from_be16(p->o_flags, o_flags); return 0; } /* Nice toy. Unfortunately, useless in real life :-) It allows to construct virtual multiprotocol broadcast "LAN" over the Internet, provided multicast routing is tuned. I have no idea was this bicycle invented before me, so that I had to set ARPHRD_IPGRE to a random value. I have an impression, that Cisco could make something similar, but this feature is apparently missing in IOS<=11.2(8). I set up 10.66.66/24 and fec0:6666:6666::0/96 as virtual networks with broadcast 224.66.66.66. If you have access to mbone, play with me :-) ping -t 255 224.66.66.66 If nobody answers, mbone does not work. ip tunnel add Universe mode gre remote 224.66.66.66 local <Your_real_addr> ttl 255 ip addr add 10.66.66.<somewhat>/24 dev Universe ifconfig Universe up ifconfig Universe add fe80::<Your_real_addr>/10 ifconfig Universe add fec0:6666:6666::<Your_real_addr>/96 ftp 10.66.66.66 ... ftp fec0:6666:6666::193.233.7.65 ... */ static int ipgre_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len) { struct ip_tunnel *t = netdev_priv(dev); struct iphdr *iph; struct gre_base_hdr *greh; iph = skb_push(skb, t->hlen + sizeof(*iph)); greh = (struct gre_base_hdr *)(iph+1); greh->flags = gre_tnl_flags_to_gre_flags(t->parms.o_flags); greh->protocol = htons(type); memcpy(iph, &t->parms.iph, sizeof(struct iphdr)); /* Set the source hardware address. */ if (saddr) memcpy(&iph->saddr, saddr, 4); if (daddr) memcpy(&iph->daddr, daddr, 4); if (iph->daddr) return t->hlen + sizeof(*iph); return -(t->hlen + sizeof(*iph)); } static int ipgre_header_parse(const struct sk_buff *skb, unsigned char *haddr) { const struct iphdr *iph = (const struct iphdr *) skb_mac_header(skb); memcpy(haddr, &iph->saddr, 4); return 4; } static const struct header_ops ipgre_header_ops = { .create = ipgre_header, .parse = ipgre_header_parse, }; #ifdef CONFIG_NET_IPGRE_BROADCAST static int ipgre_open(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); if (ipv4_is_multicast(t->parms.iph.daddr)) { struct flowi4 fl4; struct rtable *rt; rt = ip_route_output_gre(t->net, &fl4, t->parms.iph.daddr, t->parms.iph.saddr, t->parms.o_key, t->parms.iph.tos & INET_DSCP_MASK, t->parms.link); if (IS_ERR(rt)) return -EADDRNOTAVAIL; dev = rt->dst.dev; ip_rt_put(rt); if (!__in_dev_get_rtnl(dev)) return -EADDRNOTAVAIL; t->mlink = dev->ifindex; ip_mc_inc_group(__in_dev_get_rtnl(dev), t->parms.iph.daddr); } return 0; } static int ipgre_close(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); if (ipv4_is_multicast(t->parms.iph.daddr) && t->mlink) { struct in_device *in_dev; in_dev = inetdev_by_index(t->net, t->mlink); if (in_dev) ip_mc_dec_group(in_dev, t->parms.iph.daddr); } return 0; } #endif static const struct net_device_ops ipgre_netdev_ops = { .ndo_init = ipgre_tunnel_init, .ndo_uninit = ip_tunnel_uninit, #ifdef CONFIG_NET_IPGRE_BROADCAST .ndo_open = ipgre_open, .ndo_stop = ipgre_close, #endif .ndo_start_xmit = ipgre_xmit, .ndo_siocdevprivate = ip_tunnel_siocdevprivate, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_tunnel_ctl = ipgre_tunnel_ctl, }; #define GRE_FEATURES (NETIF_F_SG | \ NETIF_F_FRAGLIST | \ NETIF_F_HIGHDMA | \ NETIF_F_HW_CSUM) static void ipgre_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &ipgre_netdev_ops; dev->type = ARPHRD_IPGRE; ip_tunnel_setup(dev, ipgre_net_id); } static void __gre_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel; tunnel = netdev_priv(dev); tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags); tunnel->parms.iph.protocol = IPPROTO_GRE; tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen; dev->needed_headroom = tunnel->hlen + sizeof(tunnel->parms.iph); dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; /* TCP offload with GRE SEQ is not supported, nor can we support 2 * levels of outer headers requiring an update. */ if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.o_flags)) return; if (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags) && tunnel->encap.type != TUNNEL_ENCAP_NONE) return; dev->features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_GSO_SOFTWARE; dev->lltx = true; } static int ipgre_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; __gre_tunnel_init(dev); __dev_addr_set(dev, &iph->saddr, 4); memcpy(dev->broadcast, &iph->daddr, 4); dev->flags = IFF_NOARP; netif_keep_dst(dev); dev->addr_len = 4; if (iph->daddr && !tunnel->collect_md) { #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(iph->daddr)) { if (!iph->saddr) return -EINVAL; dev->flags = IFF_BROADCAST; dev->header_ops = &ipgre_header_ops; dev->hard_header_len = tunnel->hlen + sizeof(*iph); dev->needed_headroom = 0; } #endif } else if (!tunnel->collect_md) { dev->header_ops = &ipgre_header_ops; dev->hard_header_len = tunnel->hlen + sizeof(*iph); dev->needed_headroom = 0; } return ip_tunnel_init(dev); } static const struct gre_protocol ipgre_protocol = { .handler = gre_rcv, .err_handler = gre_err, }; static int __net_init ipgre_init_net(struct net *net) { return ip_tunnel_init_net(net, ipgre_net_id, &ipgre_link_ops, NULL); } static void __net_exit ipgre_exit_batch_rtnl(struct list_head *list_net, struct list_head *dev_to_kill) { ip_tunnel_delete_nets(list_net, ipgre_net_id, &ipgre_link_ops, dev_to_kill); } static struct pernet_operations ipgre_net_ops = { .init = ipgre_init_net, .exit_batch_rtnl = ipgre_exit_batch_rtnl, .id = &ipgre_net_id, .size = sizeof(struct ip_tunnel_net), }; static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { __be16 flags; if (!data) return 0; flags = 0; if (data[IFLA_GRE_IFLAGS]) flags |= nla_get_be16(data[IFLA_GRE_IFLAGS]); if (data[IFLA_GRE_OFLAGS]) flags |= nla_get_be16(data[IFLA_GRE_OFLAGS]); if (flags & (GRE_VERSION|GRE_ROUTING)) return -EINVAL; if (data[IFLA_GRE_COLLECT_METADATA] && data[IFLA_GRE_ENCAP_TYPE] && nla_get_u16(data[IFLA_GRE_ENCAP_TYPE]) != TUNNEL_ENCAP_NONE) return -EINVAL; return 0; } static int ipgre_tap_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { __be32 daddr; if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) return -EADDRNOTAVAIL; } if (!data) goto out; if (data[IFLA_GRE_REMOTE]) { memcpy(&daddr, nla_data(data[IFLA_GRE_REMOTE]), 4); if (!daddr) return -EINVAL; } out: return ipgre_tunnel_validate(tb, data, extack); } static int erspan_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { __be16 flags = 0; int ret; if (!data) return 0; ret = ipgre_tap_validate(tb, data, extack); if (ret) return ret; if (data[IFLA_GRE_ERSPAN_VER] && nla_get_u8(data[IFLA_GRE_ERSPAN_VER]) == 0) return 0; /* ERSPAN type II/III should only have GRE sequence and key flag */ if (data[IFLA_GRE_OFLAGS]) flags |= nla_get_be16(data[IFLA_GRE_OFLAGS]); if (data[IFLA_GRE_IFLAGS]) flags |= nla_get_be16(data[IFLA_GRE_IFLAGS]); if (!data[IFLA_GRE_COLLECT_METADATA] && flags != (GRE_SEQ | GRE_KEY)) return -EINVAL; /* ERSPAN Session ID only has 10-bit. Since we reuse * 32-bit key field as ID, check it's range. */ if (data[IFLA_GRE_IKEY] && (ntohl(nla_get_be32(data[IFLA_GRE_IKEY])) & ~ID_MASK)) return -EINVAL; if (data[IFLA_GRE_OKEY] && (ntohl(nla_get_be32(data[IFLA_GRE_OKEY])) & ~ID_MASK)) return -EINVAL; return 0; } static int ipgre_netlink_parms(struct net_device *dev, struct nlattr *data[], struct nlattr *tb[], struct ip_tunnel_parm_kern *parms, __u32 *fwmark) { struct ip_tunnel *t = netdev_priv(dev); memset(parms, 0, sizeof(*parms)); parms->iph.protocol = IPPROTO_GRE; if (!data) return 0; if (data[IFLA_GRE_LINK]) parms->link = nla_get_u32(data[IFLA_GRE_LINK]); if (data[IFLA_GRE_IFLAGS]) gre_flags_to_tnl_flags(parms->i_flags, nla_get_be16(data[IFLA_GRE_IFLAGS])); if (data[IFLA_GRE_OFLAGS]) gre_flags_to_tnl_flags(parms->o_flags, nla_get_be16(data[IFLA_GRE_OFLAGS])); if (data[IFLA_GRE_IKEY]) parms->i_key = nla_get_be32(data[IFLA_GRE_IKEY]); if (data[IFLA_GRE_OKEY]) parms->o_key = nla_get_be32(data[IFLA_GRE_OKEY]); if (data[IFLA_GRE_LOCAL]) parms->iph.saddr = nla_get_in_addr(data[IFLA_GRE_LOCAL]); if (data[IFLA_GRE_REMOTE]) parms->iph.daddr = nla_get_in_addr(data[IFLA_GRE_REMOTE]); if (data[IFLA_GRE_TTL]) parms->iph.ttl = nla_get_u8(data[IFLA_GRE_TTL]); if (data[IFLA_GRE_TOS]) parms->iph.tos = nla_get_u8(data[IFLA_GRE_TOS]); if (!data[IFLA_GRE_PMTUDISC] || nla_get_u8(data[IFLA_GRE_PMTUDISC])) { if (t->ignore_df) return -EINVAL; parms->iph.frag_off = htons(IP_DF); } if (data[IFLA_GRE_COLLECT_METADATA]) { t->collect_md = true; if (dev->type == ARPHRD_IPGRE) dev->type = ARPHRD_NONE; } if (data[IFLA_GRE_IGNORE_DF]) { if (nla_get_u8(data[IFLA_GRE_IGNORE_DF]) && (parms->iph.frag_off & htons(IP_DF))) return -EINVAL; t->ignore_df = !!nla_get_u8(data[IFLA_GRE_IGNORE_DF]); } if (data[IFLA_GRE_FWMARK]) *fwmark = nla_get_u32(data[IFLA_GRE_FWMARK]); return 0; } static int erspan_netlink_parms(struct net_device *dev, struct nlattr *data[], struct nlattr *tb[], struct ip_tunnel_parm_kern *parms, __u32 *fwmark) { struct ip_tunnel *t = netdev_priv(dev); int err; err = ipgre_netlink_parms(dev, data, tb, parms, fwmark); if (err) return err; if (!data) return 0; if (data[IFLA_GRE_ERSPAN_VER]) { t->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]); if (t->erspan_ver > 2) return -EINVAL; } if (t->erspan_ver == 1) { if (data[IFLA_GRE_ERSPAN_INDEX]) { t->index = nla_get_u32(data[IFLA_GRE_ERSPAN_INDEX]); if (t->index & ~INDEX_MASK) return -EINVAL; } } else if (t->erspan_ver == 2) { if (data[IFLA_GRE_ERSPAN_DIR]) { t->dir = nla_get_u8(data[IFLA_GRE_ERSPAN_DIR]); if (t->dir & ~(DIR_MASK >> DIR_OFFSET)) return -EINVAL; } if (data[IFLA_GRE_ERSPAN_HWID]) { t->hwid = nla_get_u16(data[IFLA_GRE_ERSPAN_HWID]); if (t->hwid & ~(HWID_MASK >> HWID_OFFSET)) return -EINVAL; } } return 0; } /* This function returns true when ENCAP attributes are present in the nl msg */ static bool ipgre_netlink_encap_parms(struct nlattr *data[], struct ip_tunnel_encap *ipencap) { bool ret = false; memset(ipencap, 0, sizeof(*ipencap)); if (!data) return ret; if (data[IFLA_GRE_ENCAP_TYPE]) { ret = true; ipencap->type = nla_get_u16(data[IFLA_GRE_ENCAP_TYPE]); } if (data[IFLA_GRE_ENCAP_FLAGS]) { ret = true; ipencap->flags = nla_get_u16(data[IFLA_GRE_ENCAP_FLAGS]); } if (data[IFLA_GRE_ENCAP_SPORT]) { ret = true; ipencap->sport = nla_get_be16(data[IFLA_GRE_ENCAP_SPORT]); } if (data[IFLA_GRE_ENCAP_DPORT]) { ret = true; ipencap->dport = nla_get_be16(data[IFLA_GRE_ENCAP_DPORT]); } return ret; } static int gre_tap_init(struct net_device *dev) { __gre_tunnel_init(dev); dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; netif_keep_dst(dev); return ip_tunnel_init(dev); } static const struct net_device_ops gre_tap_netdev_ops = { .ndo_init = gre_tap_init, .ndo_uninit = ip_tunnel_uninit, .ndo_start_xmit = gre_tap_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_fill_metadata_dst = gre_fill_metadata_dst, }; static int erspan_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); if (tunnel->erspan_ver == 0) tunnel->tun_hlen = 4; /* 4-byte GRE hdr. */ else tunnel->tun_hlen = 8; /* 8-byte GRE hdr. */ tunnel->parms.iph.protocol = IPPROTO_GRE; tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen + erspan_hdr_len(tunnel->erspan_ver); dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; netif_keep_dst(dev); return ip_tunnel_init(dev); } static const struct net_device_ops erspan_netdev_ops = { .ndo_init = erspan_tunnel_init, .ndo_uninit = ip_tunnel_uninit, .ndo_start_xmit = erspan_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_fill_metadata_dst = gre_fill_metadata_dst, }; static void ipgre_tap_setup(struct net_device *dev) { ether_setup(dev); dev->max_mtu = 0; dev->netdev_ops = &gre_tap_netdev_ops; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; ip_tunnel_setup(dev, gre_tap_net_id); } static int ipgre_newlink_encap_setup(struct net_device *dev, struct nlattr *data[]) { struct ip_tunnel_encap ipencap; if (ipgre_netlink_encap_parms(data, &ipencap)) { struct ip_tunnel *t = netdev_priv(dev); int err = ip_tunnel_encap_setup(t, &ipencap); if (err < 0) return err; } return 0; } static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel_parm_kern p; __u32 fwmark = 0; int err; err = ipgre_newlink_encap_setup(dev, data); if (err) return err; err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark); if (err < 0) return err; return ip_tunnel_newlink(dev, tb, &p, fwmark); } static int erspan_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel_parm_kern p; __u32 fwmark = 0; int err; err = ipgre_newlink_encap_setup(dev, data); if (err) return err; err = erspan_netlink_parms(dev, data, tb, &p, &fwmark); if (err) return err; return ip_tunnel_newlink(dev, tb, &p, fwmark); } static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm_kern p; __u32 fwmark = t->fwmark; int err; err = ipgre_newlink_encap_setup(dev, data); if (err) return err; err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark); if (err < 0) return err; err = ip_tunnel_changelink(dev, tb, &p, fwmark); if (err < 0) return err; ip_tunnel_flags_copy(t->parms.i_flags, p.i_flags); ip_tunnel_flags_copy(t->parms.o_flags, p.o_flags); ipgre_link_update(dev, !tb[IFLA_MTU]); return 0; } static int erspan_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm_kern p; __u32 fwmark = t->fwmark; int err; err = ipgre_newlink_encap_setup(dev, data); if (err) return err; err = erspan_netlink_parms(dev, data, tb, &p, &fwmark); if (err < 0) return err; err = ip_tunnel_changelink(dev, tb, &p, fwmark); if (err < 0) return err; ip_tunnel_flags_copy(t->parms.i_flags, p.i_flags); ip_tunnel_flags_copy(t->parms.o_flags, p.o_flags); return 0; } static size_t ipgre_get_size(const struct net_device *dev) { return /* IFLA_GRE_LINK */ nla_total_size(4) + /* IFLA_GRE_IFLAGS */ nla_total_size(2) + /* IFLA_GRE_OFLAGS */ nla_total_size(2) + /* IFLA_GRE_IKEY */ nla_total_size(4) + /* IFLA_GRE_OKEY */ nla_total_size(4) + /* IFLA_GRE_LOCAL */ nla_total_size(4) + /* IFLA_GRE_REMOTE */ nla_total_size(4) + /* IFLA_GRE_TTL */ nla_total_size(1) + /* IFLA_GRE_TOS */ nla_total_size(1) + /* IFLA_GRE_PMTUDISC */ nla_total_size(1) + /* IFLA_GRE_ENCAP_TYPE */ nla_total_size(2) + /* IFLA_GRE_ENCAP_FLAGS */ nla_total_size(2) + /* IFLA_GRE_ENCAP_SPORT */ nla_total_size(2) + /* IFLA_GRE_ENCAP_DPORT */ nla_total_size(2) + /* IFLA_GRE_COLLECT_METADATA */ nla_total_size(0) + /* IFLA_GRE_IGNORE_DF */ nla_total_size(1) + /* IFLA_GRE_FWMARK */ nla_total_size(4) + /* IFLA_GRE_ERSPAN_INDEX */ nla_total_size(4) + /* IFLA_GRE_ERSPAN_VER */ nla_total_size(1) + /* IFLA_GRE_ERSPAN_DIR */ nla_total_size(1) + /* IFLA_GRE_ERSPAN_HWID */ nla_total_size(2) + 0; } static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm_kern *p = &t->parms; IP_TUNNEL_DECLARE_FLAGS(o_flags); ip_tunnel_flags_copy(o_flags, p->o_flags); if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, gre_tnl_flags_to_gre_flags(p->i_flags)) || nla_put_be16(skb, IFLA_GRE_OFLAGS, gre_tnl_flags_to_gre_flags(o_flags)) || nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || nla_put_in_addr(skb, IFLA_GRE_LOCAL, p->iph.saddr) || nla_put_in_addr(skb, IFLA_GRE_REMOTE, p->iph.daddr) || nla_put_u8(skb, IFLA_GRE_TTL, p->iph.ttl) || nla_put_u8(skb, IFLA_GRE_TOS, p->iph.tos) || nla_put_u8(skb, IFLA_GRE_PMTUDISC, !!(p->iph.frag_off & htons(IP_DF))) || nla_put_u32(skb, IFLA_GRE_FWMARK, t->fwmark)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_GRE_ENCAP_TYPE, t->encap.type) || nla_put_be16(skb, IFLA_GRE_ENCAP_SPORT, t->encap.sport) || nla_put_be16(skb, IFLA_GRE_ENCAP_DPORT, t->encap.dport) || nla_put_u16(skb, IFLA_GRE_ENCAP_FLAGS, t->encap.flags)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_GRE_IGNORE_DF, t->ignore_df)) goto nla_put_failure; if (t->collect_md) { if (nla_put_flag(skb, IFLA_GRE_COLLECT_METADATA)) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } static int erspan_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); if (t->erspan_ver <= 2) { if (t->erspan_ver != 0 && !t->collect_md) __set_bit(IP_TUNNEL_KEY_BIT, t->parms.o_flags); if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver)) goto nla_put_failure; if (t->erspan_ver == 1) { if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index)) goto nla_put_failure; } else if (t->erspan_ver == 2) { if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid)) goto nla_put_failure; } } return ipgre_fill_info(skb, dev); nla_put_failure: return -EMSGSIZE; } static void erspan_setup(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); ether_setup(dev); dev->max_mtu = 0; dev->netdev_ops = &erspan_netdev_ops; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; ip_tunnel_setup(dev, erspan_net_id); t->erspan_ver = 1; } static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = { [IFLA_GRE_LINK] = { .type = NLA_U32 }, [IFLA_GRE_IFLAGS] = { .type = NLA_U16 }, [IFLA_GRE_OFLAGS] = { .type = NLA_U16 }, [IFLA_GRE_IKEY] = { .type = NLA_U32 }, [IFLA_GRE_OKEY] = { .type = NLA_U32 }, [IFLA_GRE_LOCAL] = { .len = sizeof_field(struct iphdr, saddr) }, [IFLA_GRE_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_GRE_TTL] = { .type = NLA_U8 }, [IFLA_GRE_TOS] = { .type = NLA_U8 }, [IFLA_GRE_PMTUDISC] = { .type = NLA_U8 }, [IFLA_GRE_ENCAP_TYPE] = { .type = NLA_U16 }, [IFLA_GRE_ENCAP_FLAGS] = { .type = NLA_U16 }, [IFLA_GRE_ENCAP_SPORT] = { .type = NLA_U16 }, [IFLA_GRE_ENCAP_DPORT] = { .type = NLA_U16 }, [IFLA_GRE_COLLECT_METADATA] = { .type = NLA_FLAG }, [IFLA_GRE_IGNORE_DF] = { .type = NLA_U8 }, [IFLA_GRE_FWMARK] = { .type = NLA_U32 }, [IFLA_GRE_ERSPAN_INDEX] = { .type = NLA_U32 }, [IFLA_GRE_ERSPAN_VER] = { .type = NLA_U8 }, [IFLA_GRE_ERSPAN_DIR] = { .type = NLA_U8 }, [IFLA_GRE_ERSPAN_HWID] = { .type = NLA_U16 }, }; static struct rtnl_link_ops ipgre_link_ops __read_mostly = { .kind = "gre", .maxtype = IFLA_GRE_MAX, .policy = ipgre_policy, .priv_size = sizeof(struct ip_tunnel), .setup = ipgre_tunnel_setup, .validate = ipgre_tunnel_validate, .newlink = ipgre_newlink, .changelink = ipgre_changelink, .dellink = ip_tunnel_dellink, .get_size = ipgre_get_size, .fill_info = ipgre_fill_info, .get_link_net = ip_tunnel_get_link_net, }; static struct rtnl_link_ops ipgre_tap_ops __read_mostly = { .kind = "gretap", .maxtype = IFLA_GRE_MAX, .policy = ipgre_policy, .priv_size = sizeof(struct ip_tunnel), .setup = ipgre_tap_setup, .validate = ipgre_tap_validate, .newlink = ipgre_newlink, .changelink = ipgre_changelink, .dellink = ip_tunnel_dellink, .get_size = ipgre_get_size, .fill_info = ipgre_fill_info, .get_link_net = ip_tunnel_get_link_net, }; static struct rtnl_link_ops erspan_link_ops __read_mostly = { .kind = "erspan", .maxtype = IFLA_GRE_MAX, .policy = ipgre_policy, .priv_size = sizeof(struct ip_tunnel), .setup = erspan_setup, .validate = erspan_validate, .newlink = erspan_newlink, .changelink = erspan_changelink, .dellink = ip_tunnel_dellink, .get_size = ipgre_get_size, .fill_info = erspan_fill_info, .get_link_net = ip_tunnel_get_link_net, }; struct net_device *gretap_fb_dev_create(struct net *net, const char *name, u8 name_assign_type) { struct nlattr *tb[IFLA_MAX + 1]; struct net_device *dev; LIST_HEAD(list_kill); struct ip_tunnel *t; int err; memset(&tb, 0, sizeof(tb)); dev = rtnl_create_link(net, name, name_assign_type, &ipgre_tap_ops, tb, NULL); if (IS_ERR(dev)) return dev; /* Configure flow based GRE device. */ t = netdev_priv(dev); t->collect_md = true; err = ipgre_newlink(net, dev, tb, NULL, NULL); if (err < 0) { free_netdev(dev); return ERR_PTR(err); } /* openvswitch users expect packet sizes to be unrestricted, * so set the largest MTU we can. */ err = __ip_tunnel_change_mtu(dev, IP_MAX_MTU, false); if (err) goto out; err = rtnl_configure_link(dev, NULL, 0, NULL); if (err < 0) goto out; return dev; out: ip_tunnel_dellink(dev, &list_kill); unregister_netdevice_many(&list_kill); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(gretap_fb_dev_create); static int __net_init ipgre_tap_init_net(struct net *net) { return ip_tunnel_init_net(net, gre_tap_net_id, &ipgre_tap_ops, "gretap0"); } static void __net_exit ipgre_tap_exit_batch_rtnl(struct list_head *list_net, struct list_head *dev_to_kill) { ip_tunnel_delete_nets(list_net, gre_tap_net_id, &ipgre_tap_ops, dev_to_kill); } static struct pernet_operations ipgre_tap_net_ops = { .init = ipgre_tap_init_net, .exit_batch_rtnl = ipgre_tap_exit_batch_rtnl, .id = &gre_tap_net_id, .size = sizeof(struct ip_tunnel_net), }; static int __net_init erspan_init_net(struct net *net) { return ip_tunnel_init_net(net, erspan_net_id, &erspan_link_ops, "erspan0"); } static void __net_exit erspan_exit_batch_rtnl(struct list_head *net_list, struct list_head *dev_to_kill) { ip_tunnel_delete_nets(net_list, erspan_net_id, &erspan_link_ops, dev_to_kill); } static struct pernet_operations erspan_net_ops = { .init = erspan_init_net, .exit_batch_rtnl = erspan_exit_batch_rtnl, .id = &erspan_net_id, .size = sizeof(struct ip_tunnel_net), }; static int __init ipgre_init(void) { int err; pr_info("GRE over IPv4 tunneling driver\n"); err = register_pernet_device(&ipgre_net_ops); if (err < 0) return err; err = register_pernet_device(&ipgre_tap_net_ops); if (err < 0) goto pnet_tap_failed; err = register_pernet_device(&erspan_net_ops); if (err < 0) goto pnet_erspan_failed; err = gre_add_protocol(&ipgre_protocol, GREPROTO_CISCO); if (err < 0) { pr_info("%s: can't add protocol\n", __func__); goto add_proto_failed; } err = rtnl_link_register(&ipgre_link_ops); if (err < 0) goto rtnl_link_failed; err = rtnl_link_register(&ipgre_tap_ops); if (err < 0) goto tap_ops_failed; err = rtnl_link_register(&erspan_link_ops); if (err < 0) goto erspan_link_failed; return 0; erspan_link_failed: rtnl_link_unregister(&ipgre_tap_ops); tap_ops_failed: rtnl_link_unregister(&ipgre_link_ops); rtnl_link_failed: gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO); add_proto_failed: unregister_pernet_device(&erspan_net_ops); pnet_erspan_failed: unregister_pernet_device(&ipgre_tap_net_ops); pnet_tap_failed: unregister_pernet_device(&ipgre_net_ops); return err; } static void __exit ipgre_fini(void) { rtnl_link_unregister(&ipgre_tap_ops); rtnl_link_unregister(&ipgre_link_ops); rtnl_link_unregister(&erspan_link_ops); gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO); unregister_pernet_device(&ipgre_tap_net_ops); unregister_pernet_device(&ipgre_net_ops); unregister_pernet_device(&erspan_net_ops); } module_init(ipgre_init); module_exit(ipgre_fini); MODULE_DESCRIPTION("IPv4 GRE tunnels over IP library"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("gre"); MODULE_ALIAS_RTNL_LINK("gretap"); MODULE_ALIAS_RTNL_LINK("erspan"); MODULE_ALIAS_NETDEV("gre0"); MODULE_ALIAS_NETDEV("gretap0"); MODULE_ALIAS_NETDEV("erspan0"); |
| 399 48 48 213 217 | 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 | #undef TRACE_SYSTEM #define TRACE_SYSTEM neigh #if !defined(_TRACE_NEIGH_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_NEIGH_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/tracepoint.h> #include <net/neighbour.h> #define neigh_state_str(state) \ __print_symbolic(state, \ { NUD_INCOMPLETE, "incomplete" }, \ { NUD_REACHABLE, "reachable" }, \ { NUD_STALE, "stale" }, \ { NUD_DELAY, "delay" }, \ { NUD_PROBE, "probe" }, \ { NUD_FAILED, "failed" }, \ { NUD_NOARP, "noarp" }, \ { NUD_PERMANENT, "permanent"}) TRACE_EVENT(neigh_create, TP_PROTO(struct neigh_table *tbl, struct net_device *dev, const void *pkey, const struct neighbour *n, bool exempt_from_gc), TP_ARGS(tbl, dev, pkey, n, exempt_from_gc), TP_STRUCT__entry( __field(u32, family) __string(dev, dev ? dev->name : "NULL") __field(int, entries) __field(u8, created) __field(u8, gc_exempt) __array(u8, primary_key4, 4) __array(u8, primary_key6, 16) ), TP_fast_assign( __be32 *p32; __entry->family = tbl->family; __assign_str(dev); __entry->entries = atomic_read(&tbl->gc_entries); __entry->created = n != NULL; __entry->gc_exempt = exempt_from_gc; p32 = (__be32 *)__entry->primary_key4; if (tbl->family == AF_INET) *p32 = *(__be32 *)pkey; else *p32 = 0; #if IS_ENABLED(CONFIG_IPV6) if (tbl->family == AF_INET6) { struct in6_addr *pin6; pin6 = (struct in6_addr *)__entry->primary_key6; *pin6 = *(struct in6_addr *)pkey; } #endif ), TP_printk("family %d dev %s entries %d primary_key4 %pI4 primary_key6 %pI6c created %d gc_exempt %d", __entry->family, __get_str(dev), __entry->entries, __entry->primary_key4, __entry->primary_key6, __entry->created, __entry->gc_exempt) ); TRACE_EVENT(neigh_update, TP_PROTO(struct neighbour *n, const u8 *lladdr, u8 new, u32 flags, u32 nlmsg_pid), TP_ARGS(n, lladdr, new, flags, nlmsg_pid), TP_STRUCT__entry( __field(u32, family) __string(dev, (n->dev ? n->dev->name : "NULL")) __array(u8, lladdr, MAX_ADDR_LEN) __field(u8, lladdr_len) __field(u8, flags) __field(u8, nud_state) __field(u8, type) __field(u8, dead) __field(int, refcnt) __array(__u8, primary_key4, 4) __array(__u8, primary_key6, 16) __field(unsigned long, confirmed) __field(unsigned long, updated) __field(unsigned long, used) __array(u8, new_lladdr, MAX_ADDR_LEN) __field(u8, new_state) __field(u32, update_flags) __field(u32, pid) ), TP_fast_assign( int lladdr_len = (n->dev ? n->dev->addr_len : MAX_ADDR_LEN); struct in6_addr *pin6; __be32 *p32; __entry->family = n->tbl->family; __assign_str(dev); __entry->lladdr_len = lladdr_len; memcpy(__entry->lladdr, n->ha, lladdr_len); __entry->flags = n->flags; __entry->nud_state = n->nud_state; __entry->type = n->type; __entry->dead = n->dead; __entry->refcnt = refcount_read(&n->refcnt); pin6 = (struct in6_addr *)__entry->primary_key6; p32 = (__be32 *)__entry->primary_key4; if (n->tbl->family == AF_INET) *p32 = *(__be32 *)n->primary_key; else *p32 = 0; #if IS_ENABLED(CONFIG_IPV6) if (n->tbl->family == AF_INET6) { pin6 = (struct in6_addr *)__entry->primary_key6; *pin6 = *(struct in6_addr *)n->primary_key; } else #endif { ipv6_addr_set_v4mapped(*p32, pin6); } __entry->confirmed = n->confirmed; __entry->updated = n->updated; __entry->used = n->used; if (lladdr) memcpy(__entry->new_lladdr, lladdr, lladdr_len); __entry->new_state = new; __entry->update_flags = flags; __entry->pid = nlmsg_pid; ), TP_printk("family %d dev %s lladdr %s flags %02x nud_state %s type %02x " "dead %d refcnt %d primary_key4 %pI4 primary_key6 %pI6c " "confirmed %lu updated %lu used %lu new_lladdr %s " "new_state %s update_flags %02x pid %d", __entry->family, __get_str(dev), __print_hex_str(__entry->lladdr, __entry->lladdr_len), __entry->flags, neigh_state_str(__entry->nud_state), __entry->type, __entry->dead, __entry->refcnt, __entry->primary_key4, __entry->primary_key6, __entry->confirmed, __entry->updated, __entry->used, __print_hex_str(__entry->new_lladdr, __entry->lladdr_len), neigh_state_str(__entry->new_state), __entry->update_flags, __entry->pid) ); DECLARE_EVENT_CLASS(neigh__update, TP_PROTO(struct neighbour *n, int err), TP_ARGS(n, err), TP_STRUCT__entry( __field(u32, family) __string(dev, (n->dev ? n->dev->name : "NULL")) __array(u8, lladdr, MAX_ADDR_LEN) __field(u8, lladdr_len) __field(u8, flags) __field(u8, nud_state) __field(u8, type) __field(u8, dead) __field(int, refcnt) __array(__u8, primary_key4, 4) __array(__u8, primary_key6, 16) __field(unsigned long, confirmed) __field(unsigned long, updated) __field(unsigned long, used) __field(u32, err) ), TP_fast_assign( int lladdr_len = (n->dev ? n->dev->addr_len : MAX_ADDR_LEN); struct in6_addr *pin6; __be32 *p32; __entry->family = n->tbl->family; __assign_str(dev); __entry->lladdr_len = lladdr_len; memcpy(__entry->lladdr, n->ha, lladdr_len); __entry->flags = n->flags; __entry->nud_state = n->nud_state; __entry->type = n->type; __entry->dead = n->dead; __entry->refcnt = refcount_read(&n->refcnt); pin6 = (struct in6_addr *)__entry->primary_key6; p32 = (__be32 *)__entry->primary_key4; if (n->tbl->family == AF_INET) *p32 = *(__be32 *)n->primary_key; else *p32 = 0; #if IS_ENABLED(CONFIG_IPV6) if (n->tbl->family == AF_INET6) { pin6 = (struct in6_addr *)__entry->primary_key6; *pin6 = *(struct in6_addr *)n->primary_key; } else #endif { ipv6_addr_set_v4mapped(*p32, pin6); } __entry->confirmed = n->confirmed; __entry->updated = n->updated; __entry->used = n->used; __entry->err = err; ), TP_printk("family %d dev %s lladdr %s flags %02x nud_state %s type %02x " "dead %d refcnt %d primary_key4 %pI4 primary_key6 %pI6c " "confirmed %lu updated %lu used %lu err %d", __entry->family, __get_str(dev), __print_hex_str(__entry->lladdr, __entry->lladdr_len), __entry->flags, neigh_state_str(__entry->nud_state), __entry->type, __entry->dead, __entry->refcnt, __entry->primary_key4, __entry->primary_key6, __entry->confirmed, __entry->updated, __entry->used, __entry->err) ); DEFINE_EVENT(neigh__update, neigh_update_done, TP_PROTO(struct neighbour *neigh, int err), TP_ARGS(neigh, err) ); DEFINE_EVENT(neigh__update, neigh_timer_handler, TP_PROTO(struct neighbour *neigh, int err), TP_ARGS(neigh, err) ); DEFINE_EVENT(neigh__update, neigh_event_send_done, TP_PROTO(struct neighbour *neigh, int err), TP_ARGS(neigh, err) ); DEFINE_EVENT(neigh__update, neigh_event_send_dead, TP_PROTO(struct neighbour *neigh, int err), TP_ARGS(neigh, err) ); DEFINE_EVENT(neigh__update, neigh_cleanup_and_release, TP_PROTO(struct neighbour *neigh, int rc), TP_ARGS(neigh, rc) ); #endif /* _TRACE_NEIGH_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 5 5 5 5 4 5 5 3 2 16 1 15 5 10 15 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * AppArmor security module * * This file contains AppArmor policy manipulation functions * * Copyright (C) 1998-2008 Novell/SUSE * Copyright 2009-2010 Canonical Ltd. * * AppArmor policy is based around profiles, which contain the rules a * task is confined by. Every task in the system has a profile attached * to it determined either by matching "unconfined" tasks against the * visible set of profiles or by following a profiles attachment rules. * * Each profile exists in a profile namespace which is a container of * visible profiles. Each namespace contains a special "unconfined" profile, * which doesn't enforce any confinement on a task beyond DAC. * * Namespace and profile names can be written together in either * of two syntaxes. * :namespace:profile - used by kernel interfaces for easy detection * namespace://profile - used by policy * * Profile names can not start with : or @ or ^ and may not contain \0 * * Reserved profile names * unconfined - special automatically generated unconfined profile * inherit - special name to indicate profile inheritance * null-XXXX-YYYY - special automatically generated learning profiles * * Namespace names may not start with / or @ and may not contain \0 or : * Reserved namespace names * user-XXXX - user defined profiles * * a // in a profile or namespace name indicates a hierarchical name with the * name before the // being the parent and the name after the child. * * Profile and namespace hierarchies serve two different but similar purposes. * The namespace contains the set of visible profiles that are considered * for attachment. The hierarchy of namespaces allows for virtualizing * the namespace so that for example a chroot can have its own set of profiles * which may define some local user namespaces. * The profile hierarchy severs two distinct purposes, * - it allows for sub profiles or hats, which allows an application to run * subprograms under its own profile with different restriction than it * self, and not have it use the system profile. * eg. if a mail program starts an editor, the policy might make the * restrictions tighter on the editor tighter than the mail program, * and definitely different than general editor restrictions * - it allows for binary hierarchy of profiles, so that execution history * is preserved. This feature isn't exploited by AppArmor reference policy * but is allowed. NOTE: this is currently suboptimal because profile * aliasing is not currently implemented so that a profile for each * level must be defined. * eg. /bin/bash///bin/ls as a name would indicate /bin/ls was started * from /bin/bash * * A profile or namespace name that can contain one or more // separators * is referred to as an hname (hierarchical). * eg. /bin/bash//bin/ls * * An fqname is a name that may contain both namespace and profile hnames. * eg. :ns:/bin/bash//bin/ls * * NOTES: * - locking of profile lists is currently fairly coarse. All profile * lists within a namespace use the namespace lock. * FIXME: move profile lists to using rcu_lists */ #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/string.h> #include <linux/cred.h> #include <linux/rculist.h> #include <linux/user_namespace.h> #include "include/apparmor.h" #include "include/capability.h" #include "include/cred.h" #include "include/file.h" #include "include/ipc.h" #include "include/match.h" #include "include/path.h" #include "include/policy.h" #include "include/policy_ns.h" #include "include/policy_unpack.h" #include "include/resource.h" int unprivileged_userns_apparmor_policy = 1; int aa_unprivileged_unconfined_restricted; const char *const aa_profile_mode_names[] = { "enforce", "complain", "kill", "unconfined", "user", }; static void aa_free_pdb(struct aa_policydb *pdb) { if (pdb) { aa_put_dfa(pdb->dfa); kvfree(pdb->perms); aa_free_str_table(&pdb->trans); kfree(pdb); } } /** * aa_pdb_free_kref - free aa_policydb by kref (called by aa_put_pdb) * @kref: kref callback for freeing of a dfa (NOT NULL) */ void aa_pdb_free_kref(struct kref *kref) { struct aa_policydb *pdb = container_of(kref, struct aa_policydb, count); aa_free_pdb(pdb); } struct aa_policydb *aa_alloc_pdb(gfp_t gfp) { struct aa_policydb *pdb = kzalloc(sizeof(struct aa_policydb), gfp); if (!pdb) return NULL; kref_init(&pdb->count); return pdb; } /** * __add_profile - add a profiles to list and label tree * @list: list to add it to (NOT NULL) * @profile: the profile to add (NOT NULL) * * refcount @profile, should be put by __list_remove_profile * * Requires: namespace lock be held, or list not be shared */ static void __add_profile(struct list_head *list, struct aa_profile *profile) { struct aa_label *l; AA_BUG(!list); AA_BUG(!profile); AA_BUG(!profile->ns); AA_BUG(!mutex_is_locked(&profile->ns->lock)); list_add_rcu(&profile->base.list, list); /* get list reference */ aa_get_profile(profile); l = aa_label_insert(&profile->ns->labels, &profile->label); AA_BUG(l != &profile->label); aa_put_label(l); } /** * __list_remove_profile - remove a profile from the list it is on * @profile: the profile to remove (NOT NULL) * * remove a profile from the list, warning generally removal should * be done with __replace_profile as most profile removals are * replacements to the unconfined profile. * * put @profile list refcount * * Requires: namespace lock be held, or list not have been live */ static void __list_remove_profile(struct aa_profile *profile) { AA_BUG(!profile); AA_BUG(!profile->ns); AA_BUG(!mutex_is_locked(&profile->ns->lock)); list_del_rcu(&profile->base.list); aa_put_profile(profile); } /** * __remove_profile - remove old profile, and children * @profile: profile to be replaced (NOT NULL) * * Requires: namespace list lock be held, or list not be shared */ static void __remove_profile(struct aa_profile *profile) { AA_BUG(!profile); AA_BUG(!profile->ns); AA_BUG(!mutex_is_locked(&profile->ns->lock)); /* release any children lists first */ __aa_profile_list_release(&profile->base.profiles); /* released by free_profile */ aa_label_remove(&profile->label); __aafs_profile_rmdir(profile); __list_remove_profile(profile); } /** * __aa_profile_list_release - remove all profiles on the list and put refs * @head: list of profiles (NOT NULL) * * Requires: namespace lock be held */ void __aa_profile_list_release(struct list_head *head) { struct aa_profile *profile, *tmp; list_for_each_entry_safe(profile, tmp, head, base.list) __remove_profile(profile); } /** * aa_free_data - free a data blob * @ptr: data to free * @arg: unused */ static void aa_free_data(void *ptr, void *arg) { struct aa_data *data = ptr; kvfree_sensitive(data->data, data->size); kfree_sensitive(data->key); kfree_sensitive(data); } static void free_attachment(struct aa_attachment *attach) { int i; for (i = 0; i < attach->xattr_count; i++) kfree_sensitive(attach->xattrs[i]); kfree_sensitive(attach->xattrs); aa_put_pdb(attach->xmatch); } static void free_ruleset(struct aa_ruleset *rules) { int i; aa_put_pdb(rules->file); aa_put_pdb(rules->policy); aa_free_cap_rules(&rules->caps); aa_free_rlimit_rules(&rules->rlimits); for (i = 0; i < rules->secmark_count; i++) kfree_sensitive(rules->secmark[i].label); kfree_sensitive(rules->secmark); kfree_sensitive(rules); } struct aa_ruleset *aa_alloc_ruleset(gfp_t gfp) { struct aa_ruleset *rules; rules = kzalloc(sizeof(*rules), gfp); if (rules) INIT_LIST_HEAD(&rules->list); return rules; } /** * aa_free_profile - free a profile * @profile: the profile to free (MAYBE NULL) * * Free a profile, its hats and null_profile. All references to the profile, * its hats and null_profile must have been put. * * If the profile was referenced from a task context, free_profile() will * be called from an rcu callback routine, so we must not sleep here. */ void aa_free_profile(struct aa_profile *profile) { struct aa_ruleset *rule, *tmp; struct rhashtable *rht; AA_DEBUG("%s(%p)\n", __func__, profile); if (!profile) return; /* free children profiles */ aa_policy_destroy(&profile->base); aa_put_profile(rcu_access_pointer(profile->parent)); aa_put_ns(profile->ns); kfree_sensitive(profile->rename); kfree_sensitive(profile->disconnected); free_attachment(&profile->attach); /* * at this point there are no tasks that can have a reference * to rules */ list_for_each_entry_safe(rule, tmp, &profile->rules, list) { list_del_init(&rule->list); free_ruleset(rule); } kfree_sensitive(profile->dirname); if (profile->data) { rht = profile->data; profile->data = NULL; rhashtable_free_and_destroy(rht, aa_free_data, NULL); kfree_sensitive(rht); } kfree_sensitive(profile->hash); aa_put_loaddata(profile->rawdata); aa_label_destroy(&profile->label); kfree_sensitive(profile); } /** * aa_alloc_profile - allocate, initialize and return a new profile * @hname: name of the profile (NOT NULL) * @proxy: proxy to use OR null if to allocate a new one * @gfp: allocation type * * Returns: refcount profile or NULL on failure */ struct aa_profile *aa_alloc_profile(const char *hname, struct aa_proxy *proxy, gfp_t gfp) { struct aa_profile *profile; struct aa_ruleset *rules; /* freed by free_profile - usually through aa_put_profile */ profile = kzalloc(struct_size(profile, label.vec, 2), gfp); if (!profile) return NULL; if (!aa_policy_init(&profile->base, NULL, hname, gfp)) goto fail; if (!aa_label_init(&profile->label, 1, gfp)) goto fail; INIT_LIST_HEAD(&profile->rules); /* allocate the first ruleset, but leave it empty */ rules = aa_alloc_ruleset(gfp); if (!rules) goto fail; list_add(&rules->list, &profile->rules); /* update being set needed by fs interface */ if (!proxy) { proxy = aa_alloc_proxy(&profile->label, gfp); if (!proxy) goto fail; } else aa_get_proxy(proxy); profile->label.proxy = proxy; profile->label.hname = profile->base.hname; profile->label.flags |= FLAG_PROFILE; profile->label.vec[0] = profile; /* refcount released by caller */ return profile; fail: aa_free_profile(profile); return NULL; } /* TODO: profile accounting - setup in remove */ /** * __strn_find_child - find a profile on @head list using substring of @name * @head: list to search (NOT NULL) * @name: name of profile (NOT NULL) * @len: length of @name substring to match * * Requires: rcu_read_lock be held * * Returns: unrefcounted profile ptr, or NULL if not found */ static struct aa_profile *__strn_find_child(struct list_head *head, const char *name, int len) { return (struct aa_profile *)__policy_strn_find(head, name, len); } /** * __find_child - find a profile on @head list with a name matching @name * @head: list to search (NOT NULL) * @name: name of profile (NOT NULL) * * Requires: rcu_read_lock be held * * Returns: unrefcounted profile ptr, or NULL if not found */ static struct aa_profile *__find_child(struct list_head *head, const char *name) { return __strn_find_child(head, name, strlen(name)); } /** * aa_find_child - find a profile by @name in @parent * @parent: profile to search (NOT NULL) * @name: profile name to search for (NOT NULL) * * Returns: a refcounted profile or NULL if not found */ struct aa_profile *aa_find_child(struct aa_profile *parent, const char *name) { struct aa_profile *profile; rcu_read_lock(); do { profile = __find_child(&parent->base.profiles, name); } while (profile && !aa_get_profile_not0(profile)); rcu_read_unlock(); /* refcount released by caller */ return profile; } /** * __lookup_parent - lookup the parent of a profile of name @hname * @ns: namespace to lookup profile in (NOT NULL) * @hname: hierarchical profile name to find parent of (NOT NULL) * * Lookups up the parent of a fully qualified profile name, the profile * that matches hname does not need to exist, in general this * is used to load a new profile. * * Requires: rcu_read_lock be held * * Returns: unrefcounted policy or NULL if not found */ static struct aa_policy *__lookup_parent(struct aa_ns *ns, const char *hname) { struct aa_policy *policy; struct aa_profile *profile = NULL; char *split; policy = &ns->base; for (split = strstr(hname, "//"); split;) { profile = __strn_find_child(&policy->profiles, hname, split - hname); if (!profile) return NULL; policy = &profile->base; hname = split + 2; split = strstr(hname, "//"); } if (!profile) return &ns->base; return &profile->base; } /** * __create_missing_ancestors - create place holders for missing ancestores * @ns: namespace to lookup profile in (NOT NULL) * @hname: hierarchical profile name to find parent of (NOT NULL) * @gfp: type of allocation. * * Requires: ns mutex lock held * * Return: unrefcounted parent policy on success or %NULL if error creating * place holder profiles. */ static struct aa_policy *__create_missing_ancestors(struct aa_ns *ns, const char *hname, gfp_t gfp) { struct aa_policy *policy; struct aa_profile *parent, *profile = NULL; char *split; AA_BUG(!ns); AA_BUG(!hname); policy = &ns->base; for (split = strstr(hname, "//"); split;) { parent = profile; profile = __strn_find_child(&policy->profiles, hname, split - hname); if (!profile) { const char *name = kstrndup(hname, split - hname, gfp); if (!name) return NULL; profile = aa_alloc_null(parent, name, gfp); kfree(name); if (!profile) return NULL; if (!parent) profile->ns = aa_get_ns(ns); } policy = &profile->base; hname = split + 2; split = strstr(hname, "//"); } if (!profile) return &ns->base; return &profile->base; } /** * __lookupn_profile - lookup the profile matching @hname * @base: base list to start looking up profile name from (NOT NULL) * @hname: hierarchical profile name (NOT NULL) * @n: length of @hname * * Requires: rcu_read_lock be held * * Returns: unrefcounted profile pointer or NULL if not found * * Do a relative name lookup, recursing through profile tree. */ static struct aa_profile *__lookupn_profile(struct aa_policy *base, const char *hname, size_t n) { struct aa_profile *profile = NULL; const char *split; for (split = strnstr(hname, "//", n); split; split = strnstr(hname, "//", n)) { profile = __strn_find_child(&base->profiles, hname, split - hname); if (!profile) return NULL; base = &profile->base; n -= split + 2 - hname; hname = split + 2; } if (n) return __strn_find_child(&base->profiles, hname, n); return NULL; } static struct aa_profile *__lookup_profile(struct aa_policy *base, const char *hname) { return __lookupn_profile(base, hname, strlen(hname)); } /** * aa_lookupn_profile - find a profile by its full or partial name * @ns: the namespace to start from (NOT NULL) * @hname: name to do lookup on. Does not contain namespace prefix (NOT NULL) * @n: size of @hname * * Returns: refcounted profile or NULL if not found */ struct aa_profile *aa_lookupn_profile(struct aa_ns *ns, const char *hname, size_t n) { struct aa_profile *profile; rcu_read_lock(); do { profile = __lookupn_profile(&ns->base, hname, n); } while (profile && !aa_get_profile_not0(profile)); rcu_read_unlock(); /* the unconfined profile is not in the regular profile list */ if (!profile && strncmp(hname, "unconfined", n) == 0) profile = aa_get_newest_profile(ns->unconfined); /* refcount released by caller */ return profile; } struct aa_profile *aa_fqlookupn_profile(struct aa_label *base, const char *fqname, size_t n) { struct aa_profile *profile; struct aa_ns *ns; const char *name, *ns_name; size_t ns_len; name = aa_splitn_fqname(fqname, n, &ns_name, &ns_len); if (ns_name) { ns = aa_lookupn_ns(labels_ns(base), ns_name, ns_len); if (!ns) return NULL; } else ns = aa_get_ns(labels_ns(base)); if (name) profile = aa_lookupn_profile(ns, name, n - (name - fqname)); else if (ns) /* default profile for ns, currently unconfined */ profile = aa_get_newest_profile(ns->unconfined); else profile = NULL; aa_put_ns(ns); return profile; } struct aa_profile *aa_alloc_null(struct aa_profile *parent, const char *name, gfp_t gfp) { struct aa_profile *profile; struct aa_ruleset *rules; profile = aa_alloc_profile(name, NULL, gfp); if (!profile) return NULL; /* TODO: ideally we should inherit abi from parent */ profile->label.flags |= FLAG_NULL; profile->attach.xmatch = aa_get_pdb(nullpdb); rules = list_first_entry(&profile->rules, typeof(*rules), list); rules->file = aa_get_pdb(nullpdb); rules->policy = aa_get_pdb(nullpdb); if (parent) { profile->path_flags = parent->path_flags; /* released on free_profile */ rcu_assign_pointer(profile->parent, aa_get_profile(parent)); profile->ns = aa_get_ns(parent->ns); } return profile; } /** * aa_new_learning_profile - create or find a null-X learning profile * @parent: profile that caused this profile to be created (NOT NULL) * @hat: true if the null- learning profile is a hat * @base: name to base the null profile off of * @gfp: type of allocation * * Find/Create a null- complain mode profile used in learning mode. The * name of the profile is unique and follows the format of parent//null-XXX. * where XXX is based on the @name or if that fails or is not supplied * a unique number * * null profiles are added to the profile list but the list does not * hold a count on them so that they are automatically released when * not in use. * * Returns: new refcounted profile else NULL on failure */ struct aa_profile *aa_new_learning_profile(struct aa_profile *parent, bool hat, const char *base, gfp_t gfp) { struct aa_profile *p, *profile; const char *bname; char *name = NULL; AA_BUG(!parent); if (base) { name = kmalloc(strlen(parent->base.hname) + 8 + strlen(base), gfp); if (name) { sprintf(name, "%s//null-%s", parent->base.hname, base); goto name; } /* fall through to try shorter uniq */ } name = kmalloc(strlen(parent->base.hname) + 2 + 7 + 8, gfp); if (!name) return NULL; sprintf(name, "%s//null-%x", parent->base.hname, atomic_inc_return(&parent->ns->uniq_null)); name: /* lookup to see if this is a dup creation */ bname = basename(name); profile = aa_find_child(parent, bname); if (profile) goto out; profile = aa_alloc_null(parent, name, gfp); if (!profile) goto fail; profile->mode = APPARMOR_COMPLAIN; if (hat) profile->label.flags |= FLAG_HAT; mutex_lock_nested(&profile->ns->lock, profile->ns->level); p = __find_child(&parent->base.profiles, bname); if (p) { aa_free_profile(profile); profile = aa_get_profile(p); } else { __add_profile(&parent->base.profiles, profile); } mutex_unlock(&profile->ns->lock); /* refcount released by caller */ out: kfree(name); return profile; fail: kfree(name); aa_free_profile(profile); return NULL; } /** * replacement_allowed - test to see if replacement is allowed * @profile: profile to test if it can be replaced (MAYBE NULL) * @noreplace: true if replacement shouldn't be allowed but addition is okay * @info: Returns - info about why replacement failed (NOT NULL) * * Returns: %0 if replacement allowed else error code */ static int replacement_allowed(struct aa_profile *profile, int noreplace, const char **info) { if (profile) { if (profile->label.flags & FLAG_IMMUTIBLE) { *info = "cannot replace immutable profile"; return -EPERM; } else if (noreplace) { *info = "profile already exists"; return -EEXIST; } } return 0; } /* audit callback for net specific fields */ static void audit_cb(struct audit_buffer *ab, void *va) { struct common_audit_data *sa = va; struct apparmor_audit_data *ad = aad(sa); if (ad->iface.ns) { audit_log_format(ab, " ns="); audit_log_untrustedstring(ab, ad->iface.ns); } } /** * audit_policy - Do auditing of policy changes * @subj_label: label to check if it can manage policy * @op: policy operation being performed * @ns_name: name of namespace being manipulated * @name: name of profile being manipulated (NOT NULL) * @info: any extra information to be audited (MAYBE NULL) * @error: error code * * Returns: the error to be returned after audit is done */ static int audit_policy(struct aa_label *subj_label, const char *op, const char *ns_name, const char *name, const char *info, int error) { DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_NONE, AA_CLASS_NONE, op); ad.iface.ns = ns_name; ad.name = name; ad.info = info; ad.error = error; ad.subj_label = subj_label; aa_audit_msg(AUDIT_APPARMOR_STATUS, &ad, audit_cb); return error; } /* don't call out to other LSMs in the stack for apparmor policy admin * permissions */ static int policy_ns_capable(const struct cred *subj_cred, struct aa_label *label, struct user_namespace *userns, int cap) { int err; /* check for MAC_ADMIN cap in cred */ err = cap_capable(subj_cred, userns, cap, CAP_OPT_NONE); if (!err) err = aa_capable(subj_cred, label, cap, CAP_OPT_NONE); return err; } /** * aa_policy_view_capable - check if viewing policy in at @ns is allowed * @subj_cred: cred of subject * @label: label that is trying to view policy in ns * @ns: namespace being viewed by @label (may be NULL if @label's ns) * * Returns: true if viewing policy is allowed * * If @ns is NULL then the namespace being viewed is assumed to be the * tasks current namespace. */ bool aa_policy_view_capable(const struct cred *subj_cred, struct aa_label *label, struct aa_ns *ns) { struct user_namespace *user_ns = subj_cred->user_ns; struct aa_ns *view_ns = labels_view(label); bool root_in_user_ns = uid_eq(current_euid(), make_kuid(user_ns, 0)) || in_egroup_p(make_kgid(user_ns, 0)); bool response = false; if (!ns) ns = view_ns; if (root_in_user_ns && aa_ns_visible(view_ns, ns, true) && (user_ns == &init_user_ns || (unprivileged_userns_apparmor_policy != 0 && user_ns->level == view_ns->level))) response = true; return response; } bool aa_policy_admin_capable(const struct cred *subj_cred, struct aa_label *label, struct aa_ns *ns) { struct user_namespace *user_ns = subj_cred->user_ns; bool capable = policy_ns_capable(subj_cred, label, user_ns, CAP_MAC_ADMIN) == 0; AA_DEBUG("cap_mac_admin? %d\n", capable); AA_DEBUG("policy locked? %d\n", aa_g_lock_policy); return aa_policy_view_capable(subj_cred, label, ns) && capable && !aa_g_lock_policy; } bool aa_current_policy_view_capable(struct aa_ns *ns) { struct aa_label *label; bool res; label = __begin_current_label_crit_section(); res = aa_policy_view_capable(current_cred(), label, ns); __end_current_label_crit_section(label); return res; } bool aa_current_policy_admin_capable(struct aa_ns *ns) { struct aa_label *label; bool res; label = __begin_current_label_crit_section(); res = aa_policy_admin_capable(current_cred(), label, ns); __end_current_label_crit_section(label); return res; } /** * aa_may_manage_policy - can the current task manage policy * @subj_cred: subjects cred * @label: label to check if it can manage policy * @ns: namespace being managed by @label (may be NULL if @label's ns) * @mask: contains the policy manipulation operation being done * * Returns: 0 if the task is allowed to manipulate policy else error */ int aa_may_manage_policy(const struct cred *subj_cred, struct aa_label *label, struct aa_ns *ns, u32 mask) { const char *op; if (mask & AA_MAY_REMOVE_POLICY) op = OP_PROF_RM; else if (mask & AA_MAY_REPLACE_POLICY) op = OP_PROF_REPL; else op = OP_PROF_LOAD; /* check if loading policy is locked out */ if (aa_g_lock_policy) return audit_policy(label, op, NULL, NULL, "policy_locked", -EACCES); if (!aa_policy_admin_capable(subj_cred, label, ns)) return audit_policy(label, op, NULL, NULL, "not policy admin", -EACCES); /* TODO: add fine grained mediation of policy loads */ return 0; } static struct aa_profile *__list_lookup_parent(struct list_head *lh, struct aa_profile *profile) { const char *base = basename(profile->base.hname); long len = base - profile->base.hname; struct aa_load_ent *ent; /* parent won't have trailing // so remove from len */ if (len <= 2) return NULL; len -= 2; list_for_each_entry(ent, lh, list) { if (ent->new == profile) continue; if (strncmp(ent->new->base.hname, profile->base.hname, len) == 0 && ent->new->base.hname[len] == 0) return ent->new; } return NULL; } /** * __replace_profile - replace @old with @new on a list * @old: profile to be replaced (NOT NULL) * @new: profile to replace @old with (NOT NULL) * * Will duplicate and refcount elements that @new inherits from @old * and will inherit @old children. * * refcount @new for list, put @old list refcount * * Requires: namespace list lock be held, or list not be shared */ static void __replace_profile(struct aa_profile *old, struct aa_profile *new) { struct aa_profile *child, *tmp; if (!list_empty(&old->base.profiles)) { LIST_HEAD(lh); list_splice_init_rcu(&old->base.profiles, &lh, synchronize_rcu); list_for_each_entry_safe(child, tmp, &lh, base.list) { struct aa_profile *p; list_del_init(&child->base.list); p = __find_child(&new->base.profiles, child->base.name); if (p) { /* @p replaces @child */ __replace_profile(child, p); continue; } /* inherit @child and its children */ /* TODO: update hname of inherited children */ /* list refcount transferred to @new */ p = aa_deref_parent(child); rcu_assign_pointer(child->parent, aa_get_profile(new)); list_add_rcu(&child->base.list, &new->base.profiles); aa_put_profile(p); } } if (!rcu_access_pointer(new->parent)) { struct aa_profile *parent = aa_deref_parent(old); rcu_assign_pointer(new->parent, aa_get_profile(parent)); } aa_label_replace(&old->label, &new->label); /* migrate dents must come after label replacement b/c update */ __aafs_profile_migrate_dents(old, new); if (list_empty(&new->base.list)) { /* new is not on a list already */ list_replace_rcu(&old->base.list, &new->base.list); aa_get_profile(new); aa_put_profile(old); } else __list_remove_profile(old); } /** * __lookup_replace - lookup replacement information for a profile * @ns: namespace the lookup occurs in * @hname: name of profile to lookup * @noreplace: true if not replacing an existing profile * @p: Returns - profile to be replaced * @info: Returns - info string on why lookup failed * * Returns: profile to replace (no ref) on success else ptr error */ static int __lookup_replace(struct aa_ns *ns, const char *hname, bool noreplace, struct aa_profile **p, const char **info) { *p = aa_get_profile(__lookup_profile(&ns->base, hname)); if (*p) { int error = replacement_allowed(*p, noreplace, info); if (error) { *info = "profile can not be replaced"; return error; } } return 0; } static void share_name(struct aa_profile *old, struct aa_profile *new) { aa_put_str(new->base.hname); aa_get_str(old->base.hname); new->base.hname = old->base.hname; new->base.name = old->base.name; new->label.hname = old->label.hname; } /* Update to newest version of parent after previous replacements * Returns: unrefcount newest version of parent */ static struct aa_profile *update_to_newest_parent(struct aa_profile *new) { struct aa_profile *parent, *newest; parent = rcu_dereference_protected(new->parent, mutex_is_locked(&new->ns->lock)); newest = aa_get_newest_profile(parent); /* parent replaced in this atomic set? */ if (newest != parent) { aa_put_profile(parent); rcu_assign_pointer(new->parent, newest); } else aa_put_profile(newest); return newest; } /** * aa_replace_profiles - replace profile(s) on the profile list * @policy_ns: namespace load is occurring on * @label: label that is attempting to load/replace policy * @mask: permission mask * @udata: serialized data stream (NOT NULL) * * unpack and replace a profile on the profile list and uses of that profile * by any task creds via invalidating the old version of the profile, which * tasks will notice to update their own cred. If the profile does not exist * on the profile list it is added. * * Returns: size of data consumed else error code on failure. */ ssize_t aa_replace_profiles(struct aa_ns *policy_ns, struct aa_label *label, u32 mask, struct aa_loaddata *udata) { const char *ns_name = NULL, *info = NULL; struct aa_ns *ns = NULL; struct aa_load_ent *ent, *tmp; struct aa_loaddata *rawdata_ent; const char *op; ssize_t count, error; LIST_HEAD(lh); op = mask & AA_MAY_REPLACE_POLICY ? OP_PROF_REPL : OP_PROF_LOAD; aa_get_loaddata(udata); /* released below */ error = aa_unpack(udata, &lh, &ns_name); if (error) goto out; /* ensure that profiles are all for the same ns * TODO: update locking to remove this constaint. All profiles in * the load set must succeed as a set or the load will * fail. Sort ent list and take ns locks in hierarchy order */ count = 0; list_for_each_entry(ent, &lh, list) { if (ns_name) { if (ent->ns_name && strcmp(ent->ns_name, ns_name) != 0) { info = "policy load has mixed namespaces"; error = -EACCES; goto fail; } } else if (ent->ns_name) { if (count) { info = "policy load has mixed namespaces"; error = -EACCES; goto fail; } ns_name = ent->ns_name; } else count++; } if (ns_name) { ns = aa_prepare_ns(policy_ns ? policy_ns : labels_ns(label), ns_name); if (IS_ERR(ns)) { op = OP_PROF_LOAD; info = "failed to prepare namespace"; error = PTR_ERR(ns); ns = NULL; ent = NULL; goto fail; } } else ns = aa_get_ns(policy_ns ? policy_ns : labels_ns(label)); mutex_lock_nested(&ns->lock, ns->level); /* check for duplicate rawdata blobs: space and file dedup */ if (!list_empty(&ns->rawdata_list)) { list_for_each_entry(rawdata_ent, &ns->rawdata_list, list) { if (aa_rawdata_eq(rawdata_ent, udata)) { struct aa_loaddata *tmp; tmp = __aa_get_loaddata(rawdata_ent); /* check we didn't fail the race */ if (tmp) { aa_put_loaddata(udata); udata = tmp; break; } } } } /* setup parent and ns info */ list_for_each_entry(ent, &lh, list) { struct aa_policy *policy; struct aa_profile *p; if (aa_g_export_binary) ent->new->rawdata = aa_get_loaddata(udata); error = __lookup_replace(ns, ent->new->base.hname, !(mask & AA_MAY_REPLACE_POLICY), &ent->old, &info); if (error) goto fail_lock; if (ent->new->rename) { error = __lookup_replace(ns, ent->new->rename, !(mask & AA_MAY_REPLACE_POLICY), &ent->rename, &info); if (error) goto fail_lock; } /* released when @new is freed */ ent->new->ns = aa_get_ns(ns); if (ent->old || ent->rename) continue; /* no ref on policy only use inside lock */ p = NULL; policy = __lookup_parent(ns, ent->new->base.hname); if (!policy) { /* first check for parent in the load set */ p = __list_lookup_parent(&lh, ent->new); if (!p) { /* * fill in missing parent with null * profile that doesn't have * permissions. This allows for * individual profile loading where * the child is loaded before the * parent, and outside of the current * atomic set. This unfortunately can * happen with some userspaces. The * null profile will be replaced once * the parent is loaded. */ policy = __create_missing_ancestors(ns, ent->new->base.hname, GFP_KERNEL); if (!policy) { error = -ENOENT; info = "parent does not exist"; goto fail_lock; } } } if (!p && policy != &ns->base) /* released on profile replacement or free_profile */ p = (struct aa_profile *) policy; rcu_assign_pointer(ent->new->parent, aa_get_profile(p)); } /* create new fs entries for introspection if needed */ if (!udata->dents[AAFS_LOADDATA_DIR] && aa_g_export_binary) { error = __aa_fs_create_rawdata(ns, udata); if (error) { info = "failed to create raw_data dir and files"; ent = NULL; goto fail_lock; } } list_for_each_entry(ent, &lh, list) { if (!ent->old) { struct dentry *parent; if (rcu_access_pointer(ent->new->parent)) { struct aa_profile *p; p = aa_deref_parent(ent->new); parent = prof_child_dir(p); } else parent = ns_subprofs_dir(ent->new->ns); error = __aafs_profile_mkdir(ent->new, parent); } if (error) { info = "failed to create"; goto fail_lock; } } /* Done with checks that may fail - do actual replacement */ __aa_bump_ns_revision(ns); if (aa_g_export_binary) __aa_loaddata_update(udata, ns->revision); list_for_each_entry_safe(ent, tmp, &lh, list) { list_del_init(&ent->list); op = (!ent->old && !ent->rename) ? OP_PROF_LOAD : OP_PROF_REPL; if (ent->old && ent->old->rawdata == ent->new->rawdata && ent->new->rawdata) { /* dedup actual profile replacement */ audit_policy(label, op, ns_name, ent->new->base.hname, "same as current profile, skipping", error); /* break refcount cycle with proxy. */ aa_put_proxy(ent->new->label.proxy); ent->new->label.proxy = NULL; goto skip; } /* * TODO: finer dedup based on profile range in data. Load set * can differ but profile may remain unchanged */ audit_policy(label, op, ns_name, ent->new->base.hname, NULL, error); if (ent->old) { share_name(ent->old, ent->new); __replace_profile(ent->old, ent->new); } else { struct list_head *lh; if (rcu_access_pointer(ent->new->parent)) { struct aa_profile *parent; parent = update_to_newest_parent(ent->new); lh = &parent->base.profiles; } else lh = &ns->base.profiles; __add_profile(lh, ent->new); } skip: aa_load_ent_free(ent); } __aa_labelset_update_subtree(ns); mutex_unlock(&ns->lock); out: aa_put_ns(ns); aa_put_loaddata(udata); kfree(ns_name); if (error) return error; return udata->size; fail_lock: mutex_unlock(&ns->lock); /* audit cause of failure */ op = (ent && !ent->old) ? OP_PROF_LOAD : OP_PROF_REPL; fail: audit_policy(label, op, ns_name, ent ? ent->new->base.hname : NULL, info, error); /* audit status that rest of profiles in the atomic set failed too */ info = "valid profile in failed atomic policy load"; list_for_each_entry(tmp, &lh, list) { if (tmp == ent) { info = "unchecked profile in failed atomic policy load"; /* skip entry that caused failure */ continue; } op = (!tmp->old) ? OP_PROF_LOAD : OP_PROF_REPL; audit_policy(label, op, ns_name, tmp->new->base.hname, info, error); } list_for_each_entry_safe(ent, tmp, &lh, list) { list_del_init(&ent->list); aa_load_ent_free(ent); } goto out; } /** * aa_remove_profiles - remove profile(s) from the system * @policy_ns: namespace the remove is being done from * @subj: label attempting to remove policy * @fqname: name of the profile or namespace to remove (NOT NULL) * @size: size of the name * * Remove a profile or sub namespace from the current namespace, so that * they can not be found anymore and mark them as replaced by unconfined * * NOTE: removing confinement does not restore rlimits to preconfinement values * * Returns: size of data consume else error code if fails */ ssize_t aa_remove_profiles(struct aa_ns *policy_ns, struct aa_label *subj, char *fqname, size_t size) { struct aa_ns *ns = NULL; struct aa_profile *profile = NULL; const char *name = fqname, *info = NULL; const char *ns_name = NULL; ssize_t error = 0; if (*fqname == 0) { info = "no profile specified"; error = -ENOENT; goto fail; } if (fqname[0] == ':') { size_t ns_len; name = aa_splitn_fqname(fqname, size, &ns_name, &ns_len); /* released below */ ns = aa_lookupn_ns(policy_ns ? policy_ns : labels_ns(subj), ns_name, ns_len); if (!ns) { info = "namespace does not exist"; error = -ENOENT; goto fail; } } else /* released below */ ns = aa_get_ns(policy_ns ? policy_ns : labels_ns(subj)); if (!name) { /* remove namespace - can only happen if fqname[0] == ':' */ mutex_lock_nested(&ns->parent->lock, ns->parent->level); __aa_bump_ns_revision(ns); __aa_remove_ns(ns); mutex_unlock(&ns->parent->lock); } else { /* remove profile */ mutex_lock_nested(&ns->lock, ns->level); profile = aa_get_profile(__lookup_profile(&ns->base, name)); if (!profile) { error = -ENOENT; info = "profile does not exist"; goto fail_ns_lock; } name = profile->base.hname; __aa_bump_ns_revision(ns); __remove_profile(profile); __aa_labelset_update_subtree(ns); mutex_unlock(&ns->lock); } /* don't fail removal if audit fails */ (void) audit_policy(subj, OP_PROF_RM, ns_name, name, info, error); aa_put_ns(ns); aa_put_profile(profile); return size; fail_ns_lock: mutex_unlock(&ns->lock); aa_put_ns(ns); fail: (void) audit_policy(subj, OP_PROF_RM, ns_name, name, info, error); return error; } |
| 3 3 3 1 1 3 2 1 3 6 6 2 1 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (C) 2008-2013 Jozsef Kadlecsik <kadlec@netfilter.org> */ /* Kernel module implementing an IP set type: the list:set type */ #include <linux/module.h> #include <linux/ip.h> #include <linux/rculist.h> #include <linux/skbuff.h> #include <linux/errno.h> #include <linux/netfilter/ipset/ip_set.h> #include <linux/netfilter/ipset/ip_set_list.h> #define IPSET_TYPE_REV_MIN 0 /* 1 Counters support added */ /* 2 Comments support added */ #define IPSET_TYPE_REV_MAX 3 /* skbinfo support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>"); IP_SET_MODULE_DESC("list:set", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX); MODULE_ALIAS("ip_set_list:set"); /* Member elements */ struct set_elem { struct rcu_head rcu; struct list_head list; struct ip_set *set; /* Sigh, in order to cleanup reference */ ip_set_id_t id; } __aligned(__alignof__(u64)); struct set_adt_elem { ip_set_id_t id; ip_set_id_t refid; int before; }; /* Type structure */ struct list_set { u32 size; /* size of set list array */ struct timer_list gc; /* garbage collection */ struct ip_set *set; /* attached to this ip_set */ struct net *net; /* namespace */ struct list_head members; /* the set members */ }; static int list_set_ktest(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, struct ip_set_adt_opt *opt, const struct ip_set_ext *ext) { struct list_set *map = set->data; struct ip_set_ext *mext = &opt->ext; struct set_elem *e; u32 flags = opt->cmdflags; int ret; /* Don't lookup sub-counters at all */ opt->cmdflags &= ~IPSET_FLAG_MATCH_COUNTERS; if (opt->cmdflags & IPSET_FLAG_SKIP_SUBCOUNTER_UPDATE) opt->cmdflags |= IPSET_FLAG_SKIP_COUNTER_UPDATE; list_for_each_entry_rcu(e, &map->members, list) { ret = ip_set_test(e->id, skb, par, opt); if (ret <= 0) continue; if (ip_set_match_extensions(set, ext, mext, flags, e)) return 1; } return 0; } static int list_set_kadd(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, struct ip_set_adt_opt *opt, const struct ip_set_ext *ext) { struct list_set *map = set->data; struct set_elem *e; int ret; list_for_each_entry_rcu(e, &map->members, list) { if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(e, set))) continue; ret = ip_set_add(e->id, skb, par, opt); if (ret == 0) return ret; } return 0; } static int list_set_kdel(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, struct ip_set_adt_opt *opt, const struct ip_set_ext *ext) { struct list_set *map = set->data; struct set_elem *e; int ret; list_for_each_entry_rcu(e, &map->members, list) { if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(e, set))) continue; ret = ip_set_del(e->id, skb, par, opt); if (ret == 0) return ret; } return 0; } static int list_set_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, struct ip_set_adt_opt *opt) { struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); int ret = -EINVAL; rcu_read_lock(); switch (adt) { case IPSET_TEST: ret = list_set_ktest(set, skb, par, opt, &ext); break; case IPSET_ADD: ret = list_set_kadd(set, skb, par, opt, &ext); break; case IPSET_DEL: ret = list_set_kdel(set, skb, par, opt, &ext); break; default: break; } rcu_read_unlock(); return ret; } /* Userspace interfaces: we are protected by the nfnl mutex */ static void __list_set_del_rcu(struct rcu_head * rcu) { struct set_elem *e = container_of(rcu, struct set_elem, rcu); struct ip_set *set = e->set; ip_set_ext_destroy(set, e); kfree(e); } static void list_set_del(struct ip_set *set, struct set_elem *e) { struct list_set *map = set->data; set->elements--; list_del_rcu(&e->list); ip_set_put_byindex(map->net, e->id); call_rcu(&e->rcu, __list_set_del_rcu); } static void list_set_replace(struct ip_set *set, struct set_elem *e, struct set_elem *old) { struct list_set *map = set->data; list_replace_rcu(&old->list, &e->list); ip_set_put_byindex(map->net, old->id); call_rcu(&old->rcu, __list_set_del_rcu); } static void set_cleanup_entries(struct ip_set *set) { struct list_set *map = set->data; struct set_elem *e, *n; list_for_each_entry_safe(e, n, &map->members, list) if (ip_set_timeout_expired(ext_timeout(e, set))) list_set_del(set, e); } static int list_set_utest(struct ip_set *set, void *value, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags) { struct list_set *map = set->data; struct set_adt_elem *d = value; struct set_elem *e, *next, *prev = NULL; int ret = 0; rcu_read_lock(); list_for_each_entry_rcu(e, &map->members, list) { if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(e, set))) continue; else if (e->id != d->id) { prev = e; continue; } if (d->before == 0) { ret = 1; goto out; } else if (d->before > 0) { next = list_next_entry(e, list); ret = !list_is_last(&e->list, &map->members) && next->id == d->refid; } else { ret = prev && prev->id == d->refid; } goto out; } out: rcu_read_unlock(); return ret; } static void list_set_init_extensions(struct ip_set *set, const struct ip_set_ext *ext, struct set_elem *e) { if (SET_WITH_COUNTER(set)) ip_set_init_counter(ext_counter(e, set), ext); if (SET_WITH_COMMENT(set)) ip_set_init_comment(set, ext_comment(e, set), ext); if (SET_WITH_SKBINFO(set)) ip_set_init_skbinfo(ext_skbinfo(e, set), ext); /* Update timeout last */ if (SET_WITH_TIMEOUT(set)) ip_set_timeout_set(ext_timeout(e, set), ext->timeout); } static int list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags) { struct list_set *map = set->data; struct set_adt_elem *d = value; struct set_elem *e, *n, *prev, *next; bool flag_exist = flags & IPSET_FLAG_EXIST; /* Find where to add the new entry */ n = prev = next = NULL; list_for_each_entry_rcu(e, &map->members, list) { if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(e, set))) continue; else if (d->id == e->id) n = e; else if (d->before == 0 || e->id != d->refid) continue; else if (d->before > 0) next = e; else prev = e; } /* If before/after is used on an empty set */ if ((d->before > 0 && !next) || (d->before < 0 && !prev)) return -IPSET_ERR_REF_EXIST; /* Re-add already existing element */ if (n) { if (!flag_exist) return -IPSET_ERR_EXIST; /* Update extensions */ ip_set_ext_destroy(set, n); list_set_init_extensions(set, ext, n); /* Set is already added to the list */ ip_set_put_byindex(map->net, d->id); return 0; } /* Add new entry */ if (d->before == 0) { /* Append */ n = list_empty(&map->members) ? NULL : list_last_entry(&map->members, struct set_elem, list); } else if (d->before > 0) { /* Insert after next element */ if (!list_is_last(&next->list, &map->members)) n = list_next_entry(next, list); } else { /* Insert before prev element */ if (prev->list.prev != &map->members) n = list_prev_entry(prev, list); } /* Can we replace a timed out entry? */ if (n && !(SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(n, set)))) n = NULL; e = kzalloc(set->dsize, GFP_ATOMIC); if (!e) return -ENOMEM; e->id = d->id; e->set = set; INIT_LIST_HEAD(&e->list); list_set_init_extensions(set, ext, e); if (n) list_set_replace(set, e, n); else if (next) list_add_tail_rcu(&e->list, &next->list); else if (prev) list_add_rcu(&e->list, &prev->list); else list_add_tail_rcu(&e->list, &map->members); set->elements++; return 0; } static int list_set_udel(struct ip_set *set, void *value, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags) { struct list_set *map = set->data; struct set_adt_elem *d = value; struct set_elem *e, *n, *next, *prev = NULL; list_for_each_entry_safe(e, n, &map->members, list) { if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(e, set))) continue; else if (e->id != d->id) { prev = e; continue; } if (d->before > 0) { next = list_next_entry(e, list); if (list_is_last(&e->list, &map->members) || next->id != d->refid) return -IPSET_ERR_REF_EXIST; } else if (d->before < 0) { if (!prev || prev->id != d->refid) return -IPSET_ERR_REF_EXIST; } list_set_del(set, e); return 0; } return d->before != 0 ? -IPSET_ERR_REF_EXIST : -IPSET_ERR_EXIST; } static int list_set_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { struct list_set *map = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct set_adt_elem e = { .refid = IPSET_INVALID_ID }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); struct ip_set *s; int ret = 0; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); if (unlikely(!tb[IPSET_ATTR_NAME] || !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; e.id = ip_set_get_byname(map->net, nla_data(tb[IPSET_ATTR_NAME]), &s); if (e.id == IPSET_INVALID_ID) return -IPSET_ERR_NAME; /* "Loop detection" */ if (s->type->features & IPSET_TYPE_NAME) { ret = -IPSET_ERR_LOOP; goto finish; } if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 f = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); e.before = f & IPSET_FLAG_BEFORE; } if (e.before && !tb[IPSET_ATTR_NAMEREF]) { ret = -IPSET_ERR_BEFORE; goto finish; } if (tb[IPSET_ATTR_NAMEREF]) { e.refid = ip_set_get_byname(map->net, nla_data(tb[IPSET_ATTR_NAMEREF]), &s); if (e.refid == IPSET_INVALID_ID) { ret = -IPSET_ERR_NAMEREF; goto finish; } if (!e.before) e.before = -1; } if (adt != IPSET_TEST && SET_WITH_TIMEOUT(set)) set_cleanup_entries(set); ret = adtfn(set, &e, &ext, &ext, flags); finish: if (e.refid != IPSET_INVALID_ID) ip_set_put_byindex(map->net, e.refid); if (adt != IPSET_ADD || ret) ip_set_put_byindex(map->net, e.id); return ip_set_eexist(ret, flags) ? 0 : ret; } static void list_set_flush(struct ip_set *set) { struct list_set *map = set->data; struct set_elem *e, *n; list_for_each_entry_safe(e, n, &map->members, list) list_set_del(set, e); set->elements = 0; set->ext_size = 0; } static void list_set_destroy(struct ip_set *set) { struct list_set *map = set->data; WARN_ON_ONCE(!list_empty(&map->members)); kfree(map); set->data = NULL; } /* Calculate the actual memory size of the set data */ static size_t list_set_memsize(const struct list_set *map, size_t dsize) { struct set_elem *e; u32 n = 0; rcu_read_lock(); list_for_each_entry_rcu(e, &map->members, list) n++; rcu_read_unlock(); return (sizeof(*map) + n * dsize); } static int list_set_head(struct ip_set *set, struct sk_buff *skb) { const struct list_set *map = set->data; struct nlattr *nested; size_t memsize = list_set_memsize(map, set->dsize) + set->ext_size; nested = nla_nest_start(skb, IPSET_ATTR_DATA); if (!nested) goto nla_put_failure; if (nla_put_net32(skb, IPSET_ATTR_SIZE, htonl(map->size)) || nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) || nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)) || nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(set->elements))) goto nla_put_failure; if (unlikely(ip_set_put_flags(skb, set))) goto nla_put_failure; nla_nest_end(skb, nested); return 0; nla_put_failure: return -EMSGSIZE; } static int list_set_list(const struct ip_set *set, struct sk_buff *skb, struct netlink_callback *cb) { const struct list_set *map = set->data; struct nlattr *atd, *nested; u32 i = 0, first = cb->args[IPSET_CB_ARG0]; char name[IPSET_MAXNAMELEN]; struct set_elem *e; int ret = 0; atd = nla_nest_start(skb, IPSET_ATTR_ADT); if (!atd) return -EMSGSIZE; rcu_read_lock(); list_for_each_entry_rcu(e, &map->members, list) { if (i < first || (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(e, set)))) { i++; continue; } nested = nla_nest_start(skb, IPSET_ATTR_DATA); if (!nested) goto nla_put_failure; ip_set_name_byindex(map->net, e->id, name); if (nla_put_string(skb, IPSET_ATTR_NAME, name)) goto nla_put_failure; if (ip_set_put_extensions(skb, set, e, true)) goto nla_put_failure; nla_nest_end(skb, nested); i++; } nla_nest_end(skb, atd); /* Set listing finished */ cb->args[IPSET_CB_ARG0] = 0; goto out; nla_put_failure: nla_nest_cancel(skb, nested); if (unlikely(i == first)) { nla_nest_cancel(skb, atd); cb->args[IPSET_CB_ARG0] = 0; ret = -EMSGSIZE; } else { cb->args[IPSET_CB_ARG0] = i; nla_nest_end(skb, atd); } out: rcu_read_unlock(); return ret; } static bool list_set_same_set(const struct ip_set *a, const struct ip_set *b) { const struct list_set *x = a->data; const struct list_set *y = b->data; return x->size == y->size && a->timeout == b->timeout && a->extensions == b->extensions; } static void list_set_cancel_gc(struct ip_set *set) { struct list_set *map = set->data; if (SET_WITH_TIMEOUT(set)) timer_shutdown_sync(&map->gc); /* Flush list to drop references to other ipsets */ list_set_flush(set); } static const struct ip_set_type_variant set_variant = { .kadt = list_set_kadt, .uadt = list_set_uadt, .adt = { [IPSET_ADD] = list_set_uadd, [IPSET_DEL] = list_set_udel, [IPSET_TEST] = list_set_utest, }, .destroy = list_set_destroy, .flush = list_set_flush, .head = list_set_head, .list = list_set_list, .same_set = list_set_same_set, .cancel_gc = list_set_cancel_gc, }; static void list_set_gc(struct timer_list *t) { struct list_set *map = from_timer(map, t, gc); struct ip_set *set = map->set; spin_lock_bh(&set->lock); set_cleanup_entries(set); spin_unlock_bh(&set->lock); map->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ; add_timer(&map->gc); } static void list_set_gc_init(struct ip_set *set, void (*gc)(struct timer_list *t)) { struct list_set *map = set->data; timer_setup(&map->gc, gc, 0); mod_timer(&map->gc, jiffies + IPSET_GC_PERIOD(set->timeout) * HZ); } /* Create list:set type of sets */ static bool init_list_set(struct net *net, struct ip_set *set, u32 size) { struct list_set *map; map = kzalloc(sizeof(*map), GFP_KERNEL); if (!map) return false; map->size = size; map->net = net; map->set = set; INIT_LIST_HEAD(&map->members); set->data = map; return true; } static int list_set_create(struct net *net, struct ip_set *set, struct nlattr *tb[], u32 flags) { u32 size = IP_SET_LIST_DEFAULT_SIZE; if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_SIZE) || !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; if (tb[IPSET_ATTR_SIZE]) size = ip_set_get_h32(tb[IPSET_ATTR_SIZE]); if (size < IP_SET_LIST_MIN_SIZE) size = IP_SET_LIST_MIN_SIZE; set->variant = &set_variant; set->dsize = ip_set_elem_len(set, tb, sizeof(struct set_elem), __alignof__(struct set_elem)); if (!init_list_set(net, set, size)) return -ENOMEM; if (tb[IPSET_ATTR_TIMEOUT]) { set->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); list_set_gc_init(set, list_set_gc); } return 0; } static struct ip_set_type list_set_type __read_mostly = { .name = "list:set", .protocol = IPSET_PROTOCOL, .features = IPSET_TYPE_NAME | IPSET_DUMP_LAST, .dimension = IPSET_DIM_ONE, .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, .create = list_set_create, .create_policy = { [IPSET_ATTR_SIZE] = { .type = NLA_U32 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, }, .adt_policy = { [IPSET_ATTR_NAME] = { .type = NLA_STRING, .len = IPSET_MAXNAMELEN }, [IPSET_ATTR_NAMEREF] = { .type = NLA_STRING, .len = IPSET_MAXNAMELEN }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, }, .me = THIS_MODULE, }; static int __init list_set_init(void) { return ip_set_type_register(&list_set_type); } static void __exit list_set_fini(void) { rcu_barrier(); ip_set_type_unregister(&list_set_type); } module_init(list_set_init); module_exit(list_set_fini); |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 | /* * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved. * Copyright (c) 2016-2017, Dave Watson <davejwatson@fb.com>. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #include <linux/list.h> #include <linux/rcupdate.h> #include <linux/spinlock.h> #include <net/inet_connection_sock.h> #include <net/tls.h> #include <net/tls_toe.h> #include "tls.h" static LIST_HEAD(device_list); static DEFINE_SPINLOCK(device_spinlock); static void tls_toe_sk_destruct(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tls_context *ctx = tls_get_ctx(sk); ctx->sk_destruct(sk); /* Free ctx */ rcu_assign_pointer(icsk->icsk_ulp_data, NULL); tls_ctx_free(sk, ctx); } int tls_toe_bypass(struct sock *sk) { struct tls_toe_device *dev; struct tls_context *ctx; int rc = 0; spin_lock_bh(&device_spinlock); list_for_each_entry(dev, &device_list, dev_list) { if (dev->feature && dev->feature(dev)) { ctx = tls_ctx_create(sk); if (!ctx) goto out; ctx->sk_destruct = sk->sk_destruct; sk->sk_destruct = tls_toe_sk_destruct; ctx->rx_conf = TLS_HW_RECORD; ctx->tx_conf = TLS_HW_RECORD; update_sk_prot(sk, ctx); rc = 1; break; } } out: spin_unlock_bh(&device_spinlock); return rc; } void tls_toe_unhash(struct sock *sk) { struct tls_context *ctx = tls_get_ctx(sk); struct tls_toe_device *dev; spin_lock_bh(&device_spinlock); list_for_each_entry(dev, &device_list, dev_list) { if (dev->unhash) { kref_get(&dev->kref); spin_unlock_bh(&device_spinlock); dev->unhash(dev, sk); kref_put(&dev->kref, dev->release); spin_lock_bh(&device_spinlock); } } spin_unlock_bh(&device_spinlock); ctx->sk_proto->unhash(sk); } int tls_toe_hash(struct sock *sk) { struct tls_context *ctx = tls_get_ctx(sk); struct tls_toe_device *dev; int err; err = ctx->sk_proto->hash(sk); spin_lock_bh(&device_spinlock); list_for_each_entry(dev, &device_list, dev_list) { if (dev->hash) { kref_get(&dev->kref); spin_unlock_bh(&device_spinlock); err |= dev->hash(dev, sk); kref_put(&dev->kref, dev->release); spin_lock_bh(&device_spinlock); } } spin_unlock_bh(&device_spinlock); if (err) tls_toe_unhash(sk); return err; } void tls_toe_register_device(struct tls_toe_device *device) { spin_lock_bh(&device_spinlock); list_add_tail(&device->dev_list, &device_list); spin_unlock_bh(&device_spinlock); } EXPORT_SYMBOL(tls_toe_register_device); void tls_toe_unregister_device(struct tls_toe_device *device) { spin_lock_bh(&device_spinlock); list_del(&device->dev_list); spin_unlock_bh(&device_spinlock); } EXPORT_SYMBOL(tls_toe_unregister_device); |
| 5 5 5 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) ST-Ericsson AB 2010 * Author: Sjur Brendeland */ #define pr_fmt(fmt) KBUILD_MODNAME ":%s(): " fmt, __func__ #include <linux/stddef.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/pkt_sched.h> #include <net/caif/caif_layer.h> #include <net/caif/cfpkt.h> #include <net/caif/cfctrl.h> #define container_obj(layr) container_of(layr, struct cfctrl, serv.layer) #define UTILITY_NAME_LENGTH 16 #define CFPKT_CTRL_PKT_LEN 20 #ifdef CAIF_NO_LOOP static int handle_loop(struct cfctrl *ctrl, int cmd, struct cfpkt *pkt){ return -1; } #else static int handle_loop(struct cfctrl *ctrl, int cmd, struct cfpkt *pkt); #endif static int cfctrl_recv(struct cflayer *layr, struct cfpkt *pkt); static void cfctrl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, int phyid); struct cflayer *cfctrl_create(void) { struct dev_info dev_info; struct cfctrl *this = kzalloc(sizeof(struct cfctrl), GFP_ATOMIC); if (!this) return NULL; caif_assert(offsetof(struct cfctrl, serv.layer) == 0); memset(&dev_info, 0, sizeof(dev_info)); dev_info.id = 0xff; cfsrvl_init(&this->serv, 0, &dev_info, false); atomic_set(&this->req_seq_no, 1); atomic_set(&this->rsp_seq_no, 1); this->serv.layer.receive = cfctrl_recv; sprintf(this->serv.layer.name, "ctrl"); this->serv.layer.ctrlcmd = cfctrl_ctrlcmd; #ifndef CAIF_NO_LOOP spin_lock_init(&this->loop_linkid_lock); this->loop_linkid = 1; #endif spin_lock_init(&this->info_list_lock); INIT_LIST_HEAD(&this->list); return &this->serv.layer; } void cfctrl_remove(struct cflayer *layer) { struct cfctrl_request_info *p, *tmp; struct cfctrl *ctrl = container_obj(layer); spin_lock_bh(&ctrl->info_list_lock); list_for_each_entry_safe(p, tmp, &ctrl->list, list) { list_del(&p->list); kfree(p); } spin_unlock_bh(&ctrl->info_list_lock); kfree(layer); } static bool param_eq(const struct cfctrl_link_param *p1, const struct cfctrl_link_param *p2) { bool eq = p1->linktype == p2->linktype && p1->priority == p2->priority && p1->phyid == p2->phyid && p1->endpoint == p2->endpoint && p1->chtype == p2->chtype; if (!eq) return false; switch (p1->linktype) { case CFCTRL_SRV_VEI: return true; case CFCTRL_SRV_DATAGRAM: return p1->u.datagram.connid == p2->u.datagram.connid; case CFCTRL_SRV_RFM: return p1->u.rfm.connid == p2->u.rfm.connid && strcmp(p1->u.rfm.volume, p2->u.rfm.volume) == 0; case CFCTRL_SRV_UTIL: return p1->u.utility.fifosize_kb == p2->u.utility.fifosize_kb && p1->u.utility.fifosize_bufs == p2->u.utility.fifosize_bufs && strcmp(p1->u.utility.name, p2->u.utility.name) == 0 && p1->u.utility.paramlen == p2->u.utility.paramlen && memcmp(p1->u.utility.params, p2->u.utility.params, p1->u.utility.paramlen) == 0; case CFCTRL_SRV_VIDEO: return p1->u.video.connid == p2->u.video.connid; case CFCTRL_SRV_DBG: return true; case CFCTRL_SRV_DECM: return false; default: return false; } return false; } static bool cfctrl_req_eq(const struct cfctrl_request_info *r1, const struct cfctrl_request_info *r2) { if (r1->cmd != r2->cmd) return false; if (r1->cmd == CFCTRL_CMD_LINK_SETUP) return param_eq(&r1->param, &r2->param); else return r1->channel_id == r2->channel_id; } /* Insert request at the end */ static void cfctrl_insert_req(struct cfctrl *ctrl, struct cfctrl_request_info *req) { spin_lock_bh(&ctrl->info_list_lock); atomic_inc(&ctrl->req_seq_no); req->sequence_no = atomic_read(&ctrl->req_seq_no); list_add_tail(&req->list, &ctrl->list); spin_unlock_bh(&ctrl->info_list_lock); } /* Compare and remove request */ static struct cfctrl_request_info *cfctrl_remove_req(struct cfctrl *ctrl, struct cfctrl_request_info *req) { struct cfctrl_request_info *p, *tmp, *first; first = list_first_entry(&ctrl->list, struct cfctrl_request_info, list); list_for_each_entry_safe(p, tmp, &ctrl->list, list) { if (cfctrl_req_eq(req, p)) { if (p != first) pr_warn("Requests are not received in order\n"); atomic_set(&ctrl->rsp_seq_no, p->sequence_no); list_del(&p->list); goto out; } } p = NULL; out: return p; } struct cfctrl_rsp *cfctrl_get_respfuncs(struct cflayer *layer) { struct cfctrl *this = container_obj(layer); return &this->res; } static void init_info(struct caif_payload_info *info, struct cfctrl *cfctrl) { info->hdr_len = 0; info->channel_id = cfctrl->serv.layer.id; info->dev_info = &cfctrl->serv.dev_info; } void cfctrl_enum_req(struct cflayer *layer, u8 physlinkid) { struct cfpkt *pkt; struct cfctrl *cfctrl = container_obj(layer); struct cflayer *dn = cfctrl->serv.layer.dn; if (!dn) { pr_debug("not able to send enum request\n"); return; } pkt = cfpkt_create(CFPKT_CTRL_PKT_LEN); if (!pkt) return; caif_assert(offsetof(struct cfctrl, serv.layer) == 0); init_info(cfpkt_info(pkt), cfctrl); cfpkt_info(pkt)->dev_info->id = physlinkid; cfctrl->serv.dev_info.id = physlinkid; cfpkt_addbdy(pkt, CFCTRL_CMD_ENUM); cfpkt_addbdy(pkt, physlinkid); cfpkt_set_prio(pkt, TC_PRIO_CONTROL); dn->transmit(dn, pkt); } int cfctrl_linkup_request(struct cflayer *layer, struct cfctrl_link_param *param, struct cflayer *user_layer) { struct cfctrl *cfctrl = container_obj(layer); struct cflayer *dn = cfctrl->serv.layer.dn; char utility_name[UTILITY_NAME_LENGTH]; struct cfctrl_request_info *req; struct cfpkt *pkt; u32 tmp32; u16 tmp16; u8 tmp8; int ret; if (!dn) { pr_debug("not able to send linkup request\n"); return -ENODEV; } if (cfctrl_cancel_req(layer, user_layer) > 0) { /* Slight Paranoia, check if already connecting */ pr_err("Duplicate connect request for same client\n"); WARN_ON(1); return -EALREADY; } pkt = cfpkt_create(CFPKT_CTRL_PKT_LEN); if (!pkt) return -ENOMEM; cfpkt_addbdy(pkt, CFCTRL_CMD_LINK_SETUP); cfpkt_addbdy(pkt, (param->chtype << 4) | param->linktype); cfpkt_addbdy(pkt, (param->priority << 3) | param->phyid); cfpkt_addbdy(pkt, param->endpoint & 0x03); switch (param->linktype) { case CFCTRL_SRV_VEI: break; case CFCTRL_SRV_VIDEO: cfpkt_addbdy(pkt, (u8) param->u.video.connid); break; case CFCTRL_SRV_DBG: break; case CFCTRL_SRV_DATAGRAM: tmp32 = cpu_to_le32(param->u.datagram.connid); cfpkt_add_body(pkt, &tmp32, 4); break; case CFCTRL_SRV_RFM: /* Construct a frame, convert DatagramConnectionID to network * format long and copy it out... */ tmp32 = cpu_to_le32(param->u.rfm.connid); cfpkt_add_body(pkt, &tmp32, 4); /* Add volume name, including zero termination... */ cfpkt_add_body(pkt, param->u.rfm.volume, strlen(param->u.rfm.volume) + 1); break; case CFCTRL_SRV_UTIL: tmp16 = cpu_to_le16(param->u.utility.fifosize_kb); cfpkt_add_body(pkt, &tmp16, 2); tmp16 = cpu_to_le16(param->u.utility.fifosize_bufs); cfpkt_add_body(pkt, &tmp16, 2); memset(utility_name, 0, sizeof(utility_name)); strscpy(utility_name, param->u.utility.name, UTILITY_NAME_LENGTH); cfpkt_add_body(pkt, utility_name, UTILITY_NAME_LENGTH); tmp8 = param->u.utility.paramlen; cfpkt_add_body(pkt, &tmp8, 1); cfpkt_add_body(pkt, param->u.utility.params, param->u.utility.paramlen); break; default: pr_warn("Request setup of bad link type = %d\n", param->linktype); cfpkt_destroy(pkt); return -EINVAL; } req = kzalloc(sizeof(*req), GFP_KERNEL); if (!req) { cfpkt_destroy(pkt); return -ENOMEM; } req->client_layer = user_layer; req->cmd = CFCTRL_CMD_LINK_SETUP; req->param = *param; cfctrl_insert_req(cfctrl, req); init_info(cfpkt_info(pkt), cfctrl); /* * NOTE:Always send linkup and linkdown request on the same * device as the payload. Otherwise old queued up payload * might arrive with the newly allocated channel ID. */ cfpkt_info(pkt)->dev_info->id = param->phyid; cfpkt_set_prio(pkt, TC_PRIO_CONTROL); ret = dn->transmit(dn, pkt); if (ret < 0) { int count; count = cfctrl_cancel_req(&cfctrl->serv.layer, user_layer); if (count != 1) { pr_err("Could not remove request (%d)", count); return -ENODEV; } } return 0; } int cfctrl_linkdown_req(struct cflayer *layer, u8 channelid, struct cflayer *client) { int ret; struct cfpkt *pkt; struct cfctrl *cfctrl = container_obj(layer); struct cflayer *dn = cfctrl->serv.layer.dn; if (!dn) { pr_debug("not able to send link-down request\n"); return -ENODEV; } pkt = cfpkt_create(CFPKT_CTRL_PKT_LEN); if (!pkt) return -ENOMEM; cfpkt_addbdy(pkt, CFCTRL_CMD_LINK_DESTROY); cfpkt_addbdy(pkt, channelid); init_info(cfpkt_info(pkt), cfctrl); cfpkt_set_prio(pkt, TC_PRIO_CONTROL); ret = dn->transmit(dn, pkt); #ifndef CAIF_NO_LOOP cfctrl->loop_linkused[channelid] = 0; #endif return ret; } int cfctrl_cancel_req(struct cflayer *layr, struct cflayer *adap_layer) { struct cfctrl_request_info *p, *tmp; struct cfctrl *ctrl = container_obj(layr); int found = 0; spin_lock_bh(&ctrl->info_list_lock); list_for_each_entry_safe(p, tmp, &ctrl->list, list) { if (p->client_layer == adap_layer) { list_del(&p->list); kfree(p); found++; } } spin_unlock_bh(&ctrl->info_list_lock); return found; } static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt) { u8 cmdrsp; u8 cmd; int ret = -1; u8 len; u8 param[255]; u8 linkid = 0; struct cfctrl *cfctrl = container_obj(layer); struct cfctrl_request_info rsp, *req; cmdrsp = cfpkt_extr_head_u8(pkt); cmd = cmdrsp & CFCTRL_CMD_MASK; if (cmd != CFCTRL_CMD_LINK_ERR && CFCTRL_RSP_BIT != (CFCTRL_RSP_BIT & cmdrsp) && CFCTRL_ERR_BIT != (CFCTRL_ERR_BIT & cmdrsp)) { if (handle_loop(cfctrl, cmd, pkt) != 0) cmdrsp |= CFCTRL_ERR_BIT; } switch (cmd) { case CFCTRL_CMD_LINK_SETUP: { enum cfctrl_srv serv; enum cfctrl_srv servtype; u8 endpoint; u8 physlinkid; u8 prio; u8 tmp; u8 *cp; int i; struct cfctrl_link_param linkparam; memset(&linkparam, 0, sizeof(linkparam)); tmp = cfpkt_extr_head_u8(pkt); serv = tmp & CFCTRL_SRV_MASK; linkparam.linktype = serv; servtype = tmp >> 4; linkparam.chtype = servtype; tmp = cfpkt_extr_head_u8(pkt); physlinkid = tmp & 0x07; prio = tmp >> 3; linkparam.priority = prio; linkparam.phyid = physlinkid; endpoint = cfpkt_extr_head_u8(pkt); linkparam.endpoint = endpoint & 0x03; switch (serv) { case CFCTRL_SRV_VEI: case CFCTRL_SRV_DBG: if (CFCTRL_ERR_BIT & cmdrsp) break; /* Link ID */ linkid = cfpkt_extr_head_u8(pkt); break; case CFCTRL_SRV_VIDEO: tmp = cfpkt_extr_head_u8(pkt); linkparam.u.video.connid = tmp; if (CFCTRL_ERR_BIT & cmdrsp) break; /* Link ID */ linkid = cfpkt_extr_head_u8(pkt); break; case CFCTRL_SRV_DATAGRAM: linkparam.u.datagram.connid = cfpkt_extr_head_u32(pkt); if (CFCTRL_ERR_BIT & cmdrsp) break; /* Link ID */ linkid = cfpkt_extr_head_u8(pkt); break; case CFCTRL_SRV_RFM: /* Construct a frame, convert * DatagramConnectionID * to network format long and copy it out... */ linkparam.u.rfm.connid = cfpkt_extr_head_u32(pkt); cp = (u8 *) linkparam.u.rfm.volume; for (tmp = cfpkt_extr_head_u8(pkt); cfpkt_more(pkt) && tmp != '\0'; tmp = cfpkt_extr_head_u8(pkt)) *cp++ = tmp; *cp = '\0'; if (CFCTRL_ERR_BIT & cmdrsp) break; /* Link ID */ linkid = cfpkt_extr_head_u8(pkt); break; case CFCTRL_SRV_UTIL: /* Construct a frame, convert * DatagramConnectionID * to network format long and copy it out... */ /* Fifosize KB */ linkparam.u.utility.fifosize_kb = cfpkt_extr_head_u16(pkt); /* Fifosize bufs */ linkparam.u.utility.fifosize_bufs = cfpkt_extr_head_u16(pkt); /* name */ cp = (u8 *) linkparam.u.utility.name; caif_assert(sizeof(linkparam.u.utility.name) >= UTILITY_NAME_LENGTH); for (i = 0; i < UTILITY_NAME_LENGTH && cfpkt_more(pkt); i++) { tmp = cfpkt_extr_head_u8(pkt); *cp++ = tmp; } /* Length */ len = cfpkt_extr_head_u8(pkt); linkparam.u.utility.paramlen = len; /* Param Data */ cp = linkparam.u.utility.params; while (cfpkt_more(pkt) && len--) { tmp = cfpkt_extr_head_u8(pkt); *cp++ = tmp; } if (CFCTRL_ERR_BIT & cmdrsp) break; /* Link ID */ linkid = cfpkt_extr_head_u8(pkt); /* Length */ len = cfpkt_extr_head_u8(pkt); /* Param Data */ cfpkt_extr_head(pkt, ¶m, len); break; default: pr_warn("Request setup, invalid type (%d)\n", serv); goto error; } rsp.cmd = cmd; rsp.param = linkparam; spin_lock_bh(&cfctrl->info_list_lock); req = cfctrl_remove_req(cfctrl, &rsp); if (CFCTRL_ERR_BIT == (CFCTRL_ERR_BIT & cmdrsp) || cfpkt_erroneous(pkt)) { pr_err("Invalid O/E bit or parse error " "on CAIF control channel\n"); cfctrl->res.reject_rsp(cfctrl->serv.layer.up, 0, req ? req->client_layer : NULL); } else { cfctrl->res.linksetup_rsp(cfctrl->serv. layer.up, linkid, serv, physlinkid, req ? req-> client_layer : NULL); } kfree(req); spin_unlock_bh(&cfctrl->info_list_lock); } break; case CFCTRL_CMD_LINK_DESTROY: linkid = cfpkt_extr_head_u8(pkt); cfctrl->res.linkdestroy_rsp(cfctrl->serv.layer.up, linkid); break; case CFCTRL_CMD_LINK_ERR: pr_err("Frame Error Indication received\n"); cfctrl->res.linkerror_ind(); break; case CFCTRL_CMD_ENUM: cfctrl->res.enum_rsp(); break; case CFCTRL_CMD_SLEEP: cfctrl->res.sleep_rsp(); break; case CFCTRL_CMD_WAKE: cfctrl->res.wake_rsp(); break; case CFCTRL_CMD_LINK_RECONF: cfctrl->res.restart_rsp(); break; case CFCTRL_CMD_RADIO_SET: cfctrl->res.radioset_rsp(); break; default: pr_err("Unrecognized Control Frame\n"); goto error; } ret = 0; error: cfpkt_destroy(pkt); return ret; } static void cfctrl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, int phyid) { struct cfctrl *this = container_obj(layr); switch (ctrl) { case _CAIF_CTRLCMD_PHYIF_FLOW_OFF_IND: case CAIF_CTRLCMD_FLOW_OFF_IND: spin_lock_bh(&this->info_list_lock); if (!list_empty(&this->list)) pr_debug("Received flow off in control layer\n"); spin_unlock_bh(&this->info_list_lock); break; case _CAIF_CTRLCMD_PHYIF_DOWN_IND: { struct cfctrl_request_info *p, *tmp; /* Find all connect request and report failure */ spin_lock_bh(&this->info_list_lock); list_for_each_entry_safe(p, tmp, &this->list, list) { if (p->param.phyid == phyid) { list_del(&p->list); p->client_layer->ctrlcmd(p->client_layer, CAIF_CTRLCMD_INIT_FAIL_RSP, phyid); kfree(p); } } spin_unlock_bh(&this->info_list_lock); break; } default: break; } } #ifndef CAIF_NO_LOOP static int handle_loop(struct cfctrl *ctrl, int cmd, struct cfpkt *pkt) { static int last_linkid; static int dec; u8 linkid, linktype, tmp; switch (cmd) { case CFCTRL_CMD_LINK_SETUP: spin_lock_bh(&ctrl->loop_linkid_lock); if (!dec) { for (linkid = last_linkid + 1; linkid < 254; linkid++) if (!ctrl->loop_linkused[linkid]) goto found; } dec = 1; for (linkid = last_linkid - 1; linkid > 1; linkid--) if (!ctrl->loop_linkused[linkid]) goto found; spin_unlock_bh(&ctrl->loop_linkid_lock); return -1; found: if (linkid < 10) dec = 0; if (!ctrl->loop_linkused[linkid]) ctrl->loop_linkused[linkid] = 1; last_linkid = linkid; cfpkt_add_trail(pkt, &linkid, 1); spin_unlock_bh(&ctrl->loop_linkid_lock); cfpkt_peek_head(pkt, &linktype, 1); if (linktype == CFCTRL_SRV_UTIL) { tmp = 0x01; cfpkt_add_trail(pkt, &tmp, 1); cfpkt_add_trail(pkt, &tmp, 1); } break; case CFCTRL_CMD_LINK_DESTROY: spin_lock_bh(&ctrl->loop_linkid_lock); cfpkt_peek_head(pkt, &linkid, 1); ctrl->loop_linkused[linkid] = 0; spin_unlock_bh(&ctrl->loop_linkid_lock); break; default: break; } return 0; } #endif |
| 1220 9 1903 19 264 897 9 9 3888 3896 322 2529 33 1985 1991 270 265 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGTABLE_H #define _ASM_X86_PGTABLE_H #include <linux/mem_encrypt.h> #include <asm/page.h> #include <asm/pgtable_types.h> /* * Macro to mark a page protection value as UC- */ #define pgprot_noncached(prot) \ ((boot_cpu_data.x86 > 3) \ ? (__pgprot(pgprot_val(prot) | \ cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS))) \ : (prot)) #ifndef __ASSEMBLY__ #include <linux/spinlock.h> #include <asm/x86_init.h> #include <asm/pkru.h> #include <asm/fpu/api.h> #include <asm/coco.h> #include <asm-generic/pgtable_uffd.h> #include <linux/page_table_check.h> extern pgd_t early_top_pgt[PTRS_PER_PGD]; bool __init __early_make_pgtable(unsigned long address, pmdval_t pmd); struct seq_file; void ptdump_walk_pgd_level(struct seq_file *m, struct mm_struct *mm); void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm, bool user); bool ptdump_walk_pgd_level_checkwx(void); #define ptdump_check_wx ptdump_walk_pgd_level_checkwx void ptdump_walk_user_pgd_level_checkwx(void); /* * Macros to add or remove encryption attribute */ #define pgprot_encrypted(prot) __pgprot(cc_mkenc(pgprot_val(prot))) #define pgprot_decrypted(prot) __pgprot(cc_mkdec(pgprot_val(prot))) #ifdef CONFIG_DEBUG_WX #define debug_checkwx_user() ptdump_walk_user_pgd_level_checkwx() #else #define debug_checkwx_user() do { } while (0) #endif /* * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. */ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __visible; #define ZERO_PAGE(vaddr) ((void)(vaddr),virt_to_page(empty_zero_page)) extern spinlock_t pgd_lock; extern struct list_head pgd_list; extern struct mm_struct *pgd_page_get_mm(struct page *page); extern pmdval_t early_pmd_flags; #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else /* !CONFIG_PARAVIRT_XXL */ #define set_pte(ptep, pte) native_set_pte(ptep, pte) #define set_pte_atomic(ptep, pte) \ native_set_pte_atomic(ptep, pte) #define set_pmd(pmdp, pmd) native_set_pmd(pmdp, pmd) #ifndef __PAGETABLE_P4D_FOLDED #define set_pgd(pgdp, pgd) native_set_pgd(pgdp, pgd) #define pgd_clear(pgd) (pgtable_l5_enabled() ? native_pgd_clear(pgd) : 0) #endif #ifndef set_p4d # define set_p4d(p4dp, p4d) native_set_p4d(p4dp, p4d) #endif #ifndef __PAGETABLE_PUD_FOLDED #define p4d_clear(p4d) native_p4d_clear(p4d) #endif #ifndef set_pud # define set_pud(pudp, pud) native_set_pud(pudp, pud) #endif #ifndef __PAGETABLE_PUD_FOLDED #define pud_clear(pud) native_pud_clear(pud) #endif #define pte_clear(mm, addr, ptep) native_pte_clear(mm, addr, ptep) #define pmd_clear(pmd) native_pmd_clear(pmd) #define pgd_val(x) native_pgd_val(x) #define __pgd(x) native_make_pgd(x) #ifndef __PAGETABLE_P4D_FOLDED #define p4d_val(x) native_p4d_val(x) #define __p4d(x) native_make_p4d(x) #endif #ifndef __PAGETABLE_PUD_FOLDED #define pud_val(x) native_pud_val(x) #define __pud(x) native_make_pud(x) #endif #ifndef __PAGETABLE_PMD_FOLDED #define pmd_val(x) native_pmd_val(x) #define __pmd(x) native_make_pmd(x) #endif #define pte_val(x) native_pte_val(x) #define __pte(x) native_make_pte(x) #define arch_end_context_switch(prev) do {} while(0) #endif /* CONFIG_PARAVIRT_XXL */ static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set) { pmdval_t v = native_pmd_val(pmd); return native_make_pmd(v | set); } static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear) { pmdval_t v = native_pmd_val(pmd); return native_make_pmd(v & ~clear); } static inline pud_t pud_set_flags(pud_t pud, pudval_t set) { pudval_t v = native_pud_val(pud); return native_make_pud(v | set); } static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear) { pudval_t v = native_pud_val(pud); return native_make_pud(v & ~clear); } /* * The following only work if pte_present() is true. * Undefined behaviour if not.. */ static inline bool pte_dirty(pte_t pte) { return pte_flags(pte) & _PAGE_DIRTY_BITS; } static inline bool pte_shstk(pte_t pte) { return cpu_feature_enabled(X86_FEATURE_SHSTK) && (pte_flags(pte) & (_PAGE_RW | _PAGE_DIRTY)) == _PAGE_DIRTY; } static inline int pte_young(pte_t pte) { return pte_flags(pte) & _PAGE_ACCESSED; } static inline bool pte_decrypted(pte_t pte) { return cc_mkdec(pte_val(pte)) == pte_val(pte); } #define pmd_dirty pmd_dirty static inline bool pmd_dirty(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_DIRTY_BITS; } static inline bool pmd_shstk(pmd_t pmd) { return cpu_feature_enabled(X86_FEATURE_SHSTK) && (pmd_flags(pmd) & (_PAGE_RW | _PAGE_DIRTY | _PAGE_PSE)) == (_PAGE_DIRTY | _PAGE_PSE); } #define pmd_young pmd_young static inline int pmd_young(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_ACCESSED; } static inline bool pud_dirty(pud_t pud) { return pud_flags(pud) & _PAGE_DIRTY_BITS; } static inline int pud_young(pud_t pud) { return pud_flags(pud) & _PAGE_ACCESSED; } static inline bool pud_shstk(pud_t pud) { return cpu_feature_enabled(X86_FEATURE_SHSTK) && (pud_flags(pud) & (_PAGE_RW | _PAGE_DIRTY | _PAGE_PSE)) == (_PAGE_DIRTY | _PAGE_PSE); } static inline int pte_write(pte_t pte) { /* * Shadow stack pages are logically writable, but do not have * _PAGE_RW. Check for them separately from _PAGE_RW itself. */ return (pte_flags(pte) & _PAGE_RW) || pte_shstk(pte); } #define pmd_write pmd_write static inline int pmd_write(pmd_t pmd) { /* * Shadow stack pages are logically writable, but do not have * _PAGE_RW. Check for them separately from _PAGE_RW itself. */ return (pmd_flags(pmd) & _PAGE_RW) || pmd_shstk(pmd); } #define pud_write pud_write static inline int pud_write(pud_t pud) { return pud_flags(pud) & _PAGE_RW; } static inline int pte_huge(pte_t pte) { return pte_flags(pte) & _PAGE_PSE; } static inline int pte_global(pte_t pte) { return pte_flags(pte) & _PAGE_GLOBAL; } static inline int pte_exec(pte_t pte) { return !(pte_flags(pte) & _PAGE_NX); } static inline int pte_special(pte_t pte) { return pte_flags(pte) & _PAGE_SPECIAL; } /* Entries that were set to PROT_NONE are inverted */ static inline u64 protnone_mask(u64 val); #define PFN_PTE_SHIFT PAGE_SHIFT static inline unsigned long pte_pfn(pte_t pte) { phys_addr_t pfn = pte_val(pte); pfn ^= protnone_mask(pfn); return (pfn & PTE_PFN_MASK) >> PAGE_SHIFT; } static inline unsigned long pmd_pfn(pmd_t pmd) { phys_addr_t pfn = pmd_val(pmd); pfn ^= protnone_mask(pfn); return (pfn & pmd_pfn_mask(pmd)) >> PAGE_SHIFT; } #define pud_pfn pud_pfn static inline unsigned long pud_pfn(pud_t pud) { phys_addr_t pfn = pud_val(pud); pfn ^= protnone_mask(pfn); return (pfn & pud_pfn_mask(pud)) >> PAGE_SHIFT; } static inline unsigned long p4d_pfn(p4d_t p4d) { return (p4d_val(p4d) & p4d_pfn_mask(p4d)) >> PAGE_SHIFT; } static inline unsigned long pgd_pfn(pgd_t pgd) { return (pgd_val(pgd) & PTE_PFN_MASK) >> PAGE_SHIFT; } #define p4d_leaf p4d_leaf static inline bool p4d_leaf(p4d_t p4d) { /* No 512 GiB pages yet */ return 0; } #define pte_page(pte) pfn_to_page(pte_pfn(pte)) #define pmd_leaf pmd_leaf static inline bool pmd_leaf(pmd_t pte) { return pmd_flags(pte) & _PAGE_PSE; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* NOTE: when predicate huge page, consider also pmd_devmap, or use pmd_leaf */ static inline int pmd_trans_huge(pmd_t pmd) { return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE; } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static inline int pud_trans_huge(pud_t pud) { return (pud_val(pud) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE; } #endif #define has_transparent_hugepage has_transparent_hugepage static inline int has_transparent_hugepage(void) { return boot_cpu_has(X86_FEATURE_PSE); } #ifdef CONFIG_ARCH_HAS_PTE_DEVMAP static inline int pmd_devmap(pmd_t pmd) { return !!(pmd_val(pmd) & _PAGE_DEVMAP); } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static inline int pud_devmap(pud_t pud) { return !!(pud_val(pud) & _PAGE_DEVMAP); } #else static inline int pud_devmap(pud_t pud) { return 0; } #endif #ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP static inline bool pmd_special(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_SPECIAL; } static inline pmd_t pmd_mkspecial(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_SPECIAL); } #endif /* CONFIG_ARCH_SUPPORTS_PMD_PFNMAP */ #ifdef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP static inline bool pud_special(pud_t pud) { return pud_flags(pud) & _PAGE_SPECIAL; } static inline pud_t pud_mkspecial(pud_t pud) { return pud_set_flags(pud, _PAGE_SPECIAL); } #endif /* CONFIG_ARCH_SUPPORTS_PUD_PFNMAP */ static inline int pgd_devmap(pgd_t pgd) { return 0; } #endif #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline pte_t pte_set_flags(pte_t pte, pteval_t set) { pteval_t v = native_pte_val(pte); return native_make_pte(v | set); } static inline pte_t pte_clear_flags(pte_t pte, pteval_t clear) { pteval_t v = native_pte_val(pte); return native_make_pte(v & ~clear); } /* * Write protection operations can result in Dirty=1,Write=0 PTEs. But in the * case of X86_FEATURE_USER_SHSTK, these PTEs denote shadow stack memory. So * when creating dirty, write-protected memory, a software bit is used: * _PAGE_BIT_SAVED_DIRTY. The following functions take a PTE and transition the * Dirty bit to SavedDirty, and vice-vesra. * * This shifting is only done if needed. In the case of shifting * Dirty->SavedDirty, the condition is if the PTE is Write=0. In the case of * shifting SavedDirty->Dirty, the condition is Write=1. */ static inline pgprotval_t mksaveddirty_shift(pgprotval_t v) { pgprotval_t cond = (~v >> _PAGE_BIT_RW) & 1; v |= ((v >> _PAGE_BIT_DIRTY) & cond) << _PAGE_BIT_SAVED_DIRTY; v &= ~(cond << _PAGE_BIT_DIRTY); return v; } static inline pgprotval_t clear_saveddirty_shift(pgprotval_t v) { pgprotval_t cond = (v >> _PAGE_BIT_RW) & 1; v |= ((v >> _PAGE_BIT_SAVED_DIRTY) & cond) << _PAGE_BIT_DIRTY; v &= ~(cond << _PAGE_BIT_SAVED_DIRTY); return v; } static inline pte_t pte_mksaveddirty(pte_t pte) { pteval_t v = native_pte_val(pte); v = mksaveddirty_shift(v); return native_make_pte(v); } static inline pte_t pte_clear_saveddirty(pte_t pte) { pteval_t v = native_pte_val(pte); v = clear_saveddirty_shift(v); return native_make_pte(v); } static inline pte_t pte_wrprotect(pte_t pte) { pte = pte_clear_flags(pte, _PAGE_RW); /* * Blindly clearing _PAGE_RW might accidentally create * a shadow stack PTE (Write=0,Dirty=1). Move the hardware * dirty value to the software bit, if present. */ return pte_mksaveddirty(pte); } #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline int pte_uffd_wp(pte_t pte) { return pte_flags(pte) & _PAGE_UFFD_WP; } static inline pte_t pte_mkuffd_wp(pte_t pte) { return pte_wrprotect(pte_set_flags(pte, _PAGE_UFFD_WP)); } static inline pte_t pte_clear_uffd_wp(pte_t pte) { return pte_clear_flags(pte, _PAGE_UFFD_WP); } #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ static inline pte_t pte_mkclean(pte_t pte) { return pte_clear_flags(pte, _PAGE_DIRTY_BITS); } static inline pte_t pte_mkold(pte_t pte) { return pte_clear_flags(pte, _PAGE_ACCESSED); } static inline pte_t pte_mkexec(pte_t pte) { return pte_clear_flags(pte, _PAGE_NX); } static inline pte_t pte_mkdirty(pte_t pte) { pte = pte_set_flags(pte, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); return pte_mksaveddirty(pte); } static inline pte_t pte_mkwrite_shstk(pte_t pte) { pte = pte_clear_flags(pte, _PAGE_RW); return pte_set_flags(pte, _PAGE_DIRTY); } static inline pte_t pte_mkyoung(pte_t pte) { return pte_set_flags(pte, _PAGE_ACCESSED); } static inline pte_t pte_mkwrite_novma(pte_t pte) { return pte_set_flags(pte, _PAGE_RW); } struct vm_area_struct; pte_t pte_mkwrite(pte_t pte, struct vm_area_struct *vma); #define pte_mkwrite pte_mkwrite static inline pte_t pte_mkhuge(pte_t pte) { return pte_set_flags(pte, _PAGE_PSE); } static inline pte_t pte_clrhuge(pte_t pte) { return pte_clear_flags(pte, _PAGE_PSE); } static inline pte_t pte_mkglobal(pte_t pte) { return pte_set_flags(pte, _PAGE_GLOBAL); } static inline pte_t pte_clrglobal(pte_t pte) { return pte_clear_flags(pte, _PAGE_GLOBAL); } static inline pte_t pte_mkspecial(pte_t pte) { return pte_set_flags(pte, _PAGE_SPECIAL); } static inline pte_t pte_mkdevmap(pte_t pte) { return pte_set_flags(pte, _PAGE_SPECIAL|_PAGE_DEVMAP); } /* See comments above mksaveddirty_shift() */ static inline pmd_t pmd_mksaveddirty(pmd_t pmd) { pmdval_t v = native_pmd_val(pmd); v = mksaveddirty_shift(v); return native_make_pmd(v); } /* See comments above mksaveddirty_shift() */ static inline pmd_t pmd_clear_saveddirty(pmd_t pmd) { pmdval_t v = native_pmd_val(pmd); v = clear_saveddirty_shift(v); return native_make_pmd(v); } static inline pmd_t pmd_wrprotect(pmd_t pmd) { pmd = pmd_clear_flags(pmd, _PAGE_RW); /* * Blindly clearing _PAGE_RW might accidentally create * a shadow stack PMD (RW=0, Dirty=1). Move the hardware * dirty value to the software bit. */ return pmd_mksaveddirty(pmd); } #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline int pmd_uffd_wp(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_UFFD_WP; } static inline pmd_t pmd_mkuffd_wp(pmd_t pmd) { return pmd_wrprotect(pmd_set_flags(pmd, _PAGE_UFFD_WP)); } static inline pmd_t pmd_clear_uffd_wp(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_UFFD_WP); } #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ static inline pmd_t pmd_mkold(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_ACCESSED); } static inline pmd_t pmd_mkclean(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_DIRTY_BITS); } static inline pmd_t pmd_mkdirty(pmd_t pmd) { pmd = pmd_set_flags(pmd, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); return pmd_mksaveddirty(pmd); } static inline pmd_t pmd_mkwrite_shstk(pmd_t pmd) { pmd = pmd_clear_flags(pmd, _PAGE_RW); return pmd_set_flags(pmd, _PAGE_DIRTY); } static inline pmd_t pmd_mkdevmap(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_DEVMAP); } static inline pmd_t pmd_mkhuge(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_PSE); } static inline pmd_t pmd_mkyoung(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_ACCESSED); } static inline pmd_t pmd_mkwrite_novma(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_RW); } pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); #define pmd_mkwrite pmd_mkwrite /* See comments above mksaveddirty_shift() */ static inline pud_t pud_mksaveddirty(pud_t pud) { pudval_t v = native_pud_val(pud); v = mksaveddirty_shift(v); return native_make_pud(v); } /* See comments above mksaveddirty_shift() */ static inline pud_t pud_clear_saveddirty(pud_t pud) { pudval_t v = native_pud_val(pud); v = clear_saveddirty_shift(v); return native_make_pud(v); } static inline pud_t pud_mkold(pud_t pud) { return pud_clear_flags(pud, _PAGE_ACCESSED); } static inline pud_t pud_mkclean(pud_t pud) { return pud_clear_flags(pud, _PAGE_DIRTY_BITS); } static inline pud_t pud_wrprotect(pud_t pud) { pud = pud_clear_flags(pud, _PAGE_RW); /* * Blindly clearing _PAGE_RW might accidentally create * a shadow stack PUD (RW=0, Dirty=1). Move the hardware * dirty value to the software bit. */ return pud_mksaveddirty(pud); } static inline pud_t pud_mkdirty(pud_t pud) { pud = pud_set_flags(pud, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); return pud_mksaveddirty(pud); } static inline pud_t pud_mkdevmap(pud_t pud) { return pud_set_flags(pud, _PAGE_DEVMAP); } static inline pud_t pud_mkhuge(pud_t pud) { return pud_set_flags(pud, _PAGE_PSE); } static inline pud_t pud_mkyoung(pud_t pud) { return pud_set_flags(pud, _PAGE_ACCESSED); } static inline pud_t pud_mkwrite(pud_t pud) { pud = pud_set_flags(pud, _PAGE_RW); return pud_clear_saveddirty(pud); } #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline int pte_soft_dirty(pte_t pte) { return pte_flags(pte) & _PAGE_SOFT_DIRTY; } static inline int pmd_soft_dirty(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_SOFT_DIRTY; } static inline int pud_soft_dirty(pud_t pud) { return pud_flags(pud) & _PAGE_SOFT_DIRTY; } static inline pte_t pte_mksoft_dirty(pte_t pte) { return pte_set_flags(pte, _PAGE_SOFT_DIRTY); } static inline pmd_t pmd_mksoft_dirty(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY); } static inline pud_t pud_mksoft_dirty(pud_t pud) { return pud_set_flags(pud, _PAGE_SOFT_DIRTY); } static inline pte_t pte_clear_soft_dirty(pte_t pte) { return pte_clear_flags(pte, _PAGE_SOFT_DIRTY); } static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_SOFT_DIRTY); } static inline pud_t pud_clear_soft_dirty(pud_t pud) { return pud_clear_flags(pud, _PAGE_SOFT_DIRTY); } #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ /* * Mask out unsupported bits in a present pgprot. Non-present pgprots * can use those bits for other purposes, so leave them be. */ static inline pgprotval_t massage_pgprot(pgprot_t pgprot) { pgprotval_t protval = pgprot_val(pgprot); if (protval & _PAGE_PRESENT) protval &= __supported_pte_mask; return protval; } static inline pgprotval_t check_pgprot(pgprot_t pgprot) { pgprotval_t massaged_val = massage_pgprot(pgprot); /* mmdebug.h can not be included here because of dependencies */ #ifdef CONFIG_DEBUG_VM WARN_ONCE(pgprot_val(pgprot) != massaged_val, "attempted to set unsupported pgprot: %016llx " "bits: %016llx supported: %016llx\n", (u64)pgprot_val(pgprot), (u64)pgprot_val(pgprot) ^ massaged_val, (u64)__supported_pte_mask); #endif return massaged_val; } static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot) { phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; pfn ^= protnone_mask(pgprot_val(pgprot)); pfn &= PTE_PFN_MASK; return __pte(pfn | check_pgprot(pgprot)); } static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot) { phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; pfn ^= protnone_mask(pgprot_val(pgprot)); pfn &= PHYSICAL_PMD_PAGE_MASK; return __pmd(pfn | check_pgprot(pgprot)); } static inline pud_t pfn_pud(unsigned long page_nr, pgprot_t pgprot) { phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; pfn ^= protnone_mask(pgprot_val(pgprot)); pfn &= PHYSICAL_PUD_PAGE_MASK; return __pud(pfn | check_pgprot(pgprot)); } static inline pmd_t pmd_mkinvalid(pmd_t pmd) { return pfn_pmd(pmd_pfn(pmd), __pgprot(pmd_flags(pmd) & ~(_PAGE_PRESENT|_PAGE_PROTNONE))); } static inline pud_t pud_mkinvalid(pud_t pud) { return pfn_pud(pud_pfn(pud), __pgprot(pud_flags(pud) & ~(_PAGE_PRESENT|_PAGE_PROTNONE))); } static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask); static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { pteval_t val = pte_val(pte), oldval = val; pte_t pte_result; /* * Chop off the NX bit (if present), and add the NX portion of * the newprot (if present): */ val &= _PAGE_CHG_MASK; val |= check_pgprot(newprot) & ~_PAGE_CHG_MASK; val = flip_protnone_guard(oldval, val, PTE_PFN_MASK); pte_result = __pte(val); /* * To avoid creating Write=0,Dirty=1 PTEs, pte_modify() needs to avoid: * 1. Marking Write=0 PTEs Dirty=1 * 2. Marking Dirty=1 PTEs Write=0 * * The first case cannot happen because the _PAGE_CHG_MASK will filter * out any Dirty bit passed in newprot. Handle the second case by * going through the mksaveddirty exercise. Only do this if the old * value was Write=1 to avoid doing this on Shadow Stack PTEs. */ if (oldval & _PAGE_RW) pte_result = pte_mksaveddirty(pte_result); else pte_result = pte_clear_saveddirty(pte_result); return pte_result; } static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { pmdval_t val = pmd_val(pmd), oldval = val; pmd_t pmd_result; val &= (_HPAGE_CHG_MASK & ~_PAGE_DIRTY); val |= check_pgprot(newprot) & ~_HPAGE_CHG_MASK; val = flip_protnone_guard(oldval, val, PHYSICAL_PMD_PAGE_MASK); pmd_result = __pmd(val); /* * Avoid creating shadow stack PMD by accident. See comment in * pte_modify(). */ if (oldval & _PAGE_RW) pmd_result = pmd_mksaveddirty(pmd_result); else pmd_result = pmd_clear_saveddirty(pmd_result); return pmd_result; } static inline pud_t pud_modify(pud_t pud, pgprot_t newprot) { pudval_t val = pud_val(pud), oldval = val; pud_t pud_result; val &= _HPAGE_CHG_MASK; val |= check_pgprot(newprot) & ~_HPAGE_CHG_MASK; val = flip_protnone_guard(oldval, val, PHYSICAL_PUD_PAGE_MASK); pud_result = __pud(val); /* * Avoid creating shadow stack PUD by accident. See comment in * pte_modify(). */ if (oldval & _PAGE_RW) pud_result = pud_mksaveddirty(pud_result); else pud_result = pud_clear_saveddirty(pud_result); return pud_result; } /* * mprotect needs to preserve PAT and encryption bits when updating * vm_page_prot */ #define pgprot_modify pgprot_modify static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) { pgprotval_t preservebits = pgprot_val(oldprot) & _PAGE_CHG_MASK; pgprotval_t addbits = pgprot_val(newprot) & ~_PAGE_CHG_MASK; return __pgprot(preservebits | addbits); } #define pte_pgprot(x) __pgprot(pte_flags(x)) #define pmd_pgprot(x) __pgprot(pmd_flags(x)) #define pud_pgprot(x) __pgprot(pud_flags(x)) #define p4d_pgprot(x) __pgprot(p4d_flags(x)) #define canon_pgprot(p) __pgprot(massage_pgprot(p)) static inline int is_new_memtype_allowed(u64 paddr, unsigned long size, enum page_cache_mode pcm, enum page_cache_mode new_pcm) { /* * PAT type is always WB for untracked ranges, so no need to check. */ if (x86_platform.is_untracked_pat_range(paddr, paddr + size)) return 1; /* * Certain new memtypes are not allowed with certain * requested memtype: * - request is uncached, return cannot be write-back * - request is write-combine, return cannot be write-back * - request is write-through, return cannot be write-back * - request is write-through, return cannot be write-combine */ if ((pcm == _PAGE_CACHE_MODE_UC_MINUS && new_pcm == _PAGE_CACHE_MODE_WB) || (pcm == _PAGE_CACHE_MODE_WC && new_pcm == _PAGE_CACHE_MODE_WB) || (pcm == _PAGE_CACHE_MODE_WT && new_pcm == _PAGE_CACHE_MODE_WB) || (pcm == _PAGE_CACHE_MODE_WT && new_pcm == _PAGE_CACHE_MODE_WC)) { return 0; } return 1; } pmd_t *populate_extra_pmd(unsigned long vaddr); pte_t *populate_extra_pte(unsigned long vaddr); #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd); /* * Take a PGD location (pgdp) and a pgd value that needs to be set there. * Populates the user and returns the resulting PGD that must be set in * the kernel copy of the page tables. */ static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) { if (!static_cpu_has(X86_FEATURE_PTI)) return pgd; return __pti_set_user_pgtbl(pgdp, pgd); } #else /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) { return pgd; } #endif /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ #endif /* __ASSEMBLY__ */ #ifdef CONFIG_X86_32 # include <asm/pgtable_32.h> #else # include <asm/pgtable_64.h> #endif #ifndef __ASSEMBLY__ #include <linux/mm_types.h> #include <linux/mmdebug.h> #include <linux/log2.h> #include <asm/fixmap.h> static inline int pte_none(pte_t pte) { return !(pte.pte & ~(_PAGE_KNL_ERRATUM_MASK)); } #define __HAVE_ARCH_PTE_SAME static inline int pte_same(pte_t a, pte_t b) { return a.pte == b.pte; } static inline pte_t pte_advance_pfn(pte_t pte, unsigned long nr) { if (__pte_needs_invert(pte_val(pte))) return __pte(pte_val(pte) - (nr << PFN_PTE_SHIFT)); return __pte(pte_val(pte) + (nr << PFN_PTE_SHIFT)); } #define pte_advance_pfn pte_advance_pfn static inline int pte_present(pte_t a) { return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE); } #ifdef CONFIG_ARCH_HAS_PTE_DEVMAP static inline int pte_devmap(pte_t a) { return (pte_flags(a) & _PAGE_DEVMAP) == _PAGE_DEVMAP; } #endif #define pte_accessible pte_accessible static inline bool pte_accessible(struct mm_struct *mm, pte_t a) { if (pte_flags(a) & _PAGE_PRESENT) return true; if ((pte_flags(a) & _PAGE_PROTNONE) && atomic_read(&mm->tlb_flush_pending)) return true; return false; } static inline int pmd_present(pmd_t pmd) { /* * Checking for _PAGE_PSE is needed too because * split_huge_page will temporarily clear the present bit (but * the _PAGE_PSE flag will remain set at all times while the * _PAGE_PRESENT bit is clear). */ return pmd_flags(pmd) & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_PSE); } #ifdef CONFIG_NUMA_BALANCING /* * These work without NUMA balancing but the kernel does not care. See the * comment in include/linux/pgtable.h */ static inline int pte_protnone(pte_t pte) { return (pte_flags(pte) & (_PAGE_PROTNONE | _PAGE_PRESENT)) == _PAGE_PROTNONE; } static inline int pmd_protnone(pmd_t pmd) { return (pmd_flags(pmd) & (_PAGE_PROTNONE | _PAGE_PRESENT)) == _PAGE_PROTNONE; } #endif /* CONFIG_NUMA_BALANCING */ static inline int pmd_none(pmd_t pmd) { /* Only check low word on 32-bit platforms, since it might be out of sync with upper half. */ unsigned long val = native_pmd_val(pmd); return (val & ~_PAGE_KNL_ERRATUM_MASK) == 0; } static inline unsigned long pmd_page_vaddr(pmd_t pmd) { return (unsigned long)__va(pmd_val(pmd) & pmd_pfn_mask(pmd)); } /* * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ #define pmd_page(pmd) pfn_to_page(pmd_pfn(pmd)) /* * Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. * * (Currently stuck as a macro because of indirect forward reference * to linux/mm.h:page_to_nid()) */ #define mk_pte(page, pgprot) \ ({ \ pgprot_t __pgprot = pgprot; \ \ WARN_ON_ONCE((pgprot_val(__pgprot) & (_PAGE_DIRTY | _PAGE_RW)) == \ _PAGE_DIRTY); \ pfn_pte(page_to_pfn(page), __pgprot); \ }) static inline int pmd_bad(pmd_t pmd) { return (pmd_flags(pmd) & ~(_PAGE_USER | _PAGE_ACCESSED)) != (_KERNPG_TABLE & ~_PAGE_ACCESSED); } static inline unsigned long pages_to_mb(unsigned long npg) { return npg >> (20 - PAGE_SHIFT); } #if CONFIG_PGTABLE_LEVELS > 2 static inline int pud_none(pud_t pud) { return (native_pud_val(pud) & ~(_PAGE_KNL_ERRATUM_MASK)) == 0; } static inline int pud_present(pud_t pud) { return pud_flags(pud) & _PAGE_PRESENT; } static inline pmd_t *pud_pgtable(pud_t pud) { return (pmd_t *)__va(pud_val(pud) & pud_pfn_mask(pud)); } /* * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ #define pud_page(pud) pfn_to_page(pud_pfn(pud)) #define pud_leaf pud_leaf static inline bool pud_leaf(pud_t pud) { return pud_val(pud) & _PAGE_PSE; } static inline int pud_bad(pud_t pud) { return (pud_flags(pud) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0; } #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #if CONFIG_PGTABLE_LEVELS > 3 static inline int p4d_none(p4d_t p4d) { return (native_p4d_val(p4d) & ~(_PAGE_KNL_ERRATUM_MASK)) == 0; } static inline int p4d_present(p4d_t p4d) { return p4d_flags(p4d) & _PAGE_PRESENT; } static inline pud_t *p4d_pgtable(p4d_t p4d) { return (pud_t *)__va(p4d_val(p4d) & p4d_pfn_mask(p4d)); } /* * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ #define p4d_page(p4d) pfn_to_page(p4d_pfn(p4d)) static inline int p4d_bad(p4d_t p4d) { unsigned long ignore_flags = _KERNPG_TABLE | _PAGE_USER; if (IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)) ignore_flags |= _PAGE_NX; return (p4d_flags(p4d) & ~ignore_flags) != 0; } #endif /* CONFIG_PGTABLE_LEVELS > 3 */ static inline unsigned long p4d_index(unsigned long address) { return (address >> P4D_SHIFT) & (PTRS_PER_P4D - 1); } #if CONFIG_PGTABLE_LEVELS > 4 static inline int pgd_present(pgd_t pgd) { if (!pgtable_l5_enabled()) return 1; return pgd_flags(pgd) & _PAGE_PRESENT; } static inline unsigned long pgd_page_vaddr(pgd_t pgd) { return (unsigned long)__va((unsigned long)pgd_val(pgd) & PTE_PFN_MASK); } /* * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ #define pgd_page(pgd) pfn_to_page(pgd_pfn(pgd)) /* to find an entry in a page-table-directory. */ static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) { if (!pgtable_l5_enabled()) return (p4d_t *)pgd; return (p4d_t *)pgd_page_vaddr(*pgd) + p4d_index(address); } static inline int pgd_bad(pgd_t pgd) { unsigned long ignore_flags = _PAGE_USER; if (!pgtable_l5_enabled()) return 0; if (IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)) ignore_flags |= _PAGE_NX; return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE; } static inline int pgd_none(pgd_t pgd) { if (!pgtable_l5_enabled()) return 0; /* * There is no need to do a workaround for the KNL stray * A/D bit erratum here. PGDs only point to page tables * except on 32-bit non-PAE which is not supported on * KNL. */ return !native_pgd_val(pgd); } #endif /* CONFIG_PGTABLE_LEVELS > 4 */ #endif /* __ASSEMBLY__ */ #define KERNEL_PGD_BOUNDARY pgd_index(PAGE_OFFSET) #define KERNEL_PGD_PTRS (PTRS_PER_PGD - KERNEL_PGD_BOUNDARY) #ifndef __ASSEMBLY__ extern int direct_gbpages; void init_mem_mapping(void); void early_alloc_pgt_buf(void); void __init poking_init(void); unsigned long init_memory_mapping(unsigned long start, unsigned long end, pgprot_t prot); #ifdef CONFIG_X86_64 extern pgd_t trampoline_pgd_entry; #endif /* local pte updates need not use xchg for locking */ static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep) { pte_t res = *ptep; /* Pure native function needs no input for mm, addr */ native_pte_clear(NULL, 0, ptep); return res; } static inline pmd_t native_local_pmdp_get_and_clear(pmd_t *pmdp) { pmd_t res = *pmdp; native_pmd_clear(pmdp); return res; } static inline pud_t native_local_pudp_get_and_clear(pud_t *pudp) { pud_t res = *pudp; native_pud_clear(pudp); return res; } static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { page_table_check_pmd_set(mm, pmdp, pmd); set_pmd(pmdp, pmd); } static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, pud_t *pudp, pud_t pud) { page_table_check_pud_set(mm, pudp, pud); native_set_pud(pudp, pud); } /* * We only update the dirty/accessed state if we set * the dirty bit by hand in the kernel, since the hardware * will do the accessed bit for us, and we don't want to * race with other CPU's that might be updating the dirty * bit at the same time. */ struct vm_area_struct; #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty); #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG extern int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH extern int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); #define __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { pte_t pte = native_ptep_get_and_clear(ptep); page_table_check_pte_clear(mm, pte); return pte; } #define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long addr, pte_t *ptep, int full) { pte_t pte; if (full) { /* * Full address destruction in progress; paravirt does not * care about updates and native needs no locking */ pte = native_local_ptep_get_and_clear(ptep); page_table_check_pte_clear(mm, pte); } else { pte = ptep_get_and_clear(mm, addr, ptep); } return pte; } #define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { /* * Avoid accidentally creating shadow stack PTEs * (Write=0,Dirty=1). Use cmpxchg() to prevent races with * the hardware setting Dirty=1. */ pte_t old_pte, new_pte; old_pte = READ_ONCE(*ptep); do { new_pte = pte_wrprotect(old_pte); } while (!try_cmpxchg((long *)&ptep->pte, (long *)&old_pte, *(long *)&new_pte)); } #define flush_tlb_fix_spurious_fault(vma, address, ptep) do { } while (0) #define mk_pmd(page, pgprot) pfn_pmd(page_to_pfn(page), (pgprot)) #define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS extern int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty); extern int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, pud_t entry, int dirty); #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG extern int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp); extern int pudp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pud_t *pudp); #define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH extern int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { pmd_t pmd = native_pmdp_get_and_clear(pmdp); page_table_check_pmd_clear(mm, pmd); return pmd; } #define __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pud_t *pudp) { pud_t pud = native_pudp_get_and_clear(pudp); page_table_check_pud_clear(mm, pud); return pud; } #define __HAVE_ARCH_PMDP_SET_WRPROTECT static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { /* * Avoid accidentally creating shadow stack PTEs * (Write=0,Dirty=1). Use cmpxchg() to prevent races with * the hardware setting Dirty=1. */ pmd_t old_pmd, new_pmd; old_pmd = READ_ONCE(*pmdp); do { new_pmd = pmd_wrprotect(old_pmd); } while (!try_cmpxchg((long *)pmdp, (long *)&old_pmd, *(long *)&new_pmd)); } #ifndef pmdp_establish #define pmdp_establish pmdp_establish static inline pmd_t pmdp_establish(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t pmd) { page_table_check_pmd_set(vma->vm_mm, pmdp, pmd); if (IS_ENABLED(CONFIG_SMP)) { return xchg(pmdp, pmd); } else { pmd_t old = *pmdp; WRITE_ONCE(*pmdp, pmd); return old; } } #endif #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static inline pud_t pudp_establish(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, pud_t pud) { page_table_check_pud_set(vma->vm_mm, pudp, pud); if (IS_ENABLED(CONFIG_SMP)) { return xchg(pudp, pud); } else { pud_t old = *pudp; WRITE_ONCE(*pudp, pud); return old; } } #endif #define __HAVE_ARCH_PMDP_INVALIDATE_AD extern pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address, pud_t *pudp); /* * Page table pages are page-aligned. The lower half of the top * level is used for userspace and the top half for the kernel. * * Returns true for parts of the PGD that map userspace and * false for the parts that map the kernel. */ static inline bool pgdp_maps_userspace(void *__ptr) { unsigned long ptr = (unsigned long)__ptr; return (((ptr & ~PAGE_MASK) / sizeof(pgd_t)) < PGD_KERNEL_START); } #define pgd_leaf pgd_leaf static inline bool pgd_leaf(pgd_t pgd) { return false; } #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION /* * All top-level MITIGATION_PAGE_TABLE_ISOLATION page tables are order-1 pages * (8k-aligned and 8k in size). The kernel one is at the beginning 4k and * the user one is in the last 4k. To switch between them, you * just need to flip the 12th bit in their addresses. */ #define PTI_PGTABLE_SWITCH_BIT PAGE_SHIFT /* * This generates better code than the inline assembly in * __set_bit(). */ static inline void *ptr_set_bit(void *ptr, int bit) { unsigned long __ptr = (unsigned long)ptr; __ptr |= BIT(bit); return (void *)__ptr; } static inline void *ptr_clear_bit(void *ptr, int bit) { unsigned long __ptr = (unsigned long)ptr; __ptr &= ~BIT(bit); return (void *)__ptr; } static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp) { return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT); } static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp) { return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT); } static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp) { return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); } static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp) { return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); } #endif /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ /* * clone_pgd_range(pgd_t *dst, pgd_t *src, int count); * * dst - pointer to pgd range anywhere on a pgd page * src - "" * count - the number of pgds to copy. * * dst and src can be on the same page, but the range must not overlap, * and must not cross a page boundary. */ static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count) { memcpy(dst, src, count * sizeof(pgd_t)); #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION if (!static_cpu_has(X86_FEATURE_PTI)) return; /* Clone the user space pgd as well */ memcpy(kernel_to_user_pgdp(dst), kernel_to_user_pgdp(src), count * sizeof(pgd_t)); #endif } #define PTE_SHIFT ilog2(PTRS_PER_PTE) static inline int page_level_shift(enum pg_level level) { return (PAGE_SHIFT - PTE_SHIFT) + level * PTE_SHIFT; } static inline unsigned long page_level_size(enum pg_level level) { return 1UL << page_level_shift(level); } static inline unsigned long page_level_mask(enum pg_level level) { return ~(page_level_size(level) - 1); } /* * The x86 doesn't have any external MMU info: the kernel page * tables contain all the necessary information. */ static inline void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { } static inline void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr) { } static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd) { } static inline void update_mmu_cache_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud) { } static inline pte_t pte_swp_mkexclusive(pte_t pte) { return pte_set_flags(pte, _PAGE_SWP_EXCLUSIVE); } static inline int pte_swp_exclusive(pte_t pte) { return pte_flags(pte) & _PAGE_SWP_EXCLUSIVE; } static inline pte_t pte_swp_clear_exclusive(pte_t pte) { return pte_clear_flags(pte, _PAGE_SWP_EXCLUSIVE); } #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline pte_t pte_swp_mksoft_dirty(pte_t pte) { return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY); } static inline int pte_swp_soft_dirty(pte_t pte) { return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY; } static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) { return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY); } #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_SWP_SOFT_DIRTY); } static inline int pmd_swp_soft_dirty(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_SWP_SOFT_DIRTY; } static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_SWP_SOFT_DIRTY); } #endif #endif #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline pte_t pte_swp_mkuffd_wp(pte_t pte) { return pte_set_flags(pte, _PAGE_SWP_UFFD_WP); } static inline int pte_swp_uffd_wp(pte_t pte) { return pte_flags(pte) & _PAGE_SWP_UFFD_WP; } static inline pte_t pte_swp_clear_uffd_wp(pte_t pte) { return pte_clear_flags(pte, _PAGE_SWP_UFFD_WP); } static inline pmd_t pmd_swp_mkuffd_wp(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_SWP_UFFD_WP); } static inline int pmd_swp_uffd_wp(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_SWP_UFFD_WP; } static inline pmd_t pmd_swp_clear_uffd_wp(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_SWP_UFFD_WP); } #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ static inline u16 pte_flags_pkey(unsigned long pte_flags) { #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS /* ifdef to avoid doing 59-bit shift on 32-bit values */ return (pte_flags & _PAGE_PKEY_MASK) >> _PAGE_BIT_PKEY_BIT0; #else return 0; #endif } static inline bool __pkru_allows_pkey(u16 pkey, bool write) { u32 pkru = read_pkru(); if (!__pkru_allows_read(pkru, pkey)) return false; if (write && !__pkru_allows_write(pkru, pkey)) return false; return true; } /* * 'pteval' can come from a PTE, PMD or PUD. We only check * _PAGE_PRESENT, _PAGE_USER, and _PAGE_RW in here which are the * same value on all 3 types. */ static inline bool __pte_access_permitted(unsigned long pteval, bool write) { unsigned long need_pte_bits = _PAGE_PRESENT|_PAGE_USER; /* * Write=0,Dirty=1 PTEs are shadow stack, which the kernel * shouldn't generally allow access to, but since they * are already Write=0, the below logic covers both cases. */ if (write) need_pte_bits |= _PAGE_RW; if ((pteval & need_pte_bits) != need_pte_bits) return 0; return __pkru_allows_pkey(pte_flags_pkey(pteval), write); } #define pte_access_permitted pte_access_permitted static inline bool pte_access_permitted(pte_t pte, bool write) { return __pte_access_permitted(pte_val(pte), write); } #define pmd_access_permitted pmd_access_permitted static inline bool pmd_access_permitted(pmd_t pmd, bool write) { return __pte_access_permitted(pmd_val(pmd), write); } #define pud_access_permitted pud_access_permitted static inline bool pud_access_permitted(pud_t pud, bool write) { return __pte_access_permitted(pud_val(pud), write); } #define __HAVE_ARCH_PFN_MODIFY_ALLOWED 1 extern bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot); static inline bool arch_has_pfn_modify_check(void) { return boot_cpu_has_bug(X86_BUG_L1TF); } #define arch_check_zapped_pte arch_check_zapped_pte void arch_check_zapped_pte(struct vm_area_struct *vma, pte_t pte); #define arch_check_zapped_pmd arch_check_zapped_pmd void arch_check_zapped_pmd(struct vm_area_struct *vma, pmd_t pmd); #define arch_check_zapped_pud arch_check_zapped_pud void arch_check_zapped_pud(struct vm_area_struct *vma, pud_t pud); #ifdef CONFIG_XEN_PV #define arch_has_hw_nonleaf_pmd_young arch_has_hw_nonleaf_pmd_young static inline bool arch_has_hw_nonleaf_pmd_young(void) { return !cpu_feature_enabled(X86_FEATURE_XENPV); } #endif #ifdef CONFIG_PAGE_TABLE_CHECK static inline bool pte_user_accessible_page(pte_t pte) { return (pte_val(pte) & _PAGE_PRESENT) && (pte_val(pte) & _PAGE_USER); } static inline bool pmd_user_accessible_page(pmd_t pmd) { return pmd_leaf(pmd) && (pmd_val(pmd) & _PAGE_PRESENT) && (pmd_val(pmd) & _PAGE_USER); } static inline bool pud_user_accessible_page(pud_t pud) { return pud_leaf(pud) && (pud_val(pud) & _PAGE_PRESENT) && (pud_val(pud) & _PAGE_USER); } #endif #ifdef CONFIG_X86_SGX int arch_memory_failure(unsigned long pfn, int flags); #define arch_memory_failure arch_memory_failure bool arch_is_platform_page(u64 paddr); #define arch_is_platform_page arch_is_platform_page #endif /* * Use set_p*_safe(), and elide TLB flushing, when confident that *no* * TLB flush will be required as a result of the "set". For example, use * in scenarios where it is known ahead of time that the routine is * setting non-present entries, or re-setting an existing entry to the * same value. Otherwise, use the typical "set" helpers and flush the * TLB. */ #define set_pte_safe(ptep, pte) \ ({ \ WARN_ON_ONCE(pte_present(*ptep) && !pte_same(*ptep, pte)); \ set_pte(ptep, pte); \ }) #define set_pmd_safe(pmdp, pmd) \ ({ \ WARN_ON_ONCE(pmd_present(*pmdp) && !pmd_same(*pmdp, pmd)); \ set_pmd(pmdp, pmd); \ }) #define set_pud_safe(pudp, pud) \ ({ \ WARN_ON_ONCE(pud_present(*pudp) && !pud_same(*pudp, pud)); \ set_pud(pudp, pud); \ }) #define set_p4d_safe(p4dp, p4d) \ ({ \ WARN_ON_ONCE(p4d_present(*p4dp) && !p4d_same(*p4dp, p4d)); \ set_p4d(p4dp, p4d); \ }) #define set_pgd_safe(pgdp, pgd) \ ({ \ WARN_ON_ONCE(pgd_present(*pgdp) && !pgd_same(*pgdp, pgd)); \ set_pgd(pgdp, pgd); \ }) #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_H */ |
| 225 138 148 30 5 5 325 18 20 2 2 3 3 3 2 3 3 3 3 3 3 3 3 228 229 6 7 13 245 229 232 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2007 Jens Axboe <jens.axboe@oracle.com> * * Scatterlist handling helpers. */ #include <linux/export.h> #include <linux/slab.h> #include <linux/scatterlist.h> #include <linux/highmem.h> #include <linux/kmemleak.h> #include <linux/bvec.h> #include <linux/uio.h> #include <linux/folio_queue.h> /** * sg_next - return the next scatterlist entry in a list * @sg: The current sg entry * * Description: * Usually the next entry will be @sg@ + 1, but if this sg element is part * of a chained scatterlist, it could jump to the start of a new * scatterlist array. * **/ struct scatterlist *sg_next(struct scatterlist *sg) { if (sg_is_last(sg)) return NULL; sg++; if (unlikely(sg_is_chain(sg))) sg = sg_chain_ptr(sg); return sg; } EXPORT_SYMBOL(sg_next); /** * sg_nents - return total count of entries in scatterlist * @sg: The scatterlist * * Description: * Allows to know how many entries are in sg, taking into account * chaining as well * **/ int sg_nents(struct scatterlist *sg) { int nents; for (nents = 0; sg; sg = sg_next(sg)) nents++; return nents; } EXPORT_SYMBOL(sg_nents); /** * sg_nents_for_len - return total count of entries in scatterlist * needed to satisfy the supplied length * @sg: The scatterlist * @len: The total required length * * Description: * Determines the number of entries in sg that are required to meet * the supplied length, taking into account chaining as well * * Returns: * the number of sg entries needed, negative error on failure * **/ int sg_nents_for_len(struct scatterlist *sg, u64 len) { int nents; u64 total; if (!len) return 0; for (nents = 0, total = 0; sg; sg = sg_next(sg)) { nents++; total += sg->length; if (total >= len) return nents; } return -EINVAL; } EXPORT_SYMBOL(sg_nents_for_len); /** * sg_last - return the last scatterlist entry in a list * @sgl: First entry in the scatterlist * @nents: Number of entries in the scatterlist * * Description: * Should only be used casually, it (currently) scans the entire list * to get the last entry. * * Note that the @sgl@ pointer passed in need not be the first one, * the important bit is that @nents@ denotes the number of entries that * exist from @sgl@. * **/ struct scatterlist *sg_last(struct scatterlist *sgl, unsigned int nents) { struct scatterlist *sg, *ret = NULL; unsigned int i; for_each_sg(sgl, sg, nents, i) ret = sg; BUG_ON(!sg_is_last(ret)); return ret; } EXPORT_SYMBOL(sg_last); /** * sg_init_table - Initialize SG table * @sgl: The SG table * @nents: Number of entries in table * * Notes: * If this is part of a chained sg table, sg_mark_end() should be * used only on the last table part. * **/ void sg_init_table(struct scatterlist *sgl, unsigned int nents) { memset(sgl, 0, sizeof(*sgl) * nents); sg_init_marker(sgl, nents); } EXPORT_SYMBOL(sg_init_table); /** * sg_init_one - Initialize a single entry sg list * @sg: SG entry * @buf: Virtual address for IO * @buflen: IO length * **/ void sg_init_one(struct scatterlist *sg, const void *buf, unsigned int buflen) { sg_init_table(sg, 1); sg_set_buf(sg, buf, buflen); } EXPORT_SYMBOL(sg_init_one); /* * The default behaviour of sg_alloc_table() is to use these kmalloc/kfree * helpers. */ static struct scatterlist *sg_kmalloc(unsigned int nents, gfp_t gfp_mask) { if (nents == SG_MAX_SINGLE_ALLOC) { /* * Kmemleak doesn't track page allocations as they are not * commonly used (in a raw form) for kernel data structures. * As we chain together a list of pages and then a normal * kmalloc (tracked by kmemleak), in order to for that last * allocation not to become decoupled (and thus a * false-positive) we need to inform kmemleak of all the * intermediate allocations. */ void *ptr = (void *) __get_free_page(gfp_mask); kmemleak_alloc(ptr, PAGE_SIZE, 1, gfp_mask); return ptr; } else return kmalloc_array(nents, sizeof(struct scatterlist), gfp_mask); } static void sg_kfree(struct scatterlist *sg, unsigned int nents) { if (nents == SG_MAX_SINGLE_ALLOC) { kmemleak_free(sg); free_page((unsigned long) sg); } else kfree(sg); } /** * __sg_free_table - Free a previously mapped sg table * @table: The sg table header to use * @max_ents: The maximum number of entries per single scatterlist * @nents_first_chunk: Number of entries int the (preallocated) first * scatterlist chunk, 0 means no such preallocated first chunk * @free_fn: Free function * @num_ents: Number of entries in the table * * Description: * Free an sg table previously allocated and setup with * __sg_alloc_table(). The @max_ents value must be identical to * that previously used with __sg_alloc_table(). * **/ void __sg_free_table(struct sg_table *table, unsigned int max_ents, unsigned int nents_first_chunk, sg_free_fn *free_fn, unsigned int num_ents) { struct scatterlist *sgl, *next; unsigned curr_max_ents = nents_first_chunk ?: max_ents; if (unlikely(!table->sgl)) return; sgl = table->sgl; while (num_ents) { unsigned int alloc_size = num_ents; unsigned int sg_size; /* * If we have more than max_ents segments left, * then assign 'next' to the sg table after the current one. * sg_size is then one less than alloc size, since the last * element is the chain pointer. */ if (alloc_size > curr_max_ents) { next = sg_chain_ptr(&sgl[curr_max_ents - 1]); alloc_size = curr_max_ents; sg_size = alloc_size - 1; } else { sg_size = alloc_size; next = NULL; } num_ents -= sg_size; if (nents_first_chunk) nents_first_chunk = 0; else free_fn(sgl, alloc_size); sgl = next; curr_max_ents = max_ents; } table->sgl = NULL; } EXPORT_SYMBOL(__sg_free_table); /** * sg_free_append_table - Free a previously allocated append sg table. * @table: The mapped sg append table header * **/ void sg_free_append_table(struct sg_append_table *table) { __sg_free_table(&table->sgt, SG_MAX_SINGLE_ALLOC, 0, sg_kfree, table->total_nents); } EXPORT_SYMBOL(sg_free_append_table); /** * sg_free_table - Free a previously allocated sg table * @table: The mapped sg table header * **/ void sg_free_table(struct sg_table *table) { __sg_free_table(table, SG_MAX_SINGLE_ALLOC, 0, sg_kfree, table->orig_nents); } EXPORT_SYMBOL(sg_free_table); /** * __sg_alloc_table - Allocate and initialize an sg table with given allocator * @table: The sg table header to use * @nents: Number of entries in sg list * @max_ents: The maximum number of entries the allocator returns per call * @first_chunk: first SGL if preallocated (may be %NULL) * @nents_first_chunk: Number of entries in the (preallocated) first * scatterlist chunk, 0 means no such preallocated chunk provided by user * @gfp_mask: GFP allocation mask * @alloc_fn: Allocator to use * * Description: * This function returns a @table @nents long. The allocator is * defined to return scatterlist chunks of maximum size @max_ents. * Thus if @nents is bigger than @max_ents, the scatterlists will be * chained in units of @max_ents. * * Notes: * If this function returns non-0 (eg failure), the caller must call * __sg_free_table() to cleanup any leftover allocations. * **/ int __sg_alloc_table(struct sg_table *table, unsigned int nents, unsigned int max_ents, struct scatterlist *first_chunk, unsigned int nents_first_chunk, gfp_t gfp_mask, sg_alloc_fn *alloc_fn) { struct scatterlist *sg, *prv; unsigned int left; unsigned curr_max_ents = nents_first_chunk ?: max_ents; unsigned prv_max_ents; memset(table, 0, sizeof(*table)); if (nents == 0) return -EINVAL; #ifdef CONFIG_ARCH_NO_SG_CHAIN if (WARN_ON_ONCE(nents > max_ents)) return -EINVAL; #endif left = nents; prv = NULL; do { unsigned int sg_size, alloc_size = left; if (alloc_size > curr_max_ents) { alloc_size = curr_max_ents; sg_size = alloc_size - 1; } else sg_size = alloc_size; left -= sg_size; if (first_chunk) { sg = first_chunk; first_chunk = NULL; } else { sg = alloc_fn(alloc_size, gfp_mask); } if (unlikely(!sg)) { /* * Adjust entry count to reflect that the last * entry of the previous table won't be used for * linkage. Without this, sg_kfree() may get * confused. */ if (prv) table->nents = ++table->orig_nents; return -ENOMEM; } sg_init_table(sg, alloc_size); table->nents = table->orig_nents += sg_size; /* * If this is the first mapping, assign the sg table header. * If this is not the first mapping, chain previous part. */ if (prv) sg_chain(prv, prv_max_ents, sg); else table->sgl = sg; /* * If no more entries after this one, mark the end */ if (!left) sg_mark_end(&sg[sg_size - 1]); prv = sg; prv_max_ents = curr_max_ents; curr_max_ents = max_ents; } while (left); return 0; } EXPORT_SYMBOL(__sg_alloc_table); /** * sg_alloc_table - Allocate and initialize an sg table * @table: The sg table header to use * @nents: Number of entries in sg list * @gfp_mask: GFP allocation mask * * Description: * Allocate and initialize an sg table. If @nents@ is larger than * SG_MAX_SINGLE_ALLOC a chained sg table will be setup. * **/ int sg_alloc_table(struct sg_table *table, unsigned int nents, gfp_t gfp_mask) { int ret; ret = __sg_alloc_table(table, nents, SG_MAX_SINGLE_ALLOC, NULL, 0, gfp_mask, sg_kmalloc); if (unlikely(ret)) sg_free_table(table); return ret; } EXPORT_SYMBOL(sg_alloc_table); static struct scatterlist *get_next_sg(struct sg_append_table *table, struct scatterlist *cur, unsigned long needed_sges, gfp_t gfp_mask) { struct scatterlist *new_sg, *next_sg; unsigned int alloc_size; if (cur) { next_sg = sg_next(cur); /* Check if last entry should be keeped for chainning */ if (!sg_is_last(next_sg) || needed_sges == 1) return next_sg; } alloc_size = min_t(unsigned long, needed_sges, SG_MAX_SINGLE_ALLOC); new_sg = sg_kmalloc(alloc_size, gfp_mask); if (!new_sg) return ERR_PTR(-ENOMEM); sg_init_table(new_sg, alloc_size); if (cur) { table->total_nents += alloc_size - 1; __sg_chain(next_sg, new_sg); } else { table->sgt.sgl = new_sg; table->total_nents = alloc_size; } return new_sg; } static bool pages_are_mergeable(struct page *a, struct page *b) { if (page_to_pfn(a) != page_to_pfn(b) + 1) return false; if (!zone_device_pages_have_same_pgmap(a, b)) return false; return true; } /** * sg_alloc_append_table_from_pages - Allocate and initialize an append sg * table from an array of pages * @sgt_append: The sg append table to use * @pages: Pointer to an array of page pointers * @n_pages: Number of pages in the pages array * @offset: Offset from start of the first page to the start of a buffer * @size: Number of valid bytes in the buffer (after offset) * @max_segment: Maximum size of a scatterlist element in bytes * @left_pages: Left pages caller have to set after this call * @gfp_mask: GFP allocation mask * * Description: * In the first call it allocate and initialize an sg table from a list of * pages, else reuse the scatterlist from sgt_append. Contiguous ranges of * the pages are squashed into a single scatterlist entry up to the maximum * size specified in @max_segment. A user may provide an offset at a start * and a size of valid data in a buffer specified by the page array. The * returned sg table is released by sg_free_append_table * * Returns: * 0 on success, negative error on failure * * Notes: * If this function returns non-0 (eg failure), the caller must call * sg_free_append_table() to cleanup any leftover allocations. * * In the fist call, sgt_append must by initialized. */ int sg_alloc_append_table_from_pages(struct sg_append_table *sgt_append, struct page **pages, unsigned int n_pages, unsigned int offset, unsigned long size, unsigned int max_segment, unsigned int left_pages, gfp_t gfp_mask) { unsigned int chunks, cur_page, seg_len, i, prv_len = 0; unsigned int added_nents = 0; struct scatterlist *s = sgt_append->prv; struct page *last_pg; /* * The algorithm below requires max_segment to be aligned to PAGE_SIZE * otherwise it can overshoot. */ max_segment = ALIGN_DOWN(max_segment, PAGE_SIZE); if (WARN_ON(max_segment < PAGE_SIZE)) return -EINVAL; if (IS_ENABLED(CONFIG_ARCH_NO_SG_CHAIN) && sgt_append->prv) return -EOPNOTSUPP; if (sgt_append->prv) { unsigned long next_pfn; if (WARN_ON(offset)) return -EINVAL; /* Merge contiguous pages into the last SG */ prv_len = sgt_append->prv->length; next_pfn = (sg_phys(sgt_append->prv) + prv_len) / PAGE_SIZE; if (page_to_pfn(pages[0]) == next_pfn) { last_pg = pfn_to_page(next_pfn - 1); while (n_pages && pages_are_mergeable(pages[0], last_pg)) { if (sgt_append->prv->length + PAGE_SIZE > max_segment) break; sgt_append->prv->length += PAGE_SIZE; last_pg = pages[0]; pages++; n_pages--; } if (!n_pages) goto out; } } /* compute number of contiguous chunks */ chunks = 1; seg_len = 0; for (i = 1; i < n_pages; i++) { seg_len += PAGE_SIZE; if (seg_len >= max_segment || !pages_are_mergeable(pages[i], pages[i - 1])) { chunks++; seg_len = 0; } } /* merging chunks and putting them into the scatterlist */ cur_page = 0; for (i = 0; i < chunks; i++) { unsigned int j, chunk_size; /* look for the end of the current chunk */ seg_len = 0; for (j = cur_page + 1; j < n_pages; j++) { seg_len += PAGE_SIZE; if (seg_len >= max_segment || !pages_are_mergeable(pages[j], pages[j - 1])) break; } /* Pass how many chunks might be left */ s = get_next_sg(sgt_append, s, chunks - i + left_pages, gfp_mask); if (IS_ERR(s)) { /* * Adjust entry length to be as before function was * called. */ if (sgt_append->prv) sgt_append->prv->length = prv_len; return PTR_ERR(s); } chunk_size = ((j - cur_page) << PAGE_SHIFT) - offset; sg_set_page(s, pages[cur_page], min_t(unsigned long, size, chunk_size), offset); added_nents++; size -= chunk_size; offset = 0; cur_page = j; } sgt_append->sgt.nents += added_nents; sgt_append->sgt.orig_nents = sgt_append->sgt.nents; sgt_append->prv = s; out: if (!left_pages) sg_mark_end(s); return 0; } EXPORT_SYMBOL(sg_alloc_append_table_from_pages); /** * sg_alloc_table_from_pages_segment - Allocate and initialize an sg table from * an array of pages and given maximum * segment. * @sgt: The sg table header to use * @pages: Pointer to an array of page pointers * @n_pages: Number of pages in the pages array * @offset: Offset from start of the first page to the start of a buffer * @size: Number of valid bytes in the buffer (after offset) * @max_segment: Maximum size of a scatterlist element in bytes * @gfp_mask: GFP allocation mask * * Description: * Allocate and initialize an sg table from a list of pages. Contiguous * ranges of the pages are squashed into a single scatterlist node up to the * maximum size specified in @max_segment. A user may provide an offset at a * start and a size of valid data in a buffer specified by the page array. * * The returned sg table is released by sg_free_table. * * Returns: * 0 on success, negative error on failure */ int sg_alloc_table_from_pages_segment(struct sg_table *sgt, struct page **pages, unsigned int n_pages, unsigned int offset, unsigned long size, unsigned int max_segment, gfp_t gfp_mask) { struct sg_append_table append = {}; int err; err = sg_alloc_append_table_from_pages(&append, pages, n_pages, offset, size, max_segment, 0, gfp_mask); if (err) { sg_free_append_table(&append); return err; } memcpy(sgt, &append.sgt, sizeof(*sgt)); WARN_ON(append.total_nents != sgt->orig_nents); return 0; } EXPORT_SYMBOL(sg_alloc_table_from_pages_segment); #ifdef CONFIG_SGL_ALLOC /** * sgl_alloc_order - allocate a scatterlist and its pages * @length: Length in bytes of the scatterlist. Must be at least one * @order: Second argument for alloc_pages() * @chainable: Whether or not to allocate an extra element in the scatterlist * for scatterlist chaining purposes * @gfp: Memory allocation flags * @nent_p: [out] Number of entries in the scatterlist that have pages * * Returns: A pointer to an initialized scatterlist or %NULL upon failure. */ struct scatterlist *sgl_alloc_order(unsigned long long length, unsigned int order, bool chainable, gfp_t gfp, unsigned int *nent_p) { struct scatterlist *sgl, *sg; struct page *page; unsigned int nent, nalloc; u32 elem_len; nent = round_up(length, PAGE_SIZE << order) >> (PAGE_SHIFT + order); /* Check for integer overflow */ if (length > (nent << (PAGE_SHIFT + order))) return NULL; nalloc = nent; if (chainable) { /* Check for integer overflow */ if (nalloc + 1 < nalloc) return NULL; nalloc++; } sgl = kmalloc_array(nalloc, sizeof(struct scatterlist), gfp & ~GFP_DMA); if (!sgl) return NULL; sg_init_table(sgl, nalloc); sg = sgl; while (length) { elem_len = min_t(u64, length, PAGE_SIZE << order); page = alloc_pages(gfp, order); if (!page) { sgl_free_order(sgl, order); return NULL; } sg_set_page(sg, page, elem_len, 0); length -= elem_len; sg = sg_next(sg); } WARN_ONCE(length, "length = %lld\n", length); if (nent_p) *nent_p = nent; return sgl; } EXPORT_SYMBOL(sgl_alloc_order); /** * sgl_alloc - allocate a scatterlist and its pages * @length: Length in bytes of the scatterlist * @gfp: Memory allocation flags * @nent_p: [out] Number of entries in the scatterlist * * Returns: A pointer to an initialized scatterlist or %NULL upon failure. */ struct scatterlist *sgl_alloc(unsigned long long length, gfp_t gfp, unsigned int *nent_p) { return sgl_alloc_order(length, 0, false, gfp, nent_p); } EXPORT_SYMBOL(sgl_alloc); /** * sgl_free_n_order - free a scatterlist and its pages * @sgl: Scatterlist with one or more elements * @nents: Maximum number of elements to free * @order: Second argument for __free_pages() * * Notes: * - If several scatterlists have been chained and each chain element is * freed separately then it's essential to set nents correctly to avoid that a * page would get freed twice. * - All pages in a chained scatterlist can be freed at once by setting @nents * to a high number. */ void sgl_free_n_order(struct scatterlist *sgl, int nents, int order) { struct scatterlist *sg; struct page *page; int i; for_each_sg(sgl, sg, nents, i) { if (!sg) break; page = sg_page(sg); if (page) __free_pages(page, order); } kfree(sgl); } EXPORT_SYMBOL(sgl_free_n_order); /** * sgl_free_order - free a scatterlist and its pages * @sgl: Scatterlist with one or more elements * @order: Second argument for __free_pages() */ void sgl_free_order(struct scatterlist *sgl, int order) { sgl_free_n_order(sgl, INT_MAX, order); } EXPORT_SYMBOL(sgl_free_order); /** * sgl_free - free a scatterlist and its pages * @sgl: Scatterlist with one or more elements */ void sgl_free(struct scatterlist *sgl) { sgl_free_order(sgl, 0); } EXPORT_SYMBOL(sgl_free); #endif /* CONFIG_SGL_ALLOC */ void __sg_page_iter_start(struct sg_page_iter *piter, struct scatterlist *sglist, unsigned int nents, unsigned long pgoffset) { piter->__pg_advance = 0; piter->__nents = nents; piter->sg = sglist; piter->sg_pgoffset = pgoffset; } EXPORT_SYMBOL(__sg_page_iter_start); static int sg_page_count(struct scatterlist *sg) { return PAGE_ALIGN(sg->offset + sg->length) >> PAGE_SHIFT; } bool __sg_page_iter_next(struct sg_page_iter *piter) { if (!piter->__nents || !piter->sg) return false; piter->sg_pgoffset += piter->__pg_advance; piter->__pg_advance = 1; while (piter->sg_pgoffset >= sg_page_count(piter->sg)) { piter->sg_pgoffset -= sg_page_count(piter->sg); piter->sg = sg_next(piter->sg); if (!--piter->__nents || !piter->sg) return false; } return true; } EXPORT_SYMBOL(__sg_page_iter_next); static int sg_dma_page_count(struct scatterlist *sg) { return PAGE_ALIGN(sg->offset + sg_dma_len(sg)) >> PAGE_SHIFT; } bool __sg_page_iter_dma_next(struct sg_dma_page_iter *dma_iter) { struct sg_page_iter *piter = &dma_iter->base; if (!piter->__nents || !piter->sg) return false; piter->sg_pgoffset += piter->__pg_advance; piter->__pg_advance = 1; while (piter->sg_pgoffset >= sg_dma_page_count(piter->sg)) { piter->sg_pgoffset -= sg_dma_page_count(piter->sg); piter->sg = sg_next(piter->sg); if (!--piter->__nents || !piter->sg) return false; } return true; } EXPORT_SYMBOL(__sg_page_iter_dma_next); /** * sg_miter_start - start mapping iteration over a sg list * @miter: sg mapping iter to be started * @sgl: sg list to iterate over * @nents: number of sg entries * @flags: sg iterator flags * * Description: * Starts mapping iterator @miter. * * Context: * Don't care. */ void sg_miter_start(struct sg_mapping_iter *miter, struct scatterlist *sgl, unsigned int nents, unsigned int flags) { memset(miter, 0, sizeof(struct sg_mapping_iter)); __sg_page_iter_start(&miter->piter, sgl, nents, 0); WARN_ON(!(flags & (SG_MITER_TO_SG | SG_MITER_FROM_SG))); miter->__flags = flags; } EXPORT_SYMBOL(sg_miter_start); static bool sg_miter_get_next_page(struct sg_mapping_iter *miter) { if (!miter->__remaining) { struct scatterlist *sg; if (!__sg_page_iter_next(&miter->piter)) return false; sg = miter->piter.sg; miter->__offset = miter->piter.sg_pgoffset ? 0 : sg->offset; miter->piter.sg_pgoffset += miter->__offset >> PAGE_SHIFT; miter->__offset &= PAGE_SIZE - 1; miter->__remaining = sg->offset + sg->length - (miter->piter.sg_pgoffset << PAGE_SHIFT) - miter->__offset; miter->__remaining = min_t(unsigned long, miter->__remaining, PAGE_SIZE - miter->__offset); } return true; } /** * sg_miter_skip - reposition mapping iterator * @miter: sg mapping iter to be skipped * @offset: number of bytes to plus the current location * * Description: * Sets the offset of @miter to its current location plus @offset bytes. * If mapping iterator @miter has been proceeded by sg_miter_next(), this * stops @miter. * * Context: * Don't care. * * Returns: * true if @miter contains the valid mapping. false if end of sg * list is reached. */ bool sg_miter_skip(struct sg_mapping_iter *miter, off_t offset) { sg_miter_stop(miter); while (offset) { off_t consumed; if (!sg_miter_get_next_page(miter)) return false; consumed = min_t(off_t, offset, miter->__remaining); miter->__offset += consumed; miter->__remaining -= consumed; offset -= consumed; } return true; } EXPORT_SYMBOL(sg_miter_skip); /** * sg_miter_next - proceed mapping iterator to the next mapping * @miter: sg mapping iter to proceed * * Description: * Proceeds @miter to the next mapping. @miter should have been started * using sg_miter_start(). On successful return, @miter->page, * @miter->addr and @miter->length point to the current mapping. * * Context: * May sleep if !SG_MITER_ATOMIC. * * Returns: * true if @miter contains the next mapping. false if end of sg * list is reached. */ bool sg_miter_next(struct sg_mapping_iter *miter) { sg_miter_stop(miter); /* * Get to the next page if necessary. * __remaining, __offset is adjusted by sg_miter_stop */ if (!sg_miter_get_next_page(miter)) return false; miter->page = sg_page_iter_page(&miter->piter); miter->consumed = miter->length = miter->__remaining; if (miter->__flags & SG_MITER_ATOMIC) miter->addr = kmap_atomic(miter->page) + miter->__offset; else miter->addr = kmap(miter->page) + miter->__offset; return true; } EXPORT_SYMBOL(sg_miter_next); /** * sg_miter_stop - stop mapping iteration * @miter: sg mapping iter to be stopped * * Description: * Stops mapping iterator @miter. @miter should have been started * using sg_miter_start(). A stopped iteration can be resumed by * calling sg_miter_next() on it. This is useful when resources (kmap) * need to be released during iteration. * * Context: * Don't care otherwise. */ void sg_miter_stop(struct sg_mapping_iter *miter) { WARN_ON(miter->consumed > miter->length); /* drop resources from the last iteration */ if (miter->addr) { miter->__offset += miter->consumed; miter->__remaining -= miter->consumed; if (miter->__flags & SG_MITER_TO_SG) flush_dcache_page(miter->page); if (miter->__flags & SG_MITER_ATOMIC) { WARN_ON_ONCE(!pagefault_disabled()); kunmap_atomic(miter->addr); } else kunmap(miter->page); miter->page = NULL; miter->addr = NULL; miter->length = 0; miter->consumed = 0; } } EXPORT_SYMBOL(sg_miter_stop); /** * sg_copy_buffer - Copy data between a linear buffer and an SG list * @sgl: The SG list * @nents: Number of SG entries * @buf: Where to copy from * @buflen: The number of bytes to copy * @skip: Number of bytes to skip before copying * @to_buffer: transfer direction (true == from an sg list to a * buffer, false == from a buffer to an sg list) * * Returns the number of copied bytes. * **/ size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents, void *buf, size_t buflen, off_t skip, bool to_buffer) { unsigned int offset = 0; struct sg_mapping_iter miter; unsigned int sg_flags = SG_MITER_ATOMIC; if (to_buffer) sg_flags |= SG_MITER_FROM_SG; else sg_flags |= SG_MITER_TO_SG; sg_miter_start(&miter, sgl, nents, sg_flags); if (!sg_miter_skip(&miter, skip)) return 0; while ((offset < buflen) && sg_miter_next(&miter)) { unsigned int len; len = min(miter.length, buflen - offset); if (to_buffer) memcpy(buf + offset, miter.addr, len); else memcpy(miter.addr, buf + offset, len); offset += len; } sg_miter_stop(&miter); return offset; } EXPORT_SYMBOL(sg_copy_buffer); /** * sg_copy_from_buffer - Copy from a linear buffer to an SG list * @sgl: The SG list * @nents: Number of SG entries * @buf: Where to copy from * @buflen: The number of bytes to copy * * Returns the number of copied bytes. * **/ size_t sg_copy_from_buffer(struct scatterlist *sgl, unsigned int nents, const void *buf, size_t buflen) { return sg_copy_buffer(sgl, nents, (void *)buf, buflen, 0, false); } EXPORT_SYMBOL(sg_copy_from_buffer); /** * sg_copy_to_buffer - Copy from an SG list to a linear buffer * @sgl: The SG list * @nents: Number of SG entries * @buf: Where to copy to * @buflen: The number of bytes to copy * * Returns the number of copied bytes. * **/ size_t sg_copy_to_buffer(struct scatterlist *sgl, unsigned int nents, void *buf, size_t buflen) { return sg_copy_buffer(sgl, nents, buf, buflen, 0, true); } EXPORT_SYMBOL(sg_copy_to_buffer); /** * sg_pcopy_from_buffer - Copy from a linear buffer to an SG list * @sgl: The SG list * @nents: Number of SG entries * @buf: Where to copy from * @buflen: The number of bytes to copy * @skip: Number of bytes to skip before copying * * Returns the number of copied bytes. * **/ size_t sg_pcopy_from_buffer(struct scatterlist *sgl, unsigned int nents, const void *buf, size_t buflen, off_t skip) { return sg_copy_buffer(sgl, nents, (void *)buf, buflen, skip, false); } EXPORT_SYMBOL(sg_pcopy_from_buffer); /** * sg_pcopy_to_buffer - Copy from an SG list to a linear buffer * @sgl: The SG list * @nents: Number of SG entries * @buf: Where to copy to * @buflen: The number of bytes to copy * @skip: Number of bytes to skip before copying * * Returns the number of copied bytes. * **/ size_t sg_pcopy_to_buffer(struct scatterlist *sgl, unsigned int nents, void *buf, size_t buflen, off_t skip) { return sg_copy_buffer(sgl, nents, buf, buflen, skip, true); } EXPORT_SYMBOL(sg_pcopy_to_buffer); /** * sg_zero_buffer - Zero-out a part of a SG list * @sgl: The SG list * @nents: Number of SG entries * @buflen: The number of bytes to zero out * @skip: Number of bytes to skip before zeroing * * Returns the number of bytes zeroed. **/ size_t sg_zero_buffer(struct scatterlist *sgl, unsigned int nents, size_t buflen, off_t skip) { unsigned int offset = 0; struct sg_mapping_iter miter; unsigned int sg_flags = SG_MITER_ATOMIC | SG_MITER_TO_SG; sg_miter_start(&miter, sgl, nents, sg_flags); if (!sg_miter_skip(&miter, skip)) return false; while (offset < buflen && sg_miter_next(&miter)) { unsigned int len; len = min(miter.length, buflen - offset); memset(miter.addr, 0, len); offset += len; } sg_miter_stop(&miter); return offset; } EXPORT_SYMBOL(sg_zero_buffer); /* * Extract and pin a list of up to sg_max pages from UBUF- or IOVEC-class * iterators, and add them to the scatterlist. */ static ssize_t extract_user_to_sg(struct iov_iter *iter, ssize_t maxsize, struct sg_table *sgtable, unsigned int sg_max, iov_iter_extraction_t extraction_flags) { struct scatterlist *sg = sgtable->sgl + sgtable->nents; struct page **pages; unsigned int npages; ssize_t ret = 0, res; size_t len, off; /* We decant the page list into the tail of the scatterlist */ pages = (void *)sgtable->sgl + array_size(sg_max, sizeof(struct scatterlist)); pages -= sg_max; do { res = iov_iter_extract_pages(iter, &pages, maxsize, sg_max, extraction_flags, &off); if (res <= 0) goto failed; len = res; maxsize -= len; ret += len; npages = DIV_ROUND_UP(off + len, PAGE_SIZE); sg_max -= npages; for (; npages > 0; npages--) { struct page *page = *pages; size_t seg = min_t(size_t, PAGE_SIZE - off, len); *pages++ = NULL; sg_set_page(sg, page, seg, off); sgtable->nents++; sg++; len -= seg; off = 0; } } while (maxsize > 0 && sg_max > 0); return ret; failed: while (sgtable->nents > sgtable->orig_nents) unpin_user_page(sg_page(&sgtable->sgl[--sgtable->nents])); return res; } /* * Extract up to sg_max pages from a BVEC-type iterator and add them to the * scatterlist. The pages are not pinned. */ static ssize_t extract_bvec_to_sg(struct iov_iter *iter, ssize_t maxsize, struct sg_table *sgtable, unsigned int sg_max, iov_iter_extraction_t extraction_flags) { const struct bio_vec *bv = iter->bvec; struct scatterlist *sg = sgtable->sgl + sgtable->nents; unsigned long start = iter->iov_offset; unsigned int i; ssize_t ret = 0; for (i = 0; i < iter->nr_segs; i++) { size_t off, len; len = bv[i].bv_len; if (start >= len) { start -= len; continue; } len = min_t(size_t, maxsize, len - start); off = bv[i].bv_offset + start; sg_set_page(sg, bv[i].bv_page, len, off); sgtable->nents++; sg++; sg_max--; ret += len; maxsize -= len; if (maxsize <= 0 || sg_max == 0) break; start = 0; } if (ret > 0) iov_iter_advance(iter, ret); return ret; } /* * Extract up to sg_max pages from a KVEC-type iterator and add them to the * scatterlist. This can deal with vmalloc'd buffers as well as kmalloc'd or * static buffers. The pages are not pinned. */ static ssize_t extract_kvec_to_sg(struct iov_iter *iter, ssize_t maxsize, struct sg_table *sgtable, unsigned int sg_max, iov_iter_extraction_t extraction_flags) { const struct kvec *kv = iter->kvec; struct scatterlist *sg = sgtable->sgl + sgtable->nents; unsigned long start = iter->iov_offset; unsigned int i; ssize_t ret = 0; for (i = 0; i < iter->nr_segs; i++) { struct page *page; unsigned long kaddr; size_t off, len, seg; len = kv[i].iov_len; if (start >= len) { start -= len; continue; } kaddr = (unsigned long)kv[i].iov_base + start; off = kaddr & ~PAGE_MASK; len = min_t(size_t, maxsize, len - start); kaddr &= PAGE_MASK; maxsize -= len; ret += len; do { seg = min_t(size_t, len, PAGE_SIZE - off); if (is_vmalloc_or_module_addr((void *)kaddr)) page = vmalloc_to_page((void *)kaddr); else page = virt_to_page((void *)kaddr); sg_set_page(sg, page, len, off); sgtable->nents++; sg++; sg_max--; len -= seg; kaddr += PAGE_SIZE; off = 0; } while (len > 0 && sg_max > 0); if (maxsize <= 0 || sg_max == 0) break; start = 0; } if (ret > 0) iov_iter_advance(iter, ret); return ret; } /* * Extract up to sg_max folios from an FOLIOQ-type iterator and add them to * the scatterlist. The pages are not pinned. */ static ssize_t extract_folioq_to_sg(struct iov_iter *iter, ssize_t maxsize, struct sg_table *sgtable, unsigned int sg_max, iov_iter_extraction_t extraction_flags) { const struct folio_queue *folioq = iter->folioq; struct scatterlist *sg = sgtable->sgl + sgtable->nents; unsigned int slot = iter->folioq_slot; ssize_t ret = 0; size_t offset = iter->iov_offset; BUG_ON(!folioq); if (slot >= folioq_nr_slots(folioq)) { folioq = folioq->next; if (WARN_ON_ONCE(!folioq)) return 0; slot = 0; } do { struct folio *folio = folioq_folio(folioq, slot); size_t fsize = folioq_folio_size(folioq, slot); if (offset < fsize) { size_t part = umin(maxsize - ret, fsize - offset); sg_set_page(sg, folio_page(folio, 0), part, offset); sgtable->nents++; sg++; sg_max--; offset += part; ret += part; } if (offset >= fsize) { offset = 0; slot++; if (slot >= folioq_nr_slots(folioq)) { if (!folioq->next) { WARN_ON_ONCE(ret < iter->count); break; } folioq = folioq->next; slot = 0; } } } while (sg_max > 0 && ret < maxsize); iter->folioq = folioq; iter->folioq_slot = slot; iter->iov_offset = offset; iter->count -= ret; return ret; } /* * Extract up to sg_max folios from an XARRAY-type iterator and add them to * the scatterlist. The pages are not pinned. */ static ssize_t extract_xarray_to_sg(struct iov_iter *iter, ssize_t maxsize, struct sg_table *sgtable, unsigned int sg_max, iov_iter_extraction_t extraction_flags) { struct scatterlist *sg = sgtable->sgl + sgtable->nents; struct xarray *xa = iter->xarray; struct folio *folio; loff_t start = iter->xarray_start + iter->iov_offset; pgoff_t index = start / PAGE_SIZE; ssize_t ret = 0; size_t offset, len; XA_STATE(xas, xa, index); rcu_read_lock(); xas_for_each(&xas, folio, ULONG_MAX) { if (xas_retry(&xas, folio)) continue; if (WARN_ON(xa_is_value(folio))) break; if (WARN_ON(folio_test_hugetlb(folio))) break; offset = offset_in_folio(folio, start); len = min_t(size_t, maxsize, folio_size(folio) - offset); sg_set_page(sg, folio_page(folio, 0), len, offset); sgtable->nents++; sg++; sg_max--; maxsize -= len; ret += len; if (maxsize <= 0 || sg_max == 0) break; } rcu_read_unlock(); if (ret > 0) iov_iter_advance(iter, ret); return ret; } /** * extract_iter_to_sg - Extract pages from an iterator and add to an sglist * @iter: The iterator to extract from * @maxsize: The amount of iterator to copy * @sgtable: The scatterlist table to fill in * @sg_max: Maximum number of elements in @sgtable that may be filled * @extraction_flags: Flags to qualify the request * * Extract the page fragments from the given amount of the source iterator and * add them to a scatterlist that refers to all of those bits, to a maximum * addition of @sg_max elements. * * The pages referred to by UBUF- and IOVEC-type iterators are extracted and * pinned; BVEC-, KVEC-, FOLIOQ- and XARRAY-type are extracted but aren't * pinned; DISCARD-type is not supported. * * No end mark is placed on the scatterlist; that's left to the caller. * * @extraction_flags can have ITER_ALLOW_P2PDMA set to request peer-to-peer DMA * be allowed on the pages extracted. * * If successful, @sgtable->nents is updated to include the number of elements * added and the number of bytes added is returned. @sgtable->orig_nents is * left unaltered. * * The iov_iter_extract_mode() function should be used to query how cleanup * should be performed. */ ssize_t extract_iter_to_sg(struct iov_iter *iter, size_t maxsize, struct sg_table *sgtable, unsigned int sg_max, iov_iter_extraction_t extraction_flags) { if (maxsize == 0) return 0; switch (iov_iter_type(iter)) { case ITER_UBUF: case ITER_IOVEC: return extract_user_to_sg(iter, maxsize, sgtable, sg_max, extraction_flags); case ITER_BVEC: return extract_bvec_to_sg(iter, maxsize, sgtable, sg_max, extraction_flags); case ITER_KVEC: return extract_kvec_to_sg(iter, maxsize, sgtable, sg_max, extraction_flags); case ITER_FOLIOQ: return extract_folioq_to_sg(iter, maxsize, sgtable, sg_max, extraction_flags); case ITER_XARRAY: return extract_xarray_to_sg(iter, maxsize, sgtable, sg_max, extraction_flags); default: pr_err("%s(%u) unsupported\n", __func__, iov_iter_type(iter)); WARN_ON_ONCE(1); return -EIO; } } EXPORT_SYMBOL_GPL(extract_iter_to_sg); |
| 1 1 1 1 5 15 1 14 4 3 5 2 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> #include <linux/filter.h> #include <linux/kmod.h> #include <linux/module.h> #include <linux/netfilter.h> #include <net/netfilter/nf_bpf_link.h> #include <uapi/linux/netfilter_ipv4.h> static unsigned int nf_hook_run_bpf(void *bpf_prog, struct sk_buff *skb, const struct nf_hook_state *s) { const struct bpf_prog *prog = bpf_prog; struct bpf_nf_ctx ctx = { .state = s, .skb = skb, }; return bpf_prog_run(prog, &ctx); } struct bpf_nf_link { struct bpf_link link; struct nf_hook_ops hook_ops; netns_tracker ns_tracker; struct net *net; u32 dead; const struct nf_defrag_hook *defrag_hook; }; #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) || IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) static const struct nf_defrag_hook * get_proto_defrag_hook(struct bpf_nf_link *link, const struct nf_defrag_hook __rcu **ptr_global_hook, const char *mod) { const struct nf_defrag_hook *hook; int err; /* RCU protects us from races against module unloading */ rcu_read_lock(); hook = rcu_dereference(*ptr_global_hook); if (!hook) { rcu_read_unlock(); err = request_module("%s", mod); if (err) return ERR_PTR(err < 0 ? err : -EINVAL); rcu_read_lock(); hook = rcu_dereference(*ptr_global_hook); } if (hook && try_module_get(hook->owner)) { /* Once we have a refcnt on the module, we no longer need RCU */ hook = rcu_pointer_handoff(hook); } else { WARN_ONCE(!hook, "%s has bad registration", mod); hook = ERR_PTR(-ENOENT); } rcu_read_unlock(); if (!IS_ERR(hook)) { err = hook->enable(link->net); if (err) { module_put(hook->owner); hook = ERR_PTR(err); } } return hook; } #endif static int bpf_nf_enable_defrag(struct bpf_nf_link *link) { const struct nf_defrag_hook __maybe_unused *hook; switch (link->hook_ops.pf) { #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) case NFPROTO_IPV4: hook = get_proto_defrag_hook(link, &nf_defrag_v4_hook, "nf_defrag_ipv4"); if (IS_ERR(hook)) return PTR_ERR(hook); link->defrag_hook = hook; return 0; #endif #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) case NFPROTO_IPV6: hook = get_proto_defrag_hook(link, &nf_defrag_v6_hook, "nf_defrag_ipv6"); if (IS_ERR(hook)) return PTR_ERR(hook); link->defrag_hook = hook; return 0; #endif default: return -EAFNOSUPPORT; } } static void bpf_nf_disable_defrag(struct bpf_nf_link *link) { const struct nf_defrag_hook *hook = link->defrag_hook; if (!hook) return; hook->disable(link->net); module_put(hook->owner); } static void bpf_nf_link_release(struct bpf_link *link) { struct bpf_nf_link *nf_link = container_of(link, struct bpf_nf_link, link); if (nf_link->dead) return; /* do not double release in case .detach was already called */ if (!cmpxchg(&nf_link->dead, 0, 1)) { nf_unregister_net_hook(nf_link->net, &nf_link->hook_ops); bpf_nf_disable_defrag(nf_link); put_net_track(nf_link->net, &nf_link->ns_tracker); } } static void bpf_nf_link_dealloc(struct bpf_link *link) { struct bpf_nf_link *nf_link = container_of(link, struct bpf_nf_link, link); kfree(nf_link); } static int bpf_nf_link_detach(struct bpf_link *link) { bpf_nf_link_release(link); return 0; } static void bpf_nf_link_show_info(const struct bpf_link *link, struct seq_file *seq) { struct bpf_nf_link *nf_link = container_of(link, struct bpf_nf_link, link); seq_printf(seq, "pf:\t%u\thooknum:\t%u\tprio:\t%d\n", nf_link->hook_ops.pf, nf_link->hook_ops.hooknum, nf_link->hook_ops.priority); } static int bpf_nf_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_nf_link *nf_link = container_of(link, struct bpf_nf_link, link); const struct nf_defrag_hook *hook = nf_link->defrag_hook; info->netfilter.pf = nf_link->hook_ops.pf; info->netfilter.hooknum = nf_link->hook_ops.hooknum; info->netfilter.priority = nf_link->hook_ops.priority; info->netfilter.flags = hook ? BPF_F_NETFILTER_IP_DEFRAG : 0; return 0; } static int bpf_nf_link_update(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog) { return -EOPNOTSUPP; } static const struct bpf_link_ops bpf_nf_link_lops = { .release = bpf_nf_link_release, .dealloc = bpf_nf_link_dealloc, .detach = bpf_nf_link_detach, .show_fdinfo = bpf_nf_link_show_info, .fill_link_info = bpf_nf_link_fill_link_info, .update_prog = bpf_nf_link_update, }; static int bpf_nf_check_pf_and_hooks(const union bpf_attr *attr) { int prio; switch (attr->link_create.netfilter.pf) { case NFPROTO_IPV4: case NFPROTO_IPV6: if (attr->link_create.netfilter.hooknum >= NF_INET_NUMHOOKS) return -EPROTO; break; default: return -EAFNOSUPPORT; } if (attr->link_create.netfilter.flags & ~BPF_F_NETFILTER_IP_DEFRAG) return -EOPNOTSUPP; /* make sure conntrack confirm is always last */ prio = attr->link_create.netfilter.priority; if (prio == NF_IP_PRI_FIRST) return -ERANGE; /* sabotage_in and other warts */ else if (prio == NF_IP_PRI_LAST) return -ERANGE; /* e.g. conntrack confirm */ else if ((attr->link_create.netfilter.flags & BPF_F_NETFILTER_IP_DEFRAG) && prio <= NF_IP_PRI_CONNTRACK_DEFRAG) return -ERANGE; /* cannot use defrag if prog runs before nf_defrag */ return 0; } int bpf_nf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct net *net = current->nsproxy->net_ns; struct bpf_link_primer link_primer; struct bpf_nf_link *link; int err; if (attr->link_create.flags) return -EINVAL; err = bpf_nf_check_pf_and_hooks(attr); if (err) return err; link = kzalloc(sizeof(*link), GFP_USER); if (!link) return -ENOMEM; bpf_link_init(&link->link, BPF_LINK_TYPE_NETFILTER, &bpf_nf_link_lops, prog); link->hook_ops.hook = nf_hook_run_bpf; link->hook_ops.hook_ops_type = NF_HOOK_OP_BPF; link->hook_ops.priv = prog; link->hook_ops.pf = attr->link_create.netfilter.pf; link->hook_ops.priority = attr->link_create.netfilter.priority; link->hook_ops.hooknum = attr->link_create.netfilter.hooknum; link->net = net; link->dead = false; link->defrag_hook = NULL; err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); return err; } if (attr->link_create.netfilter.flags & BPF_F_NETFILTER_IP_DEFRAG) { err = bpf_nf_enable_defrag(link); if (err) { bpf_link_cleanup(&link_primer); return err; } } err = nf_register_net_hook(net, &link->hook_ops); if (err) { bpf_nf_disable_defrag(link); bpf_link_cleanup(&link_primer); return err; } get_net_track(net, &link->ns_tracker, GFP_KERNEL); return bpf_link_settle(&link_primer); } const struct bpf_prog_ops netfilter_prog_ops = { .test_run = bpf_prog_test_run_nf, }; static bool nf_ptr_to_btf_id(struct bpf_insn_access_aux *info, const char *name) { struct btf *btf; s32 type_id; btf = bpf_get_btf_vmlinux(); if (IS_ERR_OR_NULL(btf)) return false; type_id = btf_find_by_name_kind(btf, name, BTF_KIND_STRUCT); if (WARN_ON_ONCE(type_id < 0)) return false; info->btf = btf; info->btf_id = type_id; info->reg_type = PTR_TO_BTF_ID | PTR_TRUSTED; return true; } static bool nf_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (off < 0 || off >= sizeof(struct bpf_nf_ctx)) return false; if (type == BPF_WRITE) return false; switch (off) { case bpf_ctx_range(struct bpf_nf_ctx, skb): if (size != sizeof_field(struct bpf_nf_ctx, skb)) return false; return nf_ptr_to_btf_id(info, "sk_buff"); case bpf_ctx_range(struct bpf_nf_ctx, state): if (size != sizeof_field(struct bpf_nf_ctx, state)) return false; return nf_ptr_to_btf_id(info, "nf_hook_state"); default: return false; } return false; } static const struct bpf_func_proto * bpf_nf_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { return bpf_base_func_proto(func_id, prog); } const struct bpf_verifier_ops netfilter_verifier_ops = { .is_valid_access = nf_is_valid_access, .get_func_proto = bpf_nf_func_proto, }; |
| 14 13 1 13 6 1 5 5 2 3 5 3 5 5 1 3 1 1 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPV6 GSO/GRO offload support * Linux INET6 implementation * * UDPv6 GSO support */ #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/indirect_call_wrapper.h> #include <net/protocol.h> #include <net/ipv6.h> #include <net/udp.h> #include <net/ip6_checksum.h> #include "ip6_offload.h" #include <net/gro.h> #include <net/gso.h> static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); unsigned int mss; unsigned int unfrag_ip6hlen, unfrag_len; struct frag_hdr *fptr; u8 *packet_start, *prevhdr; u8 nexthdr; u8 frag_hdr_sz = sizeof(struct frag_hdr); __wsum csum; int tnl_hlen; int err; if (skb->encapsulation && skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM)) segs = skb_udp_tunnel_segment(skb, features, true); else { const struct ipv6hdr *ipv6h; struct udphdr *uh; if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_UDP | SKB_GSO_UDP_L4))) goto out; if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) return __udp_gso_segment(skb, features, true); mss = skb_shinfo(skb)->gso_size; if (unlikely(skb->len <= mss)) goto out; /* Do software UFO. Complete and fill in the UDP checksum as HW cannot * do checksum of UDP packets sent as multiple IP fragments. */ uh = udp_hdr(skb); ipv6h = ipv6_hdr(skb); uh->check = 0; csum = skb_checksum(skb, 0, skb->len, 0); uh->check = udp_v6_check(skb->len, &ipv6h->saddr, &ipv6h->daddr, csum); if (uh->check == 0) uh->check = CSUM_MANGLED_0; skb->ip_summed = CHECKSUM_UNNECESSARY; /* If there is no outer header we can fake a checksum offload * due to the fact that we have already done the checksum in * software prior to segmenting the frame. */ if (!skb->encap_hdr_csum) features |= NETIF_F_HW_CSUM; /* Check if there is enough headroom to insert fragment header. */ tnl_hlen = skb_tnl_header_len(skb); if (skb->mac_header < (tnl_hlen + frag_hdr_sz)) { if (gso_pskb_expand_head(skb, tnl_hlen + frag_hdr_sz)) goto out; } /* Find the unfragmentable header and shift it left by frag_hdr_sz * bytes to insert fragment header. */ err = ip6_find_1stfragopt(skb, &prevhdr); if (err < 0) return ERR_PTR(err); unfrag_ip6hlen = err; nexthdr = *prevhdr; *prevhdr = NEXTHDR_FRAGMENT; unfrag_len = (skb_network_header(skb) - skb_mac_header(skb)) + unfrag_ip6hlen + tnl_hlen; packet_start = (u8 *) skb->head + SKB_GSO_CB(skb)->mac_offset; memmove(packet_start-frag_hdr_sz, packet_start, unfrag_len); SKB_GSO_CB(skb)->mac_offset -= frag_hdr_sz; skb->mac_header -= frag_hdr_sz; skb->network_header -= frag_hdr_sz; fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen); fptr->nexthdr = nexthdr; fptr->reserved = 0; fptr->identification = ipv6_proxy_select_ident(dev_net(skb->dev), skb); /* Fragment the skb. ipv6 header and the remaining fields of the * fragment header are updated in ipv6_gso_segment() */ segs = skb_segment(skb, features); } out: return segs; } static struct sock *udp6_gro_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport) { const struct ipv6hdr *iph = skb_gro_network_header(skb); struct net *net = dev_net(skb->dev); int iif, sdif; inet6_get_iif_sdif(skb, &iif, &sdif); return __udp6_lib_lookup(net, &iph->saddr, sport, &iph->daddr, dport, iif, sdif, net->ipv4.udp_table, NULL); } INDIRECT_CALLABLE_SCOPE struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); struct sock *sk = NULL; struct sk_buff *pp; if (unlikely(!uh)) goto flush; /* Don't bother verifying checksum if we're going to flush anyway. */ if (NAPI_GRO_CB(skb)->flush) goto skip; if (skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check, ip6_gro_compute_pseudo)) goto flush; else if (uh->check) skb_gro_checksum_try_convert(skb, IPPROTO_UDP, ip6_gro_compute_pseudo); skip: NAPI_GRO_CB(skb)->is_ipv6 = 1; if (static_branch_unlikely(&udpv6_encap_needed_key)) sk = udp6_gro_lookup_skb(skb, uh->source, uh->dest); pp = udp_gro_receive(head, skb, uh, sk); return pp; flush: NAPI_GRO_CB(skb)->flush = 1; return NULL; } INDIRECT_CALLABLE_SCOPE int udp6_gro_complete(struct sk_buff *skb, int nhoff) { const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; const struct ipv6hdr *ipv6h = (struct ipv6hdr *)(skb->data + offset); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); /* do fraglist only if there is no outer UDP encap (or we already processed it) */ if (NAPI_GRO_CB(skb)->is_flist && !NAPI_GRO_CB(skb)->encap_mark) { uh->len = htons(skb->len - nhoff); skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4); skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; __skb_incr_checksum_unnecessary(skb); return 0; } if (uh->check) uh->check = ~udp_v6_check(skb->len - nhoff, &ipv6h->saddr, &ipv6h->daddr, 0); return udp_gro_complete(skb, nhoff, udp6_lib_lookup_skb); } int __init udpv6_offload_init(void) { net_hotdata.udpv6_offload = (struct net_offload) { .callbacks = { .gso_segment = udp6_ufo_fragment, .gro_receive = udp6_gro_receive, .gro_complete = udp6_gro_complete, }, }; return inet6_add_offload(&net_hotdata.udpv6_offload, IPPROTO_UDP); } int udpv6_offload_exit(void) { return inet6_del_offload(&net_hotdata.udpv6_offload, IPPROTO_UDP); } |
| 8468 8461 8 1 1 6 1 2 4 3 3 3 3 4 1 1 2 2 2 4 486 274 11 881 881 439 70 285 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * xfrm_device.c - IPsec device offloading code. * * Copyright (c) 2015 secunet Security Networks AG * * Author: * Steffen Klassert <steffen.klassert@secunet.com> */ #include <linux/errno.h> #include <linux/module.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <net/dst.h> #include <net/gso.h> #include <net/xfrm.h> #include <linux/notifier.h> #ifdef CONFIG_XFRM_OFFLOAD static void __xfrm_transport_prep(struct xfrm_state *x, struct sk_buff *skb, unsigned int hsize) { struct xfrm_offload *xo = xfrm_offload(skb); skb_reset_mac_len(skb); if (xo->flags & XFRM_GSO_SEGMENT) skb->transport_header -= x->props.header_len; pskb_pull(skb, skb_transport_offset(skb) + x->props.header_len); } static void __xfrm_mode_tunnel_prep(struct xfrm_state *x, struct sk_buff *skb, unsigned int hsize) { struct xfrm_offload *xo = xfrm_offload(skb); if (xo->flags & XFRM_GSO_SEGMENT) skb->transport_header = skb->network_header + hsize; skb_reset_mac_len(skb); pskb_pull(skb, skb->mac_len + x->props.header_len); } static void __xfrm_mode_beet_prep(struct xfrm_state *x, struct sk_buff *skb, unsigned int hsize) { struct xfrm_offload *xo = xfrm_offload(skb); int phlen = 0; if (xo->flags & XFRM_GSO_SEGMENT) skb->transport_header = skb->network_header + hsize; skb_reset_mac_len(skb); if (x->sel.family != AF_INET6) { phlen = IPV4_BEET_PHMAXLEN; if (x->outer_mode.family == AF_INET6) phlen += sizeof(struct ipv6hdr) - sizeof(struct iphdr); } pskb_pull(skb, skb->mac_len + hsize + (x->props.header_len - phlen)); } /* Adjust pointers into the packet when IPsec is done at layer2 */ static void xfrm_outer_mode_prep(struct xfrm_state *x, struct sk_buff *skb) { switch (x->outer_mode.encap) { case XFRM_MODE_TUNNEL: if (x->outer_mode.family == AF_INET) return __xfrm_mode_tunnel_prep(x, skb, sizeof(struct iphdr)); if (x->outer_mode.family == AF_INET6) return __xfrm_mode_tunnel_prep(x, skb, sizeof(struct ipv6hdr)); break; case XFRM_MODE_TRANSPORT: if (x->outer_mode.family == AF_INET) return __xfrm_transport_prep(x, skb, sizeof(struct iphdr)); if (x->outer_mode.family == AF_INET6) return __xfrm_transport_prep(x, skb, sizeof(struct ipv6hdr)); break; case XFRM_MODE_BEET: if (x->outer_mode.family == AF_INET) return __xfrm_mode_beet_prep(x, skb, sizeof(struct iphdr)); if (x->outer_mode.family == AF_INET6) return __xfrm_mode_beet_prep(x, skb, sizeof(struct ipv6hdr)); break; case XFRM_MODE_ROUTEOPTIMIZATION: case XFRM_MODE_IN_TRIGGER: break; } } static inline bool xmit_xfrm_check_overflow(struct sk_buff *skb) { struct xfrm_offload *xo = xfrm_offload(skb); __u32 seq = xo->seq.low; seq += skb_shinfo(skb)->gso_segs; if (unlikely(seq < xo->seq.low)) return true; return false; } struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features, bool *again) { int err; unsigned long flags; struct xfrm_state *x; struct softnet_data *sd; struct sk_buff *skb2, *nskb, *pskb = NULL; netdev_features_t esp_features = features; struct xfrm_offload *xo = xfrm_offload(skb); struct net_device *dev = skb->dev; struct sec_path *sp; if (!xo || (xo->flags & XFRM_XMIT)) return skb; if (!(features & NETIF_F_HW_ESP)) esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK); sp = skb_sec_path(skb); x = sp->xvec[sp->len - 1]; if (xo->flags & XFRM_GRO || x->xso.dir == XFRM_DEV_OFFLOAD_IN) return skb; /* The packet was sent to HW IPsec packet offload engine, * but to wrong device. Drop the packet, so it won't skip * XFRM stack. */ if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET && x->xso.dev != dev) { kfree_skb(skb); dev_core_stats_tx_dropped_inc(dev); return NULL; } /* This skb was already validated on the upper/virtual dev */ if ((x->xso.dev != dev) && (x->xso.real_dev == dev)) return skb; local_irq_save(flags); sd = this_cpu_ptr(&softnet_data); err = !skb_queue_empty(&sd->xfrm_backlog); local_irq_restore(flags); if (err) { *again = true; return skb; } if (skb_is_gso(skb) && (unlikely(x->xso.dev != dev) || unlikely(xmit_xfrm_check_overflow(skb)))) { struct sk_buff *segs; /* Packet got rerouted, fixup features and segment it. */ esp_features = esp_features & ~(NETIF_F_HW_ESP | NETIF_F_GSO_ESP); segs = skb_gso_segment(skb, esp_features); if (IS_ERR(segs)) { kfree_skb(skb); dev_core_stats_tx_dropped_inc(dev); return NULL; } else { consume_skb(skb); skb = segs; } } if (!skb->next) { esp_features |= skb->dev->gso_partial_features; xfrm_outer_mode_prep(x, skb); xo->flags |= XFRM_DEV_RESUME; err = x->type_offload->xmit(x, skb, esp_features); if (err) { if (err == -EINPROGRESS) return NULL; XFRM_INC_STATS(xs_net(x), LINUX_MIB_XFRMOUTSTATEPROTOERROR); kfree_skb(skb); return NULL; } skb_push(skb, skb->data - skb_mac_header(skb)); return skb; } skb_list_walk_safe(skb, skb2, nskb) { esp_features |= skb->dev->gso_partial_features; skb_mark_not_on_list(skb2); xo = xfrm_offload(skb2); xo->flags |= XFRM_DEV_RESUME; xfrm_outer_mode_prep(x, skb2); err = x->type_offload->xmit(x, skb2, esp_features); if (!err) { skb2->next = nskb; } else if (err != -EINPROGRESS) { XFRM_INC_STATS(xs_net(x), LINUX_MIB_XFRMOUTSTATEPROTOERROR); skb2->next = nskb; kfree_skb_list(skb2); return NULL; } else { if (skb == skb2) skb = nskb; else pskb->next = nskb; continue; } skb_push(skb2, skb2->data - skb_mac_header(skb2)); pskb = skb2; } return skb; } EXPORT_SYMBOL_GPL(validate_xmit_xfrm); int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, struct xfrm_user_offload *xuo, struct netlink_ext_ack *extack) { int err; struct dst_entry *dst; struct net_device *dev; struct xfrm_dev_offload *xso = &x->xso; xfrm_address_t *saddr; xfrm_address_t *daddr; bool is_packet_offload; if (!x->type_offload) { NL_SET_ERR_MSG(extack, "Type doesn't support offload"); return -EINVAL; } if (xuo->flags & ~(XFRM_OFFLOAD_IPV6 | XFRM_OFFLOAD_INBOUND | XFRM_OFFLOAD_PACKET)) { NL_SET_ERR_MSG(extack, "Unrecognized flags in offload request"); return -EINVAL; } if ((xuo->flags & XFRM_OFFLOAD_INBOUND && x->dir == XFRM_SA_DIR_OUT) || (!(xuo->flags & XFRM_OFFLOAD_INBOUND) && x->dir == XFRM_SA_DIR_IN)) { NL_SET_ERR_MSG(extack, "Mismatched SA and offload direction"); return -EINVAL; } is_packet_offload = xuo->flags & XFRM_OFFLOAD_PACKET; /* We don't yet support TFC padding. */ if (x->tfcpad) { NL_SET_ERR_MSG(extack, "TFC padding can't be offloaded"); return -EINVAL; } dev = dev_get_by_index(net, xuo->ifindex); if (!dev) { struct xfrm_dst_lookup_params params; if (!(xuo->flags & XFRM_OFFLOAD_INBOUND)) { saddr = &x->props.saddr; daddr = &x->id.daddr; } else { saddr = &x->id.daddr; daddr = &x->props.saddr; } memset(¶ms, 0, sizeof(params)); params.net = net; params.saddr = saddr; params.daddr = daddr; params.mark = xfrm_smark_get(0, x); dst = __xfrm_dst_lookup(x->props.family, ¶ms); if (IS_ERR(dst)) return (is_packet_offload) ? -EINVAL : 0; dev = dst->dev; dev_hold(dev); dst_release(dst); } if (!dev->xfrmdev_ops || !dev->xfrmdev_ops->xdo_dev_state_add) { xso->dev = NULL; dev_put(dev); return (is_packet_offload) ? -EINVAL : 0; } if (!is_packet_offload && x->props.flags & XFRM_STATE_ESN && !dev->xfrmdev_ops->xdo_dev_state_advance_esn) { NL_SET_ERR_MSG(extack, "Device doesn't support offload with ESN"); xso->dev = NULL; dev_put(dev); return -EINVAL; } xso->dev = dev; netdev_tracker_alloc(dev, &xso->dev_tracker, GFP_ATOMIC); xso->real_dev = dev; if (xuo->flags & XFRM_OFFLOAD_INBOUND) xso->dir = XFRM_DEV_OFFLOAD_IN; else xso->dir = XFRM_DEV_OFFLOAD_OUT; if (is_packet_offload) xso->type = XFRM_DEV_OFFLOAD_PACKET; else xso->type = XFRM_DEV_OFFLOAD_CRYPTO; err = dev->xfrmdev_ops->xdo_dev_state_add(x, extack); if (err) { xso->dev = NULL; xso->dir = 0; xso->real_dev = NULL; netdev_put(dev, &xso->dev_tracker); xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; /* User explicitly requested packet offload mode and configured * policy in addition to the XFRM state. So be civil to users, * and return an error instead of taking fallback path. */ if ((err != -EOPNOTSUPP && !is_packet_offload) || is_packet_offload) { NL_SET_ERR_MSG_WEAK(extack, "Device failed to offload this state"); return err; } } return 0; } EXPORT_SYMBOL_GPL(xfrm_dev_state_add); int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp, struct xfrm_user_offload *xuo, u8 dir, struct netlink_ext_ack *extack) { struct xfrm_dev_offload *xdo = &xp->xdo; struct net_device *dev; int err; if (!xuo->flags || xuo->flags & ~XFRM_OFFLOAD_PACKET) { /* We support only packet offload mode and it means * that user must set XFRM_OFFLOAD_PACKET bit. */ NL_SET_ERR_MSG(extack, "Unrecognized flags in offload request"); return -EINVAL; } dev = dev_get_by_index(net, xuo->ifindex); if (!dev) return -EINVAL; if (!dev->xfrmdev_ops || !dev->xfrmdev_ops->xdo_dev_policy_add) { xdo->dev = NULL; dev_put(dev); NL_SET_ERR_MSG(extack, "Policy offload is not supported"); return -EINVAL; } xdo->dev = dev; netdev_tracker_alloc(dev, &xdo->dev_tracker, GFP_ATOMIC); xdo->real_dev = dev; xdo->type = XFRM_DEV_OFFLOAD_PACKET; switch (dir) { case XFRM_POLICY_IN: xdo->dir = XFRM_DEV_OFFLOAD_IN; break; case XFRM_POLICY_OUT: xdo->dir = XFRM_DEV_OFFLOAD_OUT; break; case XFRM_POLICY_FWD: xdo->dir = XFRM_DEV_OFFLOAD_FWD; break; default: xdo->dev = NULL; netdev_put(dev, &xdo->dev_tracker); NL_SET_ERR_MSG(extack, "Unrecognized offload direction"); return -EINVAL; } err = dev->xfrmdev_ops->xdo_dev_policy_add(xp, extack); if (err) { xdo->dev = NULL; xdo->real_dev = NULL; xdo->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; xdo->dir = 0; netdev_put(dev, &xdo->dev_tracker); NL_SET_ERR_MSG_WEAK(extack, "Device failed to offload this policy"); return err; } return 0; } EXPORT_SYMBOL_GPL(xfrm_dev_policy_add); bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) { int mtu; struct dst_entry *dst = skb_dst(skb); struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct net_device *dev = x->xso.dev; if (!x->type_offload || (x->xso.type == XFRM_DEV_OFFLOAD_UNSPECIFIED && x->encap)) return false; if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET || ((!dev || (dev == xfrm_dst_path(dst)->dev)) && !xdst->child->xfrm)) { mtu = xfrm_state_mtu(x, xdst->child_mtu_cached); if (skb->len <= mtu) goto ok; if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) goto ok; } return false; ok: if (dev && dev->xfrmdev_ops && dev->xfrmdev_ops->xdo_dev_offload_ok) return x->xso.dev->xfrmdev_ops->xdo_dev_offload_ok(skb, x); return true; } EXPORT_SYMBOL_GPL(xfrm_dev_offload_ok); void xfrm_dev_resume(struct sk_buff *skb) { struct net_device *dev = skb->dev; int ret = NETDEV_TX_BUSY; struct netdev_queue *txq; struct softnet_data *sd; unsigned long flags; rcu_read_lock(); txq = netdev_core_pick_tx(dev, skb, NULL); HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_xmit_frozen_or_stopped(txq)) skb = dev_hard_start_xmit(skb, dev, txq, &ret); HARD_TX_UNLOCK(dev, txq); if (!dev_xmit_complete(ret)) { local_irq_save(flags); sd = this_cpu_ptr(&softnet_data); skb_queue_tail(&sd->xfrm_backlog, skb); raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(xfrm_dev_resume); void xfrm_dev_backlog(struct softnet_data *sd) { struct sk_buff_head *xfrm_backlog = &sd->xfrm_backlog; struct sk_buff_head list; struct sk_buff *skb; if (skb_queue_empty(xfrm_backlog)) return; __skb_queue_head_init(&list); spin_lock(&xfrm_backlog->lock); skb_queue_splice_init(xfrm_backlog, &list); spin_unlock(&xfrm_backlog->lock); while (!skb_queue_empty(&list)) { skb = __skb_dequeue(&list); xfrm_dev_resume(skb); } } #endif static int xfrm_api_check(struct net_device *dev) { #ifdef CONFIG_XFRM_OFFLOAD if ((dev->features & NETIF_F_HW_ESP_TX_CSUM) && !(dev->features & NETIF_F_HW_ESP)) return NOTIFY_BAD; if ((dev->features & NETIF_F_HW_ESP) && (!(dev->xfrmdev_ops && dev->xfrmdev_ops->xdo_dev_state_add && dev->xfrmdev_ops->xdo_dev_state_delete))) return NOTIFY_BAD; #else if (dev->features & (NETIF_F_HW_ESP | NETIF_F_HW_ESP_TX_CSUM)) return NOTIFY_BAD; #endif return NOTIFY_DONE; } static int xfrm_dev_down(struct net_device *dev) { if (dev->features & NETIF_F_HW_ESP) { xfrm_dev_state_flush(dev_net(dev), dev, true); xfrm_dev_policy_flush(dev_net(dev), dev, true); } return NOTIFY_DONE; } static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); switch (event) { case NETDEV_REGISTER: return xfrm_api_check(dev); case NETDEV_FEAT_CHANGE: return xfrm_api_check(dev); case NETDEV_DOWN: case NETDEV_UNREGISTER: return xfrm_dev_down(dev); } return NOTIFY_DONE; } static struct notifier_block xfrm_dev_notifier = { .notifier_call = xfrm_dev_event, }; void __init xfrm_dev_init(void) { register_netdevice_notifier(&xfrm_dev_notifier); } |
| 6400 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_JUMP_LABEL_H #define _LINUX_JUMP_LABEL_H /* * Jump label support * * Copyright (C) 2009-2012 Jason Baron <jbaron@redhat.com> * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra * * DEPRECATED API: * * The use of 'struct static_key' directly, is now DEPRECATED. In addition * static_key_{true,false}() is also DEPRECATED. IE DO NOT use the following: * * struct static_key false = STATIC_KEY_INIT_FALSE; * struct static_key true = STATIC_KEY_INIT_TRUE; * static_key_true() * static_key_false() * * The updated API replacements are: * * DEFINE_STATIC_KEY_TRUE(key); * DEFINE_STATIC_KEY_FALSE(key); * DEFINE_STATIC_KEY_ARRAY_TRUE(keys, count); * DEFINE_STATIC_KEY_ARRAY_FALSE(keys, count); * static_branch_likely() * static_branch_unlikely() * * Jump labels provide an interface to generate dynamic branches using * self-modifying code. Assuming toolchain and architecture support, if we * define a "key" that is initially false via "DEFINE_STATIC_KEY_FALSE(key)", * an "if (static_branch_unlikely(&key))" statement is an unconditional branch * (which defaults to false - and the true block is placed out of line). * Similarly, we can define an initially true key via * "DEFINE_STATIC_KEY_TRUE(key)", and use it in the same * "if (static_branch_unlikely(&key))", in which case we will generate an * unconditional branch to the out-of-line true branch. Keys that are * initially true or false can be using in both static_branch_unlikely() * and static_branch_likely() statements. * * At runtime we can change the branch target by setting the key * to true via a call to static_branch_enable(), or false using * static_branch_disable(). If the direction of the branch is switched by * these calls then we run-time modify the branch target via a * no-op -> jump or jump -> no-op conversion. For example, for an * initially false key that is used in an "if (static_branch_unlikely(&key))" * statement, setting the key to true requires us to patch in a jump * to the out-of-line of true branch. * * In addition to static_branch_{enable,disable}, we can also reference count * the key or branch direction via static_branch_{inc,dec}. Thus, * static_branch_inc() can be thought of as a 'make more true' and * static_branch_dec() as a 'make more false'. * * Since this relies on modifying code, the branch modifying functions * must be considered absolute slow paths (machine wide synchronization etc.). * OTOH, since the affected branches are unconditional, their runtime overhead * will be absolutely minimal, esp. in the default (off) case where the total * effect is a single NOP of appropriate size. The on case will patch in a jump * to the out-of-line block. * * When the control is directly exposed to userspace, it is prudent to delay the * decrement to avoid high frequency code modifications which can (and do) * cause significant performance degradation. Struct static_key_deferred and * static_key_slow_dec_deferred() provide for this. * * Lacking toolchain and or architecture support, static keys fall back to a * simple conditional branch. * * Additional babbling in: Documentation/staging/static-keys.rst */ #ifndef __ASSEMBLY__ #include <linux/types.h> #include <linux/compiler.h> extern bool static_key_initialized; #define STATIC_KEY_CHECK_USE(key) WARN(!static_key_initialized, \ "%s(): static key '%pS' used before call to jump_label_init()", \ __func__, (key)) struct static_key { atomic_t enabled; #ifdef CONFIG_JUMP_LABEL /* * Note: * To make anonymous unions work with old compilers, the static * initialization of them requires brackets. This creates a dependency * on the order of the struct with the initializers. If any fields * are added, STATIC_KEY_INIT_TRUE and STATIC_KEY_INIT_FALSE may need * to be modified. * * bit 0 => 1 if key is initially true * 0 if initially false * bit 1 => 1 if points to struct static_key_mod * 0 if points to struct jump_entry */ union { unsigned long type; struct jump_entry *entries; struct static_key_mod *next; }; #endif /* CONFIG_JUMP_LABEL */ }; #endif /* __ASSEMBLY__ */ #ifdef CONFIG_JUMP_LABEL #include <asm/jump_label.h> #ifndef __ASSEMBLY__ #ifdef CONFIG_HAVE_ARCH_JUMP_LABEL_RELATIVE struct jump_entry { s32 code; s32 target; long key; // key may be far away from the core kernel under KASLR }; static inline unsigned long jump_entry_code(const struct jump_entry *entry) { return (unsigned long)&entry->code + entry->code; } static inline unsigned long jump_entry_target(const struct jump_entry *entry) { return (unsigned long)&entry->target + entry->target; } static inline struct static_key *jump_entry_key(const struct jump_entry *entry) { long offset = entry->key & ~3L; return (struct static_key *)((unsigned long)&entry->key + offset); } #else static inline unsigned long jump_entry_code(const struct jump_entry *entry) { return entry->code; } static inline unsigned long jump_entry_target(const struct jump_entry *entry) { return entry->target; } static inline struct static_key *jump_entry_key(const struct jump_entry *entry) { return (struct static_key *)((unsigned long)entry->key & ~3UL); } #endif static inline bool jump_entry_is_branch(const struct jump_entry *entry) { return (unsigned long)entry->key & 1UL; } static inline bool jump_entry_is_init(const struct jump_entry *entry) { return (unsigned long)entry->key & 2UL; } static inline void jump_entry_set_init(struct jump_entry *entry, bool set) { if (set) entry->key |= 2; else entry->key &= ~2; } static inline int jump_entry_size(struct jump_entry *entry) { #ifdef JUMP_LABEL_NOP_SIZE return JUMP_LABEL_NOP_SIZE; #else return arch_jump_entry_size(entry); #endif } #endif #endif #ifndef __ASSEMBLY__ enum jump_label_type { JUMP_LABEL_NOP = 0, JUMP_LABEL_JMP, }; struct module; #ifdef CONFIG_JUMP_LABEL #define JUMP_TYPE_FALSE 0UL #define JUMP_TYPE_TRUE 1UL #define JUMP_TYPE_LINKED 2UL #define JUMP_TYPE_MASK 3UL static __always_inline bool static_key_false(struct static_key *key) { return arch_static_branch(key, false); } static __always_inline bool static_key_true(struct static_key *key) { return !arch_static_branch(key, true); } extern struct jump_entry __start___jump_table[]; extern struct jump_entry __stop___jump_table[]; extern void jump_label_init(void); extern void jump_label_init_ro(void); extern void jump_label_lock(void); extern void jump_label_unlock(void); extern void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type); extern bool arch_jump_label_transform_queue(struct jump_entry *entry, enum jump_label_type type); extern void arch_jump_label_transform_apply(void); extern int jump_label_text_reserved(void *start, void *end); extern bool static_key_slow_inc(struct static_key *key); extern bool static_key_fast_inc_not_disabled(struct static_key *key); extern void static_key_slow_dec(struct static_key *key); extern bool static_key_slow_inc_cpuslocked(struct static_key *key); extern void static_key_slow_dec_cpuslocked(struct static_key *key); extern int static_key_count(struct static_key *key); extern void static_key_enable(struct static_key *key); extern void static_key_disable(struct static_key *key); extern void static_key_enable_cpuslocked(struct static_key *key); extern void static_key_disable_cpuslocked(struct static_key *key); extern enum jump_label_type jump_label_init_type(struct jump_entry *entry); /* * We should be using ATOMIC_INIT() for initializing .enabled, but * the inclusion of atomic.h is problematic for inclusion of jump_label.h * in 'low-level' headers. Thus, we are initializing .enabled with a * raw value, but have added a BUILD_BUG_ON() to catch any issues in * jump_label_init() see: kernel/jump_label.c. */ #define STATIC_KEY_INIT_TRUE \ { .enabled = { 1 }, \ { .type = JUMP_TYPE_TRUE } } #define STATIC_KEY_INIT_FALSE \ { .enabled = { 0 }, \ { .type = JUMP_TYPE_FALSE } } #else /* !CONFIG_JUMP_LABEL */ #include <linux/atomic.h> #include <linux/bug.h> static __always_inline int static_key_count(struct static_key *key) { return raw_atomic_read(&key->enabled); } static __always_inline void jump_label_init(void) { static_key_initialized = true; } static __always_inline void jump_label_init_ro(void) { } static __always_inline bool static_key_false(struct static_key *key) { if (unlikely_notrace(static_key_count(key) > 0)) return true; return false; } static __always_inline bool static_key_true(struct static_key *key) { if (likely_notrace(static_key_count(key) > 0)) return true; return false; } static inline bool static_key_fast_inc_not_disabled(struct static_key *key) { int v; STATIC_KEY_CHECK_USE(key); /* * Prevent key->enabled getting negative to follow the same semantics * as for CONFIG_JUMP_LABEL=y, see kernel/jump_label.c comment. */ v = atomic_read(&key->enabled); do { if (v < 0 || (v + 1) < 0) return false; } while (!likely(atomic_try_cmpxchg(&key->enabled, &v, v + 1))); return true; } #define static_key_slow_inc(key) static_key_fast_inc_not_disabled(key) static inline void static_key_slow_dec(struct static_key *key) { STATIC_KEY_CHECK_USE(key); atomic_dec(&key->enabled); } #define static_key_slow_inc_cpuslocked(key) static_key_slow_inc(key) #define static_key_slow_dec_cpuslocked(key) static_key_slow_dec(key) static inline int jump_label_text_reserved(void *start, void *end) { return 0; } static inline void jump_label_lock(void) {} static inline void jump_label_unlock(void) {} static inline void static_key_enable(struct static_key *key) { STATIC_KEY_CHECK_USE(key); if (atomic_read(&key->enabled) != 0) { WARN_ON_ONCE(atomic_read(&key->enabled) != 1); return; } atomic_set(&key->enabled, 1); } static inline void static_key_disable(struct static_key *key) { STATIC_KEY_CHECK_USE(key); if (atomic_read(&key->enabled) != 1) { WARN_ON_ONCE(atomic_read(&key->enabled) != 0); return; } atomic_set(&key->enabled, 0); } #define static_key_enable_cpuslocked(k) static_key_enable((k)) #define static_key_disable_cpuslocked(k) static_key_disable((k)) #define STATIC_KEY_INIT_TRUE { .enabled = ATOMIC_INIT(1) } #define STATIC_KEY_INIT_FALSE { .enabled = ATOMIC_INIT(0) } #endif /* CONFIG_JUMP_LABEL */ #define STATIC_KEY_INIT STATIC_KEY_INIT_FALSE #define jump_label_enabled static_key_enabled /* -------------------------------------------------------------------------- */ /* * Two type wrappers around static_key, such that we can use compile time * type differentiation to emit the right code. * * All the below code is macros in order to play type games. */ struct static_key_true { struct static_key key; }; struct static_key_false { struct static_key key; }; #define STATIC_KEY_TRUE_INIT (struct static_key_true) { .key = STATIC_KEY_INIT_TRUE, } #define STATIC_KEY_FALSE_INIT (struct static_key_false){ .key = STATIC_KEY_INIT_FALSE, } #define DEFINE_STATIC_KEY_TRUE(name) \ struct static_key_true name = STATIC_KEY_TRUE_INIT #define DEFINE_STATIC_KEY_TRUE_RO(name) \ struct static_key_true name __ro_after_init = STATIC_KEY_TRUE_INIT #define DECLARE_STATIC_KEY_TRUE(name) \ extern struct static_key_true name #define DEFINE_STATIC_KEY_FALSE(name) \ struct static_key_false name = STATIC_KEY_FALSE_INIT #define DEFINE_STATIC_KEY_FALSE_RO(name) \ struct static_key_false name __ro_after_init = STATIC_KEY_FALSE_INIT #define DECLARE_STATIC_KEY_FALSE(name) \ extern struct static_key_false name #define DEFINE_STATIC_KEY_ARRAY_TRUE(name, count) \ struct static_key_true name[count] = { \ [0 ... (count) - 1] = STATIC_KEY_TRUE_INIT, \ } #define DEFINE_STATIC_KEY_ARRAY_FALSE(name, count) \ struct static_key_false name[count] = { \ [0 ... (count) - 1] = STATIC_KEY_FALSE_INIT, \ } #define _DEFINE_STATIC_KEY_1(name) DEFINE_STATIC_KEY_TRUE(name) #define _DEFINE_STATIC_KEY_0(name) DEFINE_STATIC_KEY_FALSE(name) #define DEFINE_STATIC_KEY_MAYBE(cfg, name) \ __PASTE(_DEFINE_STATIC_KEY_, IS_ENABLED(cfg))(name) #define _DEFINE_STATIC_KEY_RO_1(name) DEFINE_STATIC_KEY_TRUE_RO(name) #define _DEFINE_STATIC_KEY_RO_0(name) DEFINE_STATIC_KEY_FALSE_RO(name) #define DEFINE_STATIC_KEY_MAYBE_RO(cfg, name) \ __PASTE(_DEFINE_STATIC_KEY_RO_, IS_ENABLED(cfg))(name) #define _DECLARE_STATIC_KEY_1(name) DECLARE_STATIC_KEY_TRUE(name) #define _DECLARE_STATIC_KEY_0(name) DECLARE_STATIC_KEY_FALSE(name) #define DECLARE_STATIC_KEY_MAYBE(cfg, name) \ __PASTE(_DECLARE_STATIC_KEY_, IS_ENABLED(cfg))(name) extern bool ____wrong_branch_error(void); #define static_key_enabled(x) \ ({ \ if (!__builtin_types_compatible_p(typeof(*x), struct static_key) && \ !__builtin_types_compatible_p(typeof(*x), struct static_key_true) &&\ !__builtin_types_compatible_p(typeof(*x), struct static_key_false)) \ ____wrong_branch_error(); \ static_key_count((struct static_key *)x) > 0; \ }) #ifdef CONFIG_JUMP_LABEL /* * Combine the right initial value (type) with the right branch order * to generate the desired result. * * * type\branch| likely (1) | unlikely (0) * -----------+-----------------------+------------------ * | | * true (1) | ... | ... * | NOP | JMP L * | <br-stmts> | 1: ... * | L: ... | * | | * | | L: <br-stmts> * | | jmp 1b * | | * -----------+-----------------------+------------------ * | | * false (0) | ... | ... * | JMP L | NOP * | <br-stmts> | 1: ... * | L: ... | * | | * | | L: <br-stmts> * | | jmp 1b * | | * -----------+-----------------------+------------------ * * The initial value is encoded in the LSB of static_key::entries, * type: 0 = false, 1 = true. * * The branch type is encoded in the LSB of jump_entry::key, * branch: 0 = unlikely, 1 = likely. * * This gives the following logic table: * * enabled type branch instuction * -----------------------------+----------- * 0 0 0 | NOP * 0 0 1 | JMP * 0 1 0 | NOP * 0 1 1 | JMP * * 1 0 0 | JMP * 1 0 1 | NOP * 1 1 0 | JMP * 1 1 1 | NOP * * Which gives the following functions: * * dynamic: instruction = enabled ^ branch * static: instruction = type ^ branch * * See jump_label_type() / jump_label_init_type(). */ #define static_branch_likely(x) \ ({ \ bool branch; \ if (__builtin_types_compatible_p(typeof(*x), struct static_key_true)) \ branch = !arch_static_branch(&(x)->key, true); \ else if (__builtin_types_compatible_p(typeof(*x), struct static_key_false)) \ branch = !arch_static_branch_jump(&(x)->key, true); \ else \ branch = ____wrong_branch_error(); \ likely_notrace(branch); \ }) #define static_branch_unlikely(x) \ ({ \ bool branch; \ if (__builtin_types_compatible_p(typeof(*x), struct static_key_true)) \ branch = arch_static_branch_jump(&(x)->key, false); \ else if (__builtin_types_compatible_p(typeof(*x), struct static_key_false)) \ branch = arch_static_branch(&(x)->key, false); \ else \ branch = ____wrong_branch_error(); \ unlikely_notrace(branch); \ }) #else /* !CONFIG_JUMP_LABEL */ #define static_branch_likely(x) likely_notrace(static_key_enabled(&(x)->key)) #define static_branch_unlikely(x) unlikely_notrace(static_key_enabled(&(x)->key)) #endif /* CONFIG_JUMP_LABEL */ #define static_branch_maybe(config, x) \ (IS_ENABLED(config) ? static_branch_likely(x) \ : static_branch_unlikely(x)) /* * Advanced usage; refcount, branch is enabled when: count != 0 */ #define static_branch_inc(x) static_key_slow_inc(&(x)->key) #define static_branch_dec(x) static_key_slow_dec(&(x)->key) #define static_branch_inc_cpuslocked(x) static_key_slow_inc_cpuslocked(&(x)->key) #define static_branch_dec_cpuslocked(x) static_key_slow_dec_cpuslocked(&(x)->key) /* * Normal usage; boolean enable/disable. */ #define static_branch_enable(x) static_key_enable(&(x)->key) #define static_branch_disable(x) static_key_disable(&(x)->key) #define static_branch_enable_cpuslocked(x) static_key_enable_cpuslocked(&(x)->key) #define static_branch_disable_cpuslocked(x) static_key_disable_cpuslocked(&(x)->key) #endif /* __ASSEMBLY__ */ #endif /* _LINUX_JUMP_LABEL_H */ |
| 2 2 2 2 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@netfilter.org> */ /* Kernel module implementing an IP set type: the hash:net,port type */ #include <linux/jhash.h> #include <linux/module.h> #include <linux/ip.h> #include <linux/skbuff.h> #include <linux/errno.h> #include <linux/random.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/ipset/pfxlen.h> #include <linux/netfilter/ipset/ip_set.h> #include <linux/netfilter/ipset/ip_set_getport.h> #include <linux/netfilter/ipset/ip_set_hash.h> #define IPSET_TYPE_REV_MIN 0 /* 1 SCTP and UDPLITE support added */ /* 2 Range as input support for IPv4 added */ /* 3 nomatch flag support added */ /* 4 Counters support added */ /* 5 Comments support added */ /* 6 Forceadd support added */ /* 7 skbinfo support added */ #define IPSET_TYPE_REV_MAX 8 /* bucketsize, initval support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>"); IP_SET_MODULE_DESC("hash:net,port", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX); MODULE_ALIAS("ip_set_hash:net,port"); /* Type specific function prefix */ #define HTYPE hash_netport #define IP_SET_HASH_WITH_PROTO #define IP_SET_HASH_WITH_NETS /* We squeeze the "nomatch" flag into cidr: we don't support cidr == 0 * However this way we have to store internally cidr - 1, * dancing back and forth. */ #define IP_SET_HASH_WITH_NETS_PACKED /* IPv4 variant */ /* Member elements */ struct hash_netport4_elem { __be32 ip; __be16 port; u8 proto; u8 cidr:7; u8 nomatch:1; }; /* Common functions */ static bool hash_netport4_data_equal(const struct hash_netport4_elem *ip1, const struct hash_netport4_elem *ip2, u32 *multi) { return ip1->ip == ip2->ip && ip1->port == ip2->port && ip1->proto == ip2->proto && ip1->cidr == ip2->cidr; } static int hash_netport4_do_data_match(const struct hash_netport4_elem *elem) { return elem->nomatch ? -ENOTEMPTY : 1; } static void hash_netport4_data_set_flags(struct hash_netport4_elem *elem, u32 flags) { elem->nomatch = !!((flags >> 16) & IPSET_FLAG_NOMATCH); } static void hash_netport4_data_reset_flags(struct hash_netport4_elem *elem, u8 *flags) { swap(*flags, elem->nomatch); } static void hash_netport4_data_netmask(struct hash_netport4_elem *elem, u8 cidr) { elem->ip &= ip_set_netmask(cidr); elem->cidr = cidr - 1; } static bool hash_netport4_data_list(struct sk_buff *skb, const struct hash_netport4_elem *data) { u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip) || nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr + 1) || nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) || (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; return false; nla_put_failure: return true; } static void hash_netport4_data_next(struct hash_netport4_elem *next, const struct hash_netport4_elem *d) { next->ip = d->ip; next->port = d->port; } #define MTYPE hash_netport4 #define HOST_MASK 32 #include "ip_set_hash_gen.h" static int hash_netport4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, struct ip_set_adt_opt *opt) { const struct hash_netport4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport4_elem e = { .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); if (adt == IPSET_TEST) e.cidr = HOST_MASK - 1; if (!ip_set_get_ip4_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.port, &e.proto)) return -EINVAL; ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip); e.ip &= ip_set_netmask(e.cidr + 1); return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } static int hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { struct hash_netport4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport4_elem e = { .cidr = HOST_MASK - 1 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 port, port_to, p = 0, ip = 0, ip_to = 0, i = 0; bool with_ports = false; u8 cidr; int ret; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); if (unlikely(!tb[IPSET_ATTR_IP] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); if (ret) return ret; ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; if (tb[IPSET_ATTR_CIDR]) { cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); if (!cidr || cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; e.cidr = cidr - 1; } e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); with_ports = ip_set_proto_with_ports(e.proto); if (e.proto == 0) return -IPSET_ERR_INVALID_PROTO; } else { return -IPSET_ERR_MISSING_PROTO; } if (!(with_ports || e.proto == IPPROTO_ICMP)) e.port = 0; with_ports = with_ports && tb[IPSET_ATTR_PORT_TO]; if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); if (cadt_flags & IPSET_FLAG_NOMATCH) flags |= (IPSET_FLAG_NOMATCH << 16); } if (adt == IPSET_TEST || !(with_ports || tb[IPSET_ATTR_IP_TO])) { e.ip = htonl(ip & ip_set_hostmask(e.cidr + 1)); ret = adtfn(set, &e, &ext, &ext, flags); return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } port = port_to = ntohs(e.port); if (tb[IPSET_ATTR_PORT_TO]) { port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); if (port_to < port) swap(port, port_to); } if (tb[IPSET_ATTR_IP_TO]) { ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); if (ret) return ret; if (ip_to < ip) swap(ip, ip_to); if (ip + UINT_MAX == ip_to) return -IPSET_ERR_HASH_RANGE; } else { ip_set_mask_from_to(ip, ip_to, e.cidr + 1); } if (retried) { ip = ntohl(h->next.ip); p = ntohs(h->next.port); } else { p = port; } do { e.ip = htonl(ip); ip = ip_set_range_to_cidr(ip, ip_to, &cidr); e.cidr = cidr - 1; for (; p <= port_to; p++, i++) { e.port = htons(p); if (i > IPSET_MAX_RANGE) { hash_netport4_data_next(&h->next, &e); return -ERANGE; } ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; ret = 0; } p = port; } while (ip++ < ip_to); return ret; } /* IPv6 variant */ struct hash_netport6_elem { union nf_inet_addr ip; __be16 port; u8 proto; u8 cidr:7; u8 nomatch:1; }; /* Common functions */ static bool hash_netport6_data_equal(const struct hash_netport6_elem *ip1, const struct hash_netport6_elem *ip2, u32 *multi) { return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) && ip1->port == ip2->port && ip1->proto == ip2->proto && ip1->cidr == ip2->cidr; } static int hash_netport6_do_data_match(const struct hash_netport6_elem *elem) { return elem->nomatch ? -ENOTEMPTY : 1; } static void hash_netport6_data_set_flags(struct hash_netport6_elem *elem, u32 flags) { elem->nomatch = !!((flags >> 16) & IPSET_FLAG_NOMATCH); } static void hash_netport6_data_reset_flags(struct hash_netport6_elem *elem, u8 *flags) { swap(*flags, elem->nomatch); } static void hash_netport6_data_netmask(struct hash_netport6_elem *elem, u8 cidr) { ip6_netmask(&elem->ip, cidr); elem->cidr = cidr - 1; } static bool hash_netport6_data_list(struct sk_buff *skb, const struct hash_netport6_elem *data) { u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip.in6) || nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr + 1) || nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) || (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; return false; nla_put_failure: return true; } static void hash_netport6_data_next(struct hash_netport6_elem *next, const struct hash_netport6_elem *d) { next->port = d->port; } #undef MTYPE #undef HOST_MASK #define MTYPE hash_netport6 #define HOST_MASK 128 #define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" static int hash_netport6_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, struct ip_set_adt_opt *opt) { const struct hash_netport6 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport6_elem e = { .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); if (adt == IPSET_TEST) e.cidr = HOST_MASK - 1; if (!ip_set_get_ip6_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.port, &e.proto)) return -EINVAL; ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6); ip6_netmask(&e.ip, e.cidr + 1); return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } static int hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { const struct hash_netport6 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport6_elem e = { .cidr = HOST_MASK - 1 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 port, port_to; bool with_ports = false; u8 cidr; int ret; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); if (unlikely(!tb[IPSET_ATTR_IP] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; if (unlikely(tb[IPSET_ATTR_IP_TO])) return -IPSET_ERR_HASH_RANGE_UNSUPPORTED; ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip); if (ret) return ret; ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; if (tb[IPSET_ATTR_CIDR]) { cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); if (!cidr || cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; e.cidr = cidr - 1; } ip6_netmask(&e.ip, e.cidr + 1); e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); with_ports = ip_set_proto_with_ports(e.proto); if (e.proto == 0) return -IPSET_ERR_INVALID_PROTO; } else { return -IPSET_ERR_MISSING_PROTO; } if (!(with_ports || e.proto == IPPROTO_ICMPV6)) e.port = 0; if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); if (cadt_flags & IPSET_FLAG_NOMATCH) flags |= (IPSET_FLAG_NOMATCH << 16); } if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { ret = adtfn(set, &e, &ext, &ext, flags); return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } port = ntohs(e.port); port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); if (port > port_to) swap(port, port_to); if (retried) port = ntohs(h->next.port); for (; port <= port_to; port++) { e.port = htons(port); ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; ret = 0; } return ret; } static struct ip_set_type hash_netport_type __read_mostly = { .name = "hash:net,port", .protocol = IPSET_PROTOCOL, .features = IPSET_TYPE_IP | IPSET_TYPE_PORT | IPSET_TYPE_NOMATCH, .dimension = IPSET_DIM_TWO, .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_netport_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, }, .adt_policy = { [IPSET_ATTR_IP] = { .type = NLA_NESTED }, [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, [IPSET_ATTR_PORT] = { .type = NLA_U16 }, [IPSET_ATTR_PORT_TO] = { .type = NLA_U16 }, [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, }, .me = THIS_MODULE, }; static int __init hash_netport_init(void) { return ip_set_type_register(&hash_netport_type); } static void __exit hash_netport_fini(void) { rcu_barrier(); ip_set_type_unregister(&hash_netport_type); } module_init(hash_netport_init); module_exit(hash_netport_fini); |
| 6 6 6 6 6 6 6 6 4 2 2 2 2 1 1 3 1 2 4 4 4 4 4 4 4 4 7 4 4 4 4 5 5 5 3 4 3 2 2 1 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 | // SPDX-License-Identifier: GPL-2.0-only /* * kallsyms.c: in-kernel printing of symbolic oopses and stack traces. * * Rewritten and vastly simplified by Rusty Russell for in-kernel * module loader: * Copyright 2002 Rusty Russell <rusty@rustcorp.com.au> IBM Corporation * * ChangeLog: * * (25/Aug/2004) Paulo Marques <pmarques@grupopie.com> * Changed the compression method from stem compression to "table lookup" * compression (see scripts/kallsyms.c for a more complete description) */ #include <linux/kallsyms.h> #include <linux/init.h> #include <linux/seq_file.h> #include <linux/fs.h> #include <linux/kdb.h> #include <linux/err.h> #include <linux/proc_fs.h> #include <linux/sched.h> /* for cond_resched */ #include <linux/ctype.h> #include <linux/slab.h> #include <linux/filter.h> #include <linux/ftrace.h> #include <linux/kprobes.h> #include <linux/build_bug.h> #include <linux/compiler.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/bsearch.h> #include <linux/btf_ids.h> #include "kallsyms_internal.h" /* * Expand a compressed symbol data into the resulting uncompressed string, * if uncompressed string is too long (>= maxlen), it will be truncated, * given the offset to where the symbol is in the compressed stream. */ static unsigned int kallsyms_expand_symbol(unsigned int off, char *result, size_t maxlen) { int len, skipped_first = 0; const char *tptr; const u8 *data; /* Get the compressed symbol length from the first symbol byte. */ data = &kallsyms_names[off]; len = *data; data++; off++; /* If MSB is 1, it is a "big" symbol, so needs an additional byte. */ if ((len & 0x80) != 0) { len = (len & 0x7F) | (*data << 7); data++; off++; } /* * Update the offset to return the offset for the next symbol on * the compressed stream. */ off += len; /* * For every byte on the compressed symbol data, copy the table * entry for that byte. */ while (len) { tptr = &kallsyms_token_table[kallsyms_token_index[*data]]; data++; len--; while (*tptr) { if (skipped_first) { if (maxlen <= 1) goto tail; *result = *tptr; result++; maxlen--; } else skipped_first = 1; tptr++; } } tail: if (maxlen) *result = '\0'; /* Return to offset to the next symbol. */ return off; } /* * Get symbol type information. This is encoded as a single char at the * beginning of the symbol name. */ static char kallsyms_get_symbol_type(unsigned int off) { /* * Get just the first code, look it up in the token table, * and return the first char from this token. */ return kallsyms_token_table[kallsyms_token_index[kallsyms_names[off + 1]]]; } /* * Find the offset on the compressed stream given and index in the * kallsyms array. */ static unsigned int get_symbol_offset(unsigned long pos) { const u8 *name; int i, len; /* * Use the closest marker we have. We have markers every 256 positions, * so that should be close enough. */ name = &kallsyms_names[kallsyms_markers[pos >> 8]]; /* * Sequentially scan all the symbols up to the point we're searching * for. Every symbol is stored in a [<len>][<len> bytes of data] format, * so we just need to add the len to the current pointer for every * symbol we wish to skip. */ for (i = 0; i < (pos & 0xFF); i++) { len = *name; /* * If MSB is 1, it is a "big" symbol, so we need to look into * the next byte (and skip it, too). */ if ((len & 0x80) != 0) len = ((len & 0x7F) | (name[1] << 7)) + 1; name = name + len + 1; } return name - kallsyms_names; } unsigned long kallsyms_sym_address(int idx) { /* values are unsigned offsets if --absolute-percpu is not in effect */ if (!IS_ENABLED(CONFIG_KALLSYMS_ABSOLUTE_PERCPU)) return kallsyms_relative_base + (u32)kallsyms_offsets[idx]; /* ...otherwise, positive offsets are absolute values */ if (kallsyms_offsets[idx] >= 0) return kallsyms_offsets[idx]; /* ...and negative offsets are relative to kallsyms_relative_base - 1 */ return kallsyms_relative_base - 1 - kallsyms_offsets[idx]; } static unsigned int get_symbol_seq(int index) { unsigned int i, seq = 0; for (i = 0; i < 3; i++) seq = (seq << 8) | kallsyms_seqs_of_names[3 * index + i]; return seq; } static int kallsyms_lookup_names(const char *name, unsigned int *start, unsigned int *end) { int ret; int low, mid, high; unsigned int seq, off; char namebuf[KSYM_NAME_LEN]; low = 0; high = kallsyms_num_syms - 1; while (low <= high) { mid = low + (high - low) / 2; seq = get_symbol_seq(mid); off = get_symbol_offset(seq); kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf)); ret = strcmp(name, namebuf); if (ret > 0) low = mid + 1; else if (ret < 0) high = mid - 1; else break; } if (low > high) return -ESRCH; low = mid; while (low) { seq = get_symbol_seq(low - 1); off = get_symbol_offset(seq); kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf)); if (strcmp(name, namebuf)) break; low--; } *start = low; if (end) { high = mid; while (high < kallsyms_num_syms - 1) { seq = get_symbol_seq(high + 1); off = get_symbol_offset(seq); kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf)); if (strcmp(name, namebuf)) break; high++; } *end = high; } return 0; } /* Lookup the address for this symbol. Returns 0 if not found. */ unsigned long kallsyms_lookup_name(const char *name) { int ret; unsigned int i; /* Skip the search for empty string. */ if (!*name) return 0; ret = kallsyms_lookup_names(name, &i, NULL); if (!ret) return kallsyms_sym_address(get_symbol_seq(i)); return module_kallsyms_lookup_name(name); } /* * Iterate over all symbols in vmlinux. For symbols from modules use * module_kallsyms_on_each_symbol instead. */ int kallsyms_on_each_symbol(int (*fn)(void *, const char *, unsigned long), void *data) { char namebuf[KSYM_NAME_LEN]; unsigned long i; unsigned int off; int ret; for (i = 0, off = 0; i < kallsyms_num_syms; i++) { off = kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf)); ret = fn(data, namebuf, kallsyms_sym_address(i)); if (ret != 0) return ret; cond_resched(); } return 0; } int kallsyms_on_each_match_symbol(int (*fn)(void *, unsigned long), const char *name, void *data) { int ret; unsigned int i, start, end; ret = kallsyms_lookup_names(name, &start, &end); if (ret) return 0; for (i = start; !ret && i <= end; i++) { ret = fn(data, kallsyms_sym_address(get_symbol_seq(i))); cond_resched(); } return ret; } static unsigned long get_symbol_pos(unsigned long addr, unsigned long *symbolsize, unsigned long *offset) { unsigned long symbol_start = 0, symbol_end = 0; unsigned long i, low, high, mid; /* Do a binary search on the sorted kallsyms_offsets array. */ low = 0; high = kallsyms_num_syms; while (high - low > 1) { mid = low + (high - low) / 2; if (kallsyms_sym_address(mid) <= addr) low = mid; else high = mid; } /* * Search for the first aliased symbol. Aliased * symbols are symbols with the same address. */ while (low && kallsyms_sym_address(low-1) == kallsyms_sym_address(low)) --low; symbol_start = kallsyms_sym_address(low); /* Search for next non-aliased symbol. */ for (i = low + 1; i < kallsyms_num_syms; i++) { if (kallsyms_sym_address(i) > symbol_start) { symbol_end = kallsyms_sym_address(i); break; } } /* If we found no next symbol, we use the end of the section. */ if (!symbol_end) { if (is_kernel_inittext(addr)) symbol_end = (unsigned long)_einittext; else if (IS_ENABLED(CONFIG_KALLSYMS_ALL)) symbol_end = (unsigned long)_end; else symbol_end = (unsigned long)_etext; } if (symbolsize) *symbolsize = symbol_end - symbol_start; if (offset) *offset = addr - symbol_start; return low; } /* * Lookup an address but don't bother to find any names. */ int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize, unsigned long *offset) { char namebuf[KSYM_NAME_LEN]; if (is_ksym_addr(addr)) { get_symbol_pos(addr, symbolsize, offset); return 1; } return !!module_address_lookup(addr, symbolsize, offset, NULL, NULL, namebuf) || !!__bpf_address_lookup(addr, symbolsize, offset, namebuf); } static int kallsyms_lookup_buildid(unsigned long addr, unsigned long *symbolsize, unsigned long *offset, char **modname, const unsigned char **modbuildid, char *namebuf) { int ret; namebuf[KSYM_NAME_LEN - 1] = 0; namebuf[0] = 0; if (is_ksym_addr(addr)) { unsigned long pos; pos = get_symbol_pos(addr, symbolsize, offset); /* Grab name */ kallsyms_expand_symbol(get_symbol_offset(pos), namebuf, KSYM_NAME_LEN); if (modname) *modname = NULL; if (modbuildid) *modbuildid = NULL; return strlen(namebuf); } /* See if it's in a module or a BPF JITed image. */ ret = module_address_lookup(addr, symbolsize, offset, modname, modbuildid, namebuf); if (!ret) ret = bpf_address_lookup(addr, symbolsize, offset, modname, namebuf); if (!ret) ret = ftrace_mod_address_lookup(addr, symbolsize, offset, modname, namebuf); return ret; } /* * Lookup an address * - modname is set to NULL if it's in the kernel. * - We guarantee that the returned name is valid until we reschedule even if. * It resides in a module. * - We also guarantee that modname will be valid until rescheduled. */ const char *kallsyms_lookup(unsigned long addr, unsigned long *symbolsize, unsigned long *offset, char **modname, char *namebuf) { int ret = kallsyms_lookup_buildid(addr, symbolsize, offset, modname, NULL, namebuf); if (!ret) return NULL; return namebuf; } int lookup_symbol_name(unsigned long addr, char *symname) { symname[0] = '\0'; symname[KSYM_NAME_LEN - 1] = '\0'; if (is_ksym_addr(addr)) { unsigned long pos; pos = get_symbol_pos(addr, NULL, NULL); /* Grab name */ kallsyms_expand_symbol(get_symbol_offset(pos), symname, KSYM_NAME_LEN); return 0; } /* See if it's in a module. */ return lookup_module_symbol_name(addr, symname); } /* Look up a kernel symbol and return it in a text buffer. */ static int __sprint_symbol(char *buffer, unsigned long address, int symbol_offset, int add_offset, int add_buildid) { char *modname; const unsigned char *buildid; unsigned long offset, size; int len; address += symbol_offset; len = kallsyms_lookup_buildid(address, &size, &offset, &modname, &buildid, buffer); if (!len) return sprintf(buffer, "0x%lx", address - symbol_offset); offset -= symbol_offset; if (add_offset) len += sprintf(buffer + len, "+%#lx/%#lx", offset, size); if (modname) { len += sprintf(buffer + len, " [%s", modname); #if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) if (add_buildid && buildid) { /* build ID should match length of sprintf */ #if IS_ENABLED(CONFIG_MODULES) static_assert(sizeof(typeof_member(struct module, build_id)) == 20); #endif len += sprintf(buffer + len, " %20phN", buildid); } #endif len += sprintf(buffer + len, "]"); } return len; } /** * sprint_symbol - Look up a kernel symbol and return it in a text buffer * @buffer: buffer to be stored * @address: address to lookup * * This function looks up a kernel symbol with @address and stores its name, * offset, size and module name to @buffer if possible. If no symbol was found, * just saves its @address as is. * * This function returns the number of bytes stored in @buffer. */ int sprint_symbol(char *buffer, unsigned long address) { return __sprint_symbol(buffer, address, 0, 1, 0); } EXPORT_SYMBOL_GPL(sprint_symbol); /** * sprint_symbol_build_id - Look up a kernel symbol and return it in a text buffer * @buffer: buffer to be stored * @address: address to lookup * * This function looks up a kernel symbol with @address and stores its name, * offset, size, module name and module build ID to @buffer if possible. If no * symbol was found, just saves its @address as is. * * This function returns the number of bytes stored in @buffer. */ int sprint_symbol_build_id(char *buffer, unsigned long address) { return __sprint_symbol(buffer, address, 0, 1, 1); } EXPORT_SYMBOL_GPL(sprint_symbol_build_id); /** * sprint_symbol_no_offset - Look up a kernel symbol and return it in a text buffer * @buffer: buffer to be stored * @address: address to lookup * * This function looks up a kernel symbol with @address and stores its name * and module name to @buffer if possible. If no symbol was found, just saves * its @address as is. * * This function returns the number of bytes stored in @buffer. */ int sprint_symbol_no_offset(char *buffer, unsigned long address) { return __sprint_symbol(buffer, address, 0, 0, 0); } EXPORT_SYMBOL_GPL(sprint_symbol_no_offset); /** * sprint_backtrace - Look up a backtrace symbol and return it in a text buffer * @buffer: buffer to be stored * @address: address to lookup * * This function is for stack backtrace and does the same thing as * sprint_symbol() but with modified/decreased @address. If there is a * tail-call to the function marked "noreturn", gcc optimized out code after * the call so that the stack-saved return address could point outside of the * caller. This function ensures that kallsyms will find the original caller * by decreasing @address. * * This function returns the number of bytes stored in @buffer. */ int sprint_backtrace(char *buffer, unsigned long address) { return __sprint_symbol(buffer, address, -1, 1, 0); } /** * sprint_backtrace_build_id - Look up a backtrace symbol and return it in a text buffer * @buffer: buffer to be stored * @address: address to lookup * * This function is for stack backtrace and does the same thing as * sprint_symbol() but with modified/decreased @address. If there is a * tail-call to the function marked "noreturn", gcc optimized out code after * the call so that the stack-saved return address could point outside of the * caller. This function ensures that kallsyms will find the original caller * by decreasing @address. This function also appends the module build ID to * the @buffer if @address is within a kernel module. * * This function returns the number of bytes stored in @buffer. */ int sprint_backtrace_build_id(char *buffer, unsigned long address) { return __sprint_symbol(buffer, address, -1, 1, 1); } /* To avoid using get_symbol_offset for every symbol, we carry prefix along. */ struct kallsym_iter { loff_t pos; loff_t pos_mod_end; loff_t pos_ftrace_mod_end; loff_t pos_bpf_end; unsigned long value; unsigned int nameoff; /* If iterating in core kernel symbols. */ char type; char name[KSYM_NAME_LEN]; char module_name[MODULE_NAME_LEN]; int exported; int show_value; }; static int get_ksymbol_mod(struct kallsym_iter *iter) { int ret = module_get_kallsym(iter->pos - kallsyms_num_syms, &iter->value, &iter->type, iter->name, iter->module_name, &iter->exported); if (ret < 0) { iter->pos_mod_end = iter->pos; return 0; } return 1; } /* * ftrace_mod_get_kallsym() may also get symbols for pages allocated for ftrace * purposes. In that case "__builtin__ftrace" is used as a module name, even * though "__builtin__ftrace" is not a module. */ static int get_ksymbol_ftrace_mod(struct kallsym_iter *iter) { int ret = ftrace_mod_get_kallsym(iter->pos - iter->pos_mod_end, &iter->value, &iter->type, iter->name, iter->module_name, &iter->exported); if (ret < 0) { iter->pos_ftrace_mod_end = iter->pos; return 0; } return 1; } static int get_ksymbol_bpf(struct kallsym_iter *iter) { int ret; strscpy(iter->module_name, "bpf", MODULE_NAME_LEN); iter->exported = 0; ret = bpf_get_kallsym(iter->pos - iter->pos_ftrace_mod_end, &iter->value, &iter->type, iter->name); if (ret < 0) { iter->pos_bpf_end = iter->pos; return 0; } return 1; } /* * This uses "__builtin__kprobes" as a module name for symbols for pages * allocated for kprobes' purposes, even though "__builtin__kprobes" is not a * module. */ static int get_ksymbol_kprobe(struct kallsym_iter *iter) { strscpy(iter->module_name, "__builtin__kprobes", MODULE_NAME_LEN); iter->exported = 0; return kprobe_get_kallsym(iter->pos - iter->pos_bpf_end, &iter->value, &iter->type, iter->name) < 0 ? 0 : 1; } /* Returns space to next name. */ static unsigned long get_ksymbol_core(struct kallsym_iter *iter) { unsigned off = iter->nameoff; iter->module_name[0] = '\0'; iter->value = kallsyms_sym_address(iter->pos); iter->type = kallsyms_get_symbol_type(off); off = kallsyms_expand_symbol(off, iter->name, ARRAY_SIZE(iter->name)); return off - iter->nameoff; } static void reset_iter(struct kallsym_iter *iter, loff_t new_pos) { iter->name[0] = '\0'; iter->nameoff = get_symbol_offset(new_pos); iter->pos = new_pos; if (new_pos == 0) { iter->pos_mod_end = 0; iter->pos_ftrace_mod_end = 0; iter->pos_bpf_end = 0; } } /* * The end position (last + 1) of each additional kallsyms section is recorded * in iter->pos_..._end as each section is added, and so can be used to * determine which get_ksymbol_...() function to call next. */ static int update_iter_mod(struct kallsym_iter *iter, loff_t pos) { iter->pos = pos; if ((!iter->pos_mod_end || iter->pos_mod_end > pos) && get_ksymbol_mod(iter)) return 1; if ((!iter->pos_ftrace_mod_end || iter->pos_ftrace_mod_end > pos) && get_ksymbol_ftrace_mod(iter)) return 1; if ((!iter->pos_bpf_end || iter->pos_bpf_end > pos) && get_ksymbol_bpf(iter)) return 1; return get_ksymbol_kprobe(iter); } /* Returns false if pos at or past end of file. */ static int update_iter(struct kallsym_iter *iter, loff_t pos) { /* Module symbols can be accessed randomly. */ if (pos >= kallsyms_num_syms) return update_iter_mod(iter, pos); /* If we're not on the desired position, reset to new position. */ if (pos != iter->pos) reset_iter(iter, pos); iter->nameoff += get_ksymbol_core(iter); iter->pos++; return 1; } static void *s_next(struct seq_file *m, void *p, loff_t *pos) { (*pos)++; if (!update_iter(m->private, *pos)) return NULL; return p; } static void *s_start(struct seq_file *m, loff_t *pos) { if (!update_iter(m->private, *pos)) return NULL; return m->private; } static void s_stop(struct seq_file *m, void *p) { } static int s_show(struct seq_file *m, void *p) { void *value; struct kallsym_iter *iter = m->private; /* Some debugging symbols have no name. Ignore them. */ if (!iter->name[0]) return 0; value = iter->show_value ? (void *)iter->value : NULL; if (iter->module_name[0]) { char type; /* * Label it "global" if it is exported, * "local" if not exported. */ type = iter->exported ? toupper(iter->type) : tolower(iter->type); seq_printf(m, "%px %c %s\t[%s]\n", value, type, iter->name, iter->module_name); } else seq_printf(m, "%px %c %s\n", value, iter->type, iter->name); return 0; } static const struct seq_operations kallsyms_op = { .start = s_start, .next = s_next, .stop = s_stop, .show = s_show }; #ifdef CONFIG_BPF_SYSCALL struct bpf_iter__ksym { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct kallsym_iter *, ksym); }; static int ksym_prog_seq_show(struct seq_file *m, bool in_stop) { struct bpf_iter__ksym ctx; struct bpf_iter_meta meta; struct bpf_prog *prog; meta.seq = m; prog = bpf_iter_get_info(&meta, in_stop); if (!prog) return 0; ctx.meta = &meta; ctx.ksym = m ? m->private : NULL; return bpf_iter_run_prog(prog, &ctx); } static int bpf_iter_ksym_seq_show(struct seq_file *m, void *p) { return ksym_prog_seq_show(m, false); } static void bpf_iter_ksym_seq_stop(struct seq_file *m, void *p) { if (!p) (void) ksym_prog_seq_show(m, true); else s_stop(m, p); } static const struct seq_operations bpf_iter_ksym_ops = { .start = s_start, .next = s_next, .stop = bpf_iter_ksym_seq_stop, .show = bpf_iter_ksym_seq_show, }; static int bpf_iter_ksym_init(void *priv_data, struct bpf_iter_aux_info *aux) { struct kallsym_iter *iter = priv_data; reset_iter(iter, 0); /* cache here as in kallsyms_open() case; use current process * credentials to tell BPF iterators if values should be shown. */ iter->show_value = kallsyms_show_value(current_cred()); return 0; } DEFINE_BPF_ITER_FUNC(ksym, struct bpf_iter_meta *meta, struct kallsym_iter *ksym) static const struct bpf_iter_seq_info ksym_iter_seq_info = { .seq_ops = &bpf_iter_ksym_ops, .init_seq_private = bpf_iter_ksym_init, .fini_seq_private = NULL, .seq_priv_size = sizeof(struct kallsym_iter), }; static struct bpf_iter_reg ksym_iter_reg_info = { .target = "ksym", .feature = BPF_ITER_RESCHED, .ctx_arg_info_size = 1, .ctx_arg_info = { { offsetof(struct bpf_iter__ksym, ksym), PTR_TO_BTF_ID_OR_NULL }, }, .seq_info = &ksym_iter_seq_info, }; BTF_ID_LIST(btf_ksym_iter_id) BTF_ID(struct, kallsym_iter) static int __init bpf_ksym_iter_register(void) { ksym_iter_reg_info.ctx_arg_info[0].btf_id = *btf_ksym_iter_id; return bpf_iter_reg_target(&ksym_iter_reg_info); } late_initcall(bpf_ksym_iter_register); #endif /* CONFIG_BPF_SYSCALL */ static int kallsyms_open(struct inode *inode, struct file *file) { /* * We keep iterator in m->private, since normal case is to * s_start from where we left off, so we avoid doing * using get_symbol_offset for every symbol. */ struct kallsym_iter *iter; iter = __seq_open_private(file, &kallsyms_op, sizeof(*iter)); if (!iter) return -ENOMEM; reset_iter(iter, 0); /* * Instead of checking this on every s_show() call, cache * the result here at open time. */ iter->show_value = kallsyms_show_value(file->f_cred); return 0; } #ifdef CONFIG_KGDB_KDB const char *kdb_walk_kallsyms(loff_t *pos) { static struct kallsym_iter kdb_walk_kallsyms_iter; if (*pos == 0) { memset(&kdb_walk_kallsyms_iter, 0, sizeof(kdb_walk_kallsyms_iter)); reset_iter(&kdb_walk_kallsyms_iter, 0); } while (1) { if (!update_iter(&kdb_walk_kallsyms_iter, *pos)) return NULL; ++*pos; /* Some debugging symbols have no name. Ignore them. */ if (kdb_walk_kallsyms_iter.name[0]) return kdb_walk_kallsyms_iter.name; } } #endif /* CONFIG_KGDB_KDB */ static const struct proc_ops kallsyms_proc_ops = { .proc_open = kallsyms_open, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = seq_release_private, }; static int __init kallsyms_init(void) { proc_create("kallsyms", 0444, NULL, &kallsyms_proc_ops); return 0; } device_initcall(kallsyms_init); |
| 881 883 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/etherdevice.h> #include "ipvlan.h" #include <linux/if_vlan.h> #include <linux/if_tap.h> #include <linux/interrupt.h> #include <linux/nsproxy.h> #include <linux/compat.h> #include <linux/if_tun.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/cache.h> #include <linux/sched.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/wait.h> #include <linux/cdev.h> #include <linux/idr.h> #include <linux/fs.h> #include <linux/uio.h> #include <net/net_namespace.h> #include <net/rtnetlink.h> #include <net/sock.h> #include <linux/virtio_net.h> #define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \ NETIF_F_TSO6) static dev_t ipvtap_major; static struct cdev ipvtap_cdev; static const void *ipvtap_net_namespace(const struct device *d) { const struct net_device *dev = to_net_dev(d->parent); return dev_net(dev); } static struct class ipvtap_class = { .name = "ipvtap", .ns_type = &net_ns_type_operations, .namespace = ipvtap_net_namespace, }; struct ipvtap_dev { struct ipvl_dev vlan; struct tap_dev tap; }; static void ipvtap_count_tx_dropped(struct tap_dev *tap) { struct ipvtap_dev *vlantap = container_of(tap, struct ipvtap_dev, tap); struct ipvl_dev *vlan = &vlantap->vlan; this_cpu_inc(vlan->pcpu_stats->tx_drps); } static void ipvtap_count_rx_dropped(struct tap_dev *tap) { struct ipvtap_dev *vlantap = container_of(tap, struct ipvtap_dev, tap); struct ipvl_dev *vlan = &vlantap->vlan; ipvlan_count_rx(vlan, 0, 0, 0); } static void ipvtap_update_features(struct tap_dev *tap, netdev_features_t features) { struct ipvtap_dev *vlantap = container_of(tap, struct ipvtap_dev, tap); struct ipvl_dev *vlan = &vlantap->vlan; vlan->sfeatures = features; netdev_update_features(vlan->dev); } static int ipvtap_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ipvtap_dev *vlantap = netdev_priv(dev); int err; INIT_LIST_HEAD(&vlantap->tap.queue_list); /* Since macvlan supports all offloads by default, make * tap support all offloads also. */ vlantap->tap.tap_features = TUN_OFFLOADS; vlantap->tap.count_tx_dropped = ipvtap_count_tx_dropped; vlantap->tap.update_features = ipvtap_update_features; vlantap->tap.count_rx_dropped = ipvtap_count_rx_dropped; err = netdev_rx_handler_register(dev, tap_handle_frame, &vlantap->tap); if (err) return err; /* Don't put anything that may fail after macvlan_common_newlink * because we can't undo what it does. */ err = ipvlan_link_new(src_net, dev, tb, data, extack); if (err) { netdev_rx_handler_unregister(dev); return err; } vlantap->tap.dev = vlantap->vlan.dev; return err; } static void ipvtap_dellink(struct net_device *dev, struct list_head *head) { struct ipvtap_dev *vlan = netdev_priv(dev); netdev_rx_handler_unregister(dev); tap_del_queues(&vlan->tap); ipvlan_link_delete(dev, head); } static void ipvtap_setup(struct net_device *dev) { ipvlan_link_setup(dev); dev->tx_queue_len = TUN_READQ_SIZE; dev->priv_flags &= ~IFF_NO_QUEUE; } static struct rtnl_link_ops ipvtap_link_ops __read_mostly = { .kind = "ipvtap", .setup = ipvtap_setup, .newlink = ipvtap_newlink, .dellink = ipvtap_dellink, .priv_size = sizeof(struct ipvtap_dev), }; static int ipvtap_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct ipvtap_dev *vlantap; struct device *classdev; dev_t devt; int err; char tap_name[IFNAMSIZ]; if (dev->rtnl_link_ops != &ipvtap_link_ops) return NOTIFY_DONE; snprintf(tap_name, IFNAMSIZ, "tap%d", dev->ifindex); vlantap = netdev_priv(dev); switch (event) { case NETDEV_REGISTER: /* Create the device node here after the network device has * been registered but before register_netdevice has * finished running. */ err = tap_get_minor(ipvtap_major, &vlantap->tap); if (err) return notifier_from_errno(err); devt = MKDEV(MAJOR(ipvtap_major), vlantap->tap.minor); classdev = device_create(&ipvtap_class, &dev->dev, devt, dev, "%s", tap_name); if (IS_ERR(classdev)) { tap_free_minor(ipvtap_major, &vlantap->tap); return notifier_from_errno(PTR_ERR(classdev)); } err = sysfs_create_link(&dev->dev.kobj, &classdev->kobj, tap_name); if (err) return notifier_from_errno(err); break; case NETDEV_UNREGISTER: /* vlan->minor == 0 if NETDEV_REGISTER above failed */ if (vlantap->tap.minor == 0) break; sysfs_remove_link(&dev->dev.kobj, tap_name); devt = MKDEV(MAJOR(ipvtap_major), vlantap->tap.minor); device_destroy(&ipvtap_class, devt); tap_free_minor(ipvtap_major, &vlantap->tap); break; case NETDEV_CHANGE_TX_QUEUE_LEN: if (tap_queue_resize(&vlantap->tap)) return NOTIFY_BAD; break; } return NOTIFY_DONE; } static struct notifier_block ipvtap_notifier_block __read_mostly = { .notifier_call = ipvtap_device_event, }; static int __init ipvtap_init(void) { int err; err = tap_create_cdev(&ipvtap_cdev, &ipvtap_major, "ipvtap", THIS_MODULE); if (err) goto out1; err = class_register(&ipvtap_class); if (err) goto out2; err = register_netdevice_notifier(&ipvtap_notifier_block); if (err) goto out3; err = ipvlan_link_register(&ipvtap_link_ops); if (err) goto out4; return 0; out4: unregister_netdevice_notifier(&ipvtap_notifier_block); out3: class_unregister(&ipvtap_class); out2: tap_destroy_cdev(ipvtap_major, &ipvtap_cdev); out1: return err; } module_init(ipvtap_init); static void __exit ipvtap_exit(void) { rtnl_link_unregister(&ipvtap_link_ops); unregister_netdevice_notifier(&ipvtap_notifier_block); class_unregister(&ipvtap_class); tap_destroy_cdev(ipvtap_major, &ipvtap_cdev); } module_exit(ipvtap_exit); MODULE_ALIAS_RTNL_LINK("ipvtap"); MODULE_AUTHOR("Sainath Grandhi <sainath.grandhi@intel.com>"); MODULE_DESCRIPTION("IP-VLAN based tap driver"); MODULE_LICENSE("GPL"); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_ERR_H #define _LINUX_ERR_H #include <linux/compiler.h> #include <linux/types.h> #include <asm/errno.h> /* * Kernel pointers have redundant information, so we can use a * scheme where we can return either an error code or a normal * pointer with the same return value. * * This should be a per-architecture thing, to allow different * error and pointer decisions. */ #define MAX_ERRNO 4095 #ifndef __ASSEMBLY__ /** * IS_ERR_VALUE - Detect an error pointer. * @x: The pointer to check. * * Like IS_ERR(), but does not generate a compiler warning if result is unused. */ #define IS_ERR_VALUE(x) unlikely((unsigned long)(void *)(x) >= (unsigned long)-MAX_ERRNO) /** * ERR_PTR - Create an error pointer. * @error: A negative error code. * * Encodes @error into a pointer value. Users should consider the result * opaque and not assume anything about how the error is encoded. * * Return: A pointer with @error encoded within its value. */ static inline void * __must_check ERR_PTR(long error) { return (void *) error; } /* Return the pointer in the percpu address space. */ #define ERR_PTR_PCPU(error) ((void __percpu *)(unsigned long)ERR_PTR(error)) /** * PTR_ERR - Extract the error code from an error pointer. * @ptr: An error pointer. * Return: The error code within @ptr. */ static inline long __must_check PTR_ERR(__force const void *ptr) { return (long) ptr; } /* Read an error pointer from the percpu address space. */ #define PTR_ERR_PCPU(ptr) (PTR_ERR((const void *)(__force const unsigned long)(ptr))) /** * IS_ERR - Detect an error pointer. * @ptr: The pointer to check. * Return: true if @ptr is an error pointer, false otherwise. */ static inline bool __must_check IS_ERR(__force const void *ptr) { return IS_ERR_VALUE((unsigned long)ptr); } /* Read an error pointer from the percpu address space. */ #define IS_ERR_PCPU(ptr) (IS_ERR((const void *)(__force const unsigned long)(ptr))) /** * IS_ERR_OR_NULL - Detect an error pointer or a null pointer. * @ptr: The pointer to check. * * Like IS_ERR(), but also returns true for a null pointer. */ static inline bool __must_check IS_ERR_OR_NULL(__force const void *ptr) { return unlikely(!ptr) || IS_ERR_VALUE((unsigned long)ptr); } /** * ERR_CAST - Explicitly cast an error-valued pointer to another pointer type * @ptr: The pointer to cast. * * Explicitly cast an error-valued pointer to another pointer type in such a * way as to make it clear that's what's going on. */ static inline void * __must_check ERR_CAST(__force const void *ptr) { /* cast away the const */ return (void *) ptr; } /** * PTR_ERR_OR_ZERO - Extract the error code from a pointer if it has one. * @ptr: A potential error pointer. * * Convenience function that can be used inside a function that returns * an error code to propagate errors received as error pointers. * For example, ``return PTR_ERR_OR_ZERO(ptr);`` replaces: * * .. code-block:: c * * if (IS_ERR(ptr)) * return PTR_ERR(ptr); * else * return 0; * * Return: The error code within @ptr if it is an error pointer; 0 otherwise. */ static inline int __must_check PTR_ERR_OR_ZERO(__force const void *ptr) { if (IS_ERR(ptr)) return PTR_ERR(ptr); else return 0; } #endif #endif /* _LINUX_ERR_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Paravirtualization interfaces Copyright (C) 2006 Rusty Russell IBM Corporation 2007 - x86_64 support added by Glauber de Oliveira Costa, Red Hat Inc */ #include <linux/errno.h> #include <linux/init.h> #include <linux/export.h> #include <linux/efi.h> #include <linux/bcd.h> #include <linux/highmem.h> #include <linux/kprobes.h> #include <linux/pgtable.h> #include <linux/static_call.h> #include <asm/bug.h> #include <asm/paravirt.h> #include <asm/debugreg.h> #include <asm/desc.h> #include <asm/setup.h> #include <asm/time.h> #include <asm/pgalloc.h> #include <asm/irq.h> #include <asm/delay.h> #include <asm/fixmap.h> #include <asm/apic.h> #include <asm/tlbflush.h> #include <asm/timer.h> #include <asm/special_insns.h> #include <asm/tlb.h> #include <asm/io_bitmap.h> #include <asm/gsseg.h> /* stub always returning 0. */ DEFINE_ASM_FUNC(paravirt_ret0, "xor %eax,%eax", .entry.text); void __init default_banner(void) { printk(KERN_INFO "Booting paravirtualized kernel on %s\n", pv_info.name); } #ifdef CONFIG_PARAVIRT_XXL DEFINE_ASM_FUNC(_paravirt_ident_64, "mov %rdi, %rax", .text); DEFINE_ASM_FUNC(pv_native_save_fl, "pushf; pop %rax", .noinstr.text); DEFINE_ASM_FUNC(pv_native_irq_disable, "cli", .noinstr.text); DEFINE_ASM_FUNC(pv_native_irq_enable, "sti", .noinstr.text); DEFINE_ASM_FUNC(pv_native_read_cr2, "mov %cr2, %rax", .noinstr.text); #endif DEFINE_STATIC_KEY_FALSE(virt_spin_lock_key); void __init native_pv_lock_init(void) { if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) static_branch_enable(&virt_spin_lock_key); } static void native_tlb_remove_table(struct mmu_gather *tlb, void *table) { tlb_remove_page(tlb, table); } struct static_key paravirt_steal_enabled; struct static_key paravirt_steal_rq_enabled; static u64 native_steal_clock(int cpu) { return 0; } DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock); DEFINE_STATIC_CALL(pv_sched_clock, native_sched_clock); void paravirt_set_sched_clock(u64 (*func)(void)) { static_call_update(pv_sched_clock, func); } /* These are in entry.S */ static struct resource reserve_ioports = { .start = 0, .end = IO_SPACE_LIMIT, .name = "paravirt-ioport", .flags = IORESOURCE_IO | IORESOURCE_BUSY, }; /* * Reserve the whole legacy IO space to prevent any legacy drivers * from wasting time probing for their hardware. This is a fairly * brute-force approach to disabling all non-virtual drivers. * * Note that this must be called very early to have any effect. */ int paravirt_disable_iospace(void) { return request_resource(&ioport_resource, &reserve_ioports); } #ifdef CONFIG_PARAVIRT_XXL static noinstr void pv_native_write_cr2(unsigned long val) { native_write_cr2(val); } static noinstr unsigned long pv_native_get_debugreg(int regno) { return native_get_debugreg(regno); } static noinstr void pv_native_set_debugreg(int regno, unsigned long val) { native_set_debugreg(regno, val); } noinstr void pv_native_wbinvd(void) { native_wbinvd(); } static noinstr void pv_native_safe_halt(void) { native_safe_halt(); } #endif struct pv_info pv_info = { .name = "bare hardware", #ifdef CONFIG_PARAVIRT_XXL .extra_user_64bit_cs = __USER_CS, #endif }; /* 64-bit pagetable entries */ #define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_64) struct paravirt_patch_template pv_ops = { /* Cpu ops. */ .cpu.io_delay = native_io_delay, #ifdef CONFIG_PARAVIRT_XXL .cpu.cpuid = native_cpuid, .cpu.get_debugreg = pv_native_get_debugreg, .cpu.set_debugreg = pv_native_set_debugreg, .cpu.read_cr0 = native_read_cr0, .cpu.write_cr0 = native_write_cr0, .cpu.write_cr4 = native_write_cr4, .cpu.wbinvd = pv_native_wbinvd, .cpu.read_msr = native_read_msr, .cpu.write_msr = native_write_msr, .cpu.read_msr_safe = native_read_msr_safe, .cpu.write_msr_safe = native_write_msr_safe, .cpu.read_pmc = native_read_pmc, .cpu.load_tr_desc = native_load_tr_desc, .cpu.set_ldt = native_set_ldt, .cpu.load_gdt = native_load_gdt, .cpu.load_idt = native_load_idt, .cpu.store_tr = native_store_tr, .cpu.load_tls = native_load_tls, .cpu.load_gs_index = native_load_gs_index, .cpu.write_ldt_entry = native_write_ldt_entry, .cpu.write_gdt_entry = native_write_gdt_entry, .cpu.write_idt_entry = native_write_idt_entry, .cpu.alloc_ldt = paravirt_nop, .cpu.free_ldt = paravirt_nop, .cpu.load_sp0 = native_load_sp0, #ifdef CONFIG_X86_IOPL_IOPERM .cpu.invalidate_io_bitmap = native_tss_invalidate_io_bitmap, .cpu.update_io_bitmap = native_tss_update_io_bitmap, #endif .cpu.start_context_switch = paravirt_nop, .cpu.end_context_switch = paravirt_nop, /* Irq ops. */ .irq.save_fl = __PV_IS_CALLEE_SAVE(pv_native_save_fl), .irq.irq_disable = __PV_IS_CALLEE_SAVE(pv_native_irq_disable), .irq.irq_enable = __PV_IS_CALLEE_SAVE(pv_native_irq_enable), .irq.safe_halt = pv_native_safe_halt, .irq.halt = native_halt, #endif /* CONFIG_PARAVIRT_XXL */ /* Mmu ops. */ .mmu.flush_tlb_user = native_flush_tlb_local, .mmu.flush_tlb_kernel = native_flush_tlb_global, .mmu.flush_tlb_one_user = native_flush_tlb_one_user, .mmu.flush_tlb_multi = native_flush_tlb_multi, .mmu.tlb_remove_table = native_tlb_remove_table, .mmu.exit_mmap = paravirt_nop, .mmu.notify_page_enc_status_changed = paravirt_nop, #ifdef CONFIG_PARAVIRT_XXL .mmu.read_cr2 = __PV_IS_CALLEE_SAVE(pv_native_read_cr2), .mmu.write_cr2 = pv_native_write_cr2, .mmu.read_cr3 = __native_read_cr3, .mmu.write_cr3 = native_write_cr3, .mmu.pgd_alloc = __paravirt_pgd_alloc, .mmu.pgd_free = paravirt_nop, .mmu.alloc_pte = paravirt_nop, .mmu.alloc_pmd = paravirt_nop, .mmu.alloc_pud = paravirt_nop, .mmu.alloc_p4d = paravirt_nop, .mmu.release_pte = paravirt_nop, .mmu.release_pmd = paravirt_nop, .mmu.release_pud = paravirt_nop, .mmu.release_p4d = paravirt_nop, .mmu.set_pte = native_set_pte, .mmu.set_pmd = native_set_pmd, .mmu.ptep_modify_prot_start = __ptep_modify_prot_start, .mmu.ptep_modify_prot_commit = __ptep_modify_prot_commit, .mmu.set_pud = native_set_pud, .mmu.pmd_val = PTE_IDENT, .mmu.make_pmd = PTE_IDENT, .mmu.pud_val = PTE_IDENT, .mmu.make_pud = PTE_IDENT, .mmu.set_p4d = native_set_p4d, #if CONFIG_PGTABLE_LEVELS >= 5 .mmu.p4d_val = PTE_IDENT, .mmu.make_p4d = PTE_IDENT, .mmu.set_pgd = native_set_pgd, #endif /* CONFIG_PGTABLE_LEVELS >= 5 */ .mmu.pte_val = PTE_IDENT, .mmu.pgd_val = PTE_IDENT, .mmu.make_pte = PTE_IDENT, .mmu.make_pgd = PTE_IDENT, .mmu.enter_mmap = paravirt_nop, .mmu.lazy_mode = { .enter = paravirt_nop, .leave = paravirt_nop, .flush = paravirt_nop, }, .mmu.set_fixmap = native_set_fixmap, #endif /* CONFIG_PARAVIRT_XXL */ #if defined(CONFIG_PARAVIRT_SPINLOCKS) /* Lock ops. */ #ifdef CONFIG_SMP .lock.queued_spin_lock_slowpath = native_queued_spin_lock_slowpath, .lock.queued_spin_unlock = PV_CALLEE_SAVE(__native_queued_spin_unlock), .lock.wait = paravirt_nop, .lock.kick = paravirt_nop, .lock.vcpu_is_preempted = PV_CALLEE_SAVE(__native_vcpu_is_preempted), #endif /* SMP */ #endif }; #ifdef CONFIG_PARAVIRT_XXL NOKPROBE_SYMBOL(native_load_idt); #endif EXPORT_SYMBOL(pv_ops); EXPORT_SYMBOL_GPL(pv_info); |
| 2 2 2 2 2 2 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 | /* * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. * */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/rculist.h> #include <linux/llist.h> #include "rds_single_path.h" #include "ib_mr.h" #include "rds.h" struct workqueue_struct *rds_ib_mr_wq; static void rds_ib_odp_mr_worker(struct work_struct *work); static struct rds_ib_device *rds_ib_get_device(__be32 ipaddr) { struct rds_ib_device *rds_ibdev; struct rds_ib_ipaddr *i_ipaddr; rcu_read_lock(); list_for_each_entry_rcu(rds_ibdev, &rds_ib_devices, list) { list_for_each_entry_rcu(i_ipaddr, &rds_ibdev->ipaddr_list, list) { if (i_ipaddr->ipaddr == ipaddr) { refcount_inc(&rds_ibdev->refcount); rcu_read_unlock(); return rds_ibdev; } } } rcu_read_unlock(); return NULL; } static int rds_ib_add_ipaddr(struct rds_ib_device *rds_ibdev, __be32 ipaddr) { struct rds_ib_ipaddr *i_ipaddr; i_ipaddr = kmalloc(sizeof *i_ipaddr, GFP_KERNEL); if (!i_ipaddr) return -ENOMEM; i_ipaddr->ipaddr = ipaddr; spin_lock_irq(&rds_ibdev->spinlock); list_add_tail_rcu(&i_ipaddr->list, &rds_ibdev->ipaddr_list); spin_unlock_irq(&rds_ibdev->spinlock); return 0; } static void rds_ib_remove_ipaddr(struct rds_ib_device *rds_ibdev, __be32 ipaddr) { struct rds_ib_ipaddr *i_ipaddr; struct rds_ib_ipaddr *to_free = NULL; spin_lock_irq(&rds_ibdev->spinlock); list_for_each_entry_rcu(i_ipaddr, &rds_ibdev->ipaddr_list, list) { if (i_ipaddr->ipaddr == ipaddr) { list_del_rcu(&i_ipaddr->list); to_free = i_ipaddr; break; } } spin_unlock_irq(&rds_ibdev->spinlock); if (to_free) kfree_rcu(to_free, rcu); } int rds_ib_update_ipaddr(struct rds_ib_device *rds_ibdev, struct in6_addr *ipaddr) { struct rds_ib_device *rds_ibdev_old; rds_ibdev_old = rds_ib_get_device(ipaddr->s6_addr32[3]); if (!rds_ibdev_old) return rds_ib_add_ipaddr(rds_ibdev, ipaddr->s6_addr32[3]); if (rds_ibdev_old != rds_ibdev) { rds_ib_remove_ipaddr(rds_ibdev_old, ipaddr->s6_addr32[3]); rds_ib_dev_put(rds_ibdev_old); return rds_ib_add_ipaddr(rds_ibdev, ipaddr->s6_addr32[3]); } rds_ib_dev_put(rds_ibdev_old); return 0; } void rds_ib_add_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn) { struct rds_ib_connection *ic = conn->c_transport_data; /* conn was previously on the nodev_conns_list */ spin_lock_irq(&ib_nodev_conns_lock); BUG_ON(list_empty(&ib_nodev_conns)); BUG_ON(list_empty(&ic->ib_node)); list_del(&ic->ib_node); spin_lock(&rds_ibdev->spinlock); list_add_tail(&ic->ib_node, &rds_ibdev->conn_list); spin_unlock(&rds_ibdev->spinlock); spin_unlock_irq(&ib_nodev_conns_lock); ic->rds_ibdev = rds_ibdev; refcount_inc(&rds_ibdev->refcount); } void rds_ib_remove_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn) { struct rds_ib_connection *ic = conn->c_transport_data; /* place conn on nodev_conns_list */ spin_lock(&ib_nodev_conns_lock); spin_lock_irq(&rds_ibdev->spinlock); BUG_ON(list_empty(&ic->ib_node)); list_del(&ic->ib_node); spin_unlock_irq(&rds_ibdev->spinlock); list_add_tail(&ic->ib_node, &ib_nodev_conns); spin_unlock(&ib_nodev_conns_lock); ic->rds_ibdev = NULL; rds_ib_dev_put(rds_ibdev); } void rds_ib_destroy_nodev_conns(void) { struct rds_ib_connection *ic, *_ic; LIST_HEAD(tmp_list); /* avoid calling conn_destroy with irqs off */ spin_lock_irq(&ib_nodev_conns_lock); list_splice(&ib_nodev_conns, &tmp_list); spin_unlock_irq(&ib_nodev_conns_lock); list_for_each_entry_safe(ic, _ic, &tmp_list, ib_node) rds_conn_destroy(ic->conn); } void rds_ib_get_mr_info(struct rds_ib_device *rds_ibdev, struct rds_info_rdma_connection *iinfo) { struct rds_ib_mr_pool *pool_1m = rds_ibdev->mr_1m_pool; iinfo->rdma_mr_max = pool_1m->max_items; iinfo->rdma_mr_size = pool_1m->max_pages; } #if IS_ENABLED(CONFIG_IPV6) void rds6_ib_get_mr_info(struct rds_ib_device *rds_ibdev, struct rds6_info_rdma_connection *iinfo6) { struct rds_ib_mr_pool *pool_1m = rds_ibdev->mr_1m_pool; iinfo6->rdma_mr_max = pool_1m->max_items; iinfo6->rdma_mr_size = pool_1m->max_pages; } #endif struct rds_ib_mr *rds_ib_reuse_mr(struct rds_ib_mr_pool *pool) { struct rds_ib_mr *ibmr = NULL; struct llist_node *ret; unsigned long flags; spin_lock_irqsave(&pool->clean_lock, flags); ret = llist_del_first(&pool->clean_list); spin_unlock_irqrestore(&pool->clean_lock, flags); if (ret) { ibmr = llist_entry(ret, struct rds_ib_mr, llnode); if (pool->pool_type == RDS_IB_MR_8K_POOL) rds_ib_stats_inc(s_ib_rdma_mr_8k_reused); else rds_ib_stats_inc(s_ib_rdma_mr_1m_reused); } return ibmr; } void rds_ib_sync_mr(void *trans_private, int direction) { struct rds_ib_mr *ibmr = trans_private; struct rds_ib_device *rds_ibdev = ibmr->device; if (ibmr->odp) return; switch (direction) { case DMA_FROM_DEVICE: ib_dma_sync_sg_for_cpu(rds_ibdev->dev, ibmr->sg, ibmr->sg_dma_len, DMA_BIDIRECTIONAL); break; case DMA_TO_DEVICE: ib_dma_sync_sg_for_device(rds_ibdev->dev, ibmr->sg, ibmr->sg_dma_len, DMA_BIDIRECTIONAL); break; } } void __rds_ib_teardown_mr(struct rds_ib_mr *ibmr) { struct rds_ib_device *rds_ibdev = ibmr->device; if (ibmr->sg_dma_len) { ib_dma_unmap_sg(rds_ibdev->dev, ibmr->sg, ibmr->sg_len, DMA_BIDIRECTIONAL); ibmr->sg_dma_len = 0; } /* Release the s/g list */ if (ibmr->sg_len) { unsigned int i; for (i = 0; i < ibmr->sg_len; ++i) { struct page *page = sg_page(&ibmr->sg[i]); /* FIXME we need a way to tell a r/w MR * from a r/o MR */ WARN_ON(!page->mapping && irqs_disabled()); set_page_dirty(page); put_page(page); } kfree(ibmr->sg); ibmr->sg = NULL; ibmr->sg_len = 0; } } void rds_ib_teardown_mr(struct rds_ib_mr *ibmr) { unsigned int pinned = ibmr->sg_len; __rds_ib_teardown_mr(ibmr); if (pinned) { struct rds_ib_mr_pool *pool = ibmr->pool; atomic_sub(pinned, &pool->free_pinned); } } static inline unsigned int rds_ib_flush_goal(struct rds_ib_mr_pool *pool, int free_all) { unsigned int item_count; item_count = atomic_read(&pool->item_count); if (free_all) return item_count; return 0; } /* * given an llist of mrs, put them all into the list_head for more processing */ static unsigned int llist_append_to_list(struct llist_head *llist, struct list_head *list) { struct rds_ib_mr *ibmr; struct llist_node *node; struct llist_node *next; unsigned int count = 0; node = llist_del_all(llist); while (node) { next = node->next; ibmr = llist_entry(node, struct rds_ib_mr, llnode); list_add_tail(&ibmr->unmap_list, list); node = next; count++; } return count; } /* * this takes a list head of mrs and turns it into linked llist nodes * of clusters. Each cluster has linked llist nodes of * MR_CLUSTER_SIZE mrs that are ready for reuse. */ static void list_to_llist_nodes(struct list_head *list, struct llist_node **nodes_head, struct llist_node **nodes_tail) { struct rds_ib_mr *ibmr; struct llist_node *cur = NULL; struct llist_node **next = nodes_head; list_for_each_entry(ibmr, list, unmap_list) { cur = &ibmr->llnode; *next = cur; next = &cur->next; } *next = NULL; *nodes_tail = cur; } /* * Flush our pool of MRs. * At a minimum, all currently unused MRs are unmapped. * If the number of MRs allocated exceeds the limit, we also try * to free as many MRs as needed to get back to this limit. */ int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool, int free_all, struct rds_ib_mr **ibmr_ret) { struct rds_ib_mr *ibmr; struct llist_node *clean_nodes; struct llist_node *clean_tail; LIST_HEAD(unmap_list); unsigned long unpinned = 0; unsigned int nfreed = 0, dirty_to_clean = 0, free_goal; if (pool->pool_type == RDS_IB_MR_8K_POOL) rds_ib_stats_inc(s_ib_rdma_mr_8k_pool_flush); else rds_ib_stats_inc(s_ib_rdma_mr_1m_pool_flush); if (ibmr_ret) { DEFINE_WAIT(wait); while (!mutex_trylock(&pool->flush_lock)) { ibmr = rds_ib_reuse_mr(pool); if (ibmr) { *ibmr_ret = ibmr; finish_wait(&pool->flush_wait, &wait); goto out_nolock; } prepare_to_wait(&pool->flush_wait, &wait, TASK_UNINTERRUPTIBLE); if (llist_empty(&pool->clean_list)) schedule(); ibmr = rds_ib_reuse_mr(pool); if (ibmr) { *ibmr_ret = ibmr; finish_wait(&pool->flush_wait, &wait); goto out_nolock; } } finish_wait(&pool->flush_wait, &wait); } else mutex_lock(&pool->flush_lock); if (ibmr_ret) { ibmr = rds_ib_reuse_mr(pool); if (ibmr) { *ibmr_ret = ibmr; goto out; } } /* Get the list of all MRs to be dropped. Ordering matters - * we want to put drop_list ahead of free_list. */ dirty_to_clean = llist_append_to_list(&pool->drop_list, &unmap_list); dirty_to_clean += llist_append_to_list(&pool->free_list, &unmap_list); if (free_all) { unsigned long flags; spin_lock_irqsave(&pool->clean_lock, flags); llist_append_to_list(&pool->clean_list, &unmap_list); spin_unlock_irqrestore(&pool->clean_lock, flags); } free_goal = rds_ib_flush_goal(pool, free_all); if (list_empty(&unmap_list)) goto out; rds_ib_unreg_frmr(&unmap_list, &nfreed, &unpinned, free_goal); if (!list_empty(&unmap_list)) { unsigned long flags; list_to_llist_nodes(&unmap_list, &clean_nodes, &clean_tail); if (ibmr_ret) { *ibmr_ret = llist_entry(clean_nodes, struct rds_ib_mr, llnode); clean_nodes = clean_nodes->next; } /* more than one entry in llist nodes */ if (clean_nodes) { spin_lock_irqsave(&pool->clean_lock, flags); llist_add_batch(clean_nodes, clean_tail, &pool->clean_list); spin_unlock_irqrestore(&pool->clean_lock, flags); } } atomic_sub(unpinned, &pool->free_pinned); atomic_sub(dirty_to_clean, &pool->dirty_count); atomic_sub(nfreed, &pool->item_count); out: mutex_unlock(&pool->flush_lock); if (waitqueue_active(&pool->flush_wait)) wake_up(&pool->flush_wait); out_nolock: return 0; } struct rds_ib_mr *rds_ib_try_reuse_ibmr(struct rds_ib_mr_pool *pool) { struct rds_ib_mr *ibmr = NULL; int iter = 0; while (1) { ibmr = rds_ib_reuse_mr(pool); if (ibmr) return ibmr; if (atomic_inc_return(&pool->item_count) <= pool->max_items) break; atomic_dec(&pool->item_count); if (++iter > 2) { if (pool->pool_type == RDS_IB_MR_8K_POOL) rds_ib_stats_inc(s_ib_rdma_mr_8k_pool_depleted); else rds_ib_stats_inc(s_ib_rdma_mr_1m_pool_depleted); break; } /* We do have some empty MRs. Flush them out. */ if (pool->pool_type == RDS_IB_MR_8K_POOL) rds_ib_stats_inc(s_ib_rdma_mr_8k_pool_wait); else rds_ib_stats_inc(s_ib_rdma_mr_1m_pool_wait); rds_ib_flush_mr_pool(pool, 0, &ibmr); if (ibmr) return ibmr; } return NULL; } static void rds_ib_mr_pool_flush_worker(struct work_struct *work) { struct rds_ib_mr_pool *pool = container_of(work, struct rds_ib_mr_pool, flush_worker.work); rds_ib_flush_mr_pool(pool, 0, NULL); } void rds_ib_free_mr(void *trans_private, int invalidate) { struct rds_ib_mr *ibmr = trans_private; struct rds_ib_mr_pool *pool = ibmr->pool; struct rds_ib_device *rds_ibdev = ibmr->device; rdsdebug("RDS/IB: free_mr nents %u\n", ibmr->sg_len); if (ibmr->odp) { /* A MR created and marked as use_once. We use delayed work, * because there is a change that we are in interrupt and can't * call to ib_dereg_mr() directly. */ INIT_DELAYED_WORK(&ibmr->work, rds_ib_odp_mr_worker); queue_delayed_work(rds_ib_mr_wq, &ibmr->work, 0); return; } /* Return it to the pool's free list */ rds_ib_free_frmr_list(ibmr); atomic_add(ibmr->sg_len, &pool->free_pinned); atomic_inc(&pool->dirty_count); /* If we've pinned too many pages, request a flush */ if (atomic_read(&pool->free_pinned) >= pool->max_free_pinned || atomic_read(&pool->dirty_count) >= pool->max_items / 5) queue_delayed_work(rds_ib_mr_wq, &pool->flush_worker, 10); if (invalidate) { if (likely(!in_interrupt())) { rds_ib_flush_mr_pool(pool, 0, NULL); } else { /* We get here if the user created a MR marked * as use_once and invalidate at the same time. */ queue_delayed_work(rds_ib_mr_wq, &pool->flush_worker, 10); } } rds_ib_dev_put(rds_ibdev); } void rds_ib_flush_mrs(void) { struct rds_ib_device *rds_ibdev; down_read(&rds_ib_devices_lock); list_for_each_entry(rds_ibdev, &rds_ib_devices, list) { if (rds_ibdev->mr_8k_pool) rds_ib_flush_mr_pool(rds_ibdev->mr_8k_pool, 0, NULL); if (rds_ibdev->mr_1m_pool) rds_ib_flush_mr_pool(rds_ibdev->mr_1m_pool, 0, NULL); } up_read(&rds_ib_devices_lock); } u32 rds_ib_get_lkey(void *trans_private) { struct rds_ib_mr *ibmr = trans_private; return ibmr->u.mr->lkey; } void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, struct rds_sock *rs, u32 *key_ret, struct rds_connection *conn, u64 start, u64 length, int need_odp) { struct rds_ib_device *rds_ibdev; struct rds_ib_mr *ibmr = NULL; struct rds_ib_connection *ic = NULL; int ret; rds_ibdev = rds_ib_get_device(rs->rs_bound_addr.s6_addr32[3]); if (!rds_ibdev) { ret = -ENODEV; goto out; } if (need_odp == ODP_ZEROBASED || need_odp == ODP_VIRTUAL) { u64 virt_addr = need_odp == ODP_ZEROBASED ? 0 : start; int access_flags = (IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_READ | IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_ON_DEMAND); struct ib_sge sge = {}; struct ib_mr *ib_mr; if (!rds_ibdev->odp_capable) { ret = -EOPNOTSUPP; goto out; } ib_mr = ib_reg_user_mr(rds_ibdev->pd, start, length, virt_addr, access_flags); if (IS_ERR(ib_mr)) { rdsdebug("rds_ib_get_user_mr returned %d\n", IS_ERR(ib_mr)); ret = PTR_ERR(ib_mr); goto out; } if (key_ret) *key_ret = ib_mr->rkey; ibmr = kzalloc(sizeof(*ibmr), GFP_KERNEL); if (!ibmr) { ib_dereg_mr(ib_mr); ret = -ENOMEM; goto out; } ibmr->u.mr = ib_mr; ibmr->odp = 1; sge.addr = virt_addr; sge.length = length; sge.lkey = ib_mr->lkey; ib_advise_mr(rds_ibdev->pd, IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH_WRITE, IB_UVERBS_ADVISE_MR_FLAG_FLUSH, &sge, 1); return ibmr; } if (conn) ic = conn->c_transport_data; if (!rds_ibdev->mr_8k_pool || !rds_ibdev->mr_1m_pool) { ret = -ENODEV; goto out; } ibmr = rds_ib_reg_frmr(rds_ibdev, ic, sg, nents, key_ret); if (IS_ERR(ibmr)) { ret = PTR_ERR(ibmr); pr_warn("RDS/IB: rds_ib_get_mr failed (errno=%d)\n", ret); } else { return ibmr; } out: if (rds_ibdev) rds_ib_dev_put(rds_ibdev); return ERR_PTR(ret); } void rds_ib_destroy_mr_pool(struct rds_ib_mr_pool *pool) { cancel_delayed_work_sync(&pool->flush_worker); rds_ib_flush_mr_pool(pool, 1, NULL); WARN_ON(atomic_read(&pool->item_count)); WARN_ON(atomic_read(&pool->free_pinned)); kfree(pool); } struct rds_ib_mr_pool *rds_ib_create_mr_pool(struct rds_ib_device *rds_ibdev, int pool_type) { struct rds_ib_mr_pool *pool; pool = kzalloc(sizeof(*pool), GFP_KERNEL); if (!pool) return ERR_PTR(-ENOMEM); pool->pool_type = pool_type; init_llist_head(&pool->free_list); init_llist_head(&pool->drop_list); init_llist_head(&pool->clean_list); spin_lock_init(&pool->clean_lock); mutex_init(&pool->flush_lock); init_waitqueue_head(&pool->flush_wait); INIT_DELAYED_WORK(&pool->flush_worker, rds_ib_mr_pool_flush_worker); if (pool_type == RDS_IB_MR_1M_POOL) { /* +1 allows for unaligned MRs */ pool->max_pages = RDS_MR_1M_MSG_SIZE + 1; pool->max_items = rds_ibdev->max_1m_mrs; } else { /* pool_type == RDS_IB_MR_8K_POOL */ pool->max_pages = RDS_MR_8K_MSG_SIZE + 1; pool->max_items = rds_ibdev->max_8k_mrs; } pool->max_free_pinned = pool->max_items * pool->max_pages / 4; pool->max_items_soft = rds_ibdev->max_mrs * 3 / 4; return pool; } int rds_ib_mr_init(void) { rds_ib_mr_wq = alloc_workqueue("rds_mr_flushd", WQ_MEM_RECLAIM, 0); if (!rds_ib_mr_wq) return -ENOMEM; return 0; } /* By the time this is called all the IB devices should have been torn down and * had their pools freed. As each pool is freed its work struct is waited on, * so the pool flushing work queue should be idle by the time we get here. */ void rds_ib_mr_exit(void) { destroy_workqueue(rds_ib_mr_wq); } static void rds_ib_odp_mr_worker(struct work_struct *work) { struct rds_ib_mr *ibmr; ibmr = container_of(work, struct rds_ib_mr, work.work); ib_dereg_mr(ibmr->u.mr); kfree(ibmr); } |
| 17 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Null security operations. * * Copyright (C) 2016 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <net/af_rxrpc.h> #include "ar-internal.h" static int none_init_connection_security(struct rxrpc_connection *conn, struct rxrpc_key_token *token) { return 0; } /* * Allocate an appropriately sized buffer for the amount of data remaining. */ static struct rxrpc_txbuf *none_alloc_txbuf(struct rxrpc_call *call, size_t remain, gfp_t gfp) { return rxrpc_alloc_data_txbuf(call, min_t(size_t, remain, RXRPC_JUMBO_DATALEN), 1, gfp); } static int none_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) { return 0; } static int none_verify_packet(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); sp->flags |= RXRPC_RX_VERIFIED; return 0; } static void none_free_call_crypto(struct rxrpc_call *call) { } static int none_respond_to_challenge(struct rxrpc_connection *conn, struct sk_buff *skb) { return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO, rxrpc_eproto_rxnull_challenge); } static int none_verify_response(struct rxrpc_connection *conn, struct sk_buff *skb) { return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO, rxrpc_eproto_rxnull_response); } static void none_clear(struct rxrpc_connection *conn) { } static int none_init(void) { return 0; } static void none_exit(void) { } /* * RxRPC Kerberos-based security */ const struct rxrpc_security rxrpc_no_security = { .name = "none", .security_index = RXRPC_SECURITY_NONE, .init = none_init, .exit = none_exit, .init_connection_security = none_init_connection_security, .free_call_crypto = none_free_call_crypto, .alloc_txbuf = none_alloc_txbuf, .secure_packet = none_secure_packet, .verify_packet = none_verify_packet, .respond_to_challenge = none_respond_to_challenge, .verify_response = none_verify_response, .clear = none_clear, }; |
| 3 3 2 1 3 3 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 | // SPDX-License-Identifier: GPL-2.0-only /* * Transparent proxy support for Linux/iptables * * Copyright (c) 2006-2010 BalaBit IT Ltd. * Author: Balazs Scheidler, Krisztian Kovacs */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/ip.h> #include <net/checksum.h> #include <net/udp.h> #include <net/tcp.h> #include <net/inet_sock.h> #include <net/inet_hashtables.h> #include <linux/inetdevice.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <net/netfilter/ipv4/nf_defrag_ipv4.h> #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) #define XT_TPROXY_HAVE_IPV6 1 #include <net/if_inet6.h> #include <net/addrconf.h> #include <net/inet6_hashtables.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> #endif #include <net/netfilter/nf_tproxy.h> #include <linux/netfilter/xt_TPROXY.h> static unsigned int tproxy_tg4(struct net *net, struct sk_buff *skb, __be32 laddr, __be16 lport, u_int32_t mark_mask, u_int32_t mark_value) { const struct iphdr *iph = ip_hdr(skb); struct udphdr _hdr, *hp; struct sock *sk; hp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_hdr), &_hdr); if (hp == NULL) return NF_DROP; /* check if there's an ongoing connection on the packet * addresses, this happens if the redirect already happened * and the current packet belongs to an already established * connection */ sk = nf_tproxy_get_sock_v4(net, skb, iph->protocol, iph->saddr, iph->daddr, hp->source, hp->dest, skb->dev, NF_TPROXY_LOOKUP_ESTABLISHED); laddr = nf_tproxy_laddr4(skb, laddr, iph->daddr); if (!lport) lport = hp->dest; /* UDP has no TCP_TIME_WAIT state, so we never enter here */ if (sk && sk->sk_state == TCP_TIME_WAIT) /* reopening a TIME_WAIT connection needs special handling */ sk = nf_tproxy_handle_time_wait4(net, skb, laddr, lport, sk); else if (!sk) /* no, there's no established connection, check if * there's a listener on the redirected addr/port */ sk = nf_tproxy_get_sock_v4(net, skb, iph->protocol, iph->saddr, laddr, hp->source, lport, skb->dev, NF_TPROXY_LOOKUP_LISTENER); /* NOTE: assign_sock consumes our sk reference */ if (sk && nf_tproxy_sk_is_transparent(sk)) { /* This should be in a separate target, but we don't do multiple targets on the same rule yet */ skb->mark = (skb->mark & ~mark_mask) ^ mark_value; nf_tproxy_assign_sock(skb, sk); return NF_ACCEPT; } return NF_DROP; } static unsigned int tproxy_tg4_v0(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_tproxy_target_info *tgi = par->targinfo; return tproxy_tg4(xt_net(par), skb, tgi->laddr, tgi->lport, tgi->mark_mask, tgi->mark_value); } static unsigned int tproxy_tg4_v1(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_tproxy_target_info_v1 *tgi = par->targinfo; return tproxy_tg4(xt_net(par), skb, tgi->laddr.ip, tgi->lport, tgi->mark_mask, tgi->mark_value); } #ifdef XT_TPROXY_HAVE_IPV6 static unsigned int tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par) { const struct ipv6hdr *iph = ipv6_hdr(skb); const struct xt_tproxy_target_info_v1 *tgi = par->targinfo; struct udphdr _hdr, *hp; struct sock *sk; const struct in6_addr *laddr; __be16 lport; int thoff = 0; int tproto; tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL); if (tproto < 0) return NF_DROP; hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr); if (!hp) return NF_DROP; /* check if there's an ongoing connection on the packet * addresses, this happens if the redirect already happened * and the current packet belongs to an already established * connection */ sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, tproto, &iph->saddr, &iph->daddr, hp->source, hp->dest, xt_in(par), NF_TPROXY_LOOKUP_ESTABLISHED); laddr = nf_tproxy_laddr6(skb, &tgi->laddr.in6, &iph->daddr); lport = tgi->lport ? tgi->lport : hp->dest; /* UDP has no TCP_TIME_WAIT state, so we never enter here */ if (sk && sk->sk_state == TCP_TIME_WAIT) { const struct xt_tproxy_target_info_v1 *tgi = par->targinfo; /* reopening a TIME_WAIT connection needs special handling */ sk = nf_tproxy_handle_time_wait6(skb, tproto, thoff, xt_net(par), &tgi->laddr.in6, tgi->lport, sk); } else if (!sk) /* no there's no established connection, check if * there's a listener on the redirected addr/port */ sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, tproto, &iph->saddr, laddr, hp->source, lport, xt_in(par), NF_TPROXY_LOOKUP_LISTENER); /* NOTE: assign_sock consumes our sk reference */ if (sk && nf_tproxy_sk_is_transparent(sk)) { /* This should be in a separate target, but we don't do multiple targets on the same rule yet */ skb->mark = (skb->mark & ~tgi->mark_mask) ^ tgi->mark_value; nf_tproxy_assign_sock(skb, sk); return NF_ACCEPT; } return NF_DROP; } static int tproxy_tg6_check(const struct xt_tgchk_param *par) { const struct ip6t_ip6 *i = par->entryinfo; int err; err = nf_defrag_ipv6_enable(par->net); if (err) return err; if ((i->proto == IPPROTO_TCP || i->proto == IPPROTO_UDP) && !(i->invflags & IP6T_INV_PROTO)) return 0; pr_info_ratelimited("Can be used only with -p tcp or -p udp\n"); return -EINVAL; } static void tproxy_tg6_destroy(const struct xt_tgdtor_param *par) { nf_defrag_ipv6_disable(par->net); } #endif static int tproxy_tg4_check(const struct xt_tgchk_param *par) { const struct ipt_ip *i = par->entryinfo; int err; err = nf_defrag_ipv4_enable(par->net); if (err) return err; if ((i->proto == IPPROTO_TCP || i->proto == IPPROTO_UDP) && !(i->invflags & IPT_INV_PROTO)) return 0; pr_info_ratelimited("Can be used only with -p tcp or -p udp\n"); return -EINVAL; } static void tproxy_tg4_destroy(const struct xt_tgdtor_param *par) { nf_defrag_ipv4_disable(par->net); } static struct xt_target tproxy_tg_reg[] __read_mostly = { { .name = "TPROXY", .family = NFPROTO_IPV4, .table = "mangle", .target = tproxy_tg4_v0, .revision = 0, .targetsize = sizeof(struct xt_tproxy_target_info), .checkentry = tproxy_tg4_check, .destroy = tproxy_tg4_destroy, .hooks = 1 << NF_INET_PRE_ROUTING, .me = THIS_MODULE, }, { .name = "TPROXY", .family = NFPROTO_IPV4, .table = "mangle", .target = tproxy_tg4_v1, .revision = 1, .targetsize = sizeof(struct xt_tproxy_target_info_v1), .checkentry = tproxy_tg4_check, .destroy = tproxy_tg4_destroy, .hooks = 1 << NF_INET_PRE_ROUTING, .me = THIS_MODULE, }, #ifdef XT_TPROXY_HAVE_IPV6 { .name = "TPROXY", .family = NFPROTO_IPV6, .table = "mangle", .target = tproxy_tg6_v1, .revision = 1, .targetsize = sizeof(struct xt_tproxy_target_info_v1), .checkentry = tproxy_tg6_check, .destroy = tproxy_tg6_destroy, .hooks = 1 << NF_INET_PRE_ROUTING, .me = THIS_MODULE, }, #endif }; static int __init tproxy_tg_init(void) { return xt_register_targets(tproxy_tg_reg, ARRAY_SIZE(tproxy_tg_reg)); } static void __exit tproxy_tg_exit(void) { xt_unregister_targets(tproxy_tg_reg, ARRAY_SIZE(tproxy_tg_reg)); } module_init(tproxy_tg_init); module_exit(tproxy_tg_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Balazs Scheidler, Krisztian Kovacs"); MODULE_DESCRIPTION("Netfilter transparent proxy (TPROXY) target module."); MODULE_ALIAS("ipt_TPROXY"); MODULE_ALIAS("ip6t_TPROXY"); |
| 4 4 4 4 4 3 3 3 3 1 1 1 1 1 1 3 1 1 1 3 3 1 3 3 882 884 182 182 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/core/netprio_cgroup.c Priority Control Group * * Authors: Neil Horman <nhorman@tuxdriver.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/cgroup.h> #include <linux/rcupdate.h> #include <linux/atomic.h> #include <linux/sched/task.h> #include <net/rtnetlink.h> #include <net/pkt_cls.h> #include <net/sock.h> #include <net/netprio_cgroup.h> #include <linux/fdtable.h> /* * netprio allocates per-net_device priomap array which is indexed by * css->id. Limiting css ID to 16bits doesn't lose anything. */ #define NETPRIO_ID_MAX USHRT_MAX #define PRIOMAP_MIN_SZ 128 /* * Extend @dev->priomap so that it's large enough to accommodate * @target_idx. @dev->priomap.priomap_len > @target_idx after successful * return. Must be called under rtnl lock. */ static int extend_netdev_table(struct net_device *dev, u32 target_idx) { struct netprio_map *old, *new; size_t new_sz, new_len; /* is the existing priomap large enough? */ old = rtnl_dereference(dev->priomap); if (old && old->priomap_len > target_idx) return 0; /* * Determine the new size. Let's keep it power-of-two. We start * from PRIOMAP_MIN_SZ and double it until it's large enough to * accommodate @target_idx. */ new_sz = PRIOMAP_MIN_SZ; while (true) { new_len = (new_sz - offsetof(struct netprio_map, priomap)) / sizeof(new->priomap[0]); if (new_len > target_idx) break; new_sz *= 2; /* overflowed? */ if (WARN_ON(new_sz < PRIOMAP_MIN_SZ)) return -ENOSPC; } /* allocate & copy */ new = kzalloc(new_sz, GFP_KERNEL); if (!new) return -ENOMEM; if (old) memcpy(new->priomap, old->priomap, old->priomap_len * sizeof(old->priomap[0])); new->priomap_len = new_len; /* install the new priomap */ rcu_assign_pointer(dev->priomap, new); if (old) kfree_rcu(old, rcu); return 0; } /** * netprio_prio - return the effective netprio of a cgroup-net_device pair * @css: css part of the target pair * @dev: net_device part of the target pair * * Should be called under RCU read or rtnl lock. */ static u32 netprio_prio(struct cgroup_subsys_state *css, struct net_device *dev) { struct netprio_map *map = rcu_dereference_rtnl(dev->priomap); int id = css->id; if (map && id < map->priomap_len) return map->priomap[id]; return 0; } /** * netprio_set_prio - set netprio on a cgroup-net_device pair * @css: css part of the target pair * @dev: net_device part of the target pair * @prio: prio to set * * Set netprio to @prio on @css-@dev pair. Should be called under rtnl * lock and may fail under memory pressure for non-zero @prio. */ static int netprio_set_prio(struct cgroup_subsys_state *css, struct net_device *dev, u32 prio) { struct netprio_map *map; int id = css->id; int ret; /* avoid extending priomap for zero writes */ map = rtnl_dereference(dev->priomap); if (!prio && (!map || map->priomap_len <= id)) return 0; ret = extend_netdev_table(dev, id); if (ret) return ret; map = rtnl_dereference(dev->priomap); map->priomap[id] = prio; return 0; } static struct cgroup_subsys_state * cgrp_css_alloc(struct cgroup_subsys_state *parent_css) { struct cgroup_subsys_state *css; css = kzalloc(sizeof(*css), GFP_KERNEL); if (!css) return ERR_PTR(-ENOMEM); return css; } static int cgrp_css_online(struct cgroup_subsys_state *css) { struct cgroup_subsys_state *parent_css = css->parent; struct net_device *dev; int ret = 0; if (css->id > NETPRIO_ID_MAX) return -ENOSPC; if (!parent_css) return 0; rtnl_lock(); /* * Inherit prios from the parent. As all prios are set during * onlining, there is no need to clear them on offline. */ for_each_netdev(&init_net, dev) { u32 prio = netprio_prio(parent_css, dev); ret = netprio_set_prio(css, dev, prio); if (ret) break; } rtnl_unlock(); return ret; } static void cgrp_css_free(struct cgroup_subsys_state *css) { kfree(css); } static u64 read_prioidx(struct cgroup_subsys_state *css, struct cftype *cft) { return css->id; } static int read_priomap(struct seq_file *sf, void *v) { struct net_device *dev; rcu_read_lock(); for_each_netdev_rcu(&init_net, dev) seq_printf(sf, "%s %u\n", dev->name, netprio_prio(seq_css(sf), dev)); rcu_read_unlock(); return 0; } static ssize_t write_priomap(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { char devname[IFNAMSIZ + 1]; struct net_device *dev; u32 prio; int ret; if (sscanf(buf, "%"__stringify(IFNAMSIZ)"s %u", devname, &prio) != 2) return -EINVAL; dev = dev_get_by_name(&init_net, devname); if (!dev) return -ENODEV; rtnl_lock(); ret = netprio_set_prio(of_css(of), dev, prio); rtnl_unlock(); dev_put(dev); return ret ?: nbytes; } static int update_netprio(const void *v, struct file *file, unsigned n) { struct socket *sock = sock_from_file(file); if (sock) sock_cgroup_set_prioidx(&sock->sk->sk_cgrp_data, (unsigned long)v); return 0; } static void net_prio_attach(struct cgroup_taskset *tset) { struct task_struct *p; struct cgroup_subsys_state *css; cgroup_taskset_for_each(p, css, tset) { void *v = (void *)(unsigned long)css->id; task_lock(p); iterate_fd(p->files, 0, update_netprio, v); task_unlock(p); } } static struct cftype ss_files[] = { { .name = "prioidx", .read_u64 = read_prioidx, }, { .name = "ifpriomap", .seq_show = read_priomap, .write = write_priomap, }, { } /* terminate */ }; struct cgroup_subsys net_prio_cgrp_subsys = { .css_alloc = cgrp_css_alloc, .css_online = cgrp_css_online, .css_free = cgrp_css_free, .attach = net_prio_attach, .legacy_cftypes = ss_files, }; static int netprio_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netprio_map *old; /* * Note this is called with rtnl_lock held so we have update side * protection on our rcu assignments */ switch (event) { case NETDEV_UNREGISTER: old = rtnl_dereference(dev->priomap); RCU_INIT_POINTER(dev->priomap, NULL); if (old) kfree_rcu(old, rcu); break; } return NOTIFY_DONE; } static struct notifier_block netprio_device_notifier = { .notifier_call = netprio_device_event }; static int __init init_cgroup_netprio(void) { register_netdevice_notifier(&netprio_device_notifier); return 0; } subsys_initcall(init_cgroup_netprio); |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 | // SPDX-License-Identifier: GPL-2.0 #include <linux/utsname.h> #include <net/cfg80211.h> #include "core.h" #include "rdev-ops.h" void cfg80211_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct device *pdev = wiphy_dev(wdev->wiphy); if (pdev->driver) strscpy(info->driver, pdev->driver->name, sizeof(info->driver)); else strscpy(info->driver, "N/A", sizeof(info->driver)); strscpy(info->version, init_utsname()->release, sizeof(info->version)); if (wdev->wiphy->fw_version[0]) strscpy(info->fw_version, wdev->wiphy->fw_version, sizeof(info->fw_version)); else strscpy(info->fw_version, "N/A", sizeof(info->fw_version)); strscpy(info->bus_info, dev_name(wiphy_dev(wdev->wiphy)), sizeof(info->bus_info)); } EXPORT_SYMBOL(cfg80211_get_drvinfo); |
| 2 5 2 4 5 5 5 5 4 5 5 5 5 3 1 3 3 2 3 5 5 5 5 5 5 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 7 5 3 3 8 6 6 2 6 4 6 6 6 6 6 6 1 6 6 6 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ #include <linux/mm.h> #include <linux/llist.h> #include <linux/bpf.h> #include <linux/irq_work.h> #include <linux/bpf_mem_alloc.h> #include <linux/memcontrol.h> #include <asm/local.h> /* Any context (including NMI) BPF specific memory allocator. * * Tracing BPF programs can attach to kprobe and fentry. Hence they * run in unknown context where calling plain kmalloc() might not be safe. * * Front-end kmalloc() with per-cpu per-bucket cache of free elements. * Refill this cache asynchronously from irq_work. * * CPU_0 buckets * 16 32 64 96 128 196 256 512 1024 2048 4096 * ... * CPU_N buckets * 16 32 64 96 128 196 256 512 1024 2048 4096 * * The buckets are prefilled at the start. * BPF programs always run with migration disabled. * It's safe to allocate from cache of the current cpu with irqs disabled. * Free-ing is always done into bucket of the current cpu as well. * irq_work trims extra free elements from buckets with kfree * and refills them with kmalloc, so global kmalloc logic takes care * of freeing objects allocated by one cpu and freed on another. * * Every allocated objected is padded with extra 8 bytes that contains * struct llist_node. */ #define LLIST_NODE_SZ sizeof(struct llist_node) #define BPF_MEM_ALLOC_SIZE_MAX 4096 /* similar to kmalloc, but sizeof == 8 bucket is gone */ static u8 size_index[24] __ro_after_init = { 3, /* 8 */ 3, /* 16 */ 4, /* 24 */ 4, /* 32 */ 5, /* 40 */ 5, /* 48 */ 5, /* 56 */ 5, /* 64 */ 1, /* 72 */ 1, /* 80 */ 1, /* 88 */ 1, /* 96 */ 6, /* 104 */ 6, /* 112 */ 6, /* 120 */ 6, /* 128 */ 2, /* 136 */ 2, /* 144 */ 2, /* 152 */ 2, /* 160 */ 2, /* 168 */ 2, /* 176 */ 2, /* 184 */ 2 /* 192 */ }; static int bpf_mem_cache_idx(size_t size) { if (!size || size > BPF_MEM_ALLOC_SIZE_MAX) return -1; if (size <= 192) return size_index[(size - 1) / 8] - 1; return fls(size - 1) - 2; } #define NUM_CACHES 11 struct bpf_mem_cache { /* per-cpu list of free objects of size 'unit_size'. * All accesses are done with interrupts disabled and 'active' counter * protection with __llist_add() and __llist_del_first(). */ struct llist_head free_llist; local_t active; /* Operations on the free_list from unit_alloc/unit_free/bpf_mem_refill * are sequenced by per-cpu 'active' counter. But unit_free() cannot * fail. When 'active' is busy the unit_free() will add an object to * free_llist_extra. */ struct llist_head free_llist_extra; struct irq_work refill_work; struct obj_cgroup *objcg; int unit_size; /* count of objects in free_llist */ int free_cnt; int low_watermark, high_watermark, batch; int percpu_size; bool draining; struct bpf_mem_cache *tgt; /* list of objects to be freed after RCU GP */ struct llist_head free_by_rcu; struct llist_node *free_by_rcu_tail; struct llist_head waiting_for_gp; struct llist_node *waiting_for_gp_tail; struct rcu_head rcu; atomic_t call_rcu_in_progress; struct llist_head free_llist_extra_rcu; /* list of objects to be freed after RCU tasks trace GP */ struct llist_head free_by_rcu_ttrace; struct llist_head waiting_for_gp_ttrace; struct rcu_head rcu_ttrace; atomic_t call_rcu_ttrace_in_progress; }; struct bpf_mem_caches { struct bpf_mem_cache cache[NUM_CACHES]; }; static const u16 sizes[NUM_CACHES] = {96, 192, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096}; static struct llist_node notrace *__llist_del_first(struct llist_head *head) { struct llist_node *entry, *next; entry = head->first; if (!entry) return NULL; next = entry->next; head->first = next; return entry; } static void *__alloc(struct bpf_mem_cache *c, int node, gfp_t flags) { if (c->percpu_size) { void __percpu **obj = kmalloc_node(c->percpu_size, flags, node); void __percpu *pptr = __alloc_percpu_gfp(c->unit_size, 8, flags); if (!obj || !pptr) { free_percpu(pptr); kfree(obj); return NULL; } obj[1] = pptr; return obj; } return kmalloc_node(c->unit_size, flags | __GFP_ZERO, node); } static struct mem_cgroup *get_memcg(const struct bpf_mem_cache *c) { #ifdef CONFIG_MEMCG if (c->objcg) return get_mem_cgroup_from_objcg(c->objcg); return root_mem_cgroup; #else return NULL; #endif } static void inc_active(struct bpf_mem_cache *c, unsigned long *flags) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) /* In RT irq_work runs in per-cpu kthread, so disable * interrupts to avoid preemption and interrupts and * reduce the chance of bpf prog executing on this cpu * when active counter is busy. */ local_irq_save(*flags); /* alloc_bulk runs from irq_work which will not preempt a bpf * program that does unit_alloc/unit_free since IRQs are * disabled there. There is no race to increment 'active' * counter. It protects free_llist from corruption in case NMI * bpf prog preempted this loop. */ WARN_ON_ONCE(local_inc_return(&c->active) != 1); } static void dec_active(struct bpf_mem_cache *c, unsigned long *flags) { local_dec(&c->active); if (IS_ENABLED(CONFIG_PREEMPT_RT)) local_irq_restore(*flags); } static void add_obj_to_free_list(struct bpf_mem_cache *c, void *obj) { unsigned long flags; inc_active(c, &flags); __llist_add(obj, &c->free_llist); c->free_cnt++; dec_active(c, &flags); } /* Mostly runs from irq_work except __init phase. */ static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node, bool atomic) { struct mem_cgroup *memcg = NULL, *old_memcg; gfp_t gfp; void *obj; int i; gfp = __GFP_NOWARN | __GFP_ACCOUNT; gfp |= atomic ? GFP_NOWAIT : GFP_KERNEL; for (i = 0; i < cnt; i++) { /* * For every 'c' llist_del_first(&c->free_by_rcu_ttrace); is * done only by one CPU == current CPU. Other CPUs might * llist_add() and llist_del_all() in parallel. */ obj = llist_del_first(&c->free_by_rcu_ttrace); if (!obj) break; add_obj_to_free_list(c, obj); } if (i >= cnt) return; for (; i < cnt; i++) { obj = llist_del_first(&c->waiting_for_gp_ttrace); if (!obj) break; add_obj_to_free_list(c, obj); } if (i >= cnt) return; memcg = get_memcg(c); old_memcg = set_active_memcg(memcg); for (; i < cnt; i++) { /* Allocate, but don't deplete atomic reserves that typical * GFP_ATOMIC would do. irq_work runs on this cpu and kmalloc * will allocate from the current numa node which is what we * want here. */ obj = __alloc(c, node, gfp); if (!obj) break; add_obj_to_free_list(c, obj); } set_active_memcg(old_memcg); mem_cgroup_put(memcg); } static void free_one(void *obj, bool percpu) { if (percpu) free_percpu(((void __percpu **)obj)[1]); kfree(obj); } static int free_all(struct llist_node *llnode, bool percpu) { struct llist_node *pos, *t; int cnt = 0; llist_for_each_safe(pos, t, llnode) { free_one(pos, percpu); cnt++; } return cnt; } static void __free_rcu(struct rcu_head *head) { struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu_ttrace); free_all(llist_del_all(&c->waiting_for_gp_ttrace), !!c->percpu_size); atomic_set(&c->call_rcu_ttrace_in_progress, 0); } static void __free_rcu_tasks_trace(struct rcu_head *head) { /* If RCU Tasks Trace grace period implies RCU grace period, * there is no need to invoke call_rcu(). */ if (rcu_trace_implies_rcu_gp()) __free_rcu(head); else call_rcu(head, __free_rcu); } static void enque_to_free(struct bpf_mem_cache *c, void *obj) { struct llist_node *llnode = obj; /* bpf_mem_cache is a per-cpu object. Freeing happens in irq_work. * Nothing races to add to free_by_rcu_ttrace list. */ llist_add(llnode, &c->free_by_rcu_ttrace); } static void do_call_rcu_ttrace(struct bpf_mem_cache *c) { struct llist_node *llnode, *t; if (atomic_xchg(&c->call_rcu_ttrace_in_progress, 1)) { if (unlikely(READ_ONCE(c->draining))) { llnode = llist_del_all(&c->free_by_rcu_ttrace); free_all(llnode, !!c->percpu_size); } return; } WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp_ttrace)); llist_for_each_safe(llnode, t, llist_del_all(&c->free_by_rcu_ttrace)) llist_add(llnode, &c->waiting_for_gp_ttrace); if (unlikely(READ_ONCE(c->draining))) { __free_rcu(&c->rcu_ttrace); return; } /* Use call_rcu_tasks_trace() to wait for sleepable progs to finish. * If RCU Tasks Trace grace period implies RCU grace period, free * these elements directly, else use call_rcu() to wait for normal * progs to finish and finally do free_one() on each element. */ call_rcu_tasks_trace(&c->rcu_ttrace, __free_rcu_tasks_trace); } static void free_bulk(struct bpf_mem_cache *c) { struct bpf_mem_cache *tgt = c->tgt; struct llist_node *llnode, *t; unsigned long flags; int cnt; WARN_ON_ONCE(tgt->unit_size != c->unit_size); WARN_ON_ONCE(tgt->percpu_size != c->percpu_size); do { inc_active(c, &flags); llnode = __llist_del_first(&c->free_llist); if (llnode) cnt = --c->free_cnt; else cnt = 0; dec_active(c, &flags); if (llnode) enque_to_free(tgt, llnode); } while (cnt > (c->high_watermark + c->low_watermark) / 2); /* and drain free_llist_extra */ llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra)) enque_to_free(tgt, llnode); do_call_rcu_ttrace(tgt); } static void __free_by_rcu(struct rcu_head *head) { struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu); struct bpf_mem_cache *tgt = c->tgt; struct llist_node *llnode; WARN_ON_ONCE(tgt->unit_size != c->unit_size); WARN_ON_ONCE(tgt->percpu_size != c->percpu_size); llnode = llist_del_all(&c->waiting_for_gp); if (!llnode) goto out; llist_add_batch(llnode, c->waiting_for_gp_tail, &tgt->free_by_rcu_ttrace); /* Objects went through regular RCU GP. Send them to RCU tasks trace */ do_call_rcu_ttrace(tgt); out: atomic_set(&c->call_rcu_in_progress, 0); } static void check_free_by_rcu(struct bpf_mem_cache *c) { struct llist_node *llnode, *t; unsigned long flags; /* drain free_llist_extra_rcu */ if (unlikely(!llist_empty(&c->free_llist_extra_rcu))) { inc_active(c, &flags); llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra_rcu)) if (__llist_add(llnode, &c->free_by_rcu)) c->free_by_rcu_tail = llnode; dec_active(c, &flags); } if (llist_empty(&c->free_by_rcu)) return; if (atomic_xchg(&c->call_rcu_in_progress, 1)) { /* * Instead of kmalloc-ing new rcu_head and triggering 10k * call_rcu() to hit rcutree.qhimark and force RCU to notice * the overload just ask RCU to hurry up. There could be many * objects in free_by_rcu list. * This hint reduces memory consumption for an artificial * benchmark from 2 Gbyte to 150 Mbyte. */ rcu_request_urgent_qs_task(current); return; } WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp)); inc_active(c, &flags); WRITE_ONCE(c->waiting_for_gp.first, __llist_del_all(&c->free_by_rcu)); c->waiting_for_gp_tail = c->free_by_rcu_tail; dec_active(c, &flags); if (unlikely(READ_ONCE(c->draining))) { free_all(llist_del_all(&c->waiting_for_gp), !!c->percpu_size); atomic_set(&c->call_rcu_in_progress, 0); } else { call_rcu_hurry(&c->rcu, __free_by_rcu); } } static void bpf_mem_refill(struct irq_work *work) { struct bpf_mem_cache *c = container_of(work, struct bpf_mem_cache, refill_work); int cnt; /* Racy access to free_cnt. It doesn't need to be 100% accurate */ cnt = c->free_cnt; if (cnt < c->low_watermark) /* irq_work runs on this cpu and kmalloc will allocate * from the current numa node which is what we want here. */ alloc_bulk(c, c->batch, NUMA_NO_NODE, true); else if (cnt > c->high_watermark) free_bulk(c); check_free_by_rcu(c); } static void notrace irq_work_raise(struct bpf_mem_cache *c) { irq_work_queue(&c->refill_work); } /* For typical bpf map case that uses bpf_mem_cache_alloc and single bucket * the freelist cache will be elem_size * 64 (or less) on each cpu. * * For bpf programs that don't have statically known allocation sizes and * assuming (low_mark + high_mark) / 2 as an average number of elements per * bucket and all buckets are used the total amount of memory in freelists * on each cpu will be: * 64*16 + 64*32 + 64*64 + 64*96 + 64*128 + 64*196 + 64*256 + 32*512 + 16*1024 + 8*2048 + 4*4096 * == ~ 116 Kbyte using below heuristic. * Initialized, but unused bpf allocator (not bpf map specific one) will * consume ~ 11 Kbyte per cpu. * Typical case will be between 11K and 116K closer to 11K. * bpf progs can and should share bpf_mem_cache when possible. * * Percpu allocation is typically rare. To avoid potential unnecessary large * memory consumption, set low_mark = 1 and high_mark = 3, resulting in c->batch = 1. */ static void init_refill_work(struct bpf_mem_cache *c) { init_irq_work(&c->refill_work, bpf_mem_refill); if (c->percpu_size) { c->low_watermark = 1; c->high_watermark = 3; } else if (c->unit_size <= 256) { c->low_watermark = 32; c->high_watermark = 96; } else { /* When page_size == 4k, order-0 cache will have low_mark == 2 * and high_mark == 6 with batch alloc of 3 individual pages at * a time. * 8k allocs and above low == 1, high == 3, batch == 1. */ c->low_watermark = max(32 * 256 / c->unit_size, 1); c->high_watermark = max(96 * 256 / c->unit_size, 3); } c->batch = max((c->high_watermark - c->low_watermark) / 4 * 3, 1); } static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu) { int cnt = 1; /* To avoid consuming memory, for non-percpu allocation, assume that * 1st run of bpf prog won't be doing more than 4 map_update_elem from * irq disabled region if unit size is less than or equal to 256. * For all other cases, let us just do one allocation. */ if (!c->percpu_size && c->unit_size <= 256) cnt = 4; alloc_bulk(c, cnt, cpu_to_node(cpu), false); } /* When size != 0 bpf_mem_cache for each cpu. * This is typical bpf hash map use case when all elements have equal size. * * When size == 0 allocate 11 bpf_mem_cache-s for each cpu, then rely on * kmalloc/kfree. Max allocation size is 4096 in this case. * This is bpf_dynptr and bpf_kptr use case. */ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu) { struct bpf_mem_caches *cc; struct bpf_mem_caches __percpu *pcc; struct bpf_mem_cache *c; struct bpf_mem_cache __percpu *pc; struct obj_cgroup *objcg = NULL; int cpu, i, unit_size, percpu_size = 0; if (percpu && size == 0) return -EINVAL; /* room for llist_node and per-cpu pointer */ if (percpu) percpu_size = LLIST_NODE_SZ + sizeof(void *); ma->percpu = percpu; if (size) { pc = __alloc_percpu_gfp(sizeof(*pc), 8, GFP_KERNEL); if (!pc) return -ENOMEM; if (!percpu) size += LLIST_NODE_SZ; /* room for llist_node */ unit_size = size; #ifdef CONFIG_MEMCG if (memcg_bpf_enabled()) objcg = get_obj_cgroup_from_current(); #endif ma->objcg = objcg; for_each_possible_cpu(cpu) { c = per_cpu_ptr(pc, cpu); c->unit_size = unit_size; c->objcg = objcg; c->percpu_size = percpu_size; c->tgt = c; init_refill_work(c); prefill_mem_cache(c, cpu); } ma->cache = pc; return 0; } pcc = __alloc_percpu_gfp(sizeof(*cc), 8, GFP_KERNEL); if (!pcc) return -ENOMEM; #ifdef CONFIG_MEMCG objcg = get_obj_cgroup_from_current(); #endif ma->objcg = objcg; for_each_possible_cpu(cpu) { cc = per_cpu_ptr(pcc, cpu); for (i = 0; i < NUM_CACHES; i++) { c = &cc->cache[i]; c->unit_size = sizes[i]; c->objcg = objcg; c->percpu_size = percpu_size; c->tgt = c; init_refill_work(c); prefill_mem_cache(c, cpu); } } ma->caches = pcc; return 0; } int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg) { struct bpf_mem_caches __percpu *pcc; pcc = __alloc_percpu_gfp(sizeof(struct bpf_mem_caches), 8, GFP_KERNEL); if (!pcc) return -ENOMEM; ma->caches = pcc; ma->objcg = objcg; ma->percpu = true; return 0; } int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size) { struct bpf_mem_caches *cc; struct bpf_mem_caches __percpu *pcc; int cpu, i, unit_size, percpu_size; struct obj_cgroup *objcg; struct bpf_mem_cache *c; i = bpf_mem_cache_idx(size); if (i < 0) return -EINVAL; /* room for llist_node and per-cpu pointer */ percpu_size = LLIST_NODE_SZ + sizeof(void *); unit_size = sizes[i]; objcg = ma->objcg; pcc = ma->caches; for_each_possible_cpu(cpu) { cc = per_cpu_ptr(pcc, cpu); c = &cc->cache[i]; if (c->unit_size) break; c->unit_size = unit_size; c->objcg = objcg; c->percpu_size = percpu_size; c->tgt = c; init_refill_work(c); prefill_mem_cache(c, cpu); } return 0; } static void drain_mem_cache(struct bpf_mem_cache *c) { bool percpu = !!c->percpu_size; /* No progs are using this bpf_mem_cache, but htab_map_free() called * bpf_mem_cache_free() for all remaining elements and they can be in * free_by_rcu_ttrace or in waiting_for_gp_ttrace lists, so drain those lists now. * * Except for waiting_for_gp_ttrace list, there are no concurrent operations * on these lists, so it is safe to use __llist_del_all(). */ free_all(llist_del_all(&c->free_by_rcu_ttrace), percpu); free_all(llist_del_all(&c->waiting_for_gp_ttrace), percpu); free_all(__llist_del_all(&c->free_llist), percpu); free_all(__llist_del_all(&c->free_llist_extra), percpu); free_all(__llist_del_all(&c->free_by_rcu), percpu); free_all(__llist_del_all(&c->free_llist_extra_rcu), percpu); free_all(llist_del_all(&c->waiting_for_gp), percpu); } static void check_mem_cache(struct bpf_mem_cache *c) { WARN_ON_ONCE(!llist_empty(&c->free_by_rcu_ttrace)); WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp_ttrace)); WARN_ON_ONCE(!llist_empty(&c->free_llist)); WARN_ON_ONCE(!llist_empty(&c->free_llist_extra)); WARN_ON_ONCE(!llist_empty(&c->free_by_rcu)); WARN_ON_ONCE(!llist_empty(&c->free_llist_extra_rcu)); WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp)); } static void check_leaked_objs(struct bpf_mem_alloc *ma) { struct bpf_mem_caches *cc; struct bpf_mem_cache *c; int cpu, i; if (ma->cache) { for_each_possible_cpu(cpu) { c = per_cpu_ptr(ma->cache, cpu); check_mem_cache(c); } } if (ma->caches) { for_each_possible_cpu(cpu) { cc = per_cpu_ptr(ma->caches, cpu); for (i = 0; i < NUM_CACHES; i++) { c = &cc->cache[i]; check_mem_cache(c); } } } } static void free_mem_alloc_no_barrier(struct bpf_mem_alloc *ma) { check_leaked_objs(ma); free_percpu(ma->cache); free_percpu(ma->caches); ma->cache = NULL; ma->caches = NULL; } static void free_mem_alloc(struct bpf_mem_alloc *ma) { /* waiting_for_gp[_ttrace] lists were drained, but RCU callbacks * might still execute. Wait for them. * * rcu_barrier_tasks_trace() doesn't imply synchronize_rcu_tasks_trace(), * but rcu_barrier_tasks_trace() and rcu_barrier() below are only used * to wait for the pending __free_rcu_tasks_trace() and __free_rcu(), * so if call_rcu(head, __free_rcu) is skipped due to * rcu_trace_implies_rcu_gp(), it will be OK to skip rcu_barrier() by * using rcu_trace_implies_rcu_gp() as well. */ rcu_barrier(); /* wait for __free_by_rcu */ rcu_barrier_tasks_trace(); /* wait for __free_rcu */ if (!rcu_trace_implies_rcu_gp()) rcu_barrier(); free_mem_alloc_no_barrier(ma); } static void free_mem_alloc_deferred(struct work_struct *work) { struct bpf_mem_alloc *ma = container_of(work, struct bpf_mem_alloc, work); free_mem_alloc(ma); kfree(ma); } static void destroy_mem_alloc(struct bpf_mem_alloc *ma, int rcu_in_progress) { struct bpf_mem_alloc *copy; if (!rcu_in_progress) { /* Fast path. No callbacks are pending, hence no need to do * rcu_barrier-s. */ free_mem_alloc_no_barrier(ma); return; } copy = kmemdup(ma, sizeof(*ma), GFP_KERNEL); if (!copy) { /* Slow path with inline barrier-s */ free_mem_alloc(ma); return; } /* Defer barriers into worker to let the rest of map memory to be freed */ memset(ma, 0, sizeof(*ma)); INIT_WORK(©->work, free_mem_alloc_deferred); queue_work(system_unbound_wq, ©->work); } void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma) { struct bpf_mem_caches *cc; struct bpf_mem_cache *c; int cpu, i, rcu_in_progress; if (ma->cache) { rcu_in_progress = 0; for_each_possible_cpu(cpu) { c = per_cpu_ptr(ma->cache, cpu); WRITE_ONCE(c->draining, true); irq_work_sync(&c->refill_work); drain_mem_cache(c); rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress); rcu_in_progress += atomic_read(&c->call_rcu_in_progress); } obj_cgroup_put(ma->objcg); destroy_mem_alloc(ma, rcu_in_progress); } if (ma->caches) { rcu_in_progress = 0; for_each_possible_cpu(cpu) { cc = per_cpu_ptr(ma->caches, cpu); for (i = 0; i < NUM_CACHES; i++) { c = &cc->cache[i]; WRITE_ONCE(c->draining, true); irq_work_sync(&c->refill_work); drain_mem_cache(c); rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress); rcu_in_progress += atomic_read(&c->call_rcu_in_progress); } } obj_cgroup_put(ma->objcg); destroy_mem_alloc(ma, rcu_in_progress); } } /* notrace is necessary here and in other functions to make sure * bpf programs cannot attach to them and cause llist corruptions. */ static void notrace *unit_alloc(struct bpf_mem_cache *c) { struct llist_node *llnode = NULL; unsigned long flags; int cnt = 0; /* Disable irqs to prevent the following race for majority of prog types: * prog_A * bpf_mem_alloc * preemption or irq -> prog_B * bpf_mem_alloc * * but prog_B could be a perf_event NMI prog. * Use per-cpu 'active' counter to order free_list access between * unit_alloc/unit_free/bpf_mem_refill. */ local_irq_save(flags); if (local_inc_return(&c->active) == 1) { llnode = __llist_del_first(&c->free_llist); if (llnode) { cnt = --c->free_cnt; *(struct bpf_mem_cache **)llnode = c; } } local_dec(&c->active); WARN_ON(cnt < 0); if (cnt < c->low_watermark) irq_work_raise(c); /* Enable IRQ after the enqueue of irq work completes, so irq work * will run after IRQ is enabled and free_llist may be refilled by * irq work before other task preempts current task. */ local_irq_restore(flags); return llnode; } /* Though 'ptr' object could have been allocated on a different cpu * add it to the free_llist of the current cpu. * Let kfree() logic deal with it when it's later called from irq_work. */ static void notrace unit_free(struct bpf_mem_cache *c, void *ptr) { struct llist_node *llnode = ptr - LLIST_NODE_SZ; unsigned long flags; int cnt = 0; BUILD_BUG_ON(LLIST_NODE_SZ > 8); /* * Remember bpf_mem_cache that allocated this object. * The hint is not accurate. */ c->tgt = *(struct bpf_mem_cache **)llnode; local_irq_save(flags); if (local_inc_return(&c->active) == 1) { __llist_add(llnode, &c->free_llist); cnt = ++c->free_cnt; } else { /* unit_free() cannot fail. Therefore add an object to atomic * llist. free_bulk() will drain it. Though free_llist_extra is * a per-cpu list we have to use atomic llist_add here, since * it also can be interrupted by bpf nmi prog that does another * unit_free() into the same free_llist_extra. */ llist_add(llnode, &c->free_llist_extra); } local_dec(&c->active); if (cnt > c->high_watermark) /* free few objects from current cpu into global kmalloc pool */ irq_work_raise(c); /* Enable IRQ after irq_work_raise() completes, otherwise when current * task is preempted by task which does unit_alloc(), unit_alloc() may * return NULL unexpectedly because irq work is already pending but can * not been triggered and free_llist can not be refilled timely. */ local_irq_restore(flags); } static void notrace unit_free_rcu(struct bpf_mem_cache *c, void *ptr) { struct llist_node *llnode = ptr - LLIST_NODE_SZ; unsigned long flags; c->tgt = *(struct bpf_mem_cache **)llnode; local_irq_save(flags); if (local_inc_return(&c->active) == 1) { if (__llist_add(llnode, &c->free_by_rcu)) c->free_by_rcu_tail = llnode; } else { llist_add(llnode, &c->free_llist_extra_rcu); } local_dec(&c->active); if (!atomic_read(&c->call_rcu_in_progress)) irq_work_raise(c); local_irq_restore(flags); } /* Called from BPF program or from sys_bpf syscall. * In both cases migration is disabled. */ void notrace *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size) { int idx; void *ret; if (!size) return NULL; if (!ma->percpu) size += LLIST_NODE_SZ; idx = bpf_mem_cache_idx(size); if (idx < 0) return NULL; ret = unit_alloc(this_cpu_ptr(ma->caches)->cache + idx); return !ret ? NULL : ret + LLIST_NODE_SZ; } void notrace bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr) { struct bpf_mem_cache *c; int idx; if (!ptr) return; c = *(void **)(ptr - LLIST_NODE_SZ); idx = bpf_mem_cache_idx(c->unit_size); if (WARN_ON_ONCE(idx < 0)) return; unit_free(this_cpu_ptr(ma->caches)->cache + idx, ptr); } void notrace bpf_mem_free_rcu(struct bpf_mem_alloc *ma, void *ptr) { struct bpf_mem_cache *c; int idx; if (!ptr) return; c = *(void **)(ptr - LLIST_NODE_SZ); idx = bpf_mem_cache_idx(c->unit_size); if (WARN_ON_ONCE(idx < 0)) return; unit_free_rcu(this_cpu_ptr(ma->caches)->cache + idx, ptr); } void notrace *bpf_mem_cache_alloc(struct bpf_mem_alloc *ma) { void *ret; ret = unit_alloc(this_cpu_ptr(ma->cache)); return !ret ? NULL : ret + LLIST_NODE_SZ; } void notrace bpf_mem_cache_free(struct bpf_mem_alloc *ma, void *ptr) { if (!ptr) return; unit_free(this_cpu_ptr(ma->cache), ptr); } void notrace bpf_mem_cache_free_rcu(struct bpf_mem_alloc *ma, void *ptr) { if (!ptr) return; unit_free_rcu(this_cpu_ptr(ma->cache), ptr); } /* Directly does a kfree() without putting 'ptr' back to the free_llist * for reuse and without waiting for a rcu_tasks_trace gp. * The caller must first go through the rcu_tasks_trace gp for 'ptr' * before calling bpf_mem_cache_raw_free(). * It could be used when the rcu_tasks_trace callback does not have * a hold on the original bpf_mem_alloc object that allocated the * 'ptr'. This should only be used in the uncommon code path. * Otherwise, the bpf_mem_alloc's free_llist cannot be refilled * and may affect performance. */ void bpf_mem_cache_raw_free(void *ptr) { if (!ptr) return; kfree(ptr - LLIST_NODE_SZ); } /* When flags == GFP_KERNEL, it signals that the caller will not cause * deadlock when using kmalloc. bpf_mem_cache_alloc_flags() will use * kmalloc if the free_llist is empty. */ void notrace *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags) { struct bpf_mem_cache *c; void *ret; c = this_cpu_ptr(ma->cache); ret = unit_alloc(c); if (!ret && flags == GFP_KERNEL) { struct mem_cgroup *memcg, *old_memcg; memcg = get_memcg(c); old_memcg = set_active_memcg(memcg); ret = __alloc(c, NUMA_NO_NODE, GFP_KERNEL | __GFP_NOWARN | __GFP_ACCOUNT); if (ret) *(struct bpf_mem_cache **)ret = c; set_active_memcg(old_memcg); mem_cgroup_put(memcg); } return !ret ? NULL : ret + LLIST_NODE_SZ; } int bpf_mem_alloc_check_size(bool percpu, size_t size) { /* The size of percpu allocation doesn't have LLIST_NODE_SZ overhead */ if ((percpu && size > BPF_MEM_ALLOC_SIZE_MAX) || (!percpu && size > BPF_MEM_ALLOC_SIZE_MAX - LLIST_NODE_SZ)) return -E2BIG; return 0; } |
| 5 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/net/sunrpc/stats.c * * procfs-based user access to generic RPC statistics. The stats files * reside in /proc/net/rpc. * * The read routines assume that the buffer passed in is just big enough. * If you implement an RPC service that has its own stats routine which * appends the generic RPC stats, make sure you don't exceed the PAGE_SIZE * limit. * * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de> */ #include <linux/module.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/svcsock.h> #include <linux/sunrpc/metrics.h> #include <linux/rcupdate.h> #include <trace/events/sunrpc.h> #include "netns.h" #define RPCDBG_FACILITY RPCDBG_MISC /* * Get RPC client stats */ static int rpc_proc_show(struct seq_file *seq, void *v) { const struct rpc_stat *statp = seq->private; const struct rpc_program *prog = statp->program; unsigned int i, j; seq_printf(seq, "net %u %u %u %u\n", statp->netcnt, statp->netudpcnt, statp->nettcpcnt, statp->nettcpconn); seq_printf(seq, "rpc %u %u %u\n", statp->rpccnt, statp->rpcretrans, statp->rpcauthrefresh); for (i = 0; i < prog->nrvers; i++) { const struct rpc_version *vers = prog->version[i]; if (!vers) continue; seq_printf(seq, "proc%u %u", vers->number, vers->nrprocs); for (j = 0; j < vers->nrprocs; j++) seq_printf(seq, " %u", vers->counts[j]); seq_putc(seq, '\n'); } return 0; } static int rpc_proc_open(struct inode *inode, struct file *file) { return single_open(file, rpc_proc_show, pde_data(inode)); } static const struct proc_ops rpc_proc_ops = { .proc_open = rpc_proc_open, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = single_release, }; /* * Get RPC server stats */ void svc_seq_show(struct seq_file *seq, const struct svc_stat *statp) { const struct svc_program *prog = statp->program; const struct svc_version *vers; unsigned int i, j, k; unsigned long count; seq_printf(seq, "net %u %u %u %u\n", statp->netcnt, statp->netudpcnt, statp->nettcpcnt, statp->nettcpconn); seq_printf(seq, "rpc %u %u %u %u %u\n", statp->rpccnt, statp->rpcbadfmt+statp->rpcbadauth+statp->rpcbadclnt, statp->rpcbadfmt, statp->rpcbadauth, statp->rpcbadclnt); for (i = 0; i < prog->pg_nvers; i++) { vers = prog->pg_vers[i]; if (!vers) continue; seq_printf(seq, "proc%d %u", i, vers->vs_nproc); for (j = 0; j < vers->vs_nproc; j++) { count = 0; for_each_possible_cpu(k) count += per_cpu(vers->vs_count[j], k); seq_printf(seq, " %lu", count); } seq_putc(seq, '\n'); } } EXPORT_SYMBOL_GPL(svc_seq_show); /** * rpc_alloc_iostats - allocate an rpc_iostats structure * @clnt: RPC program, version, and xprt * */ struct rpc_iostats *rpc_alloc_iostats(struct rpc_clnt *clnt) { struct rpc_iostats *stats; int i; stats = kcalloc(clnt->cl_maxproc, sizeof(*stats), GFP_KERNEL); if (stats) { for (i = 0; i < clnt->cl_maxproc; i++) spin_lock_init(&stats[i].om_lock); } return stats; } EXPORT_SYMBOL_GPL(rpc_alloc_iostats); /** * rpc_free_iostats - release an rpc_iostats structure * @stats: doomed rpc_iostats structure * */ void rpc_free_iostats(struct rpc_iostats *stats) { kfree(stats); } EXPORT_SYMBOL_GPL(rpc_free_iostats); /** * rpc_count_iostats_metrics - tally up per-task stats * @task: completed rpc_task * @op_metrics: stat structure for OP that will accumulate stats from @task */ void rpc_count_iostats_metrics(const struct rpc_task *task, struct rpc_iostats *op_metrics) { struct rpc_rqst *req = task->tk_rqstp; ktime_t backlog, execute, now; if (!op_metrics || !req) return; now = ktime_get(); spin_lock(&op_metrics->om_lock); op_metrics->om_ops++; /* kernel API: om_ops must never become larger than om_ntrans */ op_metrics->om_ntrans += max(req->rq_ntrans, 1); op_metrics->om_timeouts += task->tk_timeouts; op_metrics->om_bytes_sent += req->rq_xmit_bytes_sent; op_metrics->om_bytes_recv += req->rq_reply_bytes_recvd; backlog = 0; if (ktime_to_ns(req->rq_xtime)) { backlog = ktime_sub(req->rq_xtime, task->tk_start); op_metrics->om_queue = ktime_add(op_metrics->om_queue, backlog); } op_metrics->om_rtt = ktime_add(op_metrics->om_rtt, req->rq_rtt); execute = ktime_sub(now, task->tk_start); op_metrics->om_execute = ktime_add(op_metrics->om_execute, execute); if (task->tk_status < 0) op_metrics->om_error_status++; spin_unlock(&op_metrics->om_lock); trace_rpc_stats_latency(req->rq_task, backlog, req->rq_rtt, execute); } EXPORT_SYMBOL_GPL(rpc_count_iostats_metrics); /** * rpc_count_iostats - tally up per-task stats * @task: completed rpc_task * @stats: array of stat structures * * Uses the statidx from @task */ void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats) { rpc_count_iostats_metrics(task, &stats[task->tk_msg.rpc_proc->p_statidx]); } EXPORT_SYMBOL_GPL(rpc_count_iostats); static void _print_name(struct seq_file *seq, unsigned int op, const struct rpc_procinfo *procs) { if (procs[op].p_name) seq_printf(seq, "\t%12s: ", procs[op].p_name); else if (op == 0) seq_printf(seq, "\t NULL: "); else seq_printf(seq, "\t%12u: ", op); } static void _add_rpc_iostats(struct rpc_iostats *a, struct rpc_iostats *b) { a->om_ops += b->om_ops; a->om_ntrans += b->om_ntrans; a->om_timeouts += b->om_timeouts; a->om_bytes_sent += b->om_bytes_sent; a->om_bytes_recv += b->om_bytes_recv; a->om_queue = ktime_add(a->om_queue, b->om_queue); a->om_rtt = ktime_add(a->om_rtt, b->om_rtt); a->om_execute = ktime_add(a->om_execute, b->om_execute); a->om_error_status += b->om_error_status; } static void _print_rpc_iostats(struct seq_file *seq, struct rpc_iostats *stats, int op, const struct rpc_procinfo *procs) { _print_name(seq, op, procs); seq_printf(seq, "%lu %lu %lu %llu %llu %llu %llu %llu %lu\n", stats->om_ops, stats->om_ntrans, stats->om_timeouts, stats->om_bytes_sent, stats->om_bytes_recv, ktime_to_ms(stats->om_queue), ktime_to_ms(stats->om_rtt), ktime_to_ms(stats->om_execute), stats->om_error_status); } static int do_print_stats(struct rpc_clnt *clnt, struct rpc_xprt *xprt, void *seqv) { struct seq_file *seq = seqv; xprt->ops->print_stats(xprt, seq); return 0; } void rpc_clnt_show_stats(struct seq_file *seq, struct rpc_clnt *clnt) { unsigned int op, maxproc = clnt->cl_maxproc; if (!clnt->cl_metrics) return; seq_printf(seq, "\tRPC iostats version: %s ", RPC_IOSTATS_VERS); seq_printf(seq, "p/v: %u/%u (%s)\n", clnt->cl_prog, clnt->cl_vers, clnt->cl_program->name); rpc_clnt_iterate_for_each_xprt(clnt, do_print_stats, seq); seq_printf(seq, "\tper-op statistics\n"); for (op = 0; op < maxproc; op++) { struct rpc_iostats stats = {}; struct rpc_clnt *next = clnt; do { _add_rpc_iostats(&stats, &next->cl_metrics[op]); if (next == next->cl_parent) break; next = next->cl_parent; } while (next); _print_rpc_iostats(seq, &stats, op, clnt->cl_procinfo); } } EXPORT_SYMBOL_GPL(rpc_clnt_show_stats); /* * Register/unregister RPC proc files */ static inline struct proc_dir_entry * do_register(struct net *net, const char *name, void *data, const struct proc_ops *proc_ops) { struct sunrpc_net *sn; dprintk("RPC: registering /proc/net/rpc/%s\n", name); sn = net_generic(net, sunrpc_net_id); return proc_create_data(name, 0, sn->proc_net_rpc, proc_ops, data); } struct proc_dir_entry * rpc_proc_register(struct net *net, struct rpc_stat *statp) { return do_register(net, statp->program->name, statp, &rpc_proc_ops); } EXPORT_SYMBOL_GPL(rpc_proc_register); void rpc_proc_unregister(struct net *net, const char *name) { struct sunrpc_net *sn; sn = net_generic(net, sunrpc_net_id); remove_proc_entry(name, sn->proc_net_rpc); } EXPORT_SYMBOL_GPL(rpc_proc_unregister); struct proc_dir_entry * svc_proc_register(struct net *net, struct svc_stat *statp, const struct proc_ops *proc_ops) { return do_register(net, statp->program->pg_name, net, proc_ops); } EXPORT_SYMBOL_GPL(svc_proc_register); void svc_proc_unregister(struct net *net, const char *name) { struct sunrpc_net *sn; sn = net_generic(net, sunrpc_net_id); remove_proc_entry(name, sn->proc_net_rpc); } EXPORT_SYMBOL_GPL(svc_proc_unregister); int rpc_proc_init(struct net *net) { struct sunrpc_net *sn; dprintk("RPC: registering /proc/net/rpc\n"); sn = net_generic(net, sunrpc_net_id); sn->proc_net_rpc = proc_mkdir("rpc", net->proc_net); if (sn->proc_net_rpc == NULL) return -ENOMEM; return 0; } void rpc_proc_exit(struct net *net) { dprintk("RPC: unregistering /proc/net/rpc\n"); remove_proc_entry("rpc", net->proc_net); } |
| 24 33 22 3 2 4 18 30 3 3 12 12 11 1 3 3 8 1 5 5 5 11 11 9 3 7 5 9 2 13 10 4 2 2 13 13 3 11 13 13 5 5 1 4 1 2 7 1 4 1 1 2 1 2 2 2 2 2 6 2 1 5 1 3 8 1 2 6 1 21 5 1 1 6 4 1 1 1 1 74 42 32 3 2 1 2 1 1 1 1 130 1 5 1 2 1 1 1 1 1 1 1 65 64 1 165 17 148 13 13 1 1 1 15 15 2 14 15 2 14 2 2 13 10 1 9 9 5 5 3 1 1 1 1 1 1 1 1 1 1 5 5 1 5 1 3 11 2 1 8 1 1 3 1 3 5 10 11 11 10 11 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 | // SPDX-License-Identifier: GPL-2.0-only /* * net/dccp/proto.c * * An implementation of the DCCP protocol * Arnaldo Carvalho de Melo <acme@conectiva.com.br> */ #include <linux/dccp.h> #include <linux/module.h> #include <linux/types.h> #include <linux/sched.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/in.h> #include <linux/if_arp.h> #include <linux/init.h> #include <linux/random.h> #include <linux/slab.h> #include <net/checksum.h> #include <net/inet_sock.h> #include <net/inet_common.h> #include <net/sock.h> #include <net/xfrm.h> #include <asm/ioctls.h> #include <linux/spinlock.h> #include <linux/timer.h> #include <linux/delay.h> #include <linux/poll.h> #include "ccid.h" #include "dccp.h" #include "feat.h" #define CREATE_TRACE_POINTS #include "trace.h" DEFINE_SNMP_STAT(struct dccp_mib, dccp_statistics) __read_mostly; EXPORT_SYMBOL_GPL(dccp_statistics); DEFINE_PER_CPU(unsigned int, dccp_orphan_count); EXPORT_PER_CPU_SYMBOL_GPL(dccp_orphan_count); struct inet_hashinfo dccp_hashinfo; EXPORT_SYMBOL_GPL(dccp_hashinfo); /* the maximum queue length for tx in packets. 0 is no limit */ int sysctl_dccp_tx_qlen __read_mostly = 5; #ifdef CONFIG_IP_DCCP_DEBUG static const char *dccp_state_name(const int state) { static const char *const dccp_state_names[] = { [DCCP_OPEN] = "OPEN", [DCCP_REQUESTING] = "REQUESTING", [DCCP_PARTOPEN] = "PARTOPEN", [DCCP_LISTEN] = "LISTEN", [DCCP_RESPOND] = "RESPOND", [DCCP_CLOSING] = "CLOSING", [DCCP_ACTIVE_CLOSEREQ] = "CLOSEREQ", [DCCP_PASSIVE_CLOSE] = "PASSIVE_CLOSE", [DCCP_PASSIVE_CLOSEREQ] = "PASSIVE_CLOSEREQ", [DCCP_TIME_WAIT] = "TIME_WAIT", [DCCP_CLOSED] = "CLOSED", }; if (state >= DCCP_MAX_STATES) return "INVALID STATE!"; else return dccp_state_names[state]; } #endif void dccp_set_state(struct sock *sk, const int state) { const int oldstate = sk->sk_state; dccp_pr_debug("%s(%p) %s --> %s\n", dccp_role(sk), sk, dccp_state_name(oldstate), dccp_state_name(state)); WARN_ON(state == oldstate); switch (state) { case DCCP_OPEN: if (oldstate != DCCP_OPEN) DCCP_INC_STATS(DCCP_MIB_CURRESTAB); /* Client retransmits all Confirm options until entering OPEN */ if (oldstate == DCCP_PARTOPEN) dccp_feat_list_purge(&dccp_sk(sk)->dccps_featneg); break; case DCCP_CLOSED: if (oldstate == DCCP_OPEN || oldstate == DCCP_ACTIVE_CLOSEREQ || oldstate == DCCP_CLOSING) DCCP_INC_STATS(DCCP_MIB_ESTABRESETS); sk->sk_prot->unhash(sk); if (inet_csk(sk)->icsk_bind_hash != NULL && !(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) inet_put_port(sk); fallthrough; default: if (oldstate == DCCP_OPEN) DCCP_DEC_STATS(DCCP_MIB_CURRESTAB); } /* Change state AFTER socket is unhashed to avoid closed * socket sitting in hash tables. */ inet_sk_set_state(sk, state); } EXPORT_SYMBOL_GPL(dccp_set_state); static void dccp_finish_passive_close(struct sock *sk) { switch (sk->sk_state) { case DCCP_PASSIVE_CLOSE: /* Node (client or server) has received Close packet. */ dccp_send_reset(sk, DCCP_RESET_CODE_CLOSED); dccp_set_state(sk, DCCP_CLOSED); break; case DCCP_PASSIVE_CLOSEREQ: /* * Client received CloseReq. We set the `active' flag so that * dccp_send_close() retransmits the Close as per RFC 4340, 8.3. */ dccp_send_close(sk, 1); dccp_set_state(sk, DCCP_CLOSING); } } void dccp_done(struct sock *sk) { dccp_set_state(sk, DCCP_CLOSED); dccp_clear_xmit_timers(sk); sk->sk_shutdown = SHUTDOWN_MASK; if (!sock_flag(sk, SOCK_DEAD)) sk->sk_state_change(sk); else inet_csk_destroy_sock(sk); } EXPORT_SYMBOL_GPL(dccp_done); const char *dccp_packet_name(const int type) { static const char *const dccp_packet_names[] = { [DCCP_PKT_REQUEST] = "REQUEST", [DCCP_PKT_RESPONSE] = "RESPONSE", [DCCP_PKT_DATA] = "DATA", [DCCP_PKT_ACK] = "ACK", [DCCP_PKT_DATAACK] = "DATAACK", [DCCP_PKT_CLOSEREQ] = "CLOSEREQ", [DCCP_PKT_CLOSE] = "CLOSE", [DCCP_PKT_RESET] = "RESET", [DCCP_PKT_SYNC] = "SYNC", [DCCP_PKT_SYNCACK] = "SYNCACK", }; if (type >= DCCP_NR_PKT_TYPES) return "INVALID"; else return dccp_packet_names[type]; } EXPORT_SYMBOL_GPL(dccp_packet_name); void dccp_destruct_common(struct sock *sk) { struct dccp_sock *dp = dccp_sk(sk); ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk); dp->dccps_hc_tx_ccid = NULL; } EXPORT_SYMBOL_GPL(dccp_destruct_common); static void dccp_sk_destruct(struct sock *sk) { dccp_destruct_common(sk); inet_sock_destruct(sk); } int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized) { struct dccp_sock *dp = dccp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); pr_warn_once("DCCP is deprecated and scheduled to be removed in 2025, " "please contact the netdev mailing list\n"); icsk->icsk_rto = DCCP_TIMEOUT_INIT; icsk->icsk_syn_retries = sysctl_dccp_request_retries; sk->sk_state = DCCP_CLOSED; sk->sk_write_space = dccp_write_space; sk->sk_destruct = dccp_sk_destruct; icsk->icsk_sync_mss = dccp_sync_mss; dp->dccps_mss_cache = 536; dp->dccps_rate_last = jiffies; dp->dccps_role = DCCP_ROLE_UNDEFINED; dp->dccps_service = DCCP_SERVICE_CODE_IS_ABSENT; dp->dccps_tx_qlen = sysctl_dccp_tx_qlen; dccp_init_xmit_timers(sk); INIT_LIST_HEAD(&dp->dccps_featneg); /* control socket doesn't need feat nego */ if (likely(ctl_sock_initialized)) return dccp_feat_init(sk); return 0; } EXPORT_SYMBOL_GPL(dccp_init_sock); void dccp_destroy_sock(struct sock *sk) { struct dccp_sock *dp = dccp_sk(sk); __skb_queue_purge(&sk->sk_write_queue); if (sk->sk_send_head != NULL) { kfree_skb(sk->sk_send_head); sk->sk_send_head = NULL; } /* Clean up a referenced DCCP bind bucket. */ if (inet_csk(sk)->icsk_bind_hash != NULL) inet_put_port(sk); kfree(dp->dccps_service_list); dp->dccps_service_list = NULL; if (dp->dccps_hc_rx_ackvec != NULL) { dccp_ackvec_free(dp->dccps_hc_rx_ackvec); dp->dccps_hc_rx_ackvec = NULL; } ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk); dp->dccps_hc_rx_ccid = NULL; /* clean up feature negotiation state */ dccp_feat_list_purge(&dp->dccps_featneg); } EXPORT_SYMBOL_GPL(dccp_destroy_sock); static inline int dccp_need_reset(int state) { return state != DCCP_CLOSED && state != DCCP_LISTEN && state != DCCP_REQUESTING; } int dccp_disconnect(struct sock *sk, int flags) { struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet = inet_sk(sk); struct dccp_sock *dp = dccp_sk(sk); const int old_state = sk->sk_state; if (old_state != DCCP_CLOSED) dccp_set_state(sk, DCCP_CLOSED); /* * This corresponds to the ABORT function of RFC793, sec. 3.8 * TCP uses a RST segment, DCCP a Reset packet with Code 2, "Aborted". */ if (old_state == DCCP_LISTEN) { inet_csk_listen_stop(sk); } else if (dccp_need_reset(old_state)) { dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED); sk->sk_err = ECONNRESET; } else if (old_state == DCCP_REQUESTING) sk->sk_err = ECONNRESET; dccp_clear_xmit_timers(sk); ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk); dp->dccps_hc_rx_ccid = NULL; __skb_queue_purge(&sk->sk_receive_queue); __skb_queue_purge(&sk->sk_write_queue); if (sk->sk_send_head != NULL) { __kfree_skb(sk->sk_send_head); sk->sk_send_head = NULL; } inet->inet_dport = 0; inet_bhash2_reset_saddr(sk); sk->sk_shutdown = 0; sock_reset_flag(sk, SOCK_DONE); icsk->icsk_backoff = 0; inet_csk_delack_init(sk); __sk_dst_reset(sk); WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); sk_error_report(sk); return 0; } EXPORT_SYMBOL_GPL(dccp_disconnect); /* * Wait for a DCCP event. * * Note that we don't need to lock the socket, as the upper poll layers * take care of normal races (between the test and the event) and we don't * go look at any of the socket buffers directly. */ __poll_t dccp_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; __poll_t mask; u8 shutdown; int state; sock_poll_wait(file, sock, wait); state = inet_sk_state_load(sk); if (state == DCCP_LISTEN) return inet_csk_listen_poll(sk); /* Socket is not locked. We are protected from async events by poll logic and correct handling of state changes made by another threads is impossible in any case. */ mask = 0; if (READ_ONCE(sk->sk_err)) mask = EPOLLERR; shutdown = READ_ONCE(sk->sk_shutdown); if (shutdown == SHUTDOWN_MASK || state == DCCP_CLOSED) mask |= EPOLLHUP; if (shutdown & RCV_SHUTDOWN) mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; /* Connected? */ if ((1 << state) & ~(DCCPF_REQUESTING | DCCPF_RESPOND)) { if (atomic_read(&sk->sk_rmem_alloc) > 0) mask |= EPOLLIN | EPOLLRDNORM; if (!(shutdown & SEND_SHUTDOWN)) { if (sk_stream_is_writeable(sk)) { mask |= EPOLLOUT | EPOLLWRNORM; } else { /* send SIGIO later */ sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); /* Race breaker. If space is freed after * wspace test but before the flags are set, * IO signal will be lost. */ if (sk_stream_is_writeable(sk)) mask |= EPOLLOUT | EPOLLWRNORM; } } } return mask; } EXPORT_SYMBOL_GPL(dccp_poll); int dccp_ioctl(struct sock *sk, int cmd, int *karg) { int rc = -ENOTCONN; lock_sock(sk); if (sk->sk_state == DCCP_LISTEN) goto out; switch (cmd) { case SIOCOUTQ: { *karg = sk_wmem_alloc_get(sk); /* Using sk_wmem_alloc here because sk_wmem_queued is not used by DCCP and * always 0, comparably to UDP. */ rc = 0; } break; case SIOCINQ: { struct sk_buff *skb; *karg = 0; skb = skb_peek(&sk->sk_receive_queue); if (skb != NULL) { /* * We will only return the amount of this packet since * that is all that will be read. */ *karg = skb->len; } rc = 0; } break; default: rc = -ENOIOCTLCMD; break; } out: release_sock(sk); return rc; } EXPORT_SYMBOL_GPL(dccp_ioctl); static int dccp_setsockopt_service(struct sock *sk, const __be32 service, sockptr_t optval, unsigned int optlen) { struct dccp_sock *dp = dccp_sk(sk); struct dccp_service_list *sl = NULL; if (service == DCCP_SERVICE_INVALID_VALUE || optlen > DCCP_SERVICE_LIST_MAX_LEN * sizeof(u32)) return -EINVAL; if (optlen > sizeof(service)) { sl = kmalloc(optlen, GFP_KERNEL); if (sl == NULL) return -ENOMEM; sl->dccpsl_nr = optlen / sizeof(u32) - 1; if (copy_from_sockptr_offset(sl->dccpsl_list, optval, sizeof(service), optlen - sizeof(service)) || dccp_list_has_service(sl, DCCP_SERVICE_INVALID_VALUE)) { kfree(sl); return -EFAULT; } } lock_sock(sk); dp->dccps_service = service; kfree(dp->dccps_service_list); dp->dccps_service_list = sl; release_sock(sk); return 0; } static int dccp_setsockopt_cscov(struct sock *sk, int cscov, bool rx) { u8 *list, len; int i, rc; if (cscov < 0 || cscov > 15) return -EINVAL; /* * Populate a list of permissible values, in the range cscov...15. This * is necessary since feature negotiation of single values only works if * both sides incidentally choose the same value. Since the list starts * lowest-value first, negotiation will pick the smallest shared value. */ if (cscov == 0) return 0; len = 16 - cscov; list = kmalloc(len, GFP_KERNEL); if (list == NULL) return -ENOBUFS; for (i = 0; i < len; i++) list[i] = cscov++; rc = dccp_feat_register_sp(sk, DCCPF_MIN_CSUM_COVER, rx, list, len); if (rc == 0) { if (rx) dccp_sk(sk)->dccps_pcrlen = cscov; else dccp_sk(sk)->dccps_pcslen = cscov; } kfree(list); return rc; } static int dccp_setsockopt_ccid(struct sock *sk, int type, sockptr_t optval, unsigned int optlen) { u8 *val; int rc = 0; if (optlen < 1 || optlen > DCCP_FEAT_MAX_SP_VALS) return -EINVAL; val = memdup_sockptr(optval, optlen); if (IS_ERR(val)) return PTR_ERR(val); lock_sock(sk); if (type == DCCP_SOCKOPT_TX_CCID || type == DCCP_SOCKOPT_CCID) rc = dccp_feat_register_sp(sk, DCCPF_CCID, 1, val, optlen); if (!rc && (type == DCCP_SOCKOPT_RX_CCID || type == DCCP_SOCKOPT_CCID)) rc = dccp_feat_register_sp(sk, DCCPF_CCID, 0, val, optlen); release_sock(sk); kfree(val); return rc; } static int do_dccp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { struct dccp_sock *dp = dccp_sk(sk); int val, err = 0; switch (optname) { case DCCP_SOCKOPT_PACKET_SIZE: DCCP_WARN("sockopt(PACKET_SIZE) is deprecated: fix your app\n"); return 0; case DCCP_SOCKOPT_CHANGE_L: case DCCP_SOCKOPT_CHANGE_R: DCCP_WARN("sockopt(CHANGE_L/R) is deprecated: fix your app\n"); return 0; case DCCP_SOCKOPT_CCID: case DCCP_SOCKOPT_RX_CCID: case DCCP_SOCKOPT_TX_CCID: return dccp_setsockopt_ccid(sk, optname, optval, optlen); } if (optlen < (int)sizeof(int)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(int))) return -EFAULT; if (optname == DCCP_SOCKOPT_SERVICE) return dccp_setsockopt_service(sk, val, optval, optlen); lock_sock(sk); switch (optname) { case DCCP_SOCKOPT_SERVER_TIMEWAIT: if (dp->dccps_role != DCCP_ROLE_SERVER) err = -EOPNOTSUPP; else dp->dccps_server_timewait = (val != 0); break; case DCCP_SOCKOPT_SEND_CSCOV: err = dccp_setsockopt_cscov(sk, val, false); break; case DCCP_SOCKOPT_RECV_CSCOV: err = dccp_setsockopt_cscov(sk, val, true); break; case DCCP_SOCKOPT_QPOLICY_ID: if (sk->sk_state != DCCP_CLOSED) err = -EISCONN; else if (val < 0 || val >= DCCPQ_POLICY_MAX) err = -EINVAL; else dp->dccps_qpolicy = val; break; case DCCP_SOCKOPT_QPOLICY_TXQLEN: if (val < 0) err = -EINVAL; else dp->dccps_tx_qlen = val; break; default: err = -ENOPROTOOPT; break; } release_sock(sk); return err; } int dccp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { if (level != SOL_DCCP) return inet_csk(sk)->icsk_af_ops->setsockopt(sk, level, optname, optval, optlen); return do_dccp_setsockopt(sk, level, optname, optval, optlen); } EXPORT_SYMBOL_GPL(dccp_setsockopt); static int dccp_getsockopt_service(struct sock *sk, int len, __be32 __user *optval, int __user *optlen) { const struct dccp_sock *dp = dccp_sk(sk); const struct dccp_service_list *sl; int err = -ENOENT, slen = 0, total_len = sizeof(u32); lock_sock(sk); if ((sl = dp->dccps_service_list) != NULL) { slen = sl->dccpsl_nr * sizeof(u32); total_len += slen; } err = -EINVAL; if (total_len > len) goto out; err = 0; if (put_user(total_len, optlen) || put_user(dp->dccps_service, optval) || (sl != NULL && copy_to_user(optval + 1, sl->dccpsl_list, slen))) err = -EFAULT; out: release_sock(sk); return err; } static int do_dccp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { struct dccp_sock *dp; int val, len; if (get_user(len, optlen)) return -EFAULT; if (len < (int)sizeof(int)) return -EINVAL; dp = dccp_sk(sk); switch (optname) { case DCCP_SOCKOPT_PACKET_SIZE: DCCP_WARN("sockopt(PACKET_SIZE) is deprecated: fix your app\n"); return 0; case DCCP_SOCKOPT_SERVICE: return dccp_getsockopt_service(sk, len, (__be32 __user *)optval, optlen); case DCCP_SOCKOPT_GET_CUR_MPS: val = READ_ONCE(dp->dccps_mss_cache); break; case DCCP_SOCKOPT_AVAILABLE_CCIDS: return ccid_getsockopt_builtin_ccids(sk, len, optval, optlen); case DCCP_SOCKOPT_TX_CCID: val = ccid_get_current_tx_ccid(dp); if (val < 0) return -ENOPROTOOPT; break; case DCCP_SOCKOPT_RX_CCID: val = ccid_get_current_rx_ccid(dp); if (val < 0) return -ENOPROTOOPT; break; case DCCP_SOCKOPT_SERVER_TIMEWAIT: val = dp->dccps_server_timewait; break; case DCCP_SOCKOPT_SEND_CSCOV: val = dp->dccps_pcslen; break; case DCCP_SOCKOPT_RECV_CSCOV: val = dp->dccps_pcrlen; break; case DCCP_SOCKOPT_QPOLICY_ID: val = dp->dccps_qpolicy; break; case DCCP_SOCKOPT_QPOLICY_TXQLEN: val = dp->dccps_tx_qlen; break; case 128 ... 191: return ccid_hc_rx_getsockopt(dp->dccps_hc_rx_ccid, sk, optname, len, (u32 __user *)optval, optlen); case 192 ... 255: return ccid_hc_tx_getsockopt(dp->dccps_hc_tx_ccid, sk, optname, len, (u32 __user *)optval, optlen); default: return -ENOPROTOOPT; } len = sizeof(val); if (put_user(len, optlen) || copy_to_user(optval, &val, len)) return -EFAULT; return 0; } int dccp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { if (level != SOL_DCCP) return inet_csk(sk)->icsk_af_ops->getsockopt(sk, level, optname, optval, optlen); return do_dccp_getsockopt(sk, level, optname, optval, optlen); } EXPORT_SYMBOL_GPL(dccp_getsockopt); static int dccp_msghdr_parse(struct msghdr *msg, struct sk_buff *skb) { struct cmsghdr *cmsg; /* * Assign an (opaque) qpolicy priority value to skb->priority. * * We are overloading this skb field for use with the qpolicy subystem. * The skb->priority is normally used for the SO_PRIORITY option, which * is initialised from sk_priority. Since the assignment of sk_priority * to skb->priority happens later (on layer 3), we overload this field * for use with queueing priorities as long as the skb is on layer 4. * The default priority value (if nothing is set) is 0. */ skb->priority = 0; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; if (cmsg->cmsg_level != SOL_DCCP) continue; if (cmsg->cmsg_type <= DCCP_SCM_QPOLICY_MAX && !dccp_qpolicy_param_ok(skb->sk, cmsg->cmsg_type)) return -EINVAL; switch (cmsg->cmsg_type) { case DCCP_SCM_PRIORITY: if (cmsg->cmsg_len != CMSG_LEN(sizeof(__u32))) return -EINVAL; skb->priority = *(__u32 *)CMSG_DATA(cmsg); break; default: return -EINVAL; } } return 0; } int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { const struct dccp_sock *dp = dccp_sk(sk); const int flags = msg->msg_flags; const int noblock = flags & MSG_DONTWAIT; struct sk_buff *skb; int rc, size; long timeo; trace_dccp_probe(sk, len); if (len > READ_ONCE(dp->dccps_mss_cache)) return -EMSGSIZE; lock_sock(sk); timeo = sock_sndtimeo(sk, noblock); /* * We have to use sk_stream_wait_connect here to set sk_write_pending, * so that the trick in dccp_rcv_request_sent_state_process. */ /* Wait for a connection to finish. */ if ((1 << sk->sk_state) & ~(DCCPF_OPEN | DCCPF_PARTOPEN)) if ((rc = sk_stream_wait_connect(sk, &timeo)) != 0) goto out_release; size = sk->sk_prot->max_header + len; release_sock(sk); skb = sock_alloc_send_skb(sk, size, noblock, &rc); lock_sock(sk); if (skb == NULL) goto out_release; if (dccp_qpolicy_full(sk)) { rc = -EAGAIN; goto out_discard; } if (sk->sk_state == DCCP_CLOSED) { rc = -ENOTCONN; goto out_discard; } /* We need to check dccps_mss_cache after socket is locked. */ if (len > dp->dccps_mss_cache) { rc = -EMSGSIZE; goto out_discard; } skb_reserve(skb, sk->sk_prot->max_header); rc = memcpy_from_msg(skb_put(skb, len), msg, len); if (rc != 0) goto out_discard; rc = dccp_msghdr_parse(msg, skb); if (rc != 0) goto out_discard; dccp_qpolicy_push(sk, skb); /* * The xmit_timer is set if the TX CCID is rate-based and will expire * when congestion control permits to release further packets into the * network. Window-based CCIDs do not use this timer. */ if (!timer_pending(&dp->dccps_xmit_timer)) dccp_write_xmit(sk); out_release: release_sock(sk); return rc ? : len; out_discard: kfree_skb(skb); goto out_release; } EXPORT_SYMBOL_GPL(dccp_sendmsg); int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { const struct dccp_hdr *dh; long timeo; lock_sock(sk); if (sk->sk_state == DCCP_LISTEN) { len = -ENOTCONN; goto out; } timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); do { struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); if (skb == NULL) goto verify_sock_status; dh = dccp_hdr(skb); switch (dh->dccph_type) { case DCCP_PKT_DATA: case DCCP_PKT_DATAACK: goto found_ok_skb; case DCCP_PKT_CLOSE: case DCCP_PKT_CLOSEREQ: if (!(flags & MSG_PEEK)) dccp_finish_passive_close(sk); fallthrough; case DCCP_PKT_RESET: dccp_pr_debug("found fin (%s) ok!\n", dccp_packet_name(dh->dccph_type)); len = 0; goto found_fin_ok; default: dccp_pr_debug("packet_type=%s\n", dccp_packet_name(dh->dccph_type)); sk_eat_skb(sk, skb); } verify_sock_status: if (sock_flag(sk, SOCK_DONE)) { len = 0; break; } if (sk->sk_err) { len = sock_error(sk); break; } if (sk->sk_shutdown & RCV_SHUTDOWN) { len = 0; break; } if (sk->sk_state == DCCP_CLOSED) { if (!sock_flag(sk, SOCK_DONE)) { /* This occurs when user tries to read * from never connected socket. */ len = -ENOTCONN; break; } len = 0; break; } if (!timeo) { len = -EAGAIN; break; } if (signal_pending(current)) { len = sock_intr_errno(timeo); break; } sk_wait_data(sk, &timeo, NULL); continue; found_ok_skb: if (len > skb->len) len = skb->len; else if (len < skb->len) msg->msg_flags |= MSG_TRUNC; if (skb_copy_datagram_msg(skb, 0, msg, len)) { /* Exception. Bailout! */ len = -EFAULT; break; } if (flags & MSG_TRUNC) len = skb->len; found_fin_ok: if (!(flags & MSG_PEEK)) sk_eat_skb(sk, skb); break; } while (1); out: release_sock(sk); return len; } EXPORT_SYMBOL_GPL(dccp_recvmsg); int inet_dccp_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; unsigned char old_state; int err; lock_sock(sk); err = -EINVAL; if (sock->state != SS_UNCONNECTED || sock->type != SOCK_DCCP) goto out; old_state = sk->sk_state; if (!((1 << old_state) & (DCCPF_CLOSED | DCCPF_LISTEN))) goto out; WRITE_ONCE(sk->sk_max_ack_backlog, backlog); /* Really, if the socket is already in listen state * we can only allow the backlog to be adjusted. */ if (old_state != DCCP_LISTEN) { struct dccp_sock *dp = dccp_sk(sk); dp->dccps_role = DCCP_ROLE_LISTEN; /* do not start to listen if feature negotiation setup fails */ if (dccp_feat_finalise_settings(dp)) { err = -EPROTO; goto out; } err = inet_csk_listen_start(sk); if (err) goto out; } err = 0; out: release_sock(sk); return err; } EXPORT_SYMBOL_GPL(inet_dccp_listen); static void dccp_terminate_connection(struct sock *sk) { u8 next_state = DCCP_CLOSED; switch (sk->sk_state) { case DCCP_PASSIVE_CLOSE: case DCCP_PASSIVE_CLOSEREQ: dccp_finish_passive_close(sk); break; case DCCP_PARTOPEN: dccp_pr_debug("Stop PARTOPEN timer (%p)\n", sk); inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); fallthrough; case DCCP_OPEN: dccp_send_close(sk, 1); if (dccp_sk(sk)->dccps_role == DCCP_ROLE_SERVER && !dccp_sk(sk)->dccps_server_timewait) next_state = DCCP_ACTIVE_CLOSEREQ; else next_state = DCCP_CLOSING; fallthrough; default: dccp_set_state(sk, next_state); } } void dccp_close(struct sock *sk, long timeout) { struct dccp_sock *dp = dccp_sk(sk); struct sk_buff *skb; u32 data_was_unread = 0; int state; lock_sock(sk); sk->sk_shutdown = SHUTDOWN_MASK; if (sk->sk_state == DCCP_LISTEN) { dccp_set_state(sk, DCCP_CLOSED); /* Special case. */ inet_csk_listen_stop(sk); goto adjudge_to_death; } sk_stop_timer(sk, &dp->dccps_xmit_timer); /* * We need to flush the recv. buffs. We do this only on the * descriptor close, not protocol-sourced closes, because the *reader process may not have drained the data yet! */ while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) { data_was_unread += skb->len; __kfree_skb(skb); } /* If socket has been already reset kill it. */ if (sk->sk_state == DCCP_CLOSED) goto adjudge_to_death; if (data_was_unread) { /* Unread data was tossed, send an appropriate Reset Code */ DCCP_WARN("ABORT with %u bytes unread\n", data_was_unread); dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED); dccp_set_state(sk, DCCP_CLOSED); } else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) { /* Check zero linger _after_ checking for unread data. */ sk->sk_prot->disconnect(sk, 0); } else if (sk->sk_state != DCCP_CLOSED) { /* * Normal connection termination. May need to wait if there are * still packets in the TX queue that are delayed by the CCID. */ dccp_flush_write_queue(sk, &timeout); dccp_terminate_connection(sk); } /* * Flush write queue. This may be necessary in several cases: * - we have been closed by the peer but still have application data; * - abortive termination (unread data or zero linger time), * - normal termination but queue could not be flushed within time limit */ __skb_queue_purge(&sk->sk_write_queue); sk_stream_wait_close(sk, timeout); adjudge_to_death: state = sk->sk_state; sock_hold(sk); sock_orphan(sk); /* * It is the last release_sock in its life. It will remove backlog. */ release_sock(sk); /* * Now socket is owned by kernel and we acquire BH lock * to finish close. No need to check for user refs. */ local_bh_disable(); bh_lock_sock(sk); WARN_ON(sock_owned_by_user(sk)); this_cpu_inc(dccp_orphan_count); /* Have we already been destroyed by a softirq or backlog? */ if (state != DCCP_CLOSED && sk->sk_state == DCCP_CLOSED) goto out; if (sk->sk_state == DCCP_CLOSED) inet_csk_destroy_sock(sk); /* Otherwise, socket is reprieved until protocol close. */ out: bh_unlock_sock(sk); local_bh_enable(); sock_put(sk); } EXPORT_SYMBOL_GPL(dccp_close); void dccp_shutdown(struct sock *sk, int how) { dccp_pr_debug("called shutdown(%x)\n", how); } EXPORT_SYMBOL_GPL(dccp_shutdown); static inline int __init dccp_mib_init(void) { dccp_statistics = alloc_percpu(struct dccp_mib); if (!dccp_statistics) return -ENOMEM; return 0; } static inline void dccp_mib_exit(void) { free_percpu(dccp_statistics); } static int thash_entries; module_param(thash_entries, int, 0444); MODULE_PARM_DESC(thash_entries, "Number of ehash buckets"); #ifdef CONFIG_IP_DCCP_DEBUG bool dccp_debug; module_param(dccp_debug, bool, 0644); MODULE_PARM_DESC(dccp_debug, "Enable debug messages"); EXPORT_SYMBOL_GPL(dccp_debug); #endif static int __init dccp_init(void) { unsigned long goal; unsigned long nr_pages = totalram_pages(); int ehash_order, bhash_order, i; int rc; BUILD_BUG_ON(sizeof(struct dccp_skb_cb) > sizeof_field(struct sk_buff, cb)); rc = inet_hashinfo2_init_mod(&dccp_hashinfo); if (rc) goto out_fail; rc = -ENOBUFS; dccp_hashinfo.bind_bucket_cachep = kmem_cache_create("dccp_bind_bucket", sizeof(struct inet_bind_bucket), 0, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL); if (!dccp_hashinfo.bind_bucket_cachep) goto out_free_hashinfo2; dccp_hashinfo.bind2_bucket_cachep = kmem_cache_create("dccp_bind2_bucket", sizeof(struct inet_bind2_bucket), 0, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL); if (!dccp_hashinfo.bind2_bucket_cachep) goto out_free_bind_bucket_cachep; /* * Size and allocate the main established and bind bucket * hash tables. * * The methodology is similar to that of the buffer cache. */ if (nr_pages >= (128 * 1024)) goal = nr_pages >> (21 - PAGE_SHIFT); else goal = nr_pages >> (23 - PAGE_SHIFT); if (thash_entries) goal = (thash_entries * sizeof(struct inet_ehash_bucket)) >> PAGE_SHIFT; for (ehash_order = 0; (1UL << ehash_order) < goal; ehash_order++) ; do { unsigned long hash_size = (1UL << ehash_order) * PAGE_SIZE / sizeof(struct inet_ehash_bucket); while (hash_size & (hash_size - 1)) hash_size--; dccp_hashinfo.ehash_mask = hash_size - 1; dccp_hashinfo.ehash = (struct inet_ehash_bucket *) __get_free_pages(GFP_ATOMIC|__GFP_NOWARN, ehash_order); } while (!dccp_hashinfo.ehash && --ehash_order > 0); if (!dccp_hashinfo.ehash) { DCCP_CRIT("Failed to allocate DCCP established hash table"); goto out_free_bind2_bucket_cachep; } for (i = 0; i <= dccp_hashinfo.ehash_mask; i++) INIT_HLIST_NULLS_HEAD(&dccp_hashinfo.ehash[i].chain, i); if (inet_ehash_locks_alloc(&dccp_hashinfo)) goto out_free_dccp_ehash; bhash_order = ehash_order; do { dccp_hashinfo.bhash_size = (1UL << bhash_order) * PAGE_SIZE / sizeof(struct inet_bind_hashbucket); if ((dccp_hashinfo.bhash_size > (64 * 1024)) && bhash_order > 0) continue; dccp_hashinfo.bhash = (struct inet_bind_hashbucket *) __get_free_pages(GFP_ATOMIC|__GFP_NOWARN, bhash_order); } while (!dccp_hashinfo.bhash && --bhash_order >= 0); if (!dccp_hashinfo.bhash) { DCCP_CRIT("Failed to allocate DCCP bind hash table"); goto out_free_dccp_locks; } dccp_hashinfo.bhash2 = (struct inet_bind_hashbucket *) __get_free_pages(GFP_ATOMIC | __GFP_NOWARN, bhash_order); if (!dccp_hashinfo.bhash2) { DCCP_CRIT("Failed to allocate DCCP bind2 hash table"); goto out_free_dccp_bhash; } for (i = 0; i < dccp_hashinfo.bhash_size; i++) { spin_lock_init(&dccp_hashinfo.bhash[i].lock); INIT_HLIST_HEAD(&dccp_hashinfo.bhash[i].chain); spin_lock_init(&dccp_hashinfo.bhash2[i].lock); INIT_HLIST_HEAD(&dccp_hashinfo.bhash2[i].chain); } dccp_hashinfo.pernet = false; rc = dccp_mib_init(); if (rc) goto out_free_dccp_bhash2; rc = dccp_ackvec_init(); if (rc) goto out_free_dccp_mib; rc = dccp_sysctl_init(); if (rc) goto out_ackvec_exit; rc = ccid_initialize_builtins(); if (rc) goto out_sysctl_exit; dccp_timestamping_init(); return 0; out_sysctl_exit: dccp_sysctl_exit(); out_ackvec_exit: dccp_ackvec_exit(); out_free_dccp_mib: dccp_mib_exit(); out_free_dccp_bhash2: free_pages((unsigned long)dccp_hashinfo.bhash2, bhash_order); out_free_dccp_bhash: free_pages((unsigned long)dccp_hashinfo.bhash, bhash_order); out_free_dccp_locks: inet_ehash_locks_free(&dccp_hashinfo); out_free_dccp_ehash: free_pages((unsigned long)dccp_hashinfo.ehash, ehash_order); out_free_bind2_bucket_cachep: kmem_cache_destroy(dccp_hashinfo.bind2_bucket_cachep); out_free_bind_bucket_cachep: kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); out_free_hashinfo2: inet_hashinfo2_free_mod(&dccp_hashinfo); out_fail: dccp_hashinfo.bhash = NULL; dccp_hashinfo.bhash2 = NULL; dccp_hashinfo.ehash = NULL; dccp_hashinfo.bind_bucket_cachep = NULL; dccp_hashinfo.bind2_bucket_cachep = NULL; return rc; } static void __exit dccp_fini(void) { int bhash_order = get_order(dccp_hashinfo.bhash_size * sizeof(struct inet_bind_hashbucket)); ccid_cleanup_builtins(); dccp_mib_exit(); free_pages((unsigned long)dccp_hashinfo.bhash, bhash_order); free_pages((unsigned long)dccp_hashinfo.bhash2, bhash_order); free_pages((unsigned long)dccp_hashinfo.ehash, get_order((dccp_hashinfo.ehash_mask + 1) * sizeof(struct inet_ehash_bucket))); inet_ehash_locks_free(&dccp_hashinfo); kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); dccp_ackvec_exit(); dccp_sysctl_exit(); inet_hashinfo2_free_mod(&dccp_hashinfo); } module_init(dccp_init); module_exit(dccp_fini); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Arnaldo Carvalho de Melo <acme@conectiva.com.br>"); MODULE_DESCRIPTION("DCCP - Datagram Congestion Controlled Protocol"); |
| 1 2 2 1 1 2 2 2 2 2 2 2 2 2 1 2 2 1 1 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Glue Code for x86_64/AVX2/AES-NI assembler optimized version of Camellia * * Copyright © 2013 Jussi Kivilinna <jussi.kivilinna@mbnet.fi> */ #include <crypto/algapi.h> #include <crypto/internal/simd.h> #include <linux/crypto.h> #include <linux/err.h> #include <linux/module.h> #include <linux/types.h> #include "camellia.h" #include "ecb_cbc_helpers.h" #define CAMELLIA_AESNI_PARALLEL_BLOCKS 16 #define CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS 32 /* 32-way AVX2/AES-NI parallel cipher functions */ asmlinkage void camellia_ecb_enc_32way(const void *ctx, u8 *dst, const u8 *src); asmlinkage void camellia_ecb_dec_32way(const void *ctx, u8 *dst, const u8 *src); asmlinkage void camellia_cbc_dec_32way(const void *ctx, u8 *dst, const u8 *src); static int camellia_setkey(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) { return __camellia_setkey(crypto_skcipher_ctx(tfm), key, keylen); } static int ecb_encrypt(struct skcipher_request *req) { ECB_WALK_START(req, CAMELLIA_BLOCK_SIZE, CAMELLIA_AESNI_PARALLEL_BLOCKS); ECB_BLOCK(CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS, camellia_ecb_enc_32way); ECB_BLOCK(CAMELLIA_AESNI_PARALLEL_BLOCKS, camellia_ecb_enc_16way); ECB_BLOCK(2, camellia_enc_blk_2way); ECB_BLOCK(1, camellia_enc_blk); ECB_WALK_END(); } static int ecb_decrypt(struct skcipher_request *req) { ECB_WALK_START(req, CAMELLIA_BLOCK_SIZE, CAMELLIA_AESNI_PARALLEL_BLOCKS); ECB_BLOCK(CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS, camellia_ecb_dec_32way); ECB_BLOCK(CAMELLIA_AESNI_PARALLEL_BLOCKS, camellia_ecb_dec_16way); ECB_BLOCK(2, camellia_dec_blk_2way); ECB_BLOCK(1, camellia_dec_blk); ECB_WALK_END(); } static int cbc_encrypt(struct skcipher_request *req) { CBC_WALK_START(req, CAMELLIA_BLOCK_SIZE, -1); CBC_ENC_BLOCK(camellia_enc_blk); CBC_WALK_END(); } static int cbc_decrypt(struct skcipher_request *req) { CBC_WALK_START(req, CAMELLIA_BLOCK_SIZE, CAMELLIA_AESNI_PARALLEL_BLOCKS); CBC_DEC_BLOCK(CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS, camellia_cbc_dec_32way); CBC_DEC_BLOCK(CAMELLIA_AESNI_PARALLEL_BLOCKS, camellia_cbc_dec_16way); CBC_DEC_BLOCK(2, camellia_decrypt_cbc_2way); CBC_DEC_BLOCK(1, camellia_dec_blk); CBC_WALK_END(); } static struct skcipher_alg camellia_algs[] = { { .base.cra_name = "__ecb(camellia)", .base.cra_driver_name = "__ecb-camellia-aesni-avx2", .base.cra_priority = 500, .base.cra_flags = CRYPTO_ALG_INTERNAL, .base.cra_blocksize = CAMELLIA_BLOCK_SIZE, .base.cra_ctxsize = sizeof(struct camellia_ctx), .base.cra_module = THIS_MODULE, .min_keysize = CAMELLIA_MIN_KEY_SIZE, .max_keysize = CAMELLIA_MAX_KEY_SIZE, .setkey = camellia_setkey, .encrypt = ecb_encrypt, .decrypt = ecb_decrypt, }, { .base.cra_name = "__cbc(camellia)", .base.cra_driver_name = "__cbc-camellia-aesni-avx2", .base.cra_priority = 500, .base.cra_flags = CRYPTO_ALG_INTERNAL, .base.cra_blocksize = CAMELLIA_BLOCK_SIZE, .base.cra_ctxsize = sizeof(struct camellia_ctx), .base.cra_module = THIS_MODULE, .min_keysize = CAMELLIA_MIN_KEY_SIZE, .max_keysize = CAMELLIA_MAX_KEY_SIZE, .ivsize = CAMELLIA_BLOCK_SIZE, .setkey = camellia_setkey, .encrypt = cbc_encrypt, .decrypt = cbc_decrypt, }, }; static struct simd_skcipher_alg *camellia_simd_algs[ARRAY_SIZE(camellia_algs)]; static int __init camellia_aesni_init(void) { const char *feature_name; if (!boot_cpu_has(X86_FEATURE_AVX) || !boot_cpu_has(X86_FEATURE_AVX2) || !boot_cpu_has(X86_FEATURE_AES) || !boot_cpu_has(X86_FEATURE_OSXSAVE)) { pr_info("AVX2 or AES-NI instructions are not detected.\n"); return -ENODEV; } if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, &feature_name)) { pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; } return simd_register_skciphers_compat(camellia_algs, ARRAY_SIZE(camellia_algs), camellia_simd_algs); } static void __exit camellia_aesni_fini(void) { simd_unregister_skciphers(camellia_algs, ARRAY_SIZE(camellia_algs), camellia_simd_algs); } module_init(camellia_aesni_init); module_exit(camellia_aesni_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Camellia Cipher Algorithm, AES-NI/AVX2 optimized"); MODULE_ALIAS_CRYPTO("camellia"); MODULE_ALIAS_CRYPTO("camellia-asm"); |
| 87 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * fs/kernfs/kernfs-internal.h - kernfs internal header file * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007, 2013 Tejun Heo <teheo@suse.de> */ #ifndef __KERNFS_INTERNAL_H #define __KERNFS_INTERNAL_H #include <linux/lockdep.h> #include <linux/fs.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/xattr.h> #include <linux/kernfs.h> #include <linux/fs_context.h> struct kernfs_iattrs { kuid_t ia_uid; kgid_t ia_gid; struct timespec64 ia_atime; struct timespec64 ia_mtime; struct timespec64 ia_ctime; struct simple_xattrs xattrs; atomic_t nr_user_xattrs; atomic_t user_xattr_size; }; struct kernfs_root { /* published fields */ struct kernfs_node *kn; unsigned int flags; /* KERNFS_ROOT_* flags */ /* private fields, do not use outside kernfs proper */ struct idr ino_idr; u32 last_id_lowbits; u32 id_highbits; struct kernfs_syscall_ops *syscall_ops; /* list of kernfs_super_info of this root, protected by kernfs_rwsem */ struct list_head supers; wait_queue_head_t deactivate_waitq; struct rw_semaphore kernfs_rwsem; struct rw_semaphore kernfs_iattr_rwsem; struct rw_semaphore kernfs_supers_rwsem; struct rcu_head rcu; }; /* +1 to avoid triggering overflow warning when negating it */ #define KN_DEACTIVATED_BIAS (INT_MIN + 1) /* KERNFS_TYPE_MASK and types are defined in include/linux/kernfs.h */ /** * kernfs_root - find out the kernfs_root a kernfs_node belongs to * @kn: kernfs_node of interest * * Return: the kernfs_root @kn belongs to. */ static inline struct kernfs_root *kernfs_root(struct kernfs_node *kn) { /* if parent exists, it's always a dir; otherwise, @sd is a dir */ if (kn->parent) kn = kn->parent; return kn->dir.root; } /* * mount.c */ struct kernfs_super_info { struct super_block *sb; /* * The root associated with this super_block. Each super_block is * identified by the root and ns it's associated with. */ struct kernfs_root *root; /* * Each sb is associated with one namespace tag, currently the * network namespace of the task which mounted this kernfs * instance. If multiple tags become necessary, make the following * an array and compare kernfs_node tag against every entry. */ const void *ns; /* anchored at kernfs_root->supers, protected by kernfs_rwsem */ struct list_head node; }; #define kernfs_info(SB) ((struct kernfs_super_info *)(SB->s_fs_info)) static inline struct kernfs_node *kernfs_dentry_node(struct dentry *dentry) { if (d_really_is_negative(dentry)) return NULL; return d_inode(dentry)->i_private; } static inline void kernfs_set_rev(struct kernfs_node *parent, struct dentry *dentry) { dentry->d_time = parent->dir.rev; } static inline void kernfs_inc_rev(struct kernfs_node *parent) { parent->dir.rev++; } static inline bool kernfs_dir_changed(struct kernfs_node *parent, struct dentry *dentry) { if (parent->dir.rev != dentry->d_time) return true; return false; } extern const struct super_operations kernfs_sops; extern struct kmem_cache *kernfs_node_cache, *kernfs_iattrs_cache; /* * inode.c */ extern const struct xattr_handler * const kernfs_xattr_handlers[]; void kernfs_evict_inode(struct inode *inode); int kernfs_iop_permission(struct mnt_idmap *idmap, struct inode *inode, int mask); int kernfs_iop_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr); int kernfs_iop_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags); ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size); int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr); /* * dir.c */ extern const struct dentry_operations kernfs_dops; extern const struct file_operations kernfs_dir_fops; extern const struct inode_operations kernfs_dir_iops; struct kernfs_node *kernfs_get_active(struct kernfs_node *kn); void kernfs_put_active(struct kernfs_node *kn); int kernfs_add_one(struct kernfs_node *kn); struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, unsigned flags); /* * file.c */ extern const struct file_operations kernfs_file_fops; bool kernfs_should_drain_open_files(struct kernfs_node *kn); void kernfs_drain_open_files(struct kernfs_node *kn); /* * symlink.c */ extern const struct inode_operations kernfs_symlink_iops; /* * kernfs locks */ extern struct kernfs_global_locks *kernfs_locks; #endif /* __KERNFS_INTERNAL_H */ |
| 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 | /* SPDX-License-Identifier: GPL-2.0 */ /* * DES & Triple DES EDE key verification helpers */ #ifndef __CRYPTO_INTERNAL_DES_H #define __CRYPTO_INTERNAL_DES_H #include <linux/crypto.h> #include <linux/fips.h> #include <crypto/des.h> #include <crypto/aead.h> #include <crypto/skcipher.h> /** * crypto_des_verify_key - Check whether a DES key is weak * @tfm: the crypto algo * @key: the key buffer * * Returns -EINVAL if the key is weak and the crypto TFM does not permit weak * keys. Otherwise, 0 is returned. * * It is the job of the caller to ensure that the size of the key equals * DES_KEY_SIZE. */ static inline int crypto_des_verify_key(struct crypto_tfm *tfm, const u8 *key) { struct des_ctx tmp; int err; err = des_expand_key(&tmp, key, DES_KEY_SIZE); if (err == -ENOKEY) { if (crypto_tfm_get_flags(tfm) & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS) err = -EINVAL; else err = 0; } memzero_explicit(&tmp, sizeof(tmp)); return err; } /* * RFC2451: * * For DES-EDE3, there is no known need to reject weak or * complementation keys. Any weakness is obviated by the use of * multiple keys. * * However, if the first two or last two independent 64-bit keys are * equal (k1 == k2 or k2 == k3), then the DES3 operation is simply the * same as DES. Implementers MUST reject keys that exhibit this * property. * */ static inline int des3_ede_verify_key(const u8 *key, unsigned int key_len, bool check_weak) { int ret = fips_enabled ? -EINVAL : -ENOKEY; u32 K[6]; memcpy(K, key, DES3_EDE_KEY_SIZE); if ((!((K[0] ^ K[2]) | (K[1] ^ K[3])) || !((K[2] ^ K[4]) | (K[3] ^ K[5]))) && (fips_enabled || check_weak)) goto bad; if ((!((K[0] ^ K[4]) | (K[1] ^ K[5]))) && fips_enabled) goto bad; ret = 0; bad: memzero_explicit(K, DES3_EDE_KEY_SIZE); return ret; } /** * crypto_des3_ede_verify_key - Check whether a DES3-EDE key is weak * @tfm: the crypto algo * @key: the key buffer * * Returns -EINVAL if the key is weak and the crypto TFM does not permit weak * keys or when running in FIPS mode. Otherwise, 0 is returned. Note that some * keys are rejected in FIPS mode even if weak keys are permitted by the TFM * flags. * * It is the job of the caller to ensure that the size of the key equals * DES3_EDE_KEY_SIZE. */ static inline int crypto_des3_ede_verify_key(struct crypto_tfm *tfm, const u8 *key) { return des3_ede_verify_key(key, DES3_EDE_KEY_SIZE, crypto_tfm_get_flags(tfm) & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS); } static inline int verify_skcipher_des_key(struct crypto_skcipher *tfm, const u8 *key) { return crypto_des_verify_key(crypto_skcipher_tfm(tfm), key); } static inline int verify_skcipher_des3_key(struct crypto_skcipher *tfm, const u8 *key) { return crypto_des3_ede_verify_key(crypto_skcipher_tfm(tfm), key); } static inline int verify_aead_des_key(struct crypto_aead *tfm, const u8 *key, int keylen) { if (keylen != DES_KEY_SIZE) return -EINVAL; return crypto_des_verify_key(crypto_aead_tfm(tfm), key); } static inline int verify_aead_des3_key(struct crypto_aead *tfm, const u8 *key, int keylen) { if (keylen != DES3_EDE_KEY_SIZE) return -EINVAL; return crypto_des3_ede_verify_key(crypto_aead_tfm(tfm), key); } #endif /* __CRYPTO_INTERNAL_DES_H */ |
| 3 2 4 2 2 2 1 2 1 2 4 2 3 3 4 2 2 2 3 4 4 4 4 4 4 2 3 2 1 2 4 4 4 4 4 1 4 4 3 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2007 The University of Aberdeen, Scotland, UK * Copyright (c) 2005-7 The University of Waikato, Hamilton, New Zealand. * Copyright (c) 2005-7 Ian McDonald <ian.mcdonald@jandi.co.nz> * * An implementation of the DCCP protocol * * This code has been developed by the University of Waikato WAND * research group. For further information please see https://www.wand.net.nz/ * * This code also uses code from Lulea University, rereleased as GPL by its * authors: * Copyright (c) 2003 Nils-Erik Mattsson, Joacim Haggmark, Magnus Erixzon * * Changes to meet Linux coding standards, to make it meet latest ccid3 draft * and to make it work as a loadable module in the DCCP stack written by * Arnaldo Carvalho de Melo <acme@conectiva.com.br>. * * Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@conectiva.com.br> */ #include "../dccp.h" #include "ccid3.h" #include <linux/unaligned.h> #ifdef CONFIG_IP_DCCP_CCID3_DEBUG static bool ccid3_debug; #define ccid3_pr_debug(format, a...) DCCP_PR_DEBUG(ccid3_debug, format, ##a) #else #define ccid3_pr_debug(format, a...) #endif /* * Transmitter Half-Connection Routines */ #ifdef CONFIG_IP_DCCP_CCID3_DEBUG static const char *ccid3_tx_state_name(enum ccid3_hc_tx_states state) { static const char *const ccid3_state_names[] = { [TFRC_SSTATE_NO_SENT] = "NO_SENT", [TFRC_SSTATE_NO_FBACK] = "NO_FBACK", [TFRC_SSTATE_FBACK] = "FBACK", }; return ccid3_state_names[state]; } #endif static void ccid3_hc_tx_set_state(struct sock *sk, enum ccid3_hc_tx_states state) { struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); enum ccid3_hc_tx_states oldstate = hc->tx_state; ccid3_pr_debug("%s(%p) %-8.8s -> %s\n", dccp_role(sk), sk, ccid3_tx_state_name(oldstate), ccid3_tx_state_name(state)); WARN_ON(state == oldstate); hc->tx_state = state; } /* * Compute the initial sending rate X_init in the manner of RFC 3390: * * X_init = min(4 * s, max(2 * s, 4380 bytes)) / RTT * * Note that RFC 3390 uses MSS, RFC 4342 refers to RFC 3390, and rfc3448bis * (rev-02) clarifies the use of RFC 3390 with regard to the above formula. * For consistency with other parts of the code, X_init is scaled by 2^6. */ static inline u64 rfc3390_initial_rate(struct sock *sk) { const struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); const __u32 w_init = clamp_t(__u32, 4380U, 2 * hc->tx_s, 4 * hc->tx_s); return scaled_div(w_init << 6, hc->tx_rtt); } /** * ccid3_update_send_interval - Calculate new t_ipi = s / X_inst * @hc: socket to have the send interval updated * * This respects the granularity of X_inst (64 * bytes/second). */ static void ccid3_update_send_interval(struct ccid3_hc_tx_sock *hc) { hc->tx_t_ipi = scaled_div32(((u64)hc->tx_s) << 6, hc->tx_x); DCCP_BUG_ON(hc->tx_t_ipi == 0); ccid3_pr_debug("t_ipi=%u, s=%u, X=%u\n", hc->tx_t_ipi, hc->tx_s, (unsigned int)(hc->tx_x >> 6)); } static u32 ccid3_hc_tx_idle_rtt(struct ccid3_hc_tx_sock *hc, ktime_t now) { u32 delta = ktime_us_delta(now, hc->tx_t_last_win_count); return delta / hc->tx_rtt; } /** * ccid3_hc_tx_update_x - Update allowed sending rate X * @sk: socket to be updated * @stamp: most recent time if available - can be left NULL. * * This function tracks draft rfc3448bis, check there for latest details. * * Note: X and X_recv are both stored in units of 64 * bytes/second, to support * fine-grained resolution of sending rates. This requires scaling by 2^6 * throughout the code. Only X_calc is unscaled (in bytes/second). * */ static void ccid3_hc_tx_update_x(struct sock *sk, ktime_t *stamp) { struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); __u64 min_rate = 2 * hc->tx_x_recv; const __u64 old_x = hc->tx_x; ktime_t now = stamp ? *stamp : ktime_get_real(); /* * Handle IDLE periods: do not reduce below RFC3390 initial sending rate * when idling [RFC 4342, 5.1]. Definition of idling is from rfc3448bis: * a sender is idle if it has not sent anything over a 2-RTT-period. * For consistency with X and X_recv, min_rate is also scaled by 2^6. */ if (ccid3_hc_tx_idle_rtt(hc, now) >= 2) { min_rate = rfc3390_initial_rate(sk); min_rate = max(min_rate, 2 * hc->tx_x_recv); } if (hc->tx_p > 0) { hc->tx_x = min(((__u64)hc->tx_x_calc) << 6, min_rate); hc->tx_x = max(hc->tx_x, (((__u64)hc->tx_s) << 6) / TFRC_T_MBI); } else if (ktime_us_delta(now, hc->tx_t_ld) - (s64)hc->tx_rtt >= 0) { hc->tx_x = min(2 * hc->tx_x, min_rate); hc->tx_x = max(hc->tx_x, scaled_div(((__u64)hc->tx_s) << 6, hc->tx_rtt)); hc->tx_t_ld = now; } if (hc->tx_x != old_x) { ccid3_pr_debug("X_prev=%u, X_now=%u, X_calc=%u, " "X_recv=%u\n", (unsigned int)(old_x >> 6), (unsigned int)(hc->tx_x >> 6), hc->tx_x_calc, (unsigned int)(hc->tx_x_recv >> 6)); ccid3_update_send_interval(hc); } } /** * ccid3_hc_tx_update_s - Track the mean packet size `s' * @hc: socket to be updated * @len: DCCP packet payload size in bytes * * cf. RFC 4342, 5.3 and RFC 3448, 4.1 */ static inline void ccid3_hc_tx_update_s(struct ccid3_hc_tx_sock *hc, int len) { const u16 old_s = hc->tx_s; hc->tx_s = tfrc_ewma(hc->tx_s, len, 9); if (hc->tx_s != old_s) ccid3_update_send_interval(hc); } /* * Update Window Counter using the algorithm from [RFC 4342, 8.1]. * As elsewhere, RTT > 0 is assumed by using dccp_sample_rtt(). */ static inline void ccid3_hc_tx_update_win_count(struct ccid3_hc_tx_sock *hc, ktime_t now) { u32 delta = ktime_us_delta(now, hc->tx_t_last_win_count), quarter_rtts = (4 * delta) / hc->tx_rtt; if (quarter_rtts > 0) { hc->tx_t_last_win_count = now; hc->tx_last_win_count += min(quarter_rtts, 5U); hc->tx_last_win_count &= 0xF; /* mod 16 */ } } static void ccid3_hc_tx_no_feedback_timer(struct timer_list *t) { struct ccid3_hc_tx_sock *hc = from_timer(hc, t, tx_no_feedback_timer); struct sock *sk = hc->sk; unsigned long t_nfb = USEC_PER_SEC / 5; bh_lock_sock(sk); if (sock_owned_by_user(sk)) { /* Try again later. */ /* XXX: set some sensible MIB */ goto restart_timer; } ccid3_pr_debug("%s(%p, state=%s) - entry\n", dccp_role(sk), sk, ccid3_tx_state_name(hc->tx_state)); /* Ignore and do not restart after leaving the established state */ if ((1 << sk->sk_state) & ~(DCCPF_OPEN | DCCPF_PARTOPEN)) goto out; /* Reset feedback state to "no feedback received" */ if (hc->tx_state == TFRC_SSTATE_FBACK) ccid3_hc_tx_set_state(sk, TFRC_SSTATE_NO_FBACK); /* * Determine new allowed sending rate X as per draft rfc3448bis-00, 4.4 * RTO is 0 if and only if no feedback has been received yet. */ if (hc->tx_t_rto == 0 || hc->tx_p == 0) { /* halve send rate directly */ hc->tx_x = max(hc->tx_x / 2, (((__u64)hc->tx_s) << 6) / TFRC_T_MBI); ccid3_update_send_interval(hc); } else { /* * Modify the cached value of X_recv * * If (X_calc > 2 * X_recv) * X_recv = max(X_recv / 2, s / (2 * t_mbi)); * Else * X_recv = X_calc / 4; * * Note that X_recv is scaled by 2^6 while X_calc is not */ if (hc->tx_x_calc > (hc->tx_x_recv >> 5)) hc->tx_x_recv = max(hc->tx_x_recv / 2, (((__u64)hc->tx_s) << 6) / (2*TFRC_T_MBI)); else { hc->tx_x_recv = hc->tx_x_calc; hc->tx_x_recv <<= 4; } ccid3_hc_tx_update_x(sk, NULL); } ccid3_pr_debug("Reduced X to %llu/64 bytes/sec\n", (unsigned long long)hc->tx_x); /* * Set new timeout for the nofeedback timer. * See comments in packet_recv() regarding the value of t_RTO. */ if (unlikely(hc->tx_t_rto == 0)) /* no feedback received yet */ t_nfb = TFRC_INITIAL_TIMEOUT; else t_nfb = max(hc->tx_t_rto, 2 * hc->tx_t_ipi); restart_timer: sk_reset_timer(sk, &hc->tx_no_feedback_timer, jiffies + usecs_to_jiffies(t_nfb)); out: bh_unlock_sock(sk); sock_put(sk); } /** * ccid3_hc_tx_send_packet - Delay-based dequeueing of TX packets * @sk: socket to send packet from * @skb: next packet candidate to send on @sk * * This function uses the convention of ccid_packet_dequeue_eval() and * returns a millisecond-delay value between 0 and t_mbi = 64000 msec. */ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); ktime_t now = ktime_get_real(); s64 delay; /* * This function is called only for Data and DataAck packets. Sending * zero-sized Data(Ack)s is theoretically possible, but for congestion * control this case is pathological - ignore it. */ if (unlikely(skb->len == 0)) return -EBADMSG; if (hc->tx_state == TFRC_SSTATE_NO_SENT) { sk_reset_timer(sk, &hc->tx_no_feedback_timer, (jiffies + usecs_to_jiffies(TFRC_INITIAL_TIMEOUT))); hc->tx_last_win_count = 0; hc->tx_t_last_win_count = now; /* Set t_0 for initial packet */ hc->tx_t_nom = now; hc->tx_s = skb->len; /* * Use initial RTT sample when available: recommended by erratum * to RFC 4342. This implements the initialisation procedure of * draft rfc3448bis, section 4.2. Remember, X is scaled by 2^6. */ if (dp->dccps_syn_rtt) { ccid3_pr_debug("SYN RTT = %uus\n", dp->dccps_syn_rtt); hc->tx_rtt = dp->dccps_syn_rtt; hc->tx_x = rfc3390_initial_rate(sk); hc->tx_t_ld = now; } else { /* * Sender does not have RTT sample: * - set fallback RTT (RFC 4340, 3.4) since a RTT value * is needed in several parts (e.g. window counter); * - set sending rate X_pps = 1pps as per RFC 3448, 4.2. */ hc->tx_rtt = DCCP_FALLBACK_RTT; hc->tx_x = hc->tx_s; hc->tx_x <<= 6; } ccid3_update_send_interval(hc); ccid3_hc_tx_set_state(sk, TFRC_SSTATE_NO_FBACK); } else { delay = ktime_us_delta(hc->tx_t_nom, now); ccid3_pr_debug("delay=%ld\n", (long)delay); /* * Scheduling of packet transmissions (RFC 5348, 8.3) * * if (t_now > t_nom - delta) * // send the packet now * else * // send the packet in (t_nom - t_now) milliseconds. */ if (delay >= TFRC_T_DELTA) return (u32)delay / USEC_PER_MSEC; ccid3_hc_tx_update_win_count(hc, now); } /* prepare to send now (add options etc.) */ dp->dccps_hc_tx_insert_options = 1; DCCP_SKB_CB(skb)->dccpd_ccval = hc->tx_last_win_count; /* set the nominal send time for the next following packet */ hc->tx_t_nom = ktime_add_us(hc->tx_t_nom, hc->tx_t_ipi); return CCID_PACKET_SEND_AT_ONCE; } static void ccid3_hc_tx_packet_sent(struct sock *sk, unsigned int len) { struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); ccid3_hc_tx_update_s(hc, len); if (tfrc_tx_hist_add(&hc->tx_hist, dccp_sk(sk)->dccps_gss)) DCCP_CRIT("packet history - out of memory!"); } static void ccid3_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) { struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); struct tfrc_tx_hist_entry *acked; ktime_t now; unsigned long t_nfb; u32 r_sample; /* we are only interested in ACKs */ if (!(DCCP_SKB_CB(skb)->dccpd_type == DCCP_PKT_ACK || DCCP_SKB_CB(skb)->dccpd_type == DCCP_PKT_DATAACK)) return; /* * Locate the acknowledged packet in the TX history. * * Returning "entry not found" here can for instance happen when * - the host has not sent out anything (e.g. a passive server), * - the Ack is outdated (packet with higher Ack number was received), * - it is a bogus Ack (for a packet not sent on this connection). */ acked = tfrc_tx_hist_find_entry(hc->tx_hist, dccp_hdr_ack_seq(skb)); if (acked == NULL) return; /* For the sake of RTT sampling, ignore/remove all older entries */ tfrc_tx_hist_purge(&acked->next); /* Update the moving average for the RTT estimate (RFC 3448, 4.3) */ now = ktime_get_real(); r_sample = dccp_sample_rtt(sk, ktime_us_delta(now, acked->stamp)); hc->tx_rtt = tfrc_ewma(hc->tx_rtt, r_sample, 9); /* * Update allowed sending rate X as per draft rfc3448bis-00, 4.2/3 */ if (hc->tx_state == TFRC_SSTATE_NO_FBACK) { ccid3_hc_tx_set_state(sk, TFRC_SSTATE_FBACK); if (hc->tx_t_rto == 0) { /* * Initial feedback packet: Larger Initial Windows (4.2) */ hc->tx_x = rfc3390_initial_rate(sk); hc->tx_t_ld = now; ccid3_update_send_interval(hc); goto done_computing_x; } else if (hc->tx_p == 0) { /* * First feedback after nofeedback timer expiry (4.3) */ goto done_computing_x; } } /* Update sending rate (step 4 of [RFC 3448, 4.3]) */ if (hc->tx_p > 0) hc->tx_x_calc = tfrc_calc_x(hc->tx_s, hc->tx_rtt, hc->tx_p); ccid3_hc_tx_update_x(sk, &now); done_computing_x: ccid3_pr_debug("%s(%p), RTT=%uus (sample=%uus), s=%u, " "p=%u, X_calc=%u, X_recv=%u, X=%u\n", dccp_role(sk), sk, hc->tx_rtt, r_sample, hc->tx_s, hc->tx_p, hc->tx_x_calc, (unsigned int)(hc->tx_x_recv >> 6), (unsigned int)(hc->tx_x >> 6)); /* unschedule no feedback timer */ sk_stop_timer(sk, &hc->tx_no_feedback_timer); /* * As we have calculated new ipi, delta, t_nom it is possible * that we now can send a packet, so wake up dccp_wait_for_ccid */ sk->sk_write_space(sk); /* * Update timeout interval for the nofeedback timer. In order to control * rate halving on networks with very low RTTs (<= 1 ms), use per-route * tunable RTAX_RTO_MIN value as the lower bound. */ hc->tx_t_rto = max_t(u32, 4 * hc->tx_rtt, USEC_PER_SEC/HZ * tcp_rto_min(sk)); /* * Schedule no feedback timer to expire in * max(t_RTO, 2 * s/X) = max(t_RTO, 2 * t_ipi) */ t_nfb = max(hc->tx_t_rto, 2 * hc->tx_t_ipi); ccid3_pr_debug("%s(%p), Scheduled no feedback timer to " "expire in %lu jiffies (%luus)\n", dccp_role(sk), sk, usecs_to_jiffies(t_nfb), t_nfb); sk_reset_timer(sk, &hc->tx_no_feedback_timer, jiffies + usecs_to_jiffies(t_nfb)); } static int ccid3_hc_tx_parse_options(struct sock *sk, u8 packet_type, u8 option, u8 *optval, u8 optlen) { struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); __be32 opt_val; switch (option) { case TFRC_OPT_RECEIVE_RATE: case TFRC_OPT_LOSS_EVENT_RATE: /* Must be ignored on Data packets, cf. RFC 4342 8.3 and 8.5 */ if (packet_type == DCCP_PKT_DATA) break; if (unlikely(optlen != 4)) { DCCP_WARN("%s(%p), invalid len %d for %u\n", dccp_role(sk), sk, optlen, option); return -EINVAL; } opt_val = ntohl(get_unaligned((__be32 *)optval)); if (option == TFRC_OPT_RECEIVE_RATE) { /* Receive Rate is kept in units of 64 bytes/second */ hc->tx_x_recv = opt_val; hc->tx_x_recv <<= 6; ccid3_pr_debug("%s(%p), RECEIVE_RATE=%u\n", dccp_role(sk), sk, opt_val); } else { /* Update the fixpoint Loss Event Rate fraction */ hc->tx_p = tfrc_invert_loss_event_rate(opt_val); ccid3_pr_debug("%s(%p), LOSS_EVENT_RATE=%u\n", dccp_role(sk), sk, opt_val); } } return 0; } static int ccid3_hc_tx_init(struct ccid *ccid, struct sock *sk) { struct ccid3_hc_tx_sock *hc = ccid_priv(ccid); hc->tx_state = TFRC_SSTATE_NO_SENT; hc->tx_hist = NULL; hc->sk = sk; timer_setup(&hc->tx_no_feedback_timer, ccid3_hc_tx_no_feedback_timer, 0); return 0; } static void ccid3_hc_tx_exit(struct sock *sk) { struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); sk_stop_timer(sk, &hc->tx_no_feedback_timer); tfrc_tx_hist_purge(&hc->tx_hist); } static void ccid3_hc_tx_get_info(struct sock *sk, struct tcp_info *info) { info->tcpi_rto = ccid3_hc_tx_sk(sk)->tx_t_rto; info->tcpi_rtt = ccid3_hc_tx_sk(sk)->tx_rtt; } static int ccid3_hc_tx_getsockopt(struct sock *sk, const int optname, int len, u32 __user *optval, int __user *optlen) { const struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); struct tfrc_tx_info tfrc; const void *val; switch (optname) { case DCCP_SOCKOPT_CCID_TX_INFO: if (len < sizeof(tfrc)) return -EINVAL; memset(&tfrc, 0, sizeof(tfrc)); tfrc.tfrctx_x = hc->tx_x; tfrc.tfrctx_x_recv = hc->tx_x_recv; tfrc.tfrctx_x_calc = hc->tx_x_calc; tfrc.tfrctx_rtt = hc->tx_rtt; tfrc.tfrctx_p = hc->tx_p; tfrc.tfrctx_rto = hc->tx_t_rto; tfrc.tfrctx_ipi = hc->tx_t_ipi; len = sizeof(tfrc); val = &tfrc; break; default: return -ENOPROTOOPT; } if (put_user(len, optlen) || copy_to_user(optval, val, len)) return -EFAULT; return 0; } /* * Receiver Half-Connection Routines */ /* CCID3 feedback types */ enum ccid3_fback_type { CCID3_FBACK_NONE = 0, CCID3_FBACK_INITIAL, CCID3_FBACK_PERIODIC, CCID3_FBACK_PARAM_CHANGE }; #ifdef CONFIG_IP_DCCP_CCID3_DEBUG static const char *ccid3_rx_state_name(enum ccid3_hc_rx_states state) { static const char *const ccid3_rx_state_names[] = { [TFRC_RSTATE_NO_DATA] = "NO_DATA", [TFRC_RSTATE_DATA] = "DATA", }; return ccid3_rx_state_names[state]; } #endif static void ccid3_hc_rx_set_state(struct sock *sk, enum ccid3_hc_rx_states state) { struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); enum ccid3_hc_rx_states oldstate = hc->rx_state; ccid3_pr_debug("%s(%p) %-8.8s -> %s\n", dccp_role(sk), sk, ccid3_rx_state_name(oldstate), ccid3_rx_state_name(state)); WARN_ON(state == oldstate); hc->rx_state = state; } static void ccid3_hc_rx_send_feedback(struct sock *sk, const struct sk_buff *skb, enum ccid3_fback_type fbtype) { struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); struct dccp_sock *dp = dccp_sk(sk); ktime_t now = ktime_get(); s64 delta = 0; switch (fbtype) { case CCID3_FBACK_INITIAL: hc->rx_x_recv = 0; hc->rx_pinv = ~0U; /* see RFC 4342, 8.5 */ break; case CCID3_FBACK_PARAM_CHANGE: /* * When parameters change (new loss or p > p_prev), we do not * have a reliable estimate for R_m of [RFC 3448, 6.2] and so * need to reuse the previous value of X_recv. However, when * X_recv was 0 (due to early loss), this would kill X down to * s/t_mbi (i.e. one packet in 64 seconds). * To avoid such drastic reduction, we approximate X_recv as * the number of bytes since last feedback. * This is a safe fallback, since X is bounded above by X_calc. */ if (hc->rx_x_recv > 0) break; fallthrough; case CCID3_FBACK_PERIODIC: delta = ktime_us_delta(now, hc->rx_tstamp_last_feedback); if (delta <= 0) delta = 1; hc->rx_x_recv = scaled_div32(hc->rx_bytes_recv, delta); break; default: return; } ccid3_pr_debug("Interval %lldusec, X_recv=%u, 1/p=%u\n", delta, hc->rx_x_recv, hc->rx_pinv); hc->rx_tstamp_last_feedback = now; hc->rx_last_counter = dccp_hdr(skb)->dccph_ccval; hc->rx_bytes_recv = 0; dp->dccps_hc_rx_insert_options = 1; dccp_send_ack(sk); } static int ccid3_hc_rx_insert_options(struct sock *sk, struct sk_buff *skb) { const struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); __be32 x_recv, pinv; if (!(sk->sk_state == DCCP_OPEN || sk->sk_state == DCCP_PARTOPEN)) return 0; if (dccp_packet_without_ack(skb)) return 0; x_recv = htonl(hc->rx_x_recv); pinv = htonl(hc->rx_pinv); if (dccp_insert_option(skb, TFRC_OPT_LOSS_EVENT_RATE, &pinv, sizeof(pinv)) || dccp_insert_option(skb, TFRC_OPT_RECEIVE_RATE, &x_recv, sizeof(x_recv))) return -1; return 0; } /** * ccid3_first_li - Implements [RFC 5348, 6.3.1] * @sk: socket to calculate loss interval for * * Determine the length of the first loss interval via inverse lookup. * Assume that X_recv can be computed by the throughput equation * s * X_recv = -------- * R * fval * Find some p such that f(p) = fval; return 1/p (scaled). */ static u32 ccid3_first_li(struct sock *sk) { struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); u32 x_recv, p; s64 delta; u64 fval; if (hc->rx_rtt == 0) { DCCP_WARN("No RTT estimate available, using fallback RTT\n"); hc->rx_rtt = DCCP_FALLBACK_RTT; } delta = ktime_us_delta(ktime_get(), hc->rx_tstamp_last_feedback); if (delta <= 0) delta = 1; x_recv = scaled_div32(hc->rx_bytes_recv, delta); if (x_recv == 0) { /* would also trigger divide-by-zero */ DCCP_WARN("X_recv==0\n"); if (hc->rx_x_recv == 0) { DCCP_BUG("stored value of X_recv is zero"); return ~0U; } x_recv = hc->rx_x_recv; } fval = scaled_div(hc->rx_s, hc->rx_rtt); fval = scaled_div32(fval, x_recv); p = tfrc_calc_x_reverse_lookup(fval); ccid3_pr_debug("%s(%p), receive rate=%u bytes/s, implied " "loss rate=%u\n", dccp_role(sk), sk, x_recv, p); return p == 0 ? ~0U : scaled_div(1, p); } static void ccid3_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb) { struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); enum ccid3_fback_type do_feedback = CCID3_FBACK_NONE; const u64 ndp = dccp_sk(sk)->dccps_options_received.dccpor_ndp; const bool is_data_packet = dccp_data_packet(skb); if (unlikely(hc->rx_state == TFRC_RSTATE_NO_DATA)) { if (is_data_packet) { const u32 payload = skb->len - dccp_hdr(skb)->dccph_doff * 4; do_feedback = CCID3_FBACK_INITIAL; ccid3_hc_rx_set_state(sk, TFRC_RSTATE_DATA); hc->rx_s = payload; /* * Not necessary to update rx_bytes_recv here, * since X_recv = 0 for the first feedback packet (cf. * RFC 3448, 6.3) -- gerrit */ } goto update_records; } if (tfrc_rx_hist_duplicate(&hc->rx_hist, skb)) return; /* done receiving */ if (is_data_packet) { const u32 payload = skb->len - dccp_hdr(skb)->dccph_doff * 4; /* * Update moving-average of s and the sum of received payload bytes */ hc->rx_s = tfrc_ewma(hc->rx_s, payload, 9); hc->rx_bytes_recv += payload; } /* * Perform loss detection and handle pending losses */ if (tfrc_rx_handle_loss(&hc->rx_hist, &hc->rx_li_hist, skb, ndp, ccid3_first_li, sk)) { do_feedback = CCID3_FBACK_PARAM_CHANGE; goto done_receiving; } if (tfrc_rx_hist_loss_pending(&hc->rx_hist)) return; /* done receiving */ /* * Handle data packets: RTT sampling and monitoring p */ if (unlikely(!is_data_packet)) goto update_records; if (!tfrc_lh_is_initialised(&hc->rx_li_hist)) { const u32 sample = tfrc_rx_hist_sample_rtt(&hc->rx_hist, skb); /* * Empty loss history: no loss so far, hence p stays 0. * Sample RTT values, since an RTT estimate is required for the * computation of p when the first loss occurs; RFC 3448, 6.3.1. */ if (sample != 0) hc->rx_rtt = tfrc_ewma(hc->rx_rtt, sample, 9); } else if (tfrc_lh_update_i_mean(&hc->rx_li_hist, skb)) { /* * Step (3) of [RFC 3448, 6.1]: Recompute I_mean and, if I_mean * has decreased (resp. p has increased), send feedback now. */ do_feedback = CCID3_FBACK_PARAM_CHANGE; } /* * Check if the periodic once-per-RTT feedback is due; RFC 4342, 10.3 */ if (SUB16(dccp_hdr(skb)->dccph_ccval, hc->rx_last_counter) > 3) do_feedback = CCID3_FBACK_PERIODIC; update_records: tfrc_rx_hist_add_packet(&hc->rx_hist, skb, ndp); done_receiving: if (do_feedback) ccid3_hc_rx_send_feedback(sk, skb, do_feedback); } static int ccid3_hc_rx_init(struct ccid *ccid, struct sock *sk) { struct ccid3_hc_rx_sock *hc = ccid_priv(ccid); hc->rx_state = TFRC_RSTATE_NO_DATA; tfrc_lh_init(&hc->rx_li_hist); return tfrc_rx_hist_alloc(&hc->rx_hist); } static void ccid3_hc_rx_exit(struct sock *sk) { struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); tfrc_rx_hist_purge(&hc->rx_hist); tfrc_lh_cleanup(&hc->rx_li_hist); } static void ccid3_hc_rx_get_info(struct sock *sk, struct tcp_info *info) { info->tcpi_ca_state = ccid3_hc_rx_sk(sk)->rx_state; info->tcpi_options |= TCPI_OPT_TIMESTAMPS; info->tcpi_rcv_rtt = ccid3_hc_rx_sk(sk)->rx_rtt; } static int ccid3_hc_rx_getsockopt(struct sock *sk, const int optname, int len, u32 __user *optval, int __user *optlen) { const struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); struct tfrc_rx_info rx_info; const void *val; switch (optname) { case DCCP_SOCKOPT_CCID_RX_INFO: if (len < sizeof(rx_info)) return -EINVAL; rx_info.tfrcrx_x_recv = hc->rx_x_recv; rx_info.tfrcrx_rtt = hc->rx_rtt; rx_info.tfrcrx_p = tfrc_invert_loss_event_rate(hc->rx_pinv); len = sizeof(rx_info); val = &rx_info; break; default: return -ENOPROTOOPT; } if (put_user(len, optlen) || copy_to_user(optval, val, len)) return -EFAULT; return 0; } struct ccid_operations ccid3_ops = { .ccid_id = DCCPC_CCID3, .ccid_name = "TCP-Friendly Rate Control", .ccid_hc_tx_obj_size = sizeof(struct ccid3_hc_tx_sock), .ccid_hc_tx_init = ccid3_hc_tx_init, .ccid_hc_tx_exit = ccid3_hc_tx_exit, .ccid_hc_tx_send_packet = ccid3_hc_tx_send_packet, .ccid_hc_tx_packet_sent = ccid3_hc_tx_packet_sent, .ccid_hc_tx_packet_recv = ccid3_hc_tx_packet_recv, .ccid_hc_tx_parse_options = ccid3_hc_tx_parse_options, .ccid_hc_rx_obj_size = sizeof(struct ccid3_hc_rx_sock), .ccid_hc_rx_init = ccid3_hc_rx_init, .ccid_hc_rx_exit = ccid3_hc_rx_exit, .ccid_hc_rx_insert_options = ccid3_hc_rx_insert_options, .ccid_hc_rx_packet_recv = ccid3_hc_rx_packet_recv, .ccid_hc_rx_get_info = ccid3_hc_rx_get_info, .ccid_hc_tx_get_info = ccid3_hc_tx_get_info, .ccid_hc_rx_getsockopt = ccid3_hc_rx_getsockopt, .ccid_hc_tx_getsockopt = ccid3_hc_tx_getsockopt, }; #ifdef CONFIG_IP_DCCP_CCID3_DEBUG module_param(ccid3_debug, bool, 0644); MODULE_PARM_DESC(ccid3_debug, "Enable CCID-3 debug messages"); #endif |
| 125 1813 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_MMU_CONTEXT_H #define _ASM_X86_MMU_CONTEXT_H #include <asm/desc.h> #include <linux/atomic.h> #include <linux/mm_types.h> #include <linux/pkeys.h> #include <trace/events/tlb.h> #include <asm/tlbflush.h> #include <asm/paravirt.h> #include <asm/debugreg.h> #include <asm/gsseg.h> extern atomic64_t last_mm_ctx_id; #ifdef CONFIG_PERF_EVENTS DECLARE_STATIC_KEY_FALSE(rdpmc_never_available_key); DECLARE_STATIC_KEY_FALSE(rdpmc_always_available_key); void cr4_update_pce(void *ignored); #endif #ifdef CONFIG_MODIFY_LDT_SYSCALL /* * ldt_structs can be allocated, used, and freed, but they are never * modified while live. */ struct ldt_struct { /* * Xen requires page-aligned LDTs with special permissions. This is * needed to prevent us from installing evil descriptors such as * call gates. On native, we could merge the ldt_struct and LDT * allocations, but it's not worth trying to optimize. */ struct desc_struct *entries; unsigned int nr_entries; /* * If PTI is in use, then the entries array is not mapped while we're * in user mode. The whole array will be aliased at the addressed * given by ldt_slot_va(slot). We use two slots so that we can allocate * and map, and enable a new LDT without invalidating the mapping * of an older, still-in-use LDT. * * slot will be -1 if this LDT doesn't have an alias mapping. */ int slot; }; /* * Used for LDT copy/destruction. */ static inline void init_new_context_ldt(struct mm_struct *mm) { mm->context.ldt = NULL; init_rwsem(&mm->context.ldt_usr_sem); } int ldt_dup_context(struct mm_struct *oldmm, struct mm_struct *mm); void destroy_context_ldt(struct mm_struct *mm); void ldt_arch_exit_mmap(struct mm_struct *mm); #else /* CONFIG_MODIFY_LDT_SYSCALL */ static inline void init_new_context_ldt(struct mm_struct *mm) { } static inline int ldt_dup_context(struct mm_struct *oldmm, struct mm_struct *mm) { return 0; } static inline void destroy_context_ldt(struct mm_struct *mm) { } static inline void ldt_arch_exit_mmap(struct mm_struct *mm) { } #endif #ifdef CONFIG_MODIFY_LDT_SYSCALL extern void load_mm_ldt(struct mm_struct *mm); extern void switch_ldt(struct mm_struct *prev, struct mm_struct *next); #else static inline void load_mm_ldt(struct mm_struct *mm) { clear_LDT(); } static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next) { DEBUG_LOCKS_WARN_ON(preemptible()); } #endif #ifdef CONFIG_ADDRESS_MASKING static inline unsigned long mm_lam_cr3_mask(struct mm_struct *mm) { /* * When switch_mm_irqs_off() is called for a kthread, it may race with * LAM enablement. switch_mm_irqs_off() uses the LAM mask to do two * things: populate CR3 and populate 'cpu_tlbstate.lam'. Make sure it * reads a single value for both. */ return READ_ONCE(mm->context.lam_cr3_mask); } static inline void dup_lam(struct mm_struct *oldmm, struct mm_struct *mm) { mm->context.lam_cr3_mask = oldmm->context.lam_cr3_mask; mm->context.untag_mask = oldmm->context.untag_mask; } #define mm_untag_mask mm_untag_mask static inline unsigned long mm_untag_mask(struct mm_struct *mm) { return mm->context.untag_mask; } static inline void mm_reset_untag_mask(struct mm_struct *mm) { mm->context.untag_mask = -1UL; } #define arch_pgtable_dma_compat arch_pgtable_dma_compat static inline bool arch_pgtable_dma_compat(struct mm_struct *mm) { return !mm_lam_cr3_mask(mm) || test_bit(MM_CONTEXT_FORCE_TAGGED_SVA, &mm->context.flags); } #else static inline unsigned long mm_lam_cr3_mask(struct mm_struct *mm) { return 0; } static inline void dup_lam(struct mm_struct *oldmm, struct mm_struct *mm) { } static inline void mm_reset_untag_mask(struct mm_struct *mm) { } #endif #define enter_lazy_tlb enter_lazy_tlb extern void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk); /* * Init a new mm. Used on mm copies, like at fork() * and on mm's that are brand-new, like at execve(). */ #define init_new_context init_new_context static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { mutex_init(&mm->context.lock); mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id); atomic64_set(&mm->context.tlb_gen, 0); #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS if (cpu_feature_enabled(X86_FEATURE_OSPKE)) { /* pkey 0 is the default and allocated implicitly */ mm->context.pkey_allocation_map = 0x1; /* -1 means unallocated or invalid */ mm->context.execute_only_pkey = -1; } #endif mm_reset_untag_mask(mm); init_new_context_ldt(mm); return 0; } #define destroy_context destroy_context static inline void destroy_context(struct mm_struct *mm) { destroy_context_ldt(mm); } extern void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk); extern void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk); #define switch_mm_irqs_off switch_mm_irqs_off #define activate_mm(prev, next) \ do { \ paravirt_enter_mmap(next); \ switch_mm((prev), (next), NULL); \ } while (0); #ifdef CONFIG_X86_32 #define deactivate_mm(tsk, mm) \ do { \ loadsegment(gs, 0); \ } while (0) #else #define deactivate_mm(tsk, mm) \ do { \ shstk_free(tsk); \ load_gs_index(0); \ loadsegment(fs, 0); \ } while (0) #endif static inline void arch_dup_pkeys(struct mm_struct *oldmm, struct mm_struct *mm) { #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return; /* Duplicate the oldmm pkey state in mm: */ mm->context.pkey_allocation_map = oldmm->context.pkey_allocation_map; mm->context.execute_only_pkey = oldmm->context.execute_only_pkey; #endif } static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { arch_dup_pkeys(oldmm, mm); paravirt_enter_mmap(mm); dup_lam(oldmm, mm); return ldt_dup_context(oldmm, mm); } static inline void arch_exit_mmap(struct mm_struct *mm) { paravirt_arch_exit_mmap(mm); ldt_arch_exit_mmap(mm); } #ifdef CONFIG_X86_64 static inline bool is_64bit_mm(struct mm_struct *mm) { return !IS_ENABLED(CONFIG_IA32_EMULATION) || !test_bit(MM_CONTEXT_UPROBE_IA32, &mm->context.flags); } #else static inline bool is_64bit_mm(struct mm_struct *mm) { return false; } #endif /* * We only want to enforce protection keys on the current process * because we effectively have no access to PKRU for other * processes or any way to tell *which * PKRU in a threaded * process we could use. * * So do not enforce things if the VMA is not from the current * mm, or if we are in a kernel thread. */ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write, bool execute, bool foreign) { /* pkeys never affect instruction fetches */ if (execute) return true; /* allow access if the VMA is not one from this process */ if (foreign || vma_is_foreign(vma)) return true; return __pkru_allows_pkey(vma_pkey(vma), write); } unsigned long __get_current_cr3_fast(void); #include <asm-generic/mmu_context.h> #endif /* _ASM_X86_MMU_CONTEXT_H */ |
| 8 8 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 | // SPDX-License-Identifier: GPL-2.0-only /* * Netlink interface for IEEE 802.15.4 stack * * Copyright 2007, 2008 Siemens AG * * Written by: * Sergey Lapin <slapin@ossfans.org> * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> * Maxim Osipov <maxim.osipov@siemens.com> */ #include <linux/kernel.h> #include <linux/gfp.h> #include <net/genetlink.h> #include <linux/nl802154.h> #include "ieee802154.h" static unsigned int ieee802154_seq_num; static DEFINE_SPINLOCK(ieee802154_seq_lock); /* Requests to userspace */ struct sk_buff *ieee802154_nl_create(int flags, u8 req) { void *hdr; struct sk_buff *msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); unsigned long f; if (!msg) return NULL; spin_lock_irqsave(&ieee802154_seq_lock, f); hdr = genlmsg_put(msg, 0, ieee802154_seq_num++, &nl802154_family, flags, req); spin_unlock_irqrestore(&ieee802154_seq_lock, f); if (!hdr) { nlmsg_free(msg); return NULL; } return msg; } int ieee802154_nl_mcast(struct sk_buff *msg, unsigned int group) { struct nlmsghdr *nlh = nlmsg_hdr(msg); void *hdr = genlmsg_data(nlmsg_data(nlh)); genlmsg_end(msg, hdr); return genlmsg_multicast(&nl802154_family, msg, 0, group, GFP_ATOMIC); } struct sk_buff *ieee802154_nl_new_reply(struct genl_info *info, int flags, u8 req) { void *hdr; struct sk_buff *msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!msg) return NULL; hdr = genlmsg_put_reply(msg, info, &nl802154_family, flags, req); if (!hdr) { nlmsg_free(msg); return NULL; } return msg; } int ieee802154_nl_reply(struct sk_buff *msg, struct genl_info *info) { struct nlmsghdr *nlh = nlmsg_hdr(msg); void *hdr = genlmsg_data(nlmsg_data(nlh)); genlmsg_end(msg, hdr); return genlmsg_reply(msg, info); } static const struct genl_small_ops ieee802154_ops[] = { /* see nl-phy.c */ IEEE802154_DUMP(IEEE802154_LIST_PHY, ieee802154_list_phy, ieee802154_dump_phy), IEEE802154_OP(IEEE802154_ADD_IFACE, ieee802154_add_iface), IEEE802154_OP(IEEE802154_DEL_IFACE, ieee802154_del_iface), /* see nl-mac.c */ IEEE802154_OP(IEEE802154_ASSOCIATE_REQ, ieee802154_associate_req), IEEE802154_OP(IEEE802154_ASSOCIATE_RESP, ieee802154_associate_resp), IEEE802154_OP(IEEE802154_DISASSOCIATE_REQ, ieee802154_disassociate_req), IEEE802154_OP(IEEE802154_SCAN_REQ, ieee802154_scan_req), IEEE802154_OP(IEEE802154_START_REQ, ieee802154_start_req), IEEE802154_DUMP(IEEE802154_LIST_IFACE, ieee802154_list_iface, ieee802154_dump_iface), IEEE802154_OP(IEEE802154_SET_MACPARAMS, ieee802154_set_macparams), IEEE802154_OP(IEEE802154_LLSEC_GETPARAMS, ieee802154_llsec_getparams), IEEE802154_OP(IEEE802154_LLSEC_SETPARAMS, ieee802154_llsec_setparams), IEEE802154_DUMP(IEEE802154_LLSEC_LIST_KEY, NULL, ieee802154_llsec_dump_keys), IEEE802154_OP(IEEE802154_LLSEC_ADD_KEY, ieee802154_llsec_add_key), IEEE802154_OP(IEEE802154_LLSEC_DEL_KEY, ieee802154_llsec_del_key), IEEE802154_DUMP(IEEE802154_LLSEC_LIST_DEV, NULL, ieee802154_llsec_dump_devs), IEEE802154_OP(IEEE802154_LLSEC_ADD_DEV, ieee802154_llsec_add_dev), IEEE802154_OP(IEEE802154_LLSEC_DEL_DEV, ieee802154_llsec_del_dev), IEEE802154_DUMP(IEEE802154_LLSEC_LIST_DEVKEY, NULL, ieee802154_llsec_dump_devkeys), IEEE802154_OP(IEEE802154_LLSEC_ADD_DEVKEY, ieee802154_llsec_add_devkey), IEEE802154_OP(IEEE802154_LLSEC_DEL_DEVKEY, ieee802154_llsec_del_devkey), IEEE802154_DUMP(IEEE802154_LLSEC_LIST_SECLEVEL, NULL, ieee802154_llsec_dump_seclevels), IEEE802154_OP(IEEE802154_LLSEC_ADD_SECLEVEL, ieee802154_llsec_add_seclevel), IEEE802154_OP(IEEE802154_LLSEC_DEL_SECLEVEL, ieee802154_llsec_del_seclevel), }; static const struct genl_multicast_group ieee802154_mcgrps[] = { [IEEE802154_COORD_MCGRP] = { .name = IEEE802154_MCAST_COORD_NAME, }, [IEEE802154_BEACON_MCGRP] = { .name = IEEE802154_MCAST_BEACON_NAME, }, }; struct genl_family nl802154_family __ro_after_init = { .hdrsize = 0, .name = IEEE802154_NL_NAME, .version = 1, .maxattr = IEEE802154_ATTR_MAX, .policy = ieee802154_policy, .module = THIS_MODULE, .small_ops = ieee802154_ops, .n_small_ops = ARRAY_SIZE(ieee802154_ops), .resv_start_op = IEEE802154_LLSEC_DEL_SECLEVEL + 1, .mcgrps = ieee802154_mcgrps, .n_mcgrps = ARRAY_SIZE(ieee802154_mcgrps), }; int __init ieee802154_nl_init(void) { return genl_register_family(&nl802154_family); } void ieee802154_nl_exit(void) { genl_unregister_family(&nl802154_family); } |
| 127 119 119 1 119 119 7 7 15 15 15 15 15 14 15 7 15 15 15 207 5 12 292 172 136 199 29 30 5 19 4 15 15 1 15 2 5 86 2 166 148 162 162 160 5 157 10 4 3 3 151 2 2 3 148 147 17 6 13 9 5 5 4 1 1 12 12 4 12 1 2 2 5 1 7 3 1 1 27 26 1 6 1 2 16 5 6 1 165 129 59 3 160 2 1 2 1 2 1 12 12 1 2 5 59 21 38 2 53 2 1 41 1 2 1 5 16 24 16 22 38 9 48 2 45 8 8 8 8 6 1 34 1 34 1 32 25 1 14 16 16 16 3 11 6 8 14 2 16 16 129 19 3 18 153 1 154 11 16 11 19 8 21 5 130 1 1 1 16 1 115 2 108 4 1 3 1 2 1 1 26 26 26 1 18 2 4 120 1 16 111 120 119 111 8 119 5 5 2 1 18 106 106 3 114 1 114 16 104 25 128 1 117 1 116 3 120 152 154 146 121 139 2 1 8 117 76 23 2 17 121 103 129 12 13 26 27 1 25 1 21 4 5 1 18 18 15 2 17 2 17 1 15 2 2 11 2 3 2 4 1 1 8 1 7 6 7 2 5 1 2 4 1 1 1 1 21 17 13 15 1 3 1 1 15 3 4 3 17 2 1 9 8 1 1 11 7 4 18 2 1 9 8 6 4 14 4 2 17 1 2 1 2 2 1 1 2 16 2 2 3 29 26 2 1 1 1 19 4 23 15 14 11 10 3 1 2 2 1 3 1 2 2 1 10 1 9 1 2 3 4 3 2 4 1 5 2 10 1 7 3 3 1 1 1 1 1 1 1 1 1 10 1 1 9 1 2 2 4 3 3 10 1 1 9 3 2 2 3 3 2 4 1 1 1 1 1 1 8 1 7 5 2 2 4 2 2 1 1 1 1 10 1 9 7 1 1 2 1 1 2 2 1 3 1 1 9 1 1 7 8 7 1 5 5 5 1 3 7 1 1 5 2 1 1 1 9 1 9 2 2 2 4 3 3 1 1 1 1 1 13 1 3 9 12 6 2 2 8 5 4 7 1 1 4 1 7 1 1 1 4 12 1 1 11 2 2 4 5 5 3 3 12 1 10 3 2 4 4 6 2 2 10 1 10 2 1 4 4 6 1 2 13 1 13 2 3 4 4 6 1 2 6 1 2 4 1 1 13 1 11 1 1 1 1 1 8 6 3 1 2 2 1 1 2 2 1 3 1 3 1 1 1 1 1 8 1 7 7 10 1 1 7 2 9 3 3 3 3 4 2 8 1 7 7 12 1 1 10 2 3 2 3 3 2 16 1 1 14 2 9 8 1 8 2 4 7 1 6 2 2 21 1 1 19 2 10 3 6 5 4 16 1 15 13 4 9 8 1 7 7 5 1 1 1 1 4 4 2 1 1 11 1 1 9 1 2 6 3 5 7 1 6 6 4 1 10 1 9 9 1 6 1 8 1 7 7 8 1 1 6 5 2 11 1 1 1 8 7 2 15 1 1 1 3 9 6 4 4 506 502 54 399 398 1 20 7 8 8 2 8 4 28 11 3 3 11 11 4 7 2 8 10 2 9 2 10 2 13 7 6 13 12 11 14 6 8 5 2 2 8 11 8 12 16 9 7 20 15 8 4 11 7 10 7 8 11 15 16 2 14 17 1 1 16 2 1 1 17 1 2 14 14 9 12 12 9 2 1 22 22 12 11 23 16 16 15 1 16 8 1 2 9 4 4 13 8 16 13 10 15 15 15 1 2 2 2 16 12 9 2 12 7 4 8 1 1 6 3 1 1 1 4 1 1 1 1 1 1 1 3 1 1 3 1 2 4 1 1 1 1 11 11 5 1 6 11 6 1 5 4 1 11 1 1 6 4 4 1 1 1 1 18 16 2 1 11 4 2 15 11 3 3 2 1 3 4 4 5 1 6 1 12 15 6 1 8 8 12 9 3 1 5 1 1 9 3 1 1 1 11 1 1 9 3 1 1 1 1 3 4 1 1 2 4 3 4 4 16 1 1 9 7 4 1 6 1 4 4 5 1 4 1 5 10 1 1 8 3 2 3 1 1 1 9 1 1 7 5 2 1 5 10 1 1 8 7 2 1 5 3 1 1 10 1 1 8 6 2 1 5 11 1 1 9 6 3 3 1 6 3 1 1 12 1 1 10 8 3 1 7 11 2 1 1 9 6 2 1 2 4 3 1 1 3 1 1 12 2 1 1 10 7 2 2 6 6 2 1 1 1 2 12 1 1 10 8 2 1 2 3 1 3 9 1 1 7 3 2 11 1 1 9 8 2 1 3 3 1 3 1 2 3 1 1 1 1 3 1 1 1 7 1 1 3 1 4 4 11 1 1 1 1 7 5 2 7 10 1 1 8 2 1 2 4 1 2 1 3 1 1 1 10 1 1 8 6 3 1 5 10 1 1 8 7 1 1 5 9 1 1 1 1 5 2 2 11 1 1 1 1 8 3 1 1 1 10 1 1 8 5 4 1 6 11 1 1 9 7 2 1 6 11 1 1 9 5 5 1 7 15 1 1 13 3 1 1 6 9 1 1 7 5 2 1 5 3 1 1 8 1 1 1 5 4 1 4 4 9 1 1 7 5 2 1 4 10 1 1 8 6 2 1 5 10 1 1 8 6 2 1 5 11 1 1 9 7 3 7 13 1 1 2 1 8 6 2 2 1 6 11 1 1 1 1 8 7 3 2 1 6 503 507 2 1 4 8 3 3 4 11 4 18 15 3 10 17 35 9 10 10 3 10 11 3 10 4 3 12 3 3 12 6 12 9 11 4 7 3 9 2 10 4 3 9 10 9 12 10 11 11 15 9 3 8 9 10 10 11 13 11 21 154 152 152 138 138 138 4 5 15 15 1 14 12 8 8 1 8 8 12 144 144 1 143 11 1 11 2 9 148 1 8 3 6 9 14 1 1 13 1 2 1 9 6 7 7 5 1 6 6 3 2 144 5 9 14 14 14 14 138 2 6 6 1 4 1 13 1 10 1 1 3 2 1 1 7 7 1 6 24 24 24 5 2 20 11 1 3 7 30 31 29 29 28 28 1 5 24 29 47 27 27 68 69 69 68 1 69 85 86 5 2 2 4 35 35 35 35 32 2 35 35 3 50 141 142 108 11 18 2 28 9 5 2 1 2 2 2 1 1 1 1 15 14 1 15 15 14 1 15 15 1 13 15 15 19 18 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 8960 8961 8962 8963 8964 8965 8966 8967 8968 8969 8970 8971 8972 8973 8974 8975 8976 8977 8978 8979 8980 8981 8982 8983 8984 8985 8986 8987 8988 8989 8990 8991 8992 8993 8994 8995 8996 8997 8998 8999 9000 9001 9002 9003 9004 9005 9006 9007 9008 9009 9010 9011 9012 9013 9014 9015 9016 9017 9018 9019 9020 9021 9022 9023 9024 9025 9026 9027 9028 9029 9030 9031 9032 9033 9034 9035 9036 9037 9038 9039 9040 9041 9042 9043 9044 9045 9046 9047 9048 9049 9050 9051 9052 9053 9054 9055 9056 9057 9058 9059 9060 9061 9062 9063 9064 9065 9066 9067 9068 9069 9070 9071 9072 9073 9074 9075 9076 9077 9078 9079 9080 9081 9082 9083 9084 9085 9086 9087 9088 9089 9090 9091 9092 9093 9094 9095 9096 9097 9098 9099 9100 9101 9102 9103 9104 9105 9106 9107 9108 9109 9110 9111 9112 9113 9114 9115 9116 9117 9118 9119 9120 9121 9122 9123 9124 9125 9126 9127 9128 9129 9130 9131 9132 9133 9134 9135 9136 9137 9138 9139 9140 9141 9142 9143 9144 9145 9146 9147 9148 9149 9150 9151 9152 9153 9154 9155 9156 9157 9158 9159 9160 9161 9162 9163 9164 9165 9166 9167 9168 9169 9170 9171 9172 9173 9174 9175 9176 9177 9178 9179 9180 9181 9182 9183 9184 9185 9186 9187 9188 9189 9190 9191 9192 9193 9194 9195 9196 9197 9198 9199 9200 9201 9202 9203 9204 9205 9206 9207 9208 9209 9210 9211 9212 9213 9214 9215 9216 9217 9218 9219 9220 9221 9222 9223 9224 9225 9226 9227 9228 9229 9230 9231 9232 9233 9234 9235 9236 9237 9238 9239 9240 9241 9242 9243 9244 9245 9246 9247 9248 9249 9250 9251 9252 9253 9254 9255 9256 9257 9258 9259 9260 9261 9262 9263 9264 9265 9266 9267 9268 9269 9270 9271 9272 9273 9274 9275 9276 9277 9278 9279 9280 9281 9282 9283 9284 9285 9286 9287 9288 9289 9290 9291 9292 9293 9294 9295 9296 9297 9298 9299 9300 9301 9302 9303 9304 9305 9306 9307 9308 9309 9310 9311 9312 9313 9314 9315 9316 9317 9318 9319 9320 9321 9322 9323 9324 9325 9326 9327 9328 9329 9330 9331 9332 9333 9334 9335 9336 9337 9338 9339 9340 9341 9342 9343 9344 9345 9346 9347 9348 9349 9350 9351 9352 9353 9354 9355 9356 9357 9358 9359 9360 9361 9362 9363 9364 9365 9366 9367 9368 9369 9370 9371 9372 9373 9374 9375 9376 9377 9378 9379 9380 9381 9382 9383 9384 9385 9386 9387 9388 9389 9390 9391 9392 9393 9394 9395 9396 9397 9398 9399 9400 9401 9402 9403 9404 9405 9406 9407 9408 9409 9410 9411 9412 9413 9414 9415 9416 9417 9418 9419 9420 9421 9422 9423 9424 9425 9426 9427 9428 9429 9430 9431 9432 9433 9434 9435 9436 9437 9438 9439 9440 9441 9442 9443 9444 9445 9446 9447 9448 9449 9450 9451 9452 9453 9454 9455 9456 9457 9458 9459 9460 9461 9462 9463 9464 9465 9466 9467 9468 9469 9470 9471 9472 9473 9474 9475 9476 9477 9478 9479 9480 9481 9482 9483 9484 9485 9486 9487 9488 9489 9490 9491 9492 9493 9494 9495 9496 9497 9498 9499 9500 9501 9502 9503 9504 9505 9506 9507 9508 9509 9510 9511 9512 9513 9514 9515 9516 9517 9518 9519 9520 9521 9522 9523 9524 9525 9526 9527 9528 9529 9530 9531 9532 9533 9534 9535 9536 9537 9538 9539 9540 9541 9542 9543 9544 9545 9546 9547 9548 9549 9550 9551 9552 9553 9554 9555 9556 9557 9558 9559 9560 9561 9562 9563 9564 9565 9566 9567 9568 9569 9570 9571 9572 9573 9574 9575 9576 9577 9578 9579 9580 9581 9582 9583 9584 9585 9586 9587 9588 9589 9590 9591 9592 9593 9594 9595 9596 9597 9598 9599 9600 9601 9602 9603 9604 9605 9606 9607 9608 9609 9610 9611 9612 9613 9614 9615 9616 9617 9618 9619 9620 9621 9622 9623 9624 9625 9626 9627 9628 9629 9630 9631 9632 9633 9634 9635 9636 9637 9638 9639 9640 9641 9642 9643 9644 9645 9646 9647 9648 9649 9650 9651 9652 9653 9654 9655 9656 9657 9658 9659 9660 9661 9662 9663 9664 9665 9666 9667 9668 9669 9670 9671 9672 9673 9674 9675 9676 9677 9678 9679 9680 9681 9682 9683 9684 9685 9686 9687 9688 9689 9690 9691 9692 9693 9694 9695 9696 9697 9698 9699 9700 9701 9702 9703 9704 9705 9706 9707 9708 9709 9710 9711 9712 9713 9714 9715 9716 9717 9718 9719 9720 9721 9722 9723 9724 9725 9726 9727 9728 9729 9730 9731 9732 9733 9734 9735 9736 9737 9738 9739 9740 9741 9742 9743 9744 9745 9746 9747 9748 9749 9750 9751 9752 9753 9754 9755 9756 9757 9758 9759 9760 9761 9762 9763 9764 9765 9766 9767 9768 9769 9770 9771 | // SPDX-License-Identifier: GPL-2.0-or-later /* SCTP kernel implementation * (C) Copyright IBM Corp. 2001, 2004 * Copyright (c) 1999-2000 Cisco, Inc. * Copyright (c) 1999-2001 Motorola, Inc. * Copyright (c) 2001-2003 Intel Corp. * Copyright (c) 2001-2002 Nokia, Inc. * Copyright (c) 2001 La Monte H.P. Yarroll * * This file is part of the SCTP kernel implementation * * These functions interface with the sockets layer to implement the * SCTP Extensions for the Sockets API. * * Note that the descriptions from the specification are USER level * functions--this file is the functions which populate the struct proto * for SCTP which is the BOTTOM of the sockets interface. * * Please send any bug reports or fixes you make to the * email address(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * La Monte H.P. Yarroll <piggy@acm.org> * Narasimha Budihal <narsi@refcode.org> * Karl Knutson <karl@athena.chicago.il.us> * Jon Grimm <jgrimm@us.ibm.com> * Xingang Guo <xingang.guo@intel.com> * Daisy Chang <daisyc@us.ibm.com> * Sridhar Samudrala <samudrala@us.ibm.com> * Inaky Perez-Gonzalez <inaky.gonzalez@intel.com> * Ardelle Fan <ardelle.fan@intel.com> * Ryan Layer <rmlayer@us.ibm.com> * Anup Pemmaiah <pemmaiah@cc.usu.edu> * Kevin Gao <kevin.gao@intel.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <crypto/hash.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/wait.h> #include <linux/time.h> #include <linux/sched/signal.h> #include <linux/ip.h> #include <linux/capability.h> #include <linux/fcntl.h> #include <linux/poll.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/compat.h> #include <linux/rhashtable.h> #include <net/ip.h> #include <net/icmp.h> #include <net/route.h> #include <net/ipv6.h> #include <net/inet_common.h> #include <net/busy_poll.h> #include <trace/events/sock.h> #include <linux/socket.h> /* for sa_family_t */ #include <linux/export.h> #include <net/sock.h> #include <net/sctp/sctp.h> #include <net/sctp/sm.h> #include <net/sctp/stream_sched.h> #include <net/rps.h> /* Forward declarations for internal helper functions. */ static bool sctp_writeable(const struct sock *sk); static void sctp_wfree(struct sk_buff *skb); static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, size_t msg_len); static int sctp_wait_for_packet(struct sock *sk, int *err, long *timeo_p); static int sctp_wait_for_connect(struct sctp_association *, long *timeo_p); static int sctp_wait_for_accept(struct sock *sk, long timeo); static void sctp_wait_for_close(struct sock *sk, long timeo); static void sctp_destruct_sock(struct sock *sk); static struct sctp_af *sctp_sockaddr_af(struct sctp_sock *opt, union sctp_addr *addr, int len); static int sctp_bindx_add(struct sock *, struct sockaddr *, int); static int sctp_bindx_rem(struct sock *, struct sockaddr *, int); static int sctp_send_asconf_add_ip(struct sock *, struct sockaddr *, int); static int sctp_send_asconf_del_ip(struct sock *, struct sockaddr *, int); static int sctp_send_asconf(struct sctp_association *asoc, struct sctp_chunk *chunk); static int sctp_do_bind(struct sock *, union sctp_addr *, int); static int sctp_autobind(struct sock *sk); static int sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, struct sctp_association *assoc, enum sctp_socket_type type); static unsigned long sctp_memory_pressure; static atomic_long_t sctp_memory_allocated; static DEFINE_PER_CPU(int, sctp_memory_per_cpu_fw_alloc); struct percpu_counter sctp_sockets_allocated; static void sctp_enter_memory_pressure(struct sock *sk) { WRITE_ONCE(sctp_memory_pressure, 1); } /* Get the sndbuf space available at the time on the association. */ static inline int sctp_wspace(struct sctp_association *asoc) { struct sock *sk = asoc->base.sk; return asoc->ep->sndbuf_policy ? sk->sk_sndbuf - asoc->sndbuf_used : sk_stream_wspace(sk); } /* Increment the used sndbuf space count of the corresponding association by * the size of the outgoing data chunk. * Also, set the skb destructor for sndbuf accounting later. * * Since it is always 1-1 between chunk and skb, and also a new skb is always * allocated for chunk bundling in sctp_packet_transmit(), we can use the * destructor in the data chunk skb for the purpose of the sndbuf space * tracking. */ static inline void sctp_set_owner_w(struct sctp_chunk *chunk) { struct sctp_association *asoc = chunk->asoc; struct sock *sk = asoc->base.sk; /* The sndbuf space is tracked per association. */ sctp_association_hold(asoc); if (chunk->shkey) sctp_auth_shkey_hold(chunk->shkey); skb_set_owner_w(chunk->skb, sk); chunk->skb->destructor = sctp_wfree; /* Save the chunk pointer in skb for sctp_wfree to use later. */ skb_shinfo(chunk->skb)->destructor_arg = chunk; refcount_add(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc); asoc->sndbuf_used += chunk->skb->truesize + sizeof(struct sctp_chunk); sk_wmem_queued_add(sk, chunk->skb->truesize + sizeof(struct sctp_chunk)); sk_mem_charge(sk, chunk->skb->truesize); } static void sctp_clear_owner_w(struct sctp_chunk *chunk) { skb_orphan(chunk->skb); } #define traverse_and_process() \ do { \ msg = chunk->msg; \ if (msg == prev_msg) \ continue; \ list_for_each_entry(c, &msg->chunks, frag_list) { \ if ((clear && asoc->base.sk == c->skb->sk) || \ (!clear && asoc->base.sk != c->skb->sk)) \ cb(c); \ } \ prev_msg = msg; \ } while (0) static void sctp_for_each_tx_datachunk(struct sctp_association *asoc, bool clear, void (*cb)(struct sctp_chunk *)) { struct sctp_datamsg *msg, *prev_msg = NULL; struct sctp_outq *q = &asoc->outqueue; struct sctp_chunk *chunk, *c; struct sctp_transport *t; list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) list_for_each_entry(chunk, &t->transmitted, transmitted_list) traverse_and_process(); list_for_each_entry(chunk, &q->retransmit, transmitted_list) traverse_and_process(); list_for_each_entry(chunk, &q->sacked, transmitted_list) traverse_and_process(); list_for_each_entry(chunk, &q->abandoned, transmitted_list) traverse_and_process(); list_for_each_entry(chunk, &q->out_chunk_list, list) traverse_and_process(); } static void sctp_for_each_rx_skb(struct sctp_association *asoc, struct sock *sk, void (*cb)(struct sk_buff *, struct sock *)) { struct sk_buff *skb, *tmp; sctp_skb_for_each(skb, &asoc->ulpq.lobby, tmp) cb(skb, sk); sctp_skb_for_each(skb, &asoc->ulpq.reasm, tmp) cb(skb, sk); sctp_skb_for_each(skb, &asoc->ulpq.reasm_uo, tmp) cb(skb, sk); } /* Verify that this is a valid address. */ static inline int sctp_verify_addr(struct sock *sk, union sctp_addr *addr, int len) { struct sctp_af *af; /* Verify basic sockaddr. */ af = sctp_sockaddr_af(sctp_sk(sk), addr, len); if (!af) return -EINVAL; /* Is this a valid SCTP address? */ if (!af->addr_valid(addr, sctp_sk(sk), NULL)) return -EINVAL; if (!sctp_sk(sk)->pf->send_verify(sctp_sk(sk), (addr))) return -EINVAL; return 0; } /* Look up the association by its id. If this is not a UDP-style * socket, the ID field is always ignored. */ struct sctp_association *sctp_id2assoc(struct sock *sk, sctp_assoc_t id) { struct sctp_association *asoc = NULL; /* If this is not a UDP-style socket, assoc id should be ignored. */ if (!sctp_style(sk, UDP)) { /* Return NULL if the socket state is not ESTABLISHED. It * could be a TCP-style listening socket or a socket which * hasn't yet called connect() to establish an association. */ if (!sctp_sstate(sk, ESTABLISHED) && !sctp_sstate(sk, CLOSING)) return NULL; /* Get the first and the only association from the list. */ if (!list_empty(&sctp_sk(sk)->ep->asocs)) asoc = list_entry(sctp_sk(sk)->ep->asocs.next, struct sctp_association, asocs); return asoc; } /* Otherwise this is a UDP-style socket. */ if (id <= SCTP_ALL_ASSOC) return NULL; spin_lock_bh(&sctp_assocs_id_lock); asoc = (struct sctp_association *)idr_find(&sctp_assocs_id, (int)id); if (asoc && (asoc->base.sk != sk || asoc->base.dead)) asoc = NULL; spin_unlock_bh(&sctp_assocs_id_lock); return asoc; } /* Look up the transport from an address and an assoc id. If both address and * id are specified, the associations matching the address and the id should be * the same. */ static struct sctp_transport *sctp_addr_id2transport(struct sock *sk, struct sockaddr_storage *addr, sctp_assoc_t id) { struct sctp_association *addr_asoc = NULL, *id_asoc = NULL; struct sctp_af *af = sctp_get_af_specific(addr->ss_family); union sctp_addr *laddr = (union sctp_addr *)addr; struct sctp_transport *transport; if (!af || sctp_verify_addr(sk, laddr, af->sockaddr_len)) return NULL; addr_asoc = sctp_endpoint_lookup_assoc(sctp_sk(sk)->ep, laddr, &transport); if (!addr_asoc) return NULL; id_asoc = sctp_id2assoc(sk, id); if (id_asoc && (id_asoc != addr_asoc)) return NULL; sctp_get_pf_specific(sk->sk_family)->addr_to_user(sctp_sk(sk), (union sctp_addr *)addr); return transport; } /* API 3.1.2 bind() - UDP Style Syntax * The syntax of bind() is, * * ret = bind(int sd, struct sockaddr *addr, int addrlen); * * sd - the socket descriptor returned by socket(). * addr - the address structure (struct sockaddr_in or struct * sockaddr_in6 [RFC 2553]), * addr_len - the size of the address structure. */ static int sctp_bind(struct sock *sk, struct sockaddr *addr, int addr_len) { int retval = 0; lock_sock(sk); pr_debug("%s: sk:%p, addr:%p, addr_len:%d\n", __func__, sk, addr, addr_len); /* Disallow binding twice. */ if (!sctp_sk(sk)->ep->base.bind_addr.port) retval = sctp_do_bind(sk, (union sctp_addr *)addr, addr_len); else retval = -EINVAL; release_sock(sk); return retval; } static int sctp_get_port_local(struct sock *, union sctp_addr *); /* Verify this is a valid sockaddr. */ static struct sctp_af *sctp_sockaddr_af(struct sctp_sock *opt, union sctp_addr *addr, int len) { struct sctp_af *af; /* Check minimum size. */ if (len < sizeof (struct sockaddr)) return NULL; if (!opt->pf->af_supported(addr->sa.sa_family, opt)) return NULL; if (addr->sa.sa_family == AF_INET6) { if (len < SIN6_LEN_RFC2133) return NULL; /* V4 mapped address are really of AF_INET family */ if (ipv6_addr_v4mapped(&addr->v6.sin6_addr) && !opt->pf->af_supported(AF_INET, opt)) return NULL; } /* If we get this far, af is valid. */ af = sctp_get_af_specific(addr->sa.sa_family); if (len < af->sockaddr_len) return NULL; return af; } static void sctp_auto_asconf_init(struct sctp_sock *sp) { struct net *net = sock_net(&sp->inet.sk); if (net->sctp.default_auto_asconf) { spin_lock_bh(&net->sctp.addr_wq_lock); list_add_tail(&sp->auto_asconf_list, &net->sctp.auto_asconf_splist); spin_unlock_bh(&net->sctp.addr_wq_lock); sp->do_auto_asconf = 1; } } /* Bind a local address either to an endpoint or to an association. */ static int sctp_do_bind(struct sock *sk, union sctp_addr *addr, int len) { struct net *net = sock_net(sk); struct sctp_sock *sp = sctp_sk(sk); struct sctp_endpoint *ep = sp->ep; struct sctp_bind_addr *bp = &ep->base.bind_addr; struct sctp_af *af; unsigned short snum; int ret = 0; /* Common sockaddr verification. */ af = sctp_sockaddr_af(sp, addr, len); if (!af) { pr_debug("%s: sk:%p, newaddr:%p, len:%d EINVAL\n", __func__, sk, addr, len); return -EINVAL; } snum = ntohs(addr->v4.sin_port); pr_debug("%s: sk:%p, new addr:%pISc, port:%d, new port:%d, len:%d\n", __func__, sk, &addr->sa, bp->port, snum, len); /* PF specific bind() address verification. */ if (!sp->pf->bind_verify(sp, addr)) return -EADDRNOTAVAIL; /* We must either be unbound, or bind to the same port. * It's OK to allow 0 ports if we are already bound. * We'll just inhert an already bound port in this case */ if (bp->port) { if (!snum) snum = bp->port; else if (snum != bp->port) { pr_debug("%s: new port %d doesn't match existing port " "%d\n", __func__, snum, bp->port); return -EINVAL; } } if (snum && inet_port_requires_bind_service(net, snum) && !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) return -EACCES; /* See if the address matches any of the addresses we may have * already bound before checking against other endpoints. */ if (sctp_bind_addr_match(bp, addr, sp)) return -EINVAL; /* Make sure we are allowed to bind here. * The function sctp_get_port_local() does duplicate address * detection. */ addr->v4.sin_port = htons(snum); if (sctp_get_port_local(sk, addr)) return -EADDRINUSE; /* Refresh ephemeral port. */ if (!bp->port) { bp->port = inet_sk(sk)->inet_num; sctp_auto_asconf_init(sp); } /* Add the address to the bind address list. * Use GFP_ATOMIC since BHs will be disabled. */ ret = sctp_add_bind_addr(bp, addr, af->sockaddr_len, SCTP_ADDR_SRC, GFP_ATOMIC); if (ret) { sctp_put_port(sk); return ret; } /* Copy back into socket for getsockname() use. */ inet_sk(sk)->inet_sport = htons(inet_sk(sk)->inet_num); sp->pf->to_sk_saddr(addr, sk); return ret; } /* ADDIP Section 4.1.1 Congestion Control of ASCONF Chunks * * R1) One and only one ASCONF Chunk MAY be in transit and unacknowledged * at any one time. If a sender, after sending an ASCONF chunk, decides * it needs to transfer another ASCONF Chunk, it MUST wait until the * ASCONF-ACK Chunk returns from the previous ASCONF Chunk before sending a * subsequent ASCONF. Note this restriction binds each side, so at any * time two ASCONF may be in-transit on any given association (one sent * from each endpoint). */ static int sctp_send_asconf(struct sctp_association *asoc, struct sctp_chunk *chunk) { int retval = 0; /* If there is an outstanding ASCONF chunk, queue it for later * transmission. */ if (asoc->addip_last_asconf) { list_add_tail(&chunk->list, &asoc->addip_chunk_list); goto out; } /* Hold the chunk until an ASCONF_ACK is received. */ sctp_chunk_hold(chunk); retval = sctp_primitive_ASCONF(asoc->base.net, asoc, chunk); if (retval) sctp_chunk_free(chunk); else asoc->addip_last_asconf = chunk; out: return retval; } /* Add a list of addresses as bind addresses to local endpoint or * association. * * Basically run through each address specified in the addrs/addrcnt * array/length pair, determine if it is IPv6 or IPv4 and call * sctp_do_bind() on it. * * If any of them fails, then the operation will be reversed and the * ones that were added will be removed. * * Only sctp_setsockopt_bindx() is supposed to call this function. */ static int sctp_bindx_add(struct sock *sk, struct sockaddr *addrs, int addrcnt) { int cnt; int retval = 0; void *addr_buf; struct sockaddr *sa_addr; struct sctp_af *af; pr_debug("%s: sk:%p, addrs:%p, addrcnt:%d\n", __func__, sk, addrs, addrcnt); addr_buf = addrs; for (cnt = 0; cnt < addrcnt; cnt++) { /* The list may contain either IPv4 or IPv6 address; * determine the address length for walking thru the list. */ sa_addr = addr_buf; af = sctp_get_af_specific(sa_addr->sa_family); if (!af) { retval = -EINVAL; goto err_bindx_add; } retval = sctp_do_bind(sk, (union sctp_addr *)sa_addr, af->sockaddr_len); addr_buf += af->sockaddr_len; err_bindx_add: if (retval < 0) { /* Failed. Cleanup the ones that have been added */ if (cnt > 0) sctp_bindx_rem(sk, addrs, cnt); return retval; } } return retval; } /* Send an ASCONF chunk with Add IP address parameters to all the peers of the * associations that are part of the endpoint indicating that a list of local * addresses are added to the endpoint. * * If any of the addresses is already in the bind address list of the * association, we do not send the chunk for that association. But it will not * affect other associations. * * Only sctp_setsockopt_bindx() is supposed to call this function. */ static int sctp_send_asconf_add_ip(struct sock *sk, struct sockaddr *addrs, int addrcnt) { struct sctp_sock *sp; struct sctp_endpoint *ep; struct sctp_association *asoc; struct sctp_bind_addr *bp; struct sctp_chunk *chunk; struct sctp_sockaddr_entry *laddr; union sctp_addr *addr; union sctp_addr saveaddr; void *addr_buf; struct sctp_af *af; struct list_head *p; int i; int retval = 0; sp = sctp_sk(sk); ep = sp->ep; if (!ep->asconf_enable) return retval; pr_debug("%s: sk:%p, addrs:%p, addrcnt:%d\n", __func__, sk, addrs, addrcnt); list_for_each_entry(asoc, &ep->asocs, asocs) { if (!asoc->peer.asconf_capable) continue; if (asoc->peer.addip_disabled_mask & SCTP_PARAM_ADD_IP) continue; if (!sctp_state(asoc, ESTABLISHED)) continue; /* Check if any address in the packed array of addresses is * in the bind address list of the association. If so, * do not send the asconf chunk to its peer, but continue with * other associations. */ addr_buf = addrs; for (i = 0; i < addrcnt; i++) { addr = addr_buf; af = sctp_get_af_specific(addr->v4.sin_family); if (!af) { retval = -EINVAL; goto out; } if (sctp_assoc_lookup_laddr(asoc, addr)) break; addr_buf += af->sockaddr_len; } if (i < addrcnt) continue; /* Use the first valid address in bind addr list of * association as Address Parameter of ASCONF CHUNK. */ bp = &asoc->base.bind_addr; p = bp->address_list.next; laddr = list_entry(p, struct sctp_sockaddr_entry, list); chunk = sctp_make_asconf_update_ip(asoc, &laddr->a, addrs, addrcnt, SCTP_PARAM_ADD_IP); if (!chunk) { retval = -ENOMEM; goto out; } /* Add the new addresses to the bind address list with * use_as_src set to 0. */ addr_buf = addrs; for (i = 0; i < addrcnt; i++) { addr = addr_buf; af = sctp_get_af_specific(addr->v4.sin_family); memcpy(&saveaddr, addr, af->sockaddr_len); retval = sctp_add_bind_addr(bp, &saveaddr, sizeof(saveaddr), SCTP_ADDR_NEW, GFP_ATOMIC); addr_buf += af->sockaddr_len; } if (asoc->src_out_of_asoc_ok) { struct sctp_transport *trans; list_for_each_entry(trans, &asoc->peer.transport_addr_list, transports) { trans->cwnd = min(4*asoc->pathmtu, max_t(__u32, 2*asoc->pathmtu, 4380)); trans->ssthresh = asoc->peer.i.a_rwnd; trans->rto = asoc->rto_initial; sctp_max_rto(asoc, trans); trans->rtt = trans->srtt = trans->rttvar = 0; /* Clear the source and route cache */ sctp_transport_route(trans, NULL, sctp_sk(asoc->base.sk)); } } retval = sctp_send_asconf(asoc, chunk); } out: return retval; } /* Remove a list of addresses from bind addresses list. Do not remove the * last address. * * Basically run through each address specified in the addrs/addrcnt * array/length pair, determine if it is IPv6 or IPv4 and call * sctp_del_bind() on it. * * If any of them fails, then the operation will be reversed and the * ones that were removed will be added back. * * At least one address has to be left; if only one address is * available, the operation will return -EBUSY. * * Only sctp_setsockopt_bindx() is supposed to call this function. */ static int sctp_bindx_rem(struct sock *sk, struct sockaddr *addrs, int addrcnt) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_endpoint *ep = sp->ep; int cnt; struct sctp_bind_addr *bp = &ep->base.bind_addr; int retval = 0; void *addr_buf; union sctp_addr *sa_addr; struct sctp_af *af; pr_debug("%s: sk:%p, addrs:%p, addrcnt:%d\n", __func__, sk, addrs, addrcnt); addr_buf = addrs; for (cnt = 0; cnt < addrcnt; cnt++) { /* If the bind address list is empty or if there is only one * bind address, there is nothing more to be removed (we need * at least one address here). */ if (list_empty(&bp->address_list) || (sctp_list_single_entry(&bp->address_list))) { retval = -EBUSY; goto err_bindx_rem; } sa_addr = addr_buf; af = sctp_get_af_specific(sa_addr->sa.sa_family); if (!af) { retval = -EINVAL; goto err_bindx_rem; } if (!af->addr_valid(sa_addr, sp, NULL)) { retval = -EADDRNOTAVAIL; goto err_bindx_rem; } if (sa_addr->v4.sin_port && sa_addr->v4.sin_port != htons(bp->port)) { retval = -EINVAL; goto err_bindx_rem; } if (!sa_addr->v4.sin_port) sa_addr->v4.sin_port = htons(bp->port); /* FIXME - There is probably a need to check if sk->sk_saddr and * sk->sk_rcv_addr are currently set to one of the addresses to * be removed. This is something which needs to be looked into * when we are fixing the outstanding issues with multi-homing * socket routing and failover schemes. Refer to comments in * sctp_do_bind(). -daisy */ retval = sctp_del_bind_addr(bp, sa_addr); addr_buf += af->sockaddr_len; err_bindx_rem: if (retval < 0) { /* Failed. Add the ones that has been removed back */ if (cnt > 0) sctp_bindx_add(sk, addrs, cnt); return retval; } } return retval; } /* Send an ASCONF chunk with Delete IP address parameters to all the peers of * the associations that are part of the endpoint indicating that a list of * local addresses are removed from the endpoint. * * If any of the addresses is already in the bind address list of the * association, we do not send the chunk for that association. But it will not * affect other associations. * * Only sctp_setsockopt_bindx() is supposed to call this function. */ static int sctp_send_asconf_del_ip(struct sock *sk, struct sockaddr *addrs, int addrcnt) { struct sctp_sock *sp; struct sctp_endpoint *ep; struct sctp_association *asoc; struct sctp_transport *transport; struct sctp_bind_addr *bp; struct sctp_chunk *chunk; union sctp_addr *laddr; void *addr_buf; struct sctp_af *af; struct sctp_sockaddr_entry *saddr; int i; int retval = 0; int stored = 0; chunk = NULL; sp = sctp_sk(sk); ep = sp->ep; if (!ep->asconf_enable) return retval; pr_debug("%s: sk:%p, addrs:%p, addrcnt:%d\n", __func__, sk, addrs, addrcnt); list_for_each_entry(asoc, &ep->asocs, asocs) { if (!asoc->peer.asconf_capable) continue; if (asoc->peer.addip_disabled_mask & SCTP_PARAM_DEL_IP) continue; if (!sctp_state(asoc, ESTABLISHED)) continue; /* Check if any address in the packed array of addresses is * not present in the bind address list of the association. * If so, do not send the asconf chunk to its peer, but * continue with other associations. */ addr_buf = addrs; for (i = 0; i < addrcnt; i++) { laddr = addr_buf; af = sctp_get_af_specific(laddr->v4.sin_family); if (!af) { retval = -EINVAL; goto out; } if (!sctp_assoc_lookup_laddr(asoc, laddr)) break; addr_buf += af->sockaddr_len; } if (i < addrcnt) continue; /* Find one address in the association's bind address list * that is not in the packed array of addresses. This is to * make sure that we do not delete all the addresses in the * association. */ bp = &asoc->base.bind_addr; laddr = sctp_find_unmatch_addr(bp, (union sctp_addr *)addrs, addrcnt, sp); if ((laddr == NULL) && (addrcnt == 1)) { if (asoc->asconf_addr_del_pending) continue; asoc->asconf_addr_del_pending = kzalloc(sizeof(union sctp_addr), GFP_ATOMIC); if (asoc->asconf_addr_del_pending == NULL) { retval = -ENOMEM; goto out; } asoc->asconf_addr_del_pending->sa.sa_family = addrs->sa_family; asoc->asconf_addr_del_pending->v4.sin_port = htons(bp->port); if (addrs->sa_family == AF_INET) { struct sockaddr_in *sin; sin = (struct sockaddr_in *)addrs; asoc->asconf_addr_del_pending->v4.sin_addr.s_addr = sin->sin_addr.s_addr; } else if (addrs->sa_family == AF_INET6) { struct sockaddr_in6 *sin6; sin6 = (struct sockaddr_in6 *)addrs; asoc->asconf_addr_del_pending->v6.sin6_addr = sin6->sin6_addr; } pr_debug("%s: keep the last address asoc:%p %pISc at %p\n", __func__, asoc, &asoc->asconf_addr_del_pending->sa, asoc->asconf_addr_del_pending); asoc->src_out_of_asoc_ok = 1; stored = 1; goto skip_mkasconf; } if (laddr == NULL) return -EINVAL; /* We do not need RCU protection throughout this loop * because this is done under a socket lock from the * setsockopt call. */ chunk = sctp_make_asconf_update_ip(asoc, laddr, addrs, addrcnt, SCTP_PARAM_DEL_IP); if (!chunk) { retval = -ENOMEM; goto out; } skip_mkasconf: /* Reset use_as_src flag for the addresses in the bind address * list that are to be deleted. */ addr_buf = addrs; for (i = 0; i < addrcnt; i++) { laddr = addr_buf; af = sctp_get_af_specific(laddr->v4.sin_family); list_for_each_entry(saddr, &bp->address_list, list) { if (sctp_cmp_addr_exact(&saddr->a, laddr)) saddr->state = SCTP_ADDR_DEL; } addr_buf += af->sockaddr_len; } /* Update the route and saddr entries for all the transports * as some of the addresses in the bind address list are * about to be deleted and cannot be used as source addresses. */ list_for_each_entry(transport, &asoc->peer.transport_addr_list, transports) { sctp_transport_route(transport, NULL, sctp_sk(asoc->base.sk)); } if (stored) /* We don't need to transmit ASCONF */ continue; retval = sctp_send_asconf(asoc, chunk); } out: return retval; } /* set addr events to assocs in the endpoint. ep and addr_wq must be locked */ int sctp_asconf_mgmt(struct sctp_sock *sp, struct sctp_sockaddr_entry *addrw) { struct sock *sk = sctp_opt2sk(sp); union sctp_addr *addr; struct sctp_af *af; /* It is safe to write port space in caller. */ addr = &addrw->a; addr->v4.sin_port = htons(sp->ep->base.bind_addr.port); af = sctp_get_af_specific(addr->sa.sa_family); if (!af) return -EINVAL; if (sctp_verify_addr(sk, addr, af->sockaddr_len)) return -EINVAL; if (addrw->state == SCTP_ADDR_NEW) return sctp_send_asconf_add_ip(sk, (struct sockaddr *)addr, 1); else return sctp_send_asconf_del_ip(sk, (struct sockaddr *)addr, 1); } /* Helper for tunneling sctp_bindx() requests through sctp_setsockopt() * * API 8.1 * int sctp_bindx(int sd, struct sockaddr *addrs, int addrcnt, * int flags); * * If sd is an IPv4 socket, the addresses passed must be IPv4 addresses. * If the sd is an IPv6 socket, the addresses passed can either be IPv4 * or IPv6 addresses. * * A single address may be specified as INADDR_ANY or IN6ADDR_ANY, see * Section 3.1.2 for this usage. * * addrs is a pointer to an array of one or more socket addresses. Each * address is contained in its appropriate structure (i.e. struct * sockaddr_in or struct sockaddr_in6) the family of the address type * must be used to distinguish the address length (note that this * representation is termed a "packed array" of addresses). The caller * specifies the number of addresses in the array with addrcnt. * * On success, sctp_bindx() returns 0. On failure, sctp_bindx() returns * -1, and sets errno to the appropriate error code. * * For SCTP, the port given in each socket address must be the same, or * sctp_bindx() will fail, setting errno to EINVAL. * * The flags parameter is formed from the bitwise OR of zero or more of * the following currently defined flags: * * SCTP_BINDX_ADD_ADDR * * SCTP_BINDX_REM_ADDR * * SCTP_BINDX_ADD_ADDR directs SCTP to add the given addresses to the * association, and SCTP_BINDX_REM_ADDR directs SCTP to remove the given * addresses from the association. The two flags are mutually exclusive; * if both are given, sctp_bindx() will fail with EINVAL. A caller may * not remove all addresses from an association; sctp_bindx() will * reject such an attempt with EINVAL. * * An application can use sctp_bindx(SCTP_BINDX_ADD_ADDR) to associate * additional addresses with an endpoint after calling bind(). Or use * sctp_bindx(SCTP_BINDX_REM_ADDR) to remove some addresses a listening * socket is associated with so that no new association accepted will be * associated with those addresses. If the endpoint supports dynamic * address a SCTP_BINDX_REM_ADDR or SCTP_BINDX_ADD_ADDR may cause a * endpoint to send the appropriate message to the peer to change the * peers address lists. * * Adding and removing addresses from a connected association is * optional functionality. Implementations that do not support this * functionality should return EOPNOTSUPP. * * Basically do nothing but copying the addresses from user to kernel * land and invoking either sctp_bindx_add() or sctp_bindx_rem() on the sk. * This is used for tunneling the sctp_bindx() request through sctp_setsockopt() * from userspace. * * On exit there is no need to do sockfd_put(), sys_setsockopt() does * it. * * sk The sk of the socket * addrs The pointer to the addresses * addrssize Size of the addrs buffer * op Operation to perform (add or remove, see the flags of * sctp_bindx) * * Returns 0 if ok, <0 errno code on error. */ static int sctp_setsockopt_bindx(struct sock *sk, struct sockaddr *addrs, int addrs_size, int op) { int err; int addrcnt = 0; int walk_size = 0; struct sockaddr *sa_addr; void *addr_buf = addrs; struct sctp_af *af; pr_debug("%s: sk:%p addrs:%p addrs_size:%d opt:%d\n", __func__, sk, addr_buf, addrs_size, op); if (unlikely(addrs_size <= 0)) return -EINVAL; /* Walk through the addrs buffer and count the number of addresses. */ while (walk_size < addrs_size) { if (walk_size + sizeof(sa_family_t) > addrs_size) return -EINVAL; sa_addr = addr_buf; af = sctp_get_af_specific(sa_addr->sa_family); /* If the address family is not supported or if this address * causes the address buffer to overflow return EINVAL. */ if (!af || (walk_size + af->sockaddr_len) > addrs_size) return -EINVAL; addrcnt++; addr_buf += af->sockaddr_len; walk_size += af->sockaddr_len; } /* Do the work. */ switch (op) { case SCTP_BINDX_ADD_ADDR: /* Allow security module to validate bindx addresses. */ err = security_sctp_bind_connect(sk, SCTP_SOCKOPT_BINDX_ADD, addrs, addrs_size); if (err) return err; err = sctp_bindx_add(sk, addrs, addrcnt); if (err) return err; return sctp_send_asconf_add_ip(sk, addrs, addrcnt); case SCTP_BINDX_REM_ADDR: err = sctp_bindx_rem(sk, addrs, addrcnt); if (err) return err; return sctp_send_asconf_del_ip(sk, addrs, addrcnt); default: return -EINVAL; } } static int sctp_bind_add(struct sock *sk, struct sockaddr *addrs, int addrlen) { int err; lock_sock(sk); err = sctp_setsockopt_bindx(sk, addrs, addrlen, SCTP_BINDX_ADD_ADDR); release_sock(sk); return err; } static int sctp_connect_new_asoc(struct sctp_endpoint *ep, const union sctp_addr *daddr, const struct sctp_initmsg *init, struct sctp_transport **tp) { struct sctp_association *asoc; struct sock *sk = ep->base.sk; struct net *net = sock_net(sk); enum sctp_scope scope; int err; if (sctp_endpoint_is_peeled_off(ep, daddr)) return -EADDRNOTAVAIL; if (!ep->base.bind_addr.port) { if (sctp_autobind(sk)) return -EAGAIN; } else { if (inet_port_requires_bind_service(net, ep->base.bind_addr.port) && !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) return -EACCES; } scope = sctp_scope(daddr); asoc = sctp_association_new(ep, sk, scope, GFP_KERNEL); if (!asoc) return -ENOMEM; err = sctp_assoc_set_bind_addr_from_ep(asoc, scope, GFP_KERNEL); if (err < 0) goto free; *tp = sctp_assoc_add_peer(asoc, daddr, GFP_KERNEL, SCTP_UNKNOWN); if (!*tp) { err = -ENOMEM; goto free; } if (!init) return 0; if (init->sinit_num_ostreams) { __u16 outcnt = init->sinit_num_ostreams; asoc->c.sinit_num_ostreams = outcnt; /* outcnt has been changed, need to re-init stream */ err = sctp_stream_init(&asoc->stream, outcnt, 0, GFP_KERNEL); if (err) goto free; } if (init->sinit_max_instreams) asoc->c.sinit_max_instreams = init->sinit_max_instreams; if (init->sinit_max_attempts) asoc->max_init_attempts = init->sinit_max_attempts; if (init->sinit_max_init_timeo) asoc->max_init_timeo = msecs_to_jiffies(init->sinit_max_init_timeo); return 0; free: sctp_association_free(asoc); return err; } static int sctp_connect_add_peer(struct sctp_association *asoc, union sctp_addr *daddr, int addr_len) { struct sctp_endpoint *ep = asoc->ep; struct sctp_association *old; struct sctp_transport *t; int err; err = sctp_verify_addr(ep->base.sk, daddr, addr_len); if (err) return err; old = sctp_endpoint_lookup_assoc(ep, daddr, &t); if (old && old != asoc) return old->state >= SCTP_STATE_ESTABLISHED ? -EISCONN : -EALREADY; if (sctp_endpoint_is_peeled_off(ep, daddr)) return -EADDRNOTAVAIL; t = sctp_assoc_add_peer(asoc, daddr, GFP_KERNEL, SCTP_UNKNOWN); if (!t) return -ENOMEM; return 0; } /* __sctp_connect(struct sock* sk, struct sockaddr *kaddrs, int addrs_size) * * Common routine for handling connect() and sctp_connectx(). * Connect will come in with just a single address. */ static int __sctp_connect(struct sock *sk, struct sockaddr *kaddrs, int addrs_size, int flags, sctp_assoc_t *assoc_id) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_endpoint *ep = sp->ep; struct sctp_transport *transport; struct sctp_association *asoc; void *addr_buf = kaddrs; union sctp_addr *daddr; struct sctp_af *af; int walk_size, err; long timeo; if (sctp_sstate(sk, ESTABLISHED) || sctp_sstate(sk, CLOSING) || (sctp_style(sk, TCP) && sctp_sstate(sk, LISTENING))) return -EISCONN; daddr = addr_buf; af = sctp_get_af_specific(daddr->sa.sa_family); if (!af || af->sockaddr_len > addrs_size) return -EINVAL; err = sctp_verify_addr(sk, daddr, af->sockaddr_len); if (err) return err; asoc = sctp_endpoint_lookup_assoc(ep, daddr, &transport); if (asoc) return asoc->state >= SCTP_STATE_ESTABLISHED ? -EISCONN : -EALREADY; err = sctp_connect_new_asoc(ep, daddr, NULL, &transport); if (err) return err; asoc = transport->asoc; addr_buf += af->sockaddr_len; walk_size = af->sockaddr_len; while (walk_size < addrs_size) { err = -EINVAL; if (walk_size + sizeof(sa_family_t) > addrs_size) goto out_free; daddr = addr_buf; af = sctp_get_af_specific(daddr->sa.sa_family); if (!af || af->sockaddr_len + walk_size > addrs_size) goto out_free; if (asoc->peer.port != ntohs(daddr->v4.sin_port)) goto out_free; err = sctp_connect_add_peer(asoc, daddr, af->sockaddr_len); if (err) goto out_free; addr_buf += af->sockaddr_len; walk_size += af->sockaddr_len; } /* In case the user of sctp_connectx() wants an association * id back, assign one now. */ if (assoc_id) { err = sctp_assoc_set_id(asoc, GFP_KERNEL); if (err < 0) goto out_free; } err = sctp_primitive_ASSOCIATE(sock_net(sk), asoc, NULL); if (err < 0) goto out_free; /* Initialize sk's dport and daddr for getpeername() */ inet_sk(sk)->inet_dport = htons(asoc->peer.port); sp->pf->to_sk_daddr(daddr, sk); sk->sk_err = 0; if (assoc_id) *assoc_id = asoc->assoc_id; timeo = sock_sndtimeo(sk, flags & O_NONBLOCK); return sctp_wait_for_connect(asoc, &timeo); out_free: pr_debug("%s: took out_free path with asoc:%p kaddrs:%p err:%d\n", __func__, asoc, kaddrs, err); sctp_association_free(asoc); return err; } /* Helper for tunneling sctp_connectx() requests through sctp_setsockopt() * * API 8.9 * int sctp_connectx(int sd, struct sockaddr *addrs, int addrcnt, * sctp_assoc_t *asoc); * * If sd is an IPv4 socket, the addresses passed must be IPv4 addresses. * If the sd is an IPv6 socket, the addresses passed can either be IPv4 * or IPv6 addresses. * * A single address may be specified as INADDR_ANY or IN6ADDR_ANY, see * Section 3.1.2 for this usage. * * addrs is a pointer to an array of one or more socket addresses. Each * address is contained in its appropriate structure (i.e. struct * sockaddr_in or struct sockaddr_in6) the family of the address type * must be used to distengish the address length (note that this * representation is termed a "packed array" of addresses). The caller * specifies the number of addresses in the array with addrcnt. * * On success, sctp_connectx() returns 0. It also sets the assoc_id to * the association id of the new association. On failure, sctp_connectx() * returns -1, and sets errno to the appropriate error code. The assoc_id * is not touched by the kernel. * * For SCTP, the port given in each socket address must be the same, or * sctp_connectx() will fail, setting errno to EINVAL. * * An application can use sctp_connectx to initiate an association with * an endpoint that is multi-homed. Much like sctp_bindx() this call * allows a caller to specify multiple addresses at which a peer can be * reached. The way the SCTP stack uses the list of addresses to set up * the association is implementation dependent. This function only * specifies that the stack will try to make use of all the addresses in * the list when needed. * * Note that the list of addresses passed in is only used for setting up * the association. It does not necessarily equal the set of addresses * the peer uses for the resulting association. If the caller wants to * find out the set of peer addresses, it must use sctp_getpaddrs() to * retrieve them after the association has been set up. * * Basically do nothing but copying the addresses from user to kernel * land and invoking either sctp_connectx(). This is used for tunneling * the sctp_connectx() request through sctp_setsockopt() from userspace. * * On exit there is no need to do sockfd_put(), sys_setsockopt() does * it. * * sk The sk of the socket * addrs The pointer to the addresses * addrssize Size of the addrs buffer * * Returns >=0 if ok, <0 errno code on error. */ static int __sctp_setsockopt_connectx(struct sock *sk, struct sockaddr *kaddrs, int addrs_size, sctp_assoc_t *assoc_id) { int err = 0, flags = 0; pr_debug("%s: sk:%p addrs:%p addrs_size:%d\n", __func__, sk, kaddrs, addrs_size); /* make sure the 1st addr's sa_family is accessible later */ if (unlikely(addrs_size < sizeof(sa_family_t))) return -EINVAL; /* Allow security module to validate connectx addresses. */ err = security_sctp_bind_connect(sk, SCTP_SOCKOPT_CONNECTX, (struct sockaddr *)kaddrs, addrs_size); if (err) return err; /* in-kernel sockets don't generally have a file allocated to them * if all they do is call sock_create_kern(). */ if (sk->sk_socket->file) flags = sk->sk_socket->file->f_flags; return __sctp_connect(sk, kaddrs, addrs_size, flags, assoc_id); } /* * This is an older interface. It's kept for backward compatibility * to the option that doesn't provide association id. */ static int sctp_setsockopt_connectx_old(struct sock *sk, struct sockaddr *kaddrs, int addrs_size) { return __sctp_setsockopt_connectx(sk, kaddrs, addrs_size, NULL); } /* * New interface for the API. The since the API is done with a socket * option, to make it simple we feed back the association id is as a return * indication to the call. Error is always negative and association id is * always positive. */ static int sctp_setsockopt_connectx(struct sock *sk, struct sockaddr *kaddrs, int addrs_size) { sctp_assoc_t assoc_id = 0; int err = 0; err = __sctp_setsockopt_connectx(sk, kaddrs, addrs_size, &assoc_id); if (err) return err; else return assoc_id; } /* * New (hopefully final) interface for the API. * We use the sctp_getaddrs_old structure so that use-space library * can avoid any unnecessary allocations. The only different part * is that we store the actual length of the address buffer into the * addrs_num structure member. That way we can re-use the existing * code. */ #ifdef CONFIG_COMPAT struct compat_sctp_getaddrs_old { sctp_assoc_t assoc_id; s32 addr_num; compat_uptr_t addrs; /* struct sockaddr * */ }; #endif static int sctp_getsockopt_connectx3(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_getaddrs_old param; sctp_assoc_t assoc_id = 0; struct sockaddr *kaddrs; int err = 0; #ifdef CONFIG_COMPAT if (in_compat_syscall()) { struct compat_sctp_getaddrs_old param32; if (len < sizeof(param32)) return -EINVAL; if (copy_from_user(¶m32, optval, sizeof(param32))) return -EFAULT; param.assoc_id = param32.assoc_id; param.addr_num = param32.addr_num; param.addrs = compat_ptr(param32.addrs); } else #endif { if (len < sizeof(param)) return -EINVAL; if (copy_from_user(¶m, optval, sizeof(param))) return -EFAULT; } kaddrs = memdup_user(param.addrs, param.addr_num); if (IS_ERR(kaddrs)) return PTR_ERR(kaddrs); err = __sctp_setsockopt_connectx(sk, kaddrs, param.addr_num, &assoc_id); kfree(kaddrs); if (err == 0 || err == -EINPROGRESS) { if (copy_to_user(optval, &assoc_id, sizeof(assoc_id))) return -EFAULT; if (put_user(sizeof(assoc_id), optlen)) return -EFAULT; } return err; } /* API 3.1.4 close() - UDP Style Syntax * Applications use close() to perform graceful shutdown (as described in * Section 10.1 of [SCTP]) on ALL the associations currently represented * by a UDP-style socket. * * The syntax is * * ret = close(int sd); * * sd - the socket descriptor of the associations to be closed. * * To gracefully shutdown a specific association represented by the * UDP-style socket, an application should use the sendmsg() call, * passing no user data, but including the appropriate flag in the * ancillary data (see Section xxxx). * * If sd in the close() call is a branched-off socket representing only * one association, the shutdown is performed on that association only. * * 4.1.6 close() - TCP Style Syntax * * Applications use close() to gracefully close down an association. * * The syntax is: * * int close(int sd); * * sd - the socket descriptor of the association to be closed. * * After an application calls close() on a socket descriptor, no further * socket operations will succeed on that descriptor. * * API 7.1.4 SO_LINGER * * An application using the TCP-style socket can use this option to * perform the SCTP ABORT primitive. The linger option structure is: * * struct linger { * int l_onoff; // option on/off * int l_linger; // linger time * }; * * To enable the option, set l_onoff to 1. If the l_linger value is set * to 0, calling close() is the same as the ABORT primitive. If the * value is set to a negative value, the setsockopt() call will return * an error. If the value is set to a positive value linger_time, the * close() can be blocked for at most linger_time ms. If the graceful * shutdown phase does not finish during this period, close() will * return but the graceful shutdown phase continues in the system. */ static void sctp_close(struct sock *sk, long timeout) { struct net *net = sock_net(sk); struct sctp_endpoint *ep; struct sctp_association *asoc; struct list_head *pos, *temp; unsigned int data_was_unread; pr_debug("%s: sk:%p, timeout:%ld\n", __func__, sk, timeout); lock_sock_nested(sk, SINGLE_DEPTH_NESTING); sk->sk_shutdown = SHUTDOWN_MASK; inet_sk_set_state(sk, SCTP_SS_CLOSING); ep = sctp_sk(sk)->ep; /* Clean up any skbs sitting on the receive queue. */ data_was_unread = sctp_queue_purge_ulpevents(&sk->sk_receive_queue); data_was_unread += sctp_queue_purge_ulpevents(&sctp_sk(sk)->pd_lobby); /* Walk all associations on an endpoint. */ list_for_each_safe(pos, temp, &ep->asocs) { asoc = list_entry(pos, struct sctp_association, asocs); if (sctp_style(sk, TCP)) { /* A closed association can still be in the list if * it belongs to a TCP-style listening socket that is * not yet accepted. If so, free it. If not, send an * ABORT or SHUTDOWN based on the linger options. */ if (sctp_state(asoc, CLOSED)) { sctp_association_free(asoc); continue; } } if (data_was_unread || !skb_queue_empty(&asoc->ulpq.lobby) || !skb_queue_empty(&asoc->ulpq.reasm) || !skb_queue_empty(&asoc->ulpq.reasm_uo) || (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime)) { struct sctp_chunk *chunk; chunk = sctp_make_abort_user(asoc, NULL, 0); sctp_primitive_ABORT(net, asoc, chunk); } else sctp_primitive_SHUTDOWN(net, asoc, NULL); } /* On a TCP-style socket, block for at most linger_time if set. */ if (sctp_style(sk, TCP) && timeout) sctp_wait_for_close(sk, timeout); /* This will run the backlog queue. */ release_sock(sk); /* Supposedly, no process has access to the socket, but * the net layers still may. * Also, sctp_destroy_sock() needs to be called with addr_wq_lock * held and that should be grabbed before socket lock. */ spin_lock_bh(&net->sctp.addr_wq_lock); bh_lock_sock_nested(sk); /* Hold the sock, since sk_common_release() will put sock_put() * and we have just a little more cleanup. */ sock_hold(sk); sk_common_release(sk); bh_unlock_sock(sk); spin_unlock_bh(&net->sctp.addr_wq_lock); sock_put(sk); SCTP_DBG_OBJCNT_DEC(sock); } /* Handle EPIPE error. */ static int sctp_error(struct sock *sk, int flags, int err) { if (err == -EPIPE) err = sock_error(sk) ? : -EPIPE; if (err == -EPIPE && !(flags & MSG_NOSIGNAL)) send_sig(SIGPIPE, current, 0); return err; } /* API 3.1.3 sendmsg() - UDP Style Syntax * * An application uses sendmsg() and recvmsg() calls to transmit data to * and receive data from its peer. * * ssize_t sendmsg(int socket, const struct msghdr *message, * int flags); * * socket - the socket descriptor of the endpoint. * message - pointer to the msghdr structure which contains a single * user message and possibly some ancillary data. * * See Section 5 for complete description of the data * structures. * * flags - flags sent or received with the user message, see Section * 5 for complete description of the flags. * * Note: This function could use a rewrite especially when explicit * connect support comes in. */ /* BUG: We do not implement the equivalent of sk_stream_wait_memory(). */ static int sctp_msghdr_parse(const struct msghdr *msg, struct sctp_cmsgs *cmsgs); static int sctp_sendmsg_parse(struct sock *sk, struct sctp_cmsgs *cmsgs, struct sctp_sndrcvinfo *srinfo, const struct msghdr *msg, size_t msg_len) { __u16 sflags; int err; if (sctp_sstate(sk, LISTENING) && sctp_style(sk, TCP)) return -EPIPE; if (msg_len > sk->sk_sndbuf) return -EMSGSIZE; memset(cmsgs, 0, sizeof(*cmsgs)); err = sctp_msghdr_parse(msg, cmsgs); if (err) { pr_debug("%s: msghdr parse err:%x\n", __func__, err); return err; } memset(srinfo, 0, sizeof(*srinfo)); if (cmsgs->srinfo) { srinfo->sinfo_stream = cmsgs->srinfo->sinfo_stream; srinfo->sinfo_flags = cmsgs->srinfo->sinfo_flags; srinfo->sinfo_ppid = cmsgs->srinfo->sinfo_ppid; srinfo->sinfo_context = cmsgs->srinfo->sinfo_context; srinfo->sinfo_assoc_id = cmsgs->srinfo->sinfo_assoc_id; srinfo->sinfo_timetolive = cmsgs->srinfo->sinfo_timetolive; } if (cmsgs->sinfo) { srinfo->sinfo_stream = cmsgs->sinfo->snd_sid; srinfo->sinfo_flags = cmsgs->sinfo->snd_flags; srinfo->sinfo_ppid = cmsgs->sinfo->snd_ppid; srinfo->sinfo_context = cmsgs->sinfo->snd_context; srinfo->sinfo_assoc_id = cmsgs->sinfo->snd_assoc_id; } if (cmsgs->prinfo) { srinfo->sinfo_timetolive = cmsgs->prinfo->pr_value; SCTP_PR_SET_POLICY(srinfo->sinfo_flags, cmsgs->prinfo->pr_policy); } sflags = srinfo->sinfo_flags; if (!sflags && msg_len) return 0; if (sctp_style(sk, TCP) && (sflags & (SCTP_EOF | SCTP_ABORT))) return -EINVAL; if (((sflags & SCTP_EOF) && msg_len > 0) || (!(sflags & (SCTP_EOF | SCTP_ABORT)) && msg_len == 0)) return -EINVAL; if ((sflags & SCTP_ADDR_OVER) && !msg->msg_name) return -EINVAL; return 0; } static int sctp_sendmsg_new_asoc(struct sock *sk, __u16 sflags, struct sctp_cmsgs *cmsgs, union sctp_addr *daddr, struct sctp_transport **tp) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_association *asoc; struct cmsghdr *cmsg; __be32 flowinfo = 0; struct sctp_af *af; int err; *tp = NULL; if (sflags & (SCTP_EOF | SCTP_ABORT)) return -EINVAL; if (sctp_style(sk, TCP) && (sctp_sstate(sk, ESTABLISHED) || sctp_sstate(sk, CLOSING))) return -EADDRNOTAVAIL; /* Label connection socket for first association 1-to-many * style for client sequence socket()->sendmsg(). This * needs to be done before sctp_assoc_add_peer() as that will * set up the initial packet that needs to account for any * security ip options (CIPSO/CALIPSO) added to the packet. */ af = sctp_get_af_specific(daddr->sa.sa_family); if (!af) return -EINVAL; err = security_sctp_bind_connect(sk, SCTP_SENDMSG_CONNECT, (struct sockaddr *)daddr, af->sockaddr_len); if (err < 0) return err; err = sctp_connect_new_asoc(ep, daddr, cmsgs->init, tp); if (err) return err; asoc = (*tp)->asoc; if (!cmsgs->addrs_msg) return 0; if (daddr->sa.sa_family == AF_INET6) flowinfo = daddr->v6.sin6_flowinfo; /* sendv addr list parse */ for_each_cmsghdr(cmsg, cmsgs->addrs_msg) { union sctp_addr _daddr; int dlen; if (cmsg->cmsg_level != IPPROTO_SCTP || (cmsg->cmsg_type != SCTP_DSTADDRV4 && cmsg->cmsg_type != SCTP_DSTADDRV6)) continue; daddr = &_daddr; memset(daddr, 0, sizeof(*daddr)); dlen = cmsg->cmsg_len - sizeof(struct cmsghdr); if (cmsg->cmsg_type == SCTP_DSTADDRV4) { if (dlen < sizeof(struct in_addr)) { err = -EINVAL; goto free; } dlen = sizeof(struct in_addr); daddr->v4.sin_family = AF_INET; daddr->v4.sin_port = htons(asoc->peer.port); memcpy(&daddr->v4.sin_addr, CMSG_DATA(cmsg), dlen); } else { if (dlen < sizeof(struct in6_addr)) { err = -EINVAL; goto free; } dlen = sizeof(struct in6_addr); daddr->v6.sin6_flowinfo = flowinfo; daddr->v6.sin6_family = AF_INET6; daddr->v6.sin6_port = htons(asoc->peer.port); memcpy(&daddr->v6.sin6_addr, CMSG_DATA(cmsg), dlen); } err = sctp_connect_add_peer(asoc, daddr, sizeof(*daddr)); if (err) goto free; } return 0; free: sctp_association_free(asoc); return err; } static int sctp_sendmsg_check_sflags(struct sctp_association *asoc, __u16 sflags, struct msghdr *msg, size_t msg_len) { struct sock *sk = asoc->base.sk; struct net *net = sock_net(sk); if (sctp_state(asoc, CLOSED) && sctp_style(sk, TCP)) return -EPIPE; if ((sflags & SCTP_SENDALL) && sctp_style(sk, UDP) && !sctp_state(asoc, ESTABLISHED)) return 0; if (sflags & SCTP_EOF) { pr_debug("%s: shutting down association:%p\n", __func__, asoc); sctp_primitive_SHUTDOWN(net, asoc, NULL); return 0; } if (sflags & SCTP_ABORT) { struct sctp_chunk *chunk; chunk = sctp_make_abort_user(asoc, msg, msg_len); if (!chunk) return -ENOMEM; pr_debug("%s: aborting association:%p\n", __func__, asoc); sctp_primitive_ABORT(net, asoc, chunk); iov_iter_revert(&msg->msg_iter, msg_len); return 0; } return 1; } static int sctp_sendmsg_to_asoc(struct sctp_association *asoc, struct msghdr *msg, size_t msg_len, struct sctp_transport *transport, struct sctp_sndrcvinfo *sinfo) { struct sock *sk = asoc->base.sk; struct sctp_sock *sp = sctp_sk(sk); struct net *net = sock_net(sk); struct sctp_datamsg *datamsg; bool wait_connect = false; struct sctp_chunk *chunk; long timeo; int err; if (sinfo->sinfo_stream >= asoc->stream.outcnt) { err = -EINVAL; goto err; } if (unlikely(!SCTP_SO(&asoc->stream, sinfo->sinfo_stream)->ext)) { err = sctp_stream_init_ext(&asoc->stream, sinfo->sinfo_stream); if (err) goto err; } if (sp->disable_fragments && msg_len > asoc->frag_point) { err = -EMSGSIZE; goto err; } if (asoc->pmtu_pending) { if (sp->param_flags & SPP_PMTUD_ENABLE) sctp_assoc_sync_pmtu(asoc); asoc->pmtu_pending = 0; } if (sctp_wspace(asoc) < (int)msg_len) sctp_prsctp_prune(asoc, sinfo, msg_len - sctp_wspace(asoc)); if (sctp_wspace(asoc) <= 0 || !sk_wmem_schedule(sk, msg_len)) { timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len); if (err) goto err; if (unlikely(sinfo->sinfo_stream >= asoc->stream.outcnt)) { err = -EINVAL; goto err; } } if (sctp_state(asoc, CLOSED)) { err = sctp_primitive_ASSOCIATE(net, asoc, NULL); if (err) goto err; if (asoc->ep->intl_enable) { timeo = sock_sndtimeo(sk, 0); err = sctp_wait_for_connect(asoc, &timeo); if (err) { err = -ESRCH; goto err; } } else { wait_connect = true; } pr_debug("%s: we associated primitively\n", __func__); } datamsg = sctp_datamsg_from_user(asoc, sinfo, &msg->msg_iter); if (IS_ERR(datamsg)) { err = PTR_ERR(datamsg); goto err; } asoc->force_delay = !!(msg->msg_flags & MSG_MORE); list_for_each_entry(chunk, &datamsg->chunks, frag_list) { sctp_chunk_hold(chunk); sctp_set_owner_w(chunk); chunk->transport = transport; } err = sctp_primitive_SEND(net, asoc, datamsg); if (err) { sctp_datamsg_free(datamsg); goto err; } pr_debug("%s: we sent primitively\n", __func__); sctp_datamsg_put(datamsg); if (unlikely(wait_connect)) { timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); sctp_wait_for_connect(asoc, &timeo); } err = msg_len; err: return err; } static union sctp_addr *sctp_sendmsg_get_daddr(struct sock *sk, const struct msghdr *msg, struct sctp_cmsgs *cmsgs) { union sctp_addr *daddr = NULL; int err; if (!sctp_style(sk, UDP_HIGH_BANDWIDTH) && msg->msg_name) { int len = msg->msg_namelen; if (len > sizeof(*daddr)) len = sizeof(*daddr); daddr = (union sctp_addr *)msg->msg_name; err = sctp_verify_addr(sk, daddr, len); if (err) return ERR_PTR(err); } return daddr; } static void sctp_sendmsg_update_sinfo(struct sctp_association *asoc, struct sctp_sndrcvinfo *sinfo, struct sctp_cmsgs *cmsgs) { if (!cmsgs->srinfo && !cmsgs->sinfo) { sinfo->sinfo_stream = asoc->default_stream; sinfo->sinfo_ppid = asoc->default_ppid; sinfo->sinfo_context = asoc->default_context; sinfo->sinfo_assoc_id = sctp_assoc2id(asoc); if (!cmsgs->prinfo) sinfo->sinfo_flags = asoc->default_flags; } if (!cmsgs->srinfo && !cmsgs->prinfo) sinfo->sinfo_timetolive = asoc->default_timetolive; if (cmsgs->authinfo) { /* Reuse sinfo_tsn to indicate that authinfo was set and * sinfo_ssn to save the keyid on tx path. */ sinfo->sinfo_tsn = 1; sinfo->sinfo_ssn = cmsgs->authinfo->auth_keynumber; } } static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_transport *transport = NULL; struct sctp_sndrcvinfo _sinfo, *sinfo; struct sctp_association *asoc, *tmp; struct sctp_cmsgs cmsgs; union sctp_addr *daddr; bool new = false; __u16 sflags; int err; /* Parse and get snd_info */ err = sctp_sendmsg_parse(sk, &cmsgs, &_sinfo, msg, msg_len); if (err) goto out; sinfo = &_sinfo; sflags = sinfo->sinfo_flags; /* Get daddr from msg */ daddr = sctp_sendmsg_get_daddr(sk, msg, &cmsgs); if (IS_ERR(daddr)) { err = PTR_ERR(daddr); goto out; } lock_sock(sk); /* SCTP_SENDALL process */ if ((sflags & SCTP_SENDALL) && sctp_style(sk, UDP)) { list_for_each_entry_safe(asoc, tmp, &ep->asocs, asocs) { err = sctp_sendmsg_check_sflags(asoc, sflags, msg, msg_len); if (err == 0) continue; if (err < 0) goto out_unlock; sctp_sendmsg_update_sinfo(asoc, sinfo, &cmsgs); err = sctp_sendmsg_to_asoc(asoc, msg, msg_len, NULL, sinfo); if (err < 0) goto out_unlock; iov_iter_revert(&msg->msg_iter, err); } goto out_unlock; } /* Get and check or create asoc */ if (daddr) { asoc = sctp_endpoint_lookup_assoc(ep, daddr, &transport); if (asoc) { err = sctp_sendmsg_check_sflags(asoc, sflags, msg, msg_len); if (err <= 0) goto out_unlock; } else { err = sctp_sendmsg_new_asoc(sk, sflags, &cmsgs, daddr, &transport); if (err) goto out_unlock; asoc = transport->asoc; new = true; } if (!sctp_style(sk, TCP) && !(sflags & SCTP_ADDR_OVER)) transport = NULL; } else { asoc = sctp_id2assoc(sk, sinfo->sinfo_assoc_id); if (!asoc) { err = -EPIPE; goto out_unlock; } err = sctp_sendmsg_check_sflags(asoc, sflags, msg, msg_len); if (err <= 0) goto out_unlock; } /* Update snd_info with the asoc */ sctp_sendmsg_update_sinfo(asoc, sinfo, &cmsgs); /* Send msg to the asoc */ err = sctp_sendmsg_to_asoc(asoc, msg, msg_len, transport, sinfo); if (err < 0 && err != -ESRCH && new) sctp_association_free(asoc); out_unlock: release_sock(sk); out: return sctp_error(sk, msg->msg_flags, err); } /* This is an extended version of skb_pull() that removes the data from the * start of a skb even when data is spread across the list of skb's in the * frag_list. len specifies the total amount of data that needs to be removed. * when 'len' bytes could be removed from the skb, it returns 0. * If 'len' exceeds the total skb length, it returns the no. of bytes that * could not be removed. */ static int sctp_skb_pull(struct sk_buff *skb, int len) { struct sk_buff *list; int skb_len = skb_headlen(skb); int rlen; if (len <= skb_len) { __skb_pull(skb, len); return 0; } len -= skb_len; __skb_pull(skb, skb_len); skb_walk_frags(skb, list) { rlen = sctp_skb_pull(list, len); skb->len -= (len-rlen); skb->data_len -= (len-rlen); if (!rlen) return 0; len = rlen; } return len; } /* API 3.1.3 recvmsg() - UDP Style Syntax * * ssize_t recvmsg(int socket, struct msghdr *message, * int flags); * * socket - the socket descriptor of the endpoint. * message - pointer to the msghdr structure which contains a single * user message and possibly some ancillary data. * * See Section 5 for complete description of the data * structures. * * flags - flags sent or received with the user message, see Section * 5 for complete description of the flags. */ static int sctp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { struct sctp_ulpevent *event = NULL; struct sctp_sock *sp = sctp_sk(sk); struct sk_buff *skb, *head_skb; int copied; int err = 0; int skb_len; pr_debug("%s: sk:%p, msghdr:%p, len:%zd, flags:0x%x, addr_len:%p)\n", __func__, sk, msg, len, flags, addr_len); if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue)) sk_busy_loop(sk, flags & MSG_DONTWAIT); lock_sock(sk); if (sctp_style(sk, TCP) && !sctp_sstate(sk, ESTABLISHED) && !sctp_sstate(sk, CLOSING) && !sctp_sstate(sk, CLOSED)) { err = -ENOTCONN; goto out; } skb = sctp_skb_recv_datagram(sk, flags, &err); if (!skb) goto out; /* Get the total length of the skb including any skb's in the * frag_list. */ skb_len = skb->len; copied = skb_len; if (copied > len) copied = len; err = skb_copy_datagram_msg(skb, 0, msg, copied); event = sctp_skb2event(skb); if (err) goto out_free; if (event->chunk && event->chunk->head_skb) head_skb = event->chunk->head_skb; else head_skb = skb; sock_recv_cmsgs(msg, sk, head_skb); if (sctp_ulpevent_is_notification(event)) { msg->msg_flags |= MSG_NOTIFICATION; sp->pf->event_msgname(event, msg->msg_name, addr_len); } else { sp->pf->skb_msgname(head_skb, msg->msg_name, addr_len); } /* Check if we allow SCTP_NXTINFO. */ if (sp->recvnxtinfo) sctp_ulpevent_read_nxtinfo(event, msg, sk); /* Check if we allow SCTP_RCVINFO. */ if (sp->recvrcvinfo) sctp_ulpevent_read_rcvinfo(event, msg); /* Check if we allow SCTP_SNDRCVINFO. */ if (sctp_ulpevent_type_enabled(sp->subscribe, SCTP_DATA_IO_EVENT)) sctp_ulpevent_read_sndrcvinfo(event, msg); err = copied; /* If skb's length exceeds the user's buffer, update the skb and * push it back to the receive_queue so that the next call to * recvmsg() will return the remaining data. Don't set MSG_EOR. */ if (skb_len > copied) { msg->msg_flags &= ~MSG_EOR; if (flags & MSG_PEEK) goto out_free; sctp_skb_pull(skb, copied); skb_queue_head(&sk->sk_receive_queue, skb); /* When only partial message is copied to the user, increase * rwnd by that amount. If all the data in the skb is read, * rwnd is updated when the event is freed. */ if (!sctp_ulpevent_is_notification(event)) sctp_assoc_rwnd_increase(event->asoc, copied); goto out; } else if ((event->msg_flags & MSG_NOTIFICATION) || (event->msg_flags & MSG_EOR)) msg->msg_flags |= MSG_EOR; else msg->msg_flags &= ~MSG_EOR; out_free: if (flags & MSG_PEEK) { /* Release the skb reference acquired after peeking the skb in * sctp_skb_recv_datagram(). */ kfree_skb(skb); } else { /* Free the event which includes releasing the reference to * the owner of the skb, freeing the skb and updating the * rwnd. */ sctp_ulpevent_free(event); } out: release_sock(sk); return err; } /* 7.1.12 Enable/Disable message fragmentation (SCTP_DISABLE_FRAGMENTS) * * This option is a on/off flag. If enabled no SCTP message * fragmentation will be performed. Instead if a message being sent * exceeds the current PMTU size, the message will NOT be sent and * instead a error will be indicated to the user. */ static int sctp_setsockopt_disable_fragments(struct sock *sk, int *val, unsigned int optlen) { if (optlen < sizeof(int)) return -EINVAL; sctp_sk(sk)->disable_fragments = (*val == 0) ? 0 : 1; return 0; } static int sctp_setsockopt_events(struct sock *sk, __u8 *sn_type, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; int i; if (optlen > sizeof(struct sctp_event_subscribe)) return -EINVAL; for (i = 0; i < optlen; i++) sctp_ulpevent_type_set(&sp->subscribe, SCTP_SN_TYPE_BASE + i, sn_type[i]); list_for_each_entry(asoc, &sp->ep->asocs, asocs) asoc->subscribe = sctp_sk(sk)->subscribe; /* At the time when a user app subscribes to SCTP_SENDER_DRY_EVENT, * if there is no data to be sent or retransmit, the stack will * immediately send up this notification. */ if (sctp_ulpevent_type_enabled(sp->subscribe, SCTP_SENDER_DRY_EVENT)) { struct sctp_ulpevent *event; asoc = sctp_id2assoc(sk, 0); if (asoc && sctp_outq_is_empty(&asoc->outqueue)) { event = sctp_ulpevent_make_sender_dry_event(asoc, GFP_USER | __GFP_NOWARN); if (!event) return -ENOMEM; asoc->stream.si->enqueue_event(&asoc->ulpq, event); } } return 0; } /* 7.1.8 Automatic Close of associations (SCTP_AUTOCLOSE) * * This socket option is applicable to the UDP-style socket only. When * set it will cause associations that are idle for more than the * specified number of seconds to automatically close. An association * being idle is defined an association that has NOT sent or received * user data. The special value of '0' indicates that no automatic * close of any associations should be performed. The option expects an * integer defining the number of seconds of idle time before an * association is closed. */ static int sctp_setsockopt_autoclose(struct sock *sk, u32 *optval, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); struct net *net = sock_net(sk); /* Applicable to UDP-style socket only */ if (sctp_style(sk, TCP)) return -EOPNOTSUPP; if (optlen != sizeof(int)) return -EINVAL; sp->autoclose = *optval; if (sp->autoclose > net->sctp.max_autoclose) sp->autoclose = net->sctp.max_autoclose; return 0; } /* 7.1.13 Peer Address Parameters (SCTP_PEER_ADDR_PARAMS) * * Applications can enable or disable heartbeats for any peer address of * an association, modify an address's heartbeat interval, force a * heartbeat to be sent immediately, and adjust the address's maximum * number of retransmissions sent before an address is considered * unreachable. The following structure is used to access and modify an * address's parameters: * * struct sctp_paddrparams { * sctp_assoc_t spp_assoc_id; * struct sockaddr_storage spp_address; * uint32_t spp_hbinterval; * uint16_t spp_pathmaxrxt; * uint32_t spp_pathmtu; * uint32_t spp_sackdelay; * uint32_t spp_flags; * uint32_t spp_ipv6_flowlabel; * uint8_t spp_dscp; * }; * * spp_assoc_id - (one-to-many style socket) This is filled in the * application, and identifies the association for * this query. * spp_address - This specifies which address is of interest. * spp_hbinterval - This contains the value of the heartbeat interval, * in milliseconds. If a value of zero * is present in this field then no changes are to * be made to this parameter. * spp_pathmaxrxt - This contains the maximum number of * retransmissions before this address shall be * considered unreachable. If a value of zero * is present in this field then no changes are to * be made to this parameter. * spp_pathmtu - When Path MTU discovery is disabled the value * specified here will be the "fixed" path mtu. * Note that if the spp_address field is empty * then all associations on this address will * have this fixed path mtu set upon them. * * spp_sackdelay - When delayed sack is enabled, this value specifies * the number of milliseconds that sacks will be delayed * for. This value will apply to all addresses of an * association if the spp_address field is empty. Note * also, that if delayed sack is enabled and this * value is set to 0, no change is made to the last * recorded delayed sack timer value. * * spp_flags - These flags are used to control various features * on an association. The flag field may contain * zero or more of the following options. * * SPP_HB_ENABLE - Enable heartbeats on the * specified address. Note that if the address * field is empty all addresses for the association * have heartbeats enabled upon them. * * SPP_HB_DISABLE - Disable heartbeats on the * speicifed address. Note that if the address * field is empty all addresses for the association * will have their heartbeats disabled. Note also * that SPP_HB_ENABLE and SPP_HB_DISABLE are * mutually exclusive, only one of these two should * be specified. Enabling both fields will have * undetermined results. * * SPP_HB_DEMAND - Request a user initiated heartbeat * to be made immediately. * * SPP_HB_TIME_IS_ZERO - Specify's that the time for * heartbeat delayis to be set to the value of 0 * milliseconds. * * SPP_PMTUD_ENABLE - This field will enable PMTU * discovery upon the specified address. Note that * if the address feild is empty then all addresses * on the association are effected. * * SPP_PMTUD_DISABLE - This field will disable PMTU * discovery upon the specified address. Note that * if the address feild is empty then all addresses * on the association are effected. Not also that * SPP_PMTUD_ENABLE and SPP_PMTUD_DISABLE are mutually * exclusive. Enabling both will have undetermined * results. * * SPP_SACKDELAY_ENABLE - Setting this flag turns * on delayed sack. The time specified in spp_sackdelay * is used to specify the sack delay for this address. Note * that if spp_address is empty then all addresses will * enable delayed sack and take on the sack delay * value specified in spp_sackdelay. * SPP_SACKDELAY_DISABLE - Setting this flag turns * off delayed sack. If the spp_address field is blank then * delayed sack is disabled for the entire association. Note * also that this field is mutually exclusive to * SPP_SACKDELAY_ENABLE, setting both will have undefined * results. * * SPP_IPV6_FLOWLABEL: Setting this flag enables the * setting of the IPV6 flow label value. The value is * contained in the spp_ipv6_flowlabel field. * Upon retrieval, this flag will be set to indicate that * the spp_ipv6_flowlabel field has a valid value returned. * If a specific destination address is set (in the * spp_address field), then the value returned is that of * the address. If just an association is specified (and * no address), then the association's default flow label * is returned. If neither an association nor a destination * is specified, then the socket's default flow label is * returned. For non-IPv6 sockets, this flag will be left * cleared. * * SPP_DSCP: Setting this flag enables the setting of the * Differentiated Services Code Point (DSCP) value * associated with either the association or a specific * address. The value is obtained in the spp_dscp field. * Upon retrieval, this flag will be set to indicate that * the spp_dscp field has a valid value returned. If a * specific destination address is set when called (in the * spp_address field), then that specific destination * address's DSCP value is returned. If just an association * is specified, then the association's default DSCP is * returned. If neither an association nor a destination is * specified, then the socket's default DSCP is returned. * * spp_ipv6_flowlabel * - This field is used in conjunction with the * SPP_IPV6_FLOWLABEL flag and contains the IPv6 flow label. * The 20 least significant bits are used for the flow * label. This setting has precedence over any IPv6-layer * setting. * * spp_dscp - This field is used in conjunction with the SPP_DSCP flag * and contains the DSCP. The 6 most significant bits are * used for the DSCP. This setting has precedence over any * IPv4- or IPv6- layer setting. */ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, struct sctp_transport *trans, struct sctp_association *asoc, struct sctp_sock *sp, int hb_change, int pmtud_change, int sackdelay_change) { int error; if (params->spp_flags & SPP_HB_DEMAND && trans) { error = sctp_primitive_REQUESTHEARTBEAT(trans->asoc->base.net, trans->asoc, trans); if (error) return error; } /* Note that unless the spp_flag is set to SPP_HB_ENABLE the value of * this field is ignored. Note also that a value of zero indicates * the current setting should be left unchanged. */ if (params->spp_flags & SPP_HB_ENABLE) { /* Re-zero the interval if the SPP_HB_TIME_IS_ZERO is * set. This lets us use 0 value when this flag * is set. */ if (params->spp_flags & SPP_HB_TIME_IS_ZERO) params->spp_hbinterval = 0; if (params->spp_hbinterval || (params->spp_flags & SPP_HB_TIME_IS_ZERO)) { if (trans) { trans->hbinterval = msecs_to_jiffies(params->spp_hbinterval); sctp_transport_reset_hb_timer(trans); } else if (asoc) { asoc->hbinterval = msecs_to_jiffies(params->spp_hbinterval); } else { sp->hbinterval = params->spp_hbinterval; } } } if (hb_change) { if (trans) { trans->param_flags = (trans->param_flags & ~SPP_HB) | hb_change; } else if (asoc) { asoc->param_flags = (asoc->param_flags & ~SPP_HB) | hb_change; } else { sp->param_flags = (sp->param_flags & ~SPP_HB) | hb_change; } } /* When Path MTU discovery is disabled the value specified here will * be the "fixed" path mtu (i.e. the value of the spp_flags field must * include the flag SPP_PMTUD_DISABLE for this field to have any * effect). */ if ((params->spp_flags & SPP_PMTUD_DISABLE) && params->spp_pathmtu) { if (trans) { trans->pathmtu = params->spp_pathmtu; sctp_assoc_sync_pmtu(asoc); } else if (asoc) { sctp_assoc_set_pmtu(asoc, params->spp_pathmtu); } else { sp->pathmtu = params->spp_pathmtu; } } if (pmtud_change) { if (trans) { int update = (trans->param_flags & SPP_PMTUD_DISABLE) && (params->spp_flags & SPP_PMTUD_ENABLE); trans->param_flags = (trans->param_flags & ~SPP_PMTUD) | pmtud_change; if (update) { sctp_transport_pmtu(trans, sctp_opt2sk(sp)); sctp_assoc_sync_pmtu(asoc); } sctp_transport_pl_reset(trans); } else if (asoc) { asoc->param_flags = (asoc->param_flags & ~SPP_PMTUD) | pmtud_change; } else { sp->param_flags = (sp->param_flags & ~SPP_PMTUD) | pmtud_change; } } /* Note that unless the spp_flag is set to SPP_SACKDELAY_ENABLE the * value of this field is ignored. Note also that a value of zero * indicates the current setting should be left unchanged. */ if ((params->spp_flags & SPP_SACKDELAY_ENABLE) && params->spp_sackdelay) { if (trans) { trans->sackdelay = msecs_to_jiffies(params->spp_sackdelay); } else if (asoc) { asoc->sackdelay = msecs_to_jiffies(params->spp_sackdelay); } else { sp->sackdelay = params->spp_sackdelay; } } if (sackdelay_change) { if (trans) { trans->param_flags = (trans->param_flags & ~SPP_SACKDELAY) | sackdelay_change; } else if (asoc) { asoc->param_flags = (asoc->param_flags & ~SPP_SACKDELAY) | sackdelay_change; } else { sp->param_flags = (sp->param_flags & ~SPP_SACKDELAY) | sackdelay_change; } } /* Note that a value of zero indicates the current setting should be left unchanged. */ if (params->spp_pathmaxrxt) { if (trans) { trans->pathmaxrxt = params->spp_pathmaxrxt; } else if (asoc) { asoc->pathmaxrxt = params->spp_pathmaxrxt; } else { sp->pathmaxrxt = params->spp_pathmaxrxt; } } if (params->spp_flags & SPP_IPV6_FLOWLABEL) { if (trans) { if (trans->ipaddr.sa.sa_family == AF_INET6) { trans->flowlabel = params->spp_ipv6_flowlabel & SCTP_FLOWLABEL_VAL_MASK; trans->flowlabel |= SCTP_FLOWLABEL_SET_MASK; } } else if (asoc) { struct sctp_transport *t; list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { if (t->ipaddr.sa.sa_family != AF_INET6) continue; t->flowlabel = params->spp_ipv6_flowlabel & SCTP_FLOWLABEL_VAL_MASK; t->flowlabel |= SCTP_FLOWLABEL_SET_MASK; } asoc->flowlabel = params->spp_ipv6_flowlabel & SCTP_FLOWLABEL_VAL_MASK; asoc->flowlabel |= SCTP_FLOWLABEL_SET_MASK; } else if (sctp_opt2sk(sp)->sk_family == AF_INET6) { sp->flowlabel = params->spp_ipv6_flowlabel & SCTP_FLOWLABEL_VAL_MASK; sp->flowlabel |= SCTP_FLOWLABEL_SET_MASK; } } if (params->spp_flags & SPP_DSCP) { if (trans) { trans->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK; trans->dscp |= SCTP_DSCP_SET_MASK; } else if (asoc) { struct sctp_transport *t; list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { t->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK; t->dscp |= SCTP_DSCP_SET_MASK; } asoc->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK; asoc->dscp |= SCTP_DSCP_SET_MASK; } else { sp->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK; sp->dscp |= SCTP_DSCP_SET_MASK; } } return 0; } static int sctp_setsockopt_peer_addr_params(struct sock *sk, struct sctp_paddrparams *params, unsigned int optlen) { struct sctp_transport *trans = NULL; struct sctp_association *asoc = NULL; struct sctp_sock *sp = sctp_sk(sk); int error; int hb_change, pmtud_change, sackdelay_change; if (optlen == ALIGN(offsetof(struct sctp_paddrparams, spp_ipv6_flowlabel), 4)) { if (params->spp_flags & (SPP_DSCP | SPP_IPV6_FLOWLABEL)) return -EINVAL; } else if (optlen != sizeof(*params)) { return -EINVAL; } /* Validate flags and value parameters. */ hb_change = params->spp_flags & SPP_HB; pmtud_change = params->spp_flags & SPP_PMTUD; sackdelay_change = params->spp_flags & SPP_SACKDELAY; if (hb_change == SPP_HB || pmtud_change == SPP_PMTUD || sackdelay_change == SPP_SACKDELAY || params->spp_sackdelay > 500 || (params->spp_pathmtu && params->spp_pathmtu < SCTP_DEFAULT_MINSEGMENT)) return -EINVAL; /* If an address other than INADDR_ANY is specified, and * no transport is found, then the request is invalid. */ if (!sctp_is_any(sk, (union sctp_addr *)¶ms->spp_address)) { trans = sctp_addr_id2transport(sk, ¶ms->spp_address, params->spp_assoc_id); if (!trans) return -EINVAL; } /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the * socket is a one to many style socket, and an association * was not found, then the id was invalid. */ asoc = sctp_id2assoc(sk, params->spp_assoc_id); if (!asoc && params->spp_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; /* Heartbeat demand can only be sent on a transport or * association, but not a socket. */ if (params->spp_flags & SPP_HB_DEMAND && !trans && !asoc) return -EINVAL; /* Process parameters. */ error = sctp_apply_peer_addr_params(params, trans, asoc, sp, hb_change, pmtud_change, sackdelay_change); if (error) return error; /* If changes are for association, also apply parameters to each * transport. */ if (!trans && asoc) { list_for_each_entry(trans, &asoc->peer.transport_addr_list, transports) { sctp_apply_peer_addr_params(params, trans, asoc, sp, hb_change, pmtud_change, sackdelay_change); } } return 0; } static inline __u32 sctp_spp_sackdelay_enable(__u32 param_flags) { return (param_flags & ~SPP_SACKDELAY) | SPP_SACKDELAY_ENABLE; } static inline __u32 sctp_spp_sackdelay_disable(__u32 param_flags) { return (param_flags & ~SPP_SACKDELAY) | SPP_SACKDELAY_DISABLE; } static void sctp_apply_asoc_delayed_ack(struct sctp_sack_info *params, struct sctp_association *asoc) { struct sctp_transport *trans; if (params->sack_delay) { asoc->sackdelay = msecs_to_jiffies(params->sack_delay); asoc->param_flags = sctp_spp_sackdelay_enable(asoc->param_flags); } if (params->sack_freq == 1) { asoc->param_flags = sctp_spp_sackdelay_disable(asoc->param_flags); } else if (params->sack_freq > 1) { asoc->sackfreq = params->sack_freq; asoc->param_flags = sctp_spp_sackdelay_enable(asoc->param_flags); } list_for_each_entry(trans, &asoc->peer.transport_addr_list, transports) { if (params->sack_delay) { trans->sackdelay = msecs_to_jiffies(params->sack_delay); trans->param_flags = sctp_spp_sackdelay_enable(trans->param_flags); } if (params->sack_freq == 1) { trans->param_flags = sctp_spp_sackdelay_disable(trans->param_flags); } else if (params->sack_freq > 1) { trans->sackfreq = params->sack_freq; trans->param_flags = sctp_spp_sackdelay_enable(trans->param_flags); } } } /* * 7.1.23. Get or set delayed ack timer (SCTP_DELAYED_SACK) * * This option will effect the way delayed acks are performed. This * option allows you to get or set the delayed ack time, in * milliseconds. It also allows changing the delayed ack frequency. * Changing the frequency to 1 disables the delayed sack algorithm. If * the assoc_id is 0, then this sets or gets the endpoints default * values. If the assoc_id field is non-zero, then the set or get * effects the specified association for the one to many model (the * assoc_id field is ignored by the one to one model). Note that if * sack_delay or sack_freq are 0 when setting this option, then the * current values will remain unchanged. * * struct sctp_sack_info { * sctp_assoc_t sack_assoc_id; * uint32_t sack_delay; * uint32_t sack_freq; * }; * * sack_assoc_id - This parameter, indicates which association the user * is performing an action upon. Note that if this field's value is * zero then the endpoints default value is changed (effecting future * associations only). * * sack_delay - This parameter contains the number of milliseconds that * the user is requesting the delayed ACK timer be set to. Note that * this value is defined in the standard to be between 200 and 500 * milliseconds. * * sack_freq - This parameter contains the number of packets that must * be received before a sack is sent without waiting for the delay * timer to expire. The default value for this is 2, setting this * value to 1 will disable the delayed sack algorithm. */ static int __sctp_setsockopt_delayed_ack(struct sock *sk, struct sctp_sack_info *params) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; /* Validate value parameter. */ if (params->sack_delay > 500) return -EINVAL; /* Get association, if sack_assoc_id != SCTP_FUTURE_ASSOC and the * socket is a one to many style socket, and an association * was not found, then the id was invalid. */ asoc = sctp_id2assoc(sk, params->sack_assoc_id); if (!asoc && params->sack_assoc_id > SCTP_ALL_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) { sctp_apply_asoc_delayed_ack(params, asoc); return 0; } if (sctp_style(sk, TCP)) params->sack_assoc_id = SCTP_FUTURE_ASSOC; if (params->sack_assoc_id == SCTP_FUTURE_ASSOC || params->sack_assoc_id == SCTP_ALL_ASSOC) { if (params->sack_delay) { sp->sackdelay = params->sack_delay; sp->param_flags = sctp_spp_sackdelay_enable(sp->param_flags); } if (params->sack_freq == 1) { sp->param_flags = sctp_spp_sackdelay_disable(sp->param_flags); } else if (params->sack_freq > 1) { sp->sackfreq = params->sack_freq; sp->param_flags = sctp_spp_sackdelay_enable(sp->param_flags); } } if (params->sack_assoc_id == SCTP_CURRENT_ASSOC || params->sack_assoc_id == SCTP_ALL_ASSOC) list_for_each_entry(asoc, &sp->ep->asocs, asocs) sctp_apply_asoc_delayed_ack(params, asoc); return 0; } static int sctp_setsockopt_delayed_ack(struct sock *sk, struct sctp_sack_info *params, unsigned int optlen) { if (optlen == sizeof(struct sctp_assoc_value)) { struct sctp_assoc_value *v = (struct sctp_assoc_value *)params; struct sctp_sack_info p; pr_warn_ratelimited(DEPRECATED "%s (pid %d) " "Use of struct sctp_assoc_value in delayed_ack socket option.\n" "Use struct sctp_sack_info instead\n", current->comm, task_pid_nr(current)); p.sack_assoc_id = v->assoc_id; p.sack_delay = v->assoc_value; p.sack_freq = v->assoc_value ? 0 : 1; return __sctp_setsockopt_delayed_ack(sk, &p); } if (optlen != sizeof(struct sctp_sack_info)) return -EINVAL; if (params->sack_delay == 0 && params->sack_freq == 0) return 0; return __sctp_setsockopt_delayed_ack(sk, params); } /* 7.1.3 Initialization Parameters (SCTP_INITMSG) * * Applications can specify protocol parameters for the default association * initialization. The option name argument to setsockopt() and getsockopt() * is SCTP_INITMSG. * * Setting initialization parameters is effective only on an unconnected * socket (for UDP-style sockets only future associations are effected * by the change). With TCP-style sockets, this option is inherited by * sockets derived from a listener socket. */ static int sctp_setsockopt_initmsg(struct sock *sk, struct sctp_initmsg *sinit, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); if (optlen != sizeof(struct sctp_initmsg)) return -EINVAL; if (sinit->sinit_num_ostreams) sp->initmsg.sinit_num_ostreams = sinit->sinit_num_ostreams; if (sinit->sinit_max_instreams) sp->initmsg.sinit_max_instreams = sinit->sinit_max_instreams; if (sinit->sinit_max_attempts) sp->initmsg.sinit_max_attempts = sinit->sinit_max_attempts; if (sinit->sinit_max_init_timeo) sp->initmsg.sinit_max_init_timeo = sinit->sinit_max_init_timeo; return 0; } /* * 7.1.14 Set default send parameters (SCTP_DEFAULT_SEND_PARAM) * * Applications that wish to use the sendto() system call may wish to * specify a default set of parameters that would normally be supplied * through the inclusion of ancillary data. This socket option allows * such an application to set the default sctp_sndrcvinfo structure. * The application that wishes to use this socket option simply passes * in to this call the sctp_sndrcvinfo structure defined in Section * 5.2.2) The input parameters accepted by this call include * sinfo_stream, sinfo_flags, sinfo_ppid, sinfo_context, * sinfo_timetolive. The user must provide the sinfo_assoc_id field in * to this call if the caller is using the UDP model. */ static int sctp_setsockopt_default_send_param(struct sock *sk, struct sctp_sndrcvinfo *info, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; if (optlen != sizeof(*info)) return -EINVAL; if (info->sinfo_flags & ~(SCTP_UNORDERED | SCTP_ADDR_OVER | SCTP_ABORT | SCTP_EOF)) return -EINVAL; asoc = sctp_id2assoc(sk, info->sinfo_assoc_id); if (!asoc && info->sinfo_assoc_id > SCTP_ALL_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) { asoc->default_stream = info->sinfo_stream; asoc->default_flags = info->sinfo_flags; asoc->default_ppid = info->sinfo_ppid; asoc->default_context = info->sinfo_context; asoc->default_timetolive = info->sinfo_timetolive; return 0; } if (sctp_style(sk, TCP)) info->sinfo_assoc_id = SCTP_FUTURE_ASSOC; if (info->sinfo_assoc_id == SCTP_FUTURE_ASSOC || info->sinfo_assoc_id == SCTP_ALL_ASSOC) { sp->default_stream = info->sinfo_stream; sp->default_flags = info->sinfo_flags; sp->default_ppid = info->sinfo_ppid; sp->default_context = info->sinfo_context; sp->default_timetolive = info->sinfo_timetolive; } if (info->sinfo_assoc_id == SCTP_CURRENT_ASSOC || info->sinfo_assoc_id == SCTP_ALL_ASSOC) { list_for_each_entry(asoc, &sp->ep->asocs, asocs) { asoc->default_stream = info->sinfo_stream; asoc->default_flags = info->sinfo_flags; asoc->default_ppid = info->sinfo_ppid; asoc->default_context = info->sinfo_context; asoc->default_timetolive = info->sinfo_timetolive; } } return 0; } /* RFC6458, Section 8.1.31. Set/get Default Send Parameters * (SCTP_DEFAULT_SNDINFO) */ static int sctp_setsockopt_default_sndinfo(struct sock *sk, struct sctp_sndinfo *info, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; if (optlen != sizeof(*info)) return -EINVAL; if (info->snd_flags & ~(SCTP_UNORDERED | SCTP_ADDR_OVER | SCTP_ABORT | SCTP_EOF)) return -EINVAL; asoc = sctp_id2assoc(sk, info->snd_assoc_id); if (!asoc && info->snd_assoc_id > SCTP_ALL_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) { asoc->default_stream = info->snd_sid; asoc->default_flags = info->snd_flags; asoc->default_ppid = info->snd_ppid; asoc->default_context = info->snd_context; return 0; } if (sctp_style(sk, TCP)) info->snd_assoc_id = SCTP_FUTURE_ASSOC; if (info->snd_assoc_id == SCTP_FUTURE_ASSOC || info->snd_assoc_id == SCTP_ALL_ASSOC) { sp->default_stream = info->snd_sid; sp->default_flags = info->snd_flags; sp->default_ppid = info->snd_ppid; sp->default_context = info->snd_context; } if (info->snd_assoc_id == SCTP_CURRENT_ASSOC || info->snd_assoc_id == SCTP_ALL_ASSOC) { list_for_each_entry(asoc, &sp->ep->asocs, asocs) { asoc->default_stream = info->snd_sid; asoc->default_flags = info->snd_flags; asoc->default_ppid = info->snd_ppid; asoc->default_context = info->snd_context; } } return 0; } /* 7.1.10 Set Primary Address (SCTP_PRIMARY_ADDR) * * Requests that the local SCTP stack use the enclosed peer address as * the association primary. The enclosed address must be one of the * association peer's addresses. */ static int sctp_setsockopt_primary_addr(struct sock *sk, struct sctp_prim *prim, unsigned int optlen) { struct sctp_transport *trans; struct sctp_af *af; int err; if (optlen != sizeof(struct sctp_prim)) return -EINVAL; /* Allow security module to validate address but need address len. */ af = sctp_get_af_specific(prim->ssp_addr.ss_family); if (!af) return -EINVAL; err = security_sctp_bind_connect(sk, SCTP_PRIMARY_ADDR, (struct sockaddr *)&prim->ssp_addr, af->sockaddr_len); if (err) return err; trans = sctp_addr_id2transport(sk, &prim->ssp_addr, prim->ssp_assoc_id); if (!trans) return -EINVAL; sctp_assoc_set_primary(trans->asoc, trans); return 0; } /* * 7.1.5 SCTP_NODELAY * * Turn on/off any Nagle-like algorithm. This means that packets are * generally sent as soon as possible and no unnecessary delays are * introduced, at the cost of more packets in the network. Expects an * integer boolean flag. */ static int sctp_setsockopt_nodelay(struct sock *sk, int *val, unsigned int optlen) { if (optlen < sizeof(int)) return -EINVAL; sctp_sk(sk)->nodelay = (*val == 0) ? 0 : 1; return 0; } /* * * 7.1.1 SCTP_RTOINFO * * The protocol parameters used to initialize and bound retransmission * timeout (RTO) are tunable. sctp_rtoinfo structure is used to access * and modify these parameters. * All parameters are time values, in milliseconds. A value of 0, when * modifying the parameters, indicates that the current value should not * be changed. * */ static int sctp_setsockopt_rtoinfo(struct sock *sk, struct sctp_rtoinfo *rtoinfo, unsigned int optlen) { struct sctp_association *asoc; unsigned long rto_min, rto_max; struct sctp_sock *sp = sctp_sk(sk); if (optlen != sizeof (struct sctp_rtoinfo)) return -EINVAL; asoc = sctp_id2assoc(sk, rtoinfo->srto_assoc_id); /* Set the values to the specific association */ if (!asoc && rtoinfo->srto_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; rto_max = rtoinfo->srto_max; rto_min = rtoinfo->srto_min; if (rto_max) rto_max = asoc ? msecs_to_jiffies(rto_max) : rto_max; else rto_max = asoc ? asoc->rto_max : sp->rtoinfo.srto_max; if (rto_min) rto_min = asoc ? msecs_to_jiffies(rto_min) : rto_min; else rto_min = asoc ? asoc->rto_min : sp->rtoinfo.srto_min; if (rto_min > rto_max) return -EINVAL; if (asoc) { if (rtoinfo->srto_initial != 0) asoc->rto_initial = msecs_to_jiffies(rtoinfo->srto_initial); asoc->rto_max = rto_max; asoc->rto_min = rto_min; } else { /* If there is no association or the association-id = 0 * set the values to the endpoint. */ if (rtoinfo->srto_initial != 0) sp->rtoinfo.srto_initial = rtoinfo->srto_initial; sp->rtoinfo.srto_max = rto_max; sp->rtoinfo.srto_min = rto_min; } return 0; } /* * * 7.1.2 SCTP_ASSOCINFO * * This option is used to tune the maximum retransmission attempts * of the association. * Returns an error if the new association retransmission value is * greater than the sum of the retransmission value of the peer. * See [SCTP] for more information. * */ static int sctp_setsockopt_associnfo(struct sock *sk, struct sctp_assocparams *assocparams, unsigned int optlen) { struct sctp_association *asoc; if (optlen != sizeof(struct sctp_assocparams)) return -EINVAL; asoc = sctp_id2assoc(sk, assocparams->sasoc_assoc_id); if (!asoc && assocparams->sasoc_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; /* Set the values to the specific association */ if (asoc) { if (assocparams->sasoc_asocmaxrxt != 0) { __u32 path_sum = 0; int paths = 0; struct sctp_transport *peer_addr; list_for_each_entry(peer_addr, &asoc->peer.transport_addr_list, transports) { path_sum += peer_addr->pathmaxrxt; paths++; } /* Only validate asocmaxrxt if we have more than * one path/transport. We do this because path * retransmissions are only counted when we have more * then one path. */ if (paths > 1 && assocparams->sasoc_asocmaxrxt > path_sum) return -EINVAL; asoc->max_retrans = assocparams->sasoc_asocmaxrxt; } if (assocparams->sasoc_cookie_life != 0) asoc->cookie_life = ms_to_ktime(assocparams->sasoc_cookie_life); } else { /* Set the values to the endpoint */ struct sctp_sock *sp = sctp_sk(sk); if (assocparams->sasoc_asocmaxrxt != 0) sp->assocparams.sasoc_asocmaxrxt = assocparams->sasoc_asocmaxrxt; if (assocparams->sasoc_cookie_life != 0) sp->assocparams.sasoc_cookie_life = assocparams->sasoc_cookie_life; } return 0; } /* * 7.1.16 Set/clear IPv4 mapped addresses (SCTP_I_WANT_MAPPED_V4_ADDR) * * This socket option is a boolean flag which turns on or off mapped V4 * addresses. If this option is turned on and the socket is type * PF_INET6, then IPv4 addresses will be mapped to V6 representation. * If this option is turned off, then no mapping will be done of V4 * addresses and a user will receive both PF_INET6 and PF_INET type * addresses on the socket. */ static int sctp_setsockopt_mappedv4(struct sock *sk, int *val, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); if (optlen < sizeof(int)) return -EINVAL; if (*val) sp->v4mapped = 1; else sp->v4mapped = 0; return 0; } /* * 8.1.16. Get or Set the Maximum Fragmentation Size (SCTP_MAXSEG) * This option will get or set the maximum size to put in any outgoing * SCTP DATA chunk. If a message is larger than this size it will be * fragmented by SCTP into the specified size. Note that the underlying * SCTP implementation may fragment into smaller sized chunks when the * PMTU of the underlying association is smaller than the value set by * the user. The default value for this option is '0' which indicates * the user is NOT limiting fragmentation and only the PMTU will effect * SCTP's choice of DATA chunk size. Note also that values set larger * than the maximum size of an IP datagram will effectively let SCTP * control fragmentation (i.e. the same as setting this option to 0). * * The following structure is used to access and modify this parameter: * * struct sctp_assoc_value { * sctp_assoc_t assoc_id; * uint32_t assoc_value; * }; * * assoc_id: This parameter is ignored for one-to-one style sockets. * For one-to-many style sockets this parameter indicates which * association the user is performing an action upon. Note that if * this field's value is zero then the endpoints default value is * changed (effecting future associations only). * assoc_value: This parameter specifies the maximum size in bytes. */ static int sctp_setsockopt_maxseg(struct sock *sk, struct sctp_assoc_value *params, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; sctp_assoc_t assoc_id; int val; if (optlen == sizeof(int)) { pr_warn_ratelimited(DEPRECATED "%s (pid %d) " "Use of int in maxseg socket option.\n" "Use struct sctp_assoc_value instead\n", current->comm, task_pid_nr(current)); assoc_id = SCTP_FUTURE_ASSOC; val = *(int *)params; } else if (optlen == sizeof(struct sctp_assoc_value)) { assoc_id = params->assoc_id; val = params->assoc_value; } else { return -EINVAL; } asoc = sctp_id2assoc(sk, assoc_id); if (!asoc && assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (val) { int min_len, max_len; __u16 datasize = asoc ? sctp_datachk_len(&asoc->stream) : sizeof(struct sctp_data_chunk); min_len = sctp_min_frag_point(sp, datasize); max_len = SCTP_MAX_CHUNK_LEN - datasize; if (val < min_len || val > max_len) return -EINVAL; } if (asoc) { asoc->user_frag = val; sctp_assoc_update_frag_point(asoc); } else { sp->user_frag = val; } return 0; } /* * 7.1.9 Set Peer Primary Address (SCTP_SET_PEER_PRIMARY_ADDR) * * Requests that the peer mark the enclosed address as the association * primary. The enclosed address must be one of the association's * locally bound addresses. The following structure is used to make a * set primary request: */ static int sctp_setsockopt_peer_primary_addr(struct sock *sk, struct sctp_setpeerprim *prim, unsigned int optlen) { struct sctp_sock *sp; struct sctp_association *asoc = NULL; struct sctp_chunk *chunk; struct sctp_af *af; int err; sp = sctp_sk(sk); if (!sp->ep->asconf_enable) return -EPERM; if (optlen != sizeof(struct sctp_setpeerprim)) return -EINVAL; asoc = sctp_id2assoc(sk, prim->sspp_assoc_id); if (!asoc) return -EINVAL; if (!asoc->peer.asconf_capable) return -EPERM; if (asoc->peer.addip_disabled_mask & SCTP_PARAM_SET_PRIMARY) return -EPERM; if (!sctp_state(asoc, ESTABLISHED)) return -ENOTCONN; af = sctp_get_af_specific(prim->sspp_addr.ss_family); if (!af) return -EINVAL; if (!af->addr_valid((union sctp_addr *)&prim->sspp_addr, sp, NULL)) return -EADDRNOTAVAIL; if (!sctp_assoc_lookup_laddr(asoc, (union sctp_addr *)&prim->sspp_addr)) return -EADDRNOTAVAIL; /* Allow security module to validate address. */ err = security_sctp_bind_connect(sk, SCTP_SET_PEER_PRIMARY_ADDR, (struct sockaddr *)&prim->sspp_addr, af->sockaddr_len); if (err) return err; /* Create an ASCONF chunk with SET_PRIMARY parameter */ chunk = sctp_make_asconf_set_prim(asoc, (union sctp_addr *)&prim->sspp_addr); if (!chunk) return -ENOMEM; err = sctp_send_asconf(asoc, chunk); pr_debug("%s: we set peer primary addr primitively\n", __func__); return err; } static int sctp_setsockopt_adaptation_layer(struct sock *sk, struct sctp_setadaptation *adapt, unsigned int optlen) { if (optlen != sizeof(struct sctp_setadaptation)) return -EINVAL; sctp_sk(sk)->adaptation_ind = adapt->ssb_adaptation_ind; return 0; } /* * 7.1.29. Set or Get the default context (SCTP_CONTEXT) * * The context field in the sctp_sndrcvinfo structure is normally only * used when a failed message is retrieved holding the value that was * sent down on the actual send call. This option allows the setting of * a default context on an association basis that will be received on * reading messages from the peer. This is especially helpful in the * one-2-many model for an application to keep some reference to an * internal state machine that is processing messages on the * association. Note that the setting of this value only effects * received messages from the peer and does not effect the value that is * saved with outbound messages. */ static int sctp_setsockopt_context(struct sock *sk, struct sctp_assoc_value *params, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; if (optlen != sizeof(struct sctp_assoc_value)) return -EINVAL; asoc = sctp_id2assoc(sk, params->assoc_id); if (!asoc && params->assoc_id > SCTP_ALL_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) { asoc->default_rcv_context = params->assoc_value; return 0; } if (sctp_style(sk, TCP)) params->assoc_id = SCTP_FUTURE_ASSOC; if (params->assoc_id == SCTP_FUTURE_ASSOC || params->assoc_id == SCTP_ALL_ASSOC) sp->default_rcv_context = params->assoc_value; if (params->assoc_id == SCTP_CURRENT_ASSOC || params->assoc_id == SCTP_ALL_ASSOC) list_for_each_entry(asoc, &sp->ep->asocs, asocs) asoc->default_rcv_context = params->assoc_value; return 0; } /* * 7.1.24. Get or set fragmented interleave (SCTP_FRAGMENT_INTERLEAVE) * * This options will at a minimum specify if the implementation is doing * fragmented interleave. Fragmented interleave, for a one to many * socket, is when subsequent calls to receive a message may return * parts of messages from different associations. Some implementations * may allow you to turn this value on or off. If so, when turned off, * no fragment interleave will occur (which will cause a head of line * blocking amongst multiple associations sharing the same one to many * socket). When this option is turned on, then each receive call may * come from a different association (thus the user must receive data * with the extended calls (e.g. sctp_recvmsg) to keep track of which * association each receive belongs to. * * This option takes a boolean value. A non-zero value indicates that * fragmented interleave is on. A value of zero indicates that * fragmented interleave is off. * * Note that it is important that an implementation that allows this * option to be turned on, have it off by default. Otherwise an unaware * application using the one to many model may become confused and act * incorrectly. */ static int sctp_setsockopt_fragment_interleave(struct sock *sk, int *val, unsigned int optlen) { if (optlen != sizeof(int)) return -EINVAL; sctp_sk(sk)->frag_interleave = !!*val; if (!sctp_sk(sk)->frag_interleave) sctp_sk(sk)->ep->intl_enable = 0; return 0; } /* * 8.1.21. Set or Get the SCTP Partial Delivery Point * (SCTP_PARTIAL_DELIVERY_POINT) * * This option will set or get the SCTP partial delivery point. This * point is the size of a message where the partial delivery API will be * invoked to help free up rwnd space for the peer. Setting this to a * lower value will cause partial deliveries to happen more often. The * calls argument is an integer that sets or gets the partial delivery * point. Note also that the call will fail if the user attempts to set * this value larger than the socket receive buffer size. * * Note that any single message having a length smaller than or equal to * the SCTP partial delivery point will be delivered in one single read * call as long as the user provided buffer is large enough to hold the * message. */ static int sctp_setsockopt_partial_delivery_point(struct sock *sk, u32 *val, unsigned int optlen) { if (optlen != sizeof(u32)) return -EINVAL; /* Note: We double the receive buffer from what the user sets * it to be, also initial rwnd is based on rcvbuf/2. */ if (*val > (sk->sk_rcvbuf >> 1)) return -EINVAL; sctp_sk(sk)->pd_point = *val; return 0; /* is this the right error code? */ } /* * 7.1.28. Set or Get the maximum burst (SCTP_MAX_BURST) * * This option will allow a user to change the maximum burst of packets * that can be emitted by this association. Note that the default value * is 4, and some implementations may restrict this setting so that it * can only be lowered. * * NOTE: This text doesn't seem right. Do this on a socket basis with * future associations inheriting the socket value. */ static int sctp_setsockopt_maxburst(struct sock *sk, struct sctp_assoc_value *params, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; sctp_assoc_t assoc_id; u32 assoc_value; if (optlen == sizeof(int)) { pr_warn_ratelimited(DEPRECATED "%s (pid %d) " "Use of int in max_burst socket option deprecated.\n" "Use struct sctp_assoc_value instead\n", current->comm, task_pid_nr(current)); assoc_id = SCTP_FUTURE_ASSOC; assoc_value = *((int *)params); } else if (optlen == sizeof(struct sctp_assoc_value)) { assoc_id = params->assoc_id; assoc_value = params->assoc_value; } else return -EINVAL; asoc = sctp_id2assoc(sk, assoc_id); if (!asoc && assoc_id > SCTP_ALL_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) { asoc->max_burst = assoc_value; return 0; } if (sctp_style(sk, TCP)) assoc_id = SCTP_FUTURE_ASSOC; if (assoc_id == SCTP_FUTURE_ASSOC || assoc_id == SCTP_ALL_ASSOC) sp->max_burst = assoc_value; if (assoc_id == SCTP_CURRENT_ASSOC || assoc_id == SCTP_ALL_ASSOC) list_for_each_entry(asoc, &sp->ep->asocs, asocs) asoc->max_burst = assoc_value; return 0; } /* * 7.1.18. Add a chunk that must be authenticated (SCTP_AUTH_CHUNK) * * This set option adds a chunk type that the user is requesting to be * received only in an authenticated way. Changes to the list of chunks * will only effect future associations on the socket. */ static int sctp_setsockopt_auth_chunk(struct sock *sk, struct sctp_authchunk *val, unsigned int optlen) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; if (!ep->auth_enable) return -EACCES; if (optlen != sizeof(struct sctp_authchunk)) return -EINVAL; switch (val->sauth_chunk) { case SCTP_CID_INIT: case SCTP_CID_INIT_ACK: case SCTP_CID_SHUTDOWN_COMPLETE: case SCTP_CID_AUTH: return -EINVAL; } /* add this chunk id to the endpoint */ return sctp_auth_ep_add_chunkid(ep, val->sauth_chunk); } /* * 7.1.19. Get or set the list of supported HMAC Identifiers (SCTP_HMAC_IDENT) * * This option gets or sets the list of HMAC algorithms that the local * endpoint requires the peer to use. */ static int sctp_setsockopt_hmac_ident(struct sock *sk, struct sctp_hmacalgo *hmacs, unsigned int optlen) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; u32 idents; if (!ep->auth_enable) return -EACCES; if (optlen < sizeof(struct sctp_hmacalgo)) return -EINVAL; optlen = min_t(unsigned int, optlen, sizeof(struct sctp_hmacalgo) + SCTP_AUTH_NUM_HMACS * sizeof(u16)); idents = hmacs->shmac_num_idents; if (idents == 0 || idents > SCTP_AUTH_NUM_HMACS || (idents * sizeof(u16)) > (optlen - sizeof(struct sctp_hmacalgo))) return -EINVAL; return sctp_auth_ep_set_hmacs(ep, hmacs); } /* * 7.1.20. Set a shared key (SCTP_AUTH_KEY) * * This option will set a shared secret key which is used to build an * association shared key. */ static int sctp_setsockopt_auth_key(struct sock *sk, struct sctp_authkey *authkey, unsigned int optlen) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_association *asoc; int ret = -EINVAL; if (optlen <= sizeof(struct sctp_authkey)) return -EINVAL; /* authkey->sca_keylength is u16, so optlen can't be bigger than * this. */ optlen = min_t(unsigned int, optlen, USHRT_MAX + sizeof(*authkey)); if (authkey->sca_keylength > optlen - sizeof(*authkey)) goto out; asoc = sctp_id2assoc(sk, authkey->sca_assoc_id); if (!asoc && authkey->sca_assoc_id > SCTP_ALL_ASSOC && sctp_style(sk, UDP)) goto out; if (asoc) { ret = sctp_auth_set_key(ep, asoc, authkey); goto out; } if (sctp_style(sk, TCP)) authkey->sca_assoc_id = SCTP_FUTURE_ASSOC; if (authkey->sca_assoc_id == SCTP_FUTURE_ASSOC || authkey->sca_assoc_id == SCTP_ALL_ASSOC) { ret = sctp_auth_set_key(ep, asoc, authkey); if (ret) goto out; } ret = 0; if (authkey->sca_assoc_id == SCTP_CURRENT_ASSOC || authkey->sca_assoc_id == SCTP_ALL_ASSOC) { list_for_each_entry(asoc, &ep->asocs, asocs) { int res = sctp_auth_set_key(ep, asoc, authkey); if (res && !ret) ret = res; } } out: memzero_explicit(authkey, optlen); return ret; } /* * 7.1.21. Get or set the active shared key (SCTP_AUTH_ACTIVE_KEY) * * This option will get or set the active shared key to be used to build * the association shared key. */ static int sctp_setsockopt_active_key(struct sock *sk, struct sctp_authkeyid *val, unsigned int optlen) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_association *asoc; int ret = 0; if (optlen != sizeof(struct sctp_authkeyid)) return -EINVAL; asoc = sctp_id2assoc(sk, val->scact_assoc_id); if (!asoc && val->scact_assoc_id > SCTP_ALL_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) return sctp_auth_set_active_key(ep, asoc, val->scact_keynumber); if (sctp_style(sk, TCP)) val->scact_assoc_id = SCTP_FUTURE_ASSOC; if (val->scact_assoc_id == SCTP_FUTURE_ASSOC || val->scact_assoc_id == SCTP_ALL_ASSOC) { ret = sctp_auth_set_active_key(ep, asoc, val->scact_keynumber); if (ret) return ret; } if (val->scact_assoc_id == SCTP_CURRENT_ASSOC || val->scact_assoc_id == SCTP_ALL_ASSOC) { list_for_each_entry(asoc, &ep->asocs, asocs) { int res = sctp_auth_set_active_key(ep, asoc, val->scact_keynumber); if (res && !ret) ret = res; } } return ret; } /* * 7.1.22. Delete a shared key (SCTP_AUTH_DELETE_KEY) * * This set option will delete a shared secret key from use. */ static int sctp_setsockopt_del_key(struct sock *sk, struct sctp_authkeyid *val, unsigned int optlen) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_association *asoc; int ret = 0; if (optlen != sizeof(struct sctp_authkeyid)) return -EINVAL; asoc = sctp_id2assoc(sk, val->scact_assoc_id); if (!asoc && val->scact_assoc_id > SCTP_ALL_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) return sctp_auth_del_key_id(ep, asoc, val->scact_keynumber); if (sctp_style(sk, TCP)) val->scact_assoc_id = SCTP_FUTURE_ASSOC; if (val->scact_assoc_id == SCTP_FUTURE_ASSOC || val->scact_assoc_id == SCTP_ALL_ASSOC) { ret = sctp_auth_del_key_id(ep, asoc, val->scact_keynumber); if (ret) return ret; } if (val->scact_assoc_id == SCTP_CURRENT_ASSOC || val->scact_assoc_id == SCTP_ALL_ASSOC) { list_for_each_entry(asoc, &ep->asocs, asocs) { int res = sctp_auth_del_key_id(ep, asoc, val->scact_keynumber); if (res && !ret) ret = res; } } return ret; } /* * 8.3.4 Deactivate a Shared Key (SCTP_AUTH_DEACTIVATE_KEY) * * This set option will deactivate a shared secret key. */ static int sctp_setsockopt_deactivate_key(struct sock *sk, struct sctp_authkeyid *val, unsigned int optlen) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_association *asoc; int ret = 0; if (optlen != sizeof(struct sctp_authkeyid)) return -EINVAL; asoc = sctp_id2assoc(sk, val->scact_assoc_id); if (!asoc && val->scact_assoc_id > SCTP_ALL_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) return sctp_auth_deact_key_id(ep, asoc, val->scact_keynumber); if (sctp_style(sk, TCP)) val->scact_assoc_id = SCTP_FUTURE_ASSOC; if (val->scact_assoc_id == SCTP_FUTURE_ASSOC || val->scact_assoc_id == SCTP_ALL_ASSOC) { ret = sctp_auth_deact_key_id(ep, asoc, val->scact_keynumber); if (ret) return ret; } if (val->scact_assoc_id == SCTP_CURRENT_ASSOC || val->scact_assoc_id == SCTP_ALL_ASSOC) { list_for_each_entry(asoc, &ep->asocs, asocs) { int res = sctp_auth_deact_key_id(ep, asoc, val->scact_keynumber); if (res && !ret) ret = res; } } return ret; } /* * 8.1.23 SCTP_AUTO_ASCONF * * This option will enable or disable the use of the automatic generation of * ASCONF chunks to add and delete addresses to an existing association. Note * that this option has two caveats namely: a) it only affects sockets that * are bound to all addresses available to the SCTP stack, and b) the system * administrator may have an overriding control that turns the ASCONF feature * off no matter what setting the socket option may have. * This option expects an integer boolean flag, where a non-zero value turns on * the option, and a zero value turns off the option. * Note. In this implementation, socket operation overrides default parameter * being set by sysctl as well as FreeBSD implementation */ static int sctp_setsockopt_auto_asconf(struct sock *sk, int *val, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); if (optlen < sizeof(int)) return -EINVAL; if (!sctp_is_ep_boundall(sk) && *val) return -EINVAL; if ((*val && sp->do_auto_asconf) || (!*val && !sp->do_auto_asconf)) return 0; spin_lock_bh(&sock_net(sk)->sctp.addr_wq_lock); if (*val == 0 && sp->do_auto_asconf) { list_del(&sp->auto_asconf_list); sp->do_auto_asconf = 0; } else if (*val && !sp->do_auto_asconf) { list_add_tail(&sp->auto_asconf_list, &sock_net(sk)->sctp.auto_asconf_splist); sp->do_auto_asconf = 1; } spin_unlock_bh(&sock_net(sk)->sctp.addr_wq_lock); return 0; } /* * SCTP_PEER_ADDR_THLDS * * This option allows us to alter the partially failed threshold for one or all * transports in an association. See Section 6.1 of: * http://www.ietf.org/id/draft-nishida-tsvwg-sctp-failover-05.txt */ static int sctp_setsockopt_paddr_thresholds(struct sock *sk, struct sctp_paddrthlds_v2 *val, unsigned int optlen, bool v2) { struct sctp_transport *trans; struct sctp_association *asoc; int len; len = v2 ? sizeof(*val) : sizeof(struct sctp_paddrthlds); if (optlen < len) return -EINVAL; if (v2 && val->spt_pathpfthld > val->spt_pathcpthld) return -EINVAL; if (!sctp_is_any(sk, (const union sctp_addr *)&val->spt_address)) { trans = sctp_addr_id2transport(sk, &val->spt_address, val->spt_assoc_id); if (!trans) return -ENOENT; if (val->spt_pathmaxrxt) trans->pathmaxrxt = val->spt_pathmaxrxt; if (v2) trans->ps_retrans = val->spt_pathcpthld; trans->pf_retrans = val->spt_pathpfthld; return 0; } asoc = sctp_id2assoc(sk, val->spt_assoc_id); if (!asoc && val->spt_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) { list_for_each_entry(trans, &asoc->peer.transport_addr_list, transports) { if (val->spt_pathmaxrxt) trans->pathmaxrxt = val->spt_pathmaxrxt; if (v2) trans->ps_retrans = val->spt_pathcpthld; trans->pf_retrans = val->spt_pathpfthld; } if (val->spt_pathmaxrxt) asoc->pathmaxrxt = val->spt_pathmaxrxt; if (v2) asoc->ps_retrans = val->spt_pathcpthld; asoc->pf_retrans = val->spt_pathpfthld; } else { struct sctp_sock *sp = sctp_sk(sk); if (val->spt_pathmaxrxt) sp->pathmaxrxt = val->spt_pathmaxrxt; if (v2) sp->ps_retrans = val->spt_pathcpthld; sp->pf_retrans = val->spt_pathpfthld; } return 0; } static int sctp_setsockopt_recvrcvinfo(struct sock *sk, int *val, unsigned int optlen) { if (optlen < sizeof(int)) return -EINVAL; sctp_sk(sk)->recvrcvinfo = (*val == 0) ? 0 : 1; return 0; } static int sctp_setsockopt_recvnxtinfo(struct sock *sk, int *val, unsigned int optlen) { if (optlen < sizeof(int)) return -EINVAL; sctp_sk(sk)->recvnxtinfo = (*val == 0) ? 0 : 1; return 0; } static int sctp_setsockopt_pr_supported(struct sock *sk, struct sctp_assoc_value *params, unsigned int optlen) { struct sctp_association *asoc; if (optlen != sizeof(*params)) return -EINVAL; asoc = sctp_id2assoc(sk, params->assoc_id); if (!asoc && params->assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; sctp_sk(sk)->ep->prsctp_enable = !!params->assoc_value; return 0; } static int sctp_setsockopt_default_prinfo(struct sock *sk, struct sctp_default_prinfo *info, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; int retval = -EINVAL; if (optlen != sizeof(*info)) goto out; if (info->pr_policy & ~SCTP_PR_SCTP_MASK) goto out; if (info->pr_policy == SCTP_PR_SCTP_NONE) info->pr_value = 0; asoc = sctp_id2assoc(sk, info->pr_assoc_id); if (!asoc && info->pr_assoc_id > SCTP_ALL_ASSOC && sctp_style(sk, UDP)) goto out; retval = 0; if (asoc) { SCTP_PR_SET_POLICY(asoc->default_flags, info->pr_policy); asoc->default_timetolive = info->pr_value; goto out; } if (sctp_style(sk, TCP)) info->pr_assoc_id = SCTP_FUTURE_ASSOC; if (info->pr_assoc_id == SCTP_FUTURE_ASSOC || info->pr_assoc_id == SCTP_ALL_ASSOC) { SCTP_PR_SET_POLICY(sp->default_flags, info->pr_policy); sp->default_timetolive = info->pr_value; } if (info->pr_assoc_id == SCTP_CURRENT_ASSOC || info->pr_assoc_id == SCTP_ALL_ASSOC) { list_for_each_entry(asoc, &sp->ep->asocs, asocs) { SCTP_PR_SET_POLICY(asoc->default_flags, info->pr_policy); asoc->default_timetolive = info->pr_value; } } out: return retval; } static int sctp_setsockopt_reconfig_supported(struct sock *sk, struct sctp_assoc_value *params, unsigned int optlen) { struct sctp_association *asoc; int retval = -EINVAL; if (optlen != sizeof(*params)) goto out; asoc = sctp_id2assoc(sk, params->assoc_id); if (!asoc && params->assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) goto out; sctp_sk(sk)->ep->reconf_enable = !!params->assoc_value; retval = 0; out: return retval; } static int sctp_setsockopt_enable_strreset(struct sock *sk, struct sctp_assoc_value *params, unsigned int optlen) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_association *asoc; int retval = -EINVAL; if (optlen != sizeof(*params)) goto out; if (params->assoc_value & (~SCTP_ENABLE_STRRESET_MASK)) goto out; asoc = sctp_id2assoc(sk, params->assoc_id); if (!asoc && params->assoc_id > SCTP_ALL_ASSOC && sctp_style(sk, UDP)) goto out; retval = 0; if (asoc) { asoc->strreset_enable = params->assoc_value; goto out; } if (sctp_style(sk, TCP)) params->assoc_id = SCTP_FUTURE_ASSOC; if (params->assoc_id == SCTP_FUTURE_ASSOC || params->assoc_id == SCTP_ALL_ASSOC) ep->strreset_enable = params->assoc_value; if (params->assoc_id == SCTP_CURRENT_ASSOC || params->assoc_id == SCTP_ALL_ASSOC) list_for_each_entry(asoc, &ep->asocs, asocs) asoc->strreset_enable = params->assoc_value; out: return retval; } static int sctp_setsockopt_reset_streams(struct sock *sk, struct sctp_reset_streams *params, unsigned int optlen) { struct sctp_association *asoc; if (optlen < sizeof(*params)) return -EINVAL; /* srs_number_streams is u16, so optlen can't be bigger than this. */ optlen = min_t(unsigned int, optlen, USHRT_MAX + sizeof(__u16) * sizeof(*params)); if (params->srs_number_streams * sizeof(__u16) > optlen - sizeof(*params)) return -EINVAL; asoc = sctp_id2assoc(sk, params->srs_assoc_id); if (!asoc) return -EINVAL; return sctp_send_reset_streams(asoc, params); } static int sctp_setsockopt_reset_assoc(struct sock *sk, sctp_assoc_t *associd, unsigned int optlen) { struct sctp_association *asoc; if (optlen != sizeof(*associd)) return -EINVAL; asoc = sctp_id2assoc(sk, *associd); if (!asoc) return -EINVAL; return sctp_send_reset_assoc(asoc); } static int sctp_setsockopt_add_streams(struct sock *sk, struct sctp_add_streams *params, unsigned int optlen) { struct sctp_association *asoc; if (optlen != sizeof(*params)) return -EINVAL; asoc = sctp_id2assoc(sk, params->sas_assoc_id); if (!asoc) return -EINVAL; return sctp_send_add_streams(asoc, params); } static int sctp_setsockopt_scheduler(struct sock *sk, struct sctp_assoc_value *params, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; int retval = 0; if (optlen < sizeof(*params)) return -EINVAL; if (params->assoc_value > SCTP_SS_MAX) return -EINVAL; asoc = sctp_id2assoc(sk, params->assoc_id); if (!asoc && params->assoc_id > SCTP_ALL_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) return sctp_sched_set_sched(asoc, params->assoc_value); if (sctp_style(sk, TCP)) params->assoc_id = SCTP_FUTURE_ASSOC; if (params->assoc_id == SCTP_FUTURE_ASSOC || params->assoc_id == SCTP_ALL_ASSOC) sp->default_ss = params->assoc_value; if (params->assoc_id == SCTP_CURRENT_ASSOC || params->assoc_id == SCTP_ALL_ASSOC) { list_for_each_entry(asoc, &sp->ep->asocs, asocs) { int ret = sctp_sched_set_sched(asoc, params->assoc_value); if (ret && !retval) retval = ret; } } return retval; } static int sctp_setsockopt_scheduler_value(struct sock *sk, struct sctp_stream_value *params, unsigned int optlen) { struct sctp_association *asoc; int retval = -EINVAL; if (optlen < sizeof(*params)) goto out; asoc = sctp_id2assoc(sk, params->assoc_id); if (!asoc && params->assoc_id != SCTP_CURRENT_ASSOC && sctp_style(sk, UDP)) goto out; if (asoc) { retval = sctp_sched_set_value(asoc, params->stream_id, params->stream_value, GFP_KERNEL); goto out; } retval = 0; list_for_each_entry(asoc, &sctp_sk(sk)->ep->asocs, asocs) { int ret = sctp_sched_set_value(asoc, params->stream_id, params->stream_value, GFP_KERNEL); if (ret && !retval) /* try to return the 1st error. */ retval = ret; } out: return retval; } static int sctp_setsockopt_interleaving_supported(struct sock *sk, struct sctp_assoc_value *p, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; if (optlen < sizeof(*p)) return -EINVAL; asoc = sctp_id2assoc(sk, p->assoc_id); if (!asoc && p->assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (!sock_net(sk)->sctp.intl_enable || !sp->frag_interleave) { return -EPERM; } sp->ep->intl_enable = !!p->assoc_value; return 0; } static int sctp_setsockopt_reuse_port(struct sock *sk, int *val, unsigned int optlen) { if (!sctp_style(sk, TCP)) return -EOPNOTSUPP; if (sctp_sk(sk)->ep->base.bind_addr.port) return -EFAULT; if (optlen < sizeof(int)) return -EINVAL; sctp_sk(sk)->reuse = !!*val; return 0; } static int sctp_assoc_ulpevent_type_set(struct sctp_event *param, struct sctp_association *asoc) { struct sctp_ulpevent *event; sctp_ulpevent_type_set(&asoc->subscribe, param->se_type, param->se_on); if (param->se_type == SCTP_SENDER_DRY_EVENT && param->se_on) { if (sctp_outq_is_empty(&asoc->outqueue)) { event = sctp_ulpevent_make_sender_dry_event(asoc, GFP_USER | __GFP_NOWARN); if (!event) return -ENOMEM; asoc->stream.si->enqueue_event(&asoc->ulpq, event); } } return 0; } static int sctp_setsockopt_event(struct sock *sk, struct sctp_event *param, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; int retval = 0; if (optlen < sizeof(*param)) return -EINVAL; if (param->se_type < SCTP_SN_TYPE_BASE || param->se_type > SCTP_SN_TYPE_MAX) return -EINVAL; asoc = sctp_id2assoc(sk, param->se_assoc_id); if (!asoc && param->se_assoc_id > SCTP_ALL_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) return sctp_assoc_ulpevent_type_set(param, asoc); if (sctp_style(sk, TCP)) param->se_assoc_id = SCTP_FUTURE_ASSOC; if (param->se_assoc_id == SCTP_FUTURE_ASSOC || param->se_assoc_id == SCTP_ALL_ASSOC) sctp_ulpevent_type_set(&sp->subscribe, param->se_type, param->se_on); if (param->se_assoc_id == SCTP_CURRENT_ASSOC || param->se_assoc_id == SCTP_ALL_ASSOC) { list_for_each_entry(asoc, &sp->ep->asocs, asocs) { int ret = sctp_assoc_ulpevent_type_set(param, asoc); if (ret && !retval) retval = ret; } } return retval; } static int sctp_setsockopt_asconf_supported(struct sock *sk, struct sctp_assoc_value *params, unsigned int optlen) { struct sctp_association *asoc; struct sctp_endpoint *ep; int retval = -EINVAL; if (optlen != sizeof(*params)) goto out; asoc = sctp_id2assoc(sk, params->assoc_id); if (!asoc && params->assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) goto out; ep = sctp_sk(sk)->ep; ep->asconf_enable = !!params->assoc_value; if (ep->asconf_enable && ep->auth_enable) { sctp_auth_ep_add_chunkid(ep, SCTP_CID_ASCONF); sctp_auth_ep_add_chunkid(ep, SCTP_CID_ASCONF_ACK); } retval = 0; out: return retval; } static int sctp_setsockopt_auth_supported(struct sock *sk, struct sctp_assoc_value *params, unsigned int optlen) { struct sctp_association *asoc; struct sctp_endpoint *ep; int retval = -EINVAL; if (optlen != sizeof(*params)) goto out; asoc = sctp_id2assoc(sk, params->assoc_id); if (!asoc && params->assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) goto out; ep = sctp_sk(sk)->ep; if (params->assoc_value) { retval = sctp_auth_init(ep, GFP_KERNEL); if (retval) goto out; if (ep->asconf_enable) { sctp_auth_ep_add_chunkid(ep, SCTP_CID_ASCONF); sctp_auth_ep_add_chunkid(ep, SCTP_CID_ASCONF_ACK); } } ep->auth_enable = !!params->assoc_value; retval = 0; out: return retval; } static int sctp_setsockopt_ecn_supported(struct sock *sk, struct sctp_assoc_value *params, unsigned int optlen) { struct sctp_association *asoc; int retval = -EINVAL; if (optlen != sizeof(*params)) goto out; asoc = sctp_id2assoc(sk, params->assoc_id); if (!asoc && params->assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) goto out; sctp_sk(sk)->ep->ecn_enable = !!params->assoc_value; retval = 0; out: return retval; } static int sctp_setsockopt_pf_expose(struct sock *sk, struct sctp_assoc_value *params, unsigned int optlen) { struct sctp_association *asoc; int retval = -EINVAL; if (optlen != sizeof(*params)) goto out; if (params->assoc_value > SCTP_PF_EXPOSE_MAX) goto out; asoc = sctp_id2assoc(sk, params->assoc_id); if (!asoc && params->assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) goto out; if (asoc) asoc->pf_expose = params->assoc_value; else sctp_sk(sk)->pf_expose = params->assoc_value; retval = 0; out: return retval; } static int sctp_setsockopt_encap_port(struct sock *sk, struct sctp_udpencaps *encap, unsigned int optlen) { struct sctp_association *asoc; struct sctp_transport *t; __be16 encap_port; if (optlen != sizeof(*encap)) return -EINVAL; /* If an address other than INADDR_ANY is specified, and * no transport is found, then the request is invalid. */ encap_port = (__force __be16)encap->sue_port; if (!sctp_is_any(sk, (union sctp_addr *)&encap->sue_address)) { t = sctp_addr_id2transport(sk, &encap->sue_address, encap->sue_assoc_id); if (!t) return -EINVAL; t->encap_port = encap_port; return 0; } /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the * socket is a one to many style socket, and an association * was not found, then the id was invalid. */ asoc = sctp_id2assoc(sk, encap->sue_assoc_id); if (!asoc && encap->sue_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; /* If changes are for association, also apply encap_port to * each transport. */ if (asoc) { list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) t->encap_port = encap_port; asoc->encap_port = encap_port; return 0; } sctp_sk(sk)->encap_port = encap_port; return 0; } static int sctp_setsockopt_probe_interval(struct sock *sk, struct sctp_probeinterval *params, unsigned int optlen) { struct sctp_association *asoc; struct sctp_transport *t; __u32 probe_interval; if (optlen != sizeof(*params)) return -EINVAL; probe_interval = params->spi_interval; if (probe_interval && probe_interval < SCTP_PROBE_TIMER_MIN) return -EINVAL; /* If an address other than INADDR_ANY is specified, and * no transport is found, then the request is invalid. */ if (!sctp_is_any(sk, (union sctp_addr *)¶ms->spi_address)) { t = sctp_addr_id2transport(sk, ¶ms->spi_address, params->spi_assoc_id); if (!t) return -EINVAL; t->probe_interval = msecs_to_jiffies(probe_interval); sctp_transport_pl_reset(t); return 0; } /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the * socket is a one to many style socket, and an association * was not found, then the id was invalid. */ asoc = sctp_id2assoc(sk, params->spi_assoc_id); if (!asoc && params->spi_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; /* If changes are for association, also apply probe_interval to * each transport. */ if (asoc) { list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { t->probe_interval = msecs_to_jiffies(probe_interval); sctp_transport_pl_reset(t); } asoc->probe_interval = msecs_to_jiffies(probe_interval); return 0; } sctp_sk(sk)->probe_interval = probe_interval; return 0; } /* API 6.2 setsockopt(), getsockopt() * * Applications use setsockopt() and getsockopt() to set or retrieve * socket options. Socket options are used to change the default * behavior of sockets calls. They are described in Section 7. * * The syntax is: * * ret = getsockopt(int sd, int level, int optname, void __user *optval, * int __user *optlen); * ret = setsockopt(int sd, int level, int optname, const void __user *optval, * int optlen); * * sd - the socket descript. * level - set to IPPROTO_SCTP for all SCTP options. * optname - the option name. * optval - the buffer to store the value of the option. * optlen - the size of the buffer. */ static int sctp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { void *kopt = NULL; int retval = 0; pr_debug("%s: sk:%p, optname:%d\n", __func__, sk, optname); /* I can hardly begin to describe how wrong this is. This is * so broken as to be worse than useless. The API draft * REALLY is NOT helpful here... I am not convinced that the * semantics of setsockopt() with a level OTHER THAN SOL_SCTP * are at all well-founded. */ if (level != SOL_SCTP) { struct sctp_af *af = sctp_sk(sk)->pf->af; return af->setsockopt(sk, level, optname, optval, optlen); } if (optlen > 0) { /* Trim it to the biggest size sctp sockopt may need if necessary */ optlen = min_t(unsigned int, optlen, PAGE_ALIGN(USHRT_MAX + sizeof(__u16) * sizeof(struct sctp_reset_streams))); kopt = memdup_sockptr(optval, optlen); if (IS_ERR(kopt)) return PTR_ERR(kopt); } lock_sock(sk); switch (optname) { case SCTP_SOCKOPT_BINDX_ADD: /* 'optlen' is the size of the addresses buffer. */ retval = sctp_setsockopt_bindx(sk, kopt, optlen, SCTP_BINDX_ADD_ADDR); break; case SCTP_SOCKOPT_BINDX_REM: /* 'optlen' is the size of the addresses buffer. */ retval = sctp_setsockopt_bindx(sk, kopt, optlen, SCTP_BINDX_REM_ADDR); break; case SCTP_SOCKOPT_CONNECTX_OLD: /* 'optlen' is the size of the addresses buffer. */ retval = sctp_setsockopt_connectx_old(sk, kopt, optlen); break; case SCTP_SOCKOPT_CONNECTX: /* 'optlen' is the size of the addresses buffer. */ retval = sctp_setsockopt_connectx(sk, kopt, optlen); break; case SCTP_DISABLE_FRAGMENTS: retval = sctp_setsockopt_disable_fragments(sk, kopt, optlen); break; case SCTP_EVENTS: retval = sctp_setsockopt_events(sk, kopt, optlen); break; case SCTP_AUTOCLOSE: retval = sctp_setsockopt_autoclose(sk, kopt, optlen); break; case SCTP_PEER_ADDR_PARAMS: retval = sctp_setsockopt_peer_addr_params(sk, kopt, optlen); break; case SCTP_DELAYED_SACK: retval = sctp_setsockopt_delayed_ack(sk, kopt, optlen); break; case SCTP_PARTIAL_DELIVERY_POINT: retval = sctp_setsockopt_partial_delivery_point(sk, kopt, optlen); break; case SCTP_INITMSG: retval = sctp_setsockopt_initmsg(sk, kopt, optlen); break; case SCTP_DEFAULT_SEND_PARAM: retval = sctp_setsockopt_default_send_param(sk, kopt, optlen); break; case SCTP_DEFAULT_SNDINFO: retval = sctp_setsockopt_default_sndinfo(sk, kopt, optlen); break; case SCTP_PRIMARY_ADDR: retval = sctp_setsockopt_primary_addr(sk, kopt, optlen); break; case SCTP_SET_PEER_PRIMARY_ADDR: retval = sctp_setsockopt_peer_primary_addr(sk, kopt, optlen); break; case SCTP_NODELAY: retval = sctp_setsockopt_nodelay(sk, kopt, optlen); break; case SCTP_RTOINFO: retval = sctp_setsockopt_rtoinfo(sk, kopt, optlen); break; case SCTP_ASSOCINFO: retval = sctp_setsockopt_associnfo(sk, kopt, optlen); break; case SCTP_I_WANT_MAPPED_V4_ADDR: retval = sctp_setsockopt_mappedv4(sk, kopt, optlen); break; case SCTP_MAXSEG: retval = sctp_setsockopt_maxseg(sk, kopt, optlen); break; case SCTP_ADAPTATION_LAYER: retval = sctp_setsockopt_adaptation_layer(sk, kopt, optlen); break; case SCTP_CONTEXT: retval = sctp_setsockopt_context(sk, kopt, optlen); break; case SCTP_FRAGMENT_INTERLEAVE: retval = sctp_setsockopt_fragment_interleave(sk, kopt, optlen); break; case SCTP_MAX_BURST: retval = sctp_setsockopt_maxburst(sk, kopt, optlen); break; case SCTP_AUTH_CHUNK: retval = sctp_setsockopt_auth_chunk(sk, kopt, optlen); break; case SCTP_HMAC_IDENT: retval = sctp_setsockopt_hmac_ident(sk, kopt, optlen); break; case SCTP_AUTH_KEY: retval = sctp_setsockopt_auth_key(sk, kopt, optlen); break; case SCTP_AUTH_ACTIVE_KEY: retval = sctp_setsockopt_active_key(sk, kopt, optlen); break; case SCTP_AUTH_DELETE_KEY: retval = sctp_setsockopt_del_key(sk, kopt, optlen); break; case SCTP_AUTH_DEACTIVATE_KEY: retval = sctp_setsockopt_deactivate_key(sk, kopt, optlen); break; case SCTP_AUTO_ASCONF: retval = sctp_setsockopt_auto_asconf(sk, kopt, optlen); break; case SCTP_PEER_ADDR_THLDS: retval = sctp_setsockopt_paddr_thresholds(sk, kopt, optlen, false); break; case SCTP_PEER_ADDR_THLDS_V2: retval = sctp_setsockopt_paddr_thresholds(sk, kopt, optlen, true); break; case SCTP_RECVRCVINFO: retval = sctp_setsockopt_recvrcvinfo(sk, kopt, optlen); break; case SCTP_RECVNXTINFO: retval = sctp_setsockopt_recvnxtinfo(sk, kopt, optlen); break; case SCTP_PR_SUPPORTED: retval = sctp_setsockopt_pr_supported(sk, kopt, optlen); break; case SCTP_DEFAULT_PRINFO: retval = sctp_setsockopt_default_prinfo(sk, kopt, optlen); break; case SCTP_RECONFIG_SUPPORTED: retval = sctp_setsockopt_reconfig_supported(sk, kopt, optlen); break; case SCTP_ENABLE_STREAM_RESET: retval = sctp_setsockopt_enable_strreset(sk, kopt, optlen); break; case SCTP_RESET_STREAMS: retval = sctp_setsockopt_reset_streams(sk, kopt, optlen); break; case SCTP_RESET_ASSOC: retval = sctp_setsockopt_reset_assoc(sk, kopt, optlen); break; case SCTP_ADD_STREAMS: retval = sctp_setsockopt_add_streams(sk, kopt, optlen); break; case SCTP_STREAM_SCHEDULER: retval = sctp_setsockopt_scheduler(sk, kopt, optlen); break; case SCTP_STREAM_SCHEDULER_VALUE: retval = sctp_setsockopt_scheduler_value(sk, kopt, optlen); break; case SCTP_INTERLEAVING_SUPPORTED: retval = sctp_setsockopt_interleaving_supported(sk, kopt, optlen); break; case SCTP_REUSE_PORT: retval = sctp_setsockopt_reuse_port(sk, kopt, optlen); break; case SCTP_EVENT: retval = sctp_setsockopt_event(sk, kopt, optlen); break; case SCTP_ASCONF_SUPPORTED: retval = sctp_setsockopt_asconf_supported(sk, kopt, optlen); break; case SCTP_AUTH_SUPPORTED: retval = sctp_setsockopt_auth_supported(sk, kopt, optlen); break; case SCTP_ECN_SUPPORTED: retval = sctp_setsockopt_ecn_supported(sk, kopt, optlen); break; case SCTP_EXPOSE_POTENTIALLY_FAILED_STATE: retval = sctp_setsockopt_pf_expose(sk, kopt, optlen); break; case SCTP_REMOTE_UDP_ENCAPS_PORT: retval = sctp_setsockopt_encap_port(sk, kopt, optlen); break; case SCTP_PLPMTUD_PROBE_INTERVAL: retval = sctp_setsockopt_probe_interval(sk, kopt, optlen); break; default: retval = -ENOPROTOOPT; break; } release_sock(sk); kfree(kopt); return retval; } /* API 3.1.6 connect() - UDP Style Syntax * * An application may use the connect() call in the UDP model to initiate an * association without sending data. * * The syntax is: * * ret = connect(int sd, const struct sockaddr *nam, socklen_t len); * * sd: the socket descriptor to have a new association added to. * * nam: the address structure (either struct sockaddr_in or struct * sockaddr_in6 defined in RFC2553 [7]). * * len: the size of the address. */ static int sctp_connect(struct sock *sk, struct sockaddr *addr, int addr_len, int flags) { struct sctp_af *af; int err = -EINVAL; lock_sock(sk); pr_debug("%s: sk:%p, sockaddr:%p, addr_len:%d\n", __func__, sk, addr, addr_len); /* Validate addr_len before calling common connect/connectx routine. */ af = sctp_get_af_specific(addr->sa_family); if (af && addr_len >= af->sockaddr_len) err = __sctp_connect(sk, addr, af->sockaddr_len, flags, NULL); release_sock(sk); return err; } int sctp_inet_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags) { if (addr_len < sizeof(uaddr->sa_family)) return -EINVAL; if (uaddr->sa_family == AF_UNSPEC) return -EOPNOTSUPP; return sctp_connect(sock->sk, uaddr, addr_len, flags); } /* Only called when shutdown a listening SCTP socket. */ static int sctp_disconnect(struct sock *sk, int flags) { if (!sctp_style(sk, TCP)) return -EOPNOTSUPP; sk->sk_shutdown |= RCV_SHUTDOWN; return 0; } /* 4.1.4 accept() - TCP Style Syntax * * Applications use accept() call to remove an established SCTP * association from the accept queue of the endpoint. A new socket * descriptor will be returned from accept() to represent the newly * formed association. */ static struct sock *sctp_accept(struct sock *sk, struct proto_accept_arg *arg) { struct sctp_sock *sp; struct sctp_endpoint *ep; struct sock *newsk = NULL; struct sctp_association *asoc; long timeo; int error = 0; lock_sock(sk); sp = sctp_sk(sk); ep = sp->ep; if (!sctp_style(sk, TCP)) { error = -EOPNOTSUPP; goto out; } if (!sctp_sstate(sk, LISTENING) || (sk->sk_shutdown & RCV_SHUTDOWN)) { error = -EINVAL; goto out; } timeo = sock_rcvtimeo(sk, arg->flags & O_NONBLOCK); error = sctp_wait_for_accept(sk, timeo); if (error) goto out; /* We treat the list of associations on the endpoint as the accept * queue and pick the first association on the list. */ asoc = list_entry(ep->asocs.next, struct sctp_association, asocs); newsk = sp->pf->create_accept_sk(sk, asoc, arg->kern); if (!newsk) { error = -ENOMEM; goto out; } /* Populate the fields of the newsk from the oldsk and migrate the * asoc to the newsk. */ error = sctp_sock_migrate(sk, newsk, asoc, SCTP_SOCKET_TCP); if (error) { sk_common_release(newsk); newsk = NULL; } out: release_sock(sk); arg->err = error; return newsk; } /* The SCTP ioctl handler. */ static int sctp_ioctl(struct sock *sk, int cmd, int *karg) { int rc = -ENOTCONN; lock_sock(sk); /* * SEQPACKET-style sockets in LISTENING state are valid, for * SCTP, so only discard TCP-style sockets in LISTENING state. */ if (sctp_style(sk, TCP) && sctp_sstate(sk, LISTENING)) goto out; switch (cmd) { case SIOCINQ: { struct sk_buff *skb; *karg = 0; skb = skb_peek(&sk->sk_receive_queue); if (skb != NULL) { /* * We will only return the amount of this packet since * that is all that will be read. */ *karg = skb->len; } rc = 0; break; } default: rc = -ENOIOCTLCMD; break; } out: release_sock(sk); return rc; } /* This is the function which gets called during socket creation to * initialized the SCTP-specific portion of the sock. * The sock structure should already be zero-filled memory. */ static int sctp_init_sock(struct sock *sk) { struct net *net = sock_net(sk); struct sctp_sock *sp; pr_debug("%s: sk:%p\n", __func__, sk); sp = sctp_sk(sk); /* Initialize the SCTP per socket area. */ switch (sk->sk_type) { case SOCK_SEQPACKET: sp->type = SCTP_SOCKET_UDP; break; case SOCK_STREAM: sp->type = SCTP_SOCKET_TCP; break; default: return -ESOCKTNOSUPPORT; } sk->sk_gso_type = SKB_GSO_SCTP; /* Initialize default send parameters. These parameters can be * modified with the SCTP_DEFAULT_SEND_PARAM socket option. */ sp->default_stream = 0; sp->default_ppid = 0; sp->default_flags = 0; sp->default_context = 0; sp->default_timetolive = 0; sp->default_rcv_context = 0; sp->max_burst = net->sctp.max_burst; sp->sctp_hmac_alg = net->sctp.sctp_hmac_alg; /* Initialize default setup parameters. These parameters * can be modified with the SCTP_INITMSG socket option or * overridden by the SCTP_INIT CMSG. */ sp->initmsg.sinit_num_ostreams = sctp_max_outstreams; sp->initmsg.sinit_max_instreams = sctp_max_instreams; sp->initmsg.sinit_max_attempts = net->sctp.max_retrans_init; sp->initmsg.sinit_max_init_timeo = net->sctp.rto_max; /* Initialize default RTO related parameters. These parameters can * be modified for with the SCTP_RTOINFO socket option. */ sp->rtoinfo.srto_initial = net->sctp.rto_initial; sp->rtoinfo.srto_max = net->sctp.rto_max; sp->rtoinfo.srto_min = net->sctp.rto_min; /* Initialize default association related parameters. These parameters * can be modified with the SCTP_ASSOCINFO socket option. */ sp->assocparams.sasoc_asocmaxrxt = net->sctp.max_retrans_association; sp->assocparams.sasoc_number_peer_destinations = 0; sp->assocparams.sasoc_peer_rwnd = 0; sp->assocparams.sasoc_local_rwnd = 0; sp->assocparams.sasoc_cookie_life = net->sctp.valid_cookie_life; /* Initialize default event subscriptions. By default, all the * options are off. */ sp->subscribe = 0; /* Default Peer Address Parameters. These defaults can * be modified via SCTP_PEER_ADDR_PARAMS */ sp->hbinterval = net->sctp.hb_interval; sp->udp_port = htons(net->sctp.udp_port); sp->encap_port = htons(net->sctp.encap_port); sp->pathmaxrxt = net->sctp.max_retrans_path; sp->pf_retrans = net->sctp.pf_retrans; sp->ps_retrans = net->sctp.ps_retrans; sp->pf_expose = net->sctp.pf_expose; sp->pathmtu = 0; /* allow default discovery */ sp->sackdelay = net->sctp.sack_timeout; sp->sackfreq = 2; sp->param_flags = SPP_HB_ENABLE | SPP_PMTUD_ENABLE | SPP_SACKDELAY_ENABLE; sp->default_ss = SCTP_SS_DEFAULT; /* If enabled no SCTP message fragmentation will be performed. * Configure through SCTP_DISABLE_FRAGMENTS socket option. */ sp->disable_fragments = 0; /* Enable Nagle algorithm by default. */ sp->nodelay = 0; sp->recvrcvinfo = 0; sp->recvnxtinfo = 0; /* Enable by default. */ sp->v4mapped = 1; /* Auto-close idle associations after the configured * number of seconds. A value of 0 disables this * feature. Configure through the SCTP_AUTOCLOSE socket option, * for UDP-style sockets only. */ sp->autoclose = 0; /* User specified fragmentation limit. */ sp->user_frag = 0; sp->adaptation_ind = 0; sp->pf = sctp_get_pf_specific(sk->sk_family); /* Control variables for partial data delivery. */ atomic_set(&sp->pd_mode, 0); skb_queue_head_init(&sp->pd_lobby); sp->frag_interleave = 0; sp->probe_interval = net->sctp.probe_interval; /* Create a per socket endpoint structure. Even if we * change the data structure relationships, this may still * be useful for storing pre-connect address information. */ sp->ep = sctp_endpoint_new(sk, GFP_KERNEL); if (!sp->ep) return -ENOMEM; sp->hmac = NULL; sk->sk_destruct = sctp_destruct_sock; SCTP_DBG_OBJCNT_INC(sock); sk_sockets_allocated_inc(sk); sock_prot_inuse_add(net, sk->sk_prot, 1); return 0; } /* Cleanup any SCTP per socket resources. Must be called with * sock_net(sk)->sctp.addr_wq_lock held if sp->do_auto_asconf is true */ static void sctp_destroy_sock(struct sock *sk) { struct sctp_sock *sp; pr_debug("%s: sk:%p\n", __func__, sk); /* Release our hold on the endpoint. */ sp = sctp_sk(sk); /* This could happen during socket init, thus we bail out * early, since the rest of the below is not setup either. */ if (sp->ep == NULL) return; if (sp->do_auto_asconf) { sp->do_auto_asconf = 0; list_del(&sp->auto_asconf_list); } sctp_endpoint_free(sp->ep); sk_sockets_allocated_dec(sk); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); } /* Triggered when there are no references on the socket anymore */ static void sctp_destruct_common(struct sock *sk) { struct sctp_sock *sp = sctp_sk(sk); /* Free up the HMAC transform. */ crypto_free_shash(sp->hmac); } static void sctp_destruct_sock(struct sock *sk) { sctp_destruct_common(sk); inet_sock_destruct(sk); } /* API 4.1.7 shutdown() - TCP Style Syntax * int shutdown(int socket, int how); * * sd - the socket descriptor of the association to be closed. * how - Specifies the type of shutdown. The values are * as follows: * SHUT_RD * Disables further receive operations. No SCTP * protocol action is taken. * SHUT_WR * Disables further send operations, and initiates * the SCTP shutdown sequence. * SHUT_RDWR * Disables further send and receive operations * and initiates the SCTP shutdown sequence. */ static void sctp_shutdown(struct sock *sk, int how) { struct net *net = sock_net(sk); struct sctp_endpoint *ep; if (!sctp_style(sk, TCP)) return; ep = sctp_sk(sk)->ep; if (how & SEND_SHUTDOWN && !list_empty(&ep->asocs)) { struct sctp_association *asoc; inet_sk_set_state(sk, SCTP_SS_CLOSING); asoc = list_entry(ep->asocs.next, struct sctp_association, asocs); sctp_primitive_SHUTDOWN(net, asoc, NULL); } } int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc, struct sctp_info *info) { struct sctp_transport *prim; struct list_head *pos; int mask; memset(info, 0, sizeof(*info)); if (!asoc) { struct sctp_sock *sp = sctp_sk(sk); info->sctpi_s_autoclose = sp->autoclose; info->sctpi_s_adaptation_ind = sp->adaptation_ind; info->sctpi_s_pd_point = sp->pd_point; info->sctpi_s_nodelay = sp->nodelay; info->sctpi_s_disable_fragments = sp->disable_fragments; info->sctpi_s_v4mapped = sp->v4mapped; info->sctpi_s_frag_interleave = sp->frag_interleave; info->sctpi_s_type = sp->type; return 0; } info->sctpi_tag = asoc->c.my_vtag; info->sctpi_state = asoc->state; info->sctpi_rwnd = asoc->a_rwnd; info->sctpi_unackdata = asoc->unack_data; info->sctpi_penddata = sctp_tsnmap_pending(&asoc->peer.tsn_map); info->sctpi_instrms = asoc->stream.incnt; info->sctpi_outstrms = asoc->stream.outcnt; list_for_each(pos, &asoc->base.inqueue.in_chunk_list) info->sctpi_inqueue++; list_for_each(pos, &asoc->outqueue.out_chunk_list) info->sctpi_outqueue++; info->sctpi_overall_error = asoc->overall_error_count; info->sctpi_max_burst = asoc->max_burst; info->sctpi_maxseg = asoc->frag_point; info->sctpi_peer_rwnd = asoc->peer.rwnd; info->sctpi_peer_tag = asoc->c.peer_vtag; mask = asoc->peer.intl_capable << 1; mask = (mask | asoc->peer.ecn_capable) << 1; mask = (mask | asoc->peer.ipv4_address) << 1; mask = (mask | asoc->peer.ipv6_address) << 1; mask = (mask | asoc->peer.reconf_capable) << 1; mask = (mask | asoc->peer.asconf_capable) << 1; mask = (mask | asoc->peer.prsctp_capable) << 1; mask = (mask | asoc->peer.auth_capable); info->sctpi_peer_capable = mask; mask = asoc->peer.sack_needed << 1; mask = (mask | asoc->peer.sack_generation) << 1; mask = (mask | asoc->peer.zero_window_announced); info->sctpi_peer_sack = mask; info->sctpi_isacks = asoc->stats.isacks; info->sctpi_osacks = asoc->stats.osacks; info->sctpi_opackets = asoc->stats.opackets; info->sctpi_ipackets = asoc->stats.ipackets; info->sctpi_rtxchunks = asoc->stats.rtxchunks; info->sctpi_outofseqtsns = asoc->stats.outofseqtsns; info->sctpi_idupchunks = asoc->stats.idupchunks; info->sctpi_gapcnt = asoc->stats.gapcnt; info->sctpi_ouodchunks = asoc->stats.ouodchunks; info->sctpi_iuodchunks = asoc->stats.iuodchunks; info->sctpi_oodchunks = asoc->stats.oodchunks; info->sctpi_iodchunks = asoc->stats.iodchunks; info->sctpi_octrlchunks = asoc->stats.octrlchunks; info->sctpi_ictrlchunks = asoc->stats.ictrlchunks; prim = asoc->peer.primary_path; memcpy(&info->sctpi_p_address, &prim->ipaddr, sizeof(prim->ipaddr)); info->sctpi_p_state = prim->state; info->sctpi_p_cwnd = prim->cwnd; info->sctpi_p_srtt = prim->srtt; info->sctpi_p_rto = jiffies_to_msecs(prim->rto); info->sctpi_p_hbinterval = prim->hbinterval; info->sctpi_p_pathmaxrxt = prim->pathmaxrxt; info->sctpi_p_sackdelay = jiffies_to_msecs(prim->sackdelay); info->sctpi_p_ssthresh = prim->ssthresh; info->sctpi_p_partial_bytes_acked = prim->partial_bytes_acked; info->sctpi_p_flight_size = prim->flight_size; info->sctpi_p_error = prim->error_count; return 0; } EXPORT_SYMBOL_GPL(sctp_get_sctp_info); /* use callback to avoid exporting the core structure */ void sctp_transport_walk_start(struct rhashtable_iter *iter) __acquires(RCU) { rhltable_walk_enter(&sctp_transport_hashtable, iter); rhashtable_walk_start(iter); } void sctp_transport_walk_stop(struct rhashtable_iter *iter) __releases(RCU) { rhashtable_walk_stop(iter); rhashtable_walk_exit(iter); } struct sctp_transport *sctp_transport_get_next(struct net *net, struct rhashtable_iter *iter) { struct sctp_transport *t; t = rhashtable_walk_next(iter); for (; t; t = rhashtable_walk_next(iter)) { if (IS_ERR(t)) { if (PTR_ERR(t) == -EAGAIN) continue; break; } if (!sctp_transport_hold(t)) continue; if (net_eq(t->asoc->base.net, net) && t->asoc->peer.primary_path == t) break; sctp_transport_put(t); } return t; } struct sctp_transport *sctp_transport_get_idx(struct net *net, struct rhashtable_iter *iter, int pos) { struct sctp_transport *t; if (!pos) return SEQ_START_TOKEN; while ((t = sctp_transport_get_next(net, iter)) && !IS_ERR(t)) { if (!--pos) break; sctp_transport_put(t); } return t; } int sctp_for_each_endpoint(int (*cb)(struct sctp_endpoint *, void *), void *p) { int err = 0; int hash = 0; struct sctp_endpoint *ep; struct sctp_hashbucket *head; for (head = sctp_ep_hashtable; hash < sctp_ep_hashsize; hash++, head++) { read_lock_bh(&head->lock); sctp_for_each_hentry(ep, &head->chain) { err = cb(ep, p); if (err) break; } read_unlock_bh(&head->lock); } return err; } EXPORT_SYMBOL_GPL(sctp_for_each_endpoint); int sctp_transport_lookup_process(sctp_callback_t cb, struct net *net, const union sctp_addr *laddr, const union sctp_addr *paddr, void *p, int dif) { struct sctp_transport *transport; struct sctp_endpoint *ep; int err = -ENOENT; rcu_read_lock(); transport = sctp_addrs_lookup_transport(net, laddr, paddr, dif, dif); if (!transport) { rcu_read_unlock(); return err; } ep = transport->asoc->ep; if (!sctp_endpoint_hold(ep)) { /* asoc can be peeled off */ sctp_transport_put(transport); rcu_read_unlock(); return err; } rcu_read_unlock(); err = cb(ep, transport, p); sctp_endpoint_put(ep); sctp_transport_put(transport); return err; } EXPORT_SYMBOL_GPL(sctp_transport_lookup_process); int sctp_transport_traverse_process(sctp_callback_t cb, sctp_callback_t cb_done, struct net *net, int *pos, void *p) { struct rhashtable_iter hti; struct sctp_transport *tsp; struct sctp_endpoint *ep; int ret; again: ret = 0; sctp_transport_walk_start(&hti); tsp = sctp_transport_get_idx(net, &hti, *pos + 1); for (; !IS_ERR_OR_NULL(tsp); tsp = sctp_transport_get_next(net, &hti)) { ep = tsp->asoc->ep; if (sctp_endpoint_hold(ep)) { /* asoc can be peeled off */ ret = cb(ep, tsp, p); if (ret) break; sctp_endpoint_put(ep); } (*pos)++; sctp_transport_put(tsp); } sctp_transport_walk_stop(&hti); if (ret) { if (cb_done && !cb_done(ep, tsp, p)) { (*pos)++; sctp_endpoint_put(ep); sctp_transport_put(tsp); goto again; } sctp_endpoint_put(ep); sctp_transport_put(tsp); } return ret; } EXPORT_SYMBOL_GPL(sctp_transport_traverse_process); /* 7.2.1 Association Status (SCTP_STATUS) * Applications can retrieve current status information about an * association, including association state, peer receiver window size, * number of unacked data chunks, and number of data chunks pending * receipt. This information is read-only. */ static int sctp_getsockopt_sctp_status(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_status status; struct sctp_association *asoc = NULL; struct sctp_transport *transport; sctp_assoc_t associd; int retval = 0; if (len < sizeof(status)) { retval = -EINVAL; goto out; } len = sizeof(status); if (copy_from_user(&status, optval, len)) { retval = -EFAULT; goto out; } associd = status.sstat_assoc_id; asoc = sctp_id2assoc(sk, associd); if (!asoc) { retval = -EINVAL; goto out; } transport = asoc->peer.primary_path; status.sstat_assoc_id = sctp_assoc2id(asoc); status.sstat_state = sctp_assoc_to_state(asoc); status.sstat_rwnd = asoc->peer.rwnd; status.sstat_unackdata = asoc->unack_data; status.sstat_penddata = sctp_tsnmap_pending(&asoc->peer.tsn_map); status.sstat_instrms = asoc->stream.incnt; status.sstat_outstrms = asoc->stream.outcnt; status.sstat_fragmentation_point = asoc->frag_point; status.sstat_primary.spinfo_assoc_id = sctp_assoc2id(transport->asoc); memcpy(&status.sstat_primary.spinfo_address, &transport->ipaddr, transport->af_specific->sockaddr_len); /* Map ipv4 address into v4-mapped-on-v6 address. */ sctp_get_pf_specific(sk->sk_family)->addr_to_user(sctp_sk(sk), (union sctp_addr *)&status.sstat_primary.spinfo_address); status.sstat_primary.spinfo_state = transport->state; status.sstat_primary.spinfo_cwnd = transport->cwnd; status.sstat_primary.spinfo_srtt = transport->srtt; status.sstat_primary.spinfo_rto = jiffies_to_msecs(transport->rto); status.sstat_primary.spinfo_mtu = transport->pathmtu; if (status.sstat_primary.spinfo_state == SCTP_UNKNOWN) status.sstat_primary.spinfo_state = SCTP_ACTIVE; if (put_user(len, optlen)) { retval = -EFAULT; goto out; } pr_debug("%s: len:%d, state:%d, rwnd:%d, assoc_id:%d\n", __func__, len, status.sstat_state, status.sstat_rwnd, status.sstat_assoc_id); if (copy_to_user(optval, &status, len)) { retval = -EFAULT; goto out; } out: return retval; } /* 7.2.2 Peer Address Information (SCTP_GET_PEER_ADDR_INFO) * * Applications can retrieve information about a specific peer address * of an association, including its reachability state, congestion * window, and retransmission timer values. This information is * read-only. */ static int sctp_getsockopt_peer_addr_info(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_paddrinfo pinfo; struct sctp_transport *transport; int retval = 0; if (len < sizeof(pinfo)) { retval = -EINVAL; goto out; } len = sizeof(pinfo); if (copy_from_user(&pinfo, optval, len)) { retval = -EFAULT; goto out; } transport = sctp_addr_id2transport(sk, &pinfo.spinfo_address, pinfo.spinfo_assoc_id); if (!transport) { retval = -EINVAL; goto out; } if (transport->state == SCTP_PF && transport->asoc->pf_expose == SCTP_PF_EXPOSE_DISABLE) { retval = -EACCES; goto out; } pinfo.spinfo_assoc_id = sctp_assoc2id(transport->asoc); pinfo.spinfo_state = transport->state; pinfo.spinfo_cwnd = transport->cwnd; pinfo.spinfo_srtt = transport->srtt; pinfo.spinfo_rto = jiffies_to_msecs(transport->rto); pinfo.spinfo_mtu = transport->pathmtu; if (pinfo.spinfo_state == SCTP_UNKNOWN) pinfo.spinfo_state = SCTP_ACTIVE; if (put_user(len, optlen)) { retval = -EFAULT; goto out; } if (copy_to_user(optval, &pinfo, len)) { retval = -EFAULT; goto out; } out: return retval; } /* 7.1.12 Enable/Disable message fragmentation (SCTP_DISABLE_FRAGMENTS) * * This option is a on/off flag. If enabled no SCTP message * fragmentation will be performed. Instead if a message being sent * exceeds the current PMTU size, the message will NOT be sent and * instead a error will be indicated to the user. */ static int sctp_getsockopt_disable_fragments(struct sock *sk, int len, char __user *optval, int __user *optlen) { int val; if (len < sizeof(int)) return -EINVAL; len = sizeof(int); val = (sctp_sk(sk)->disable_fragments == 1); if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } /* 7.1.15 Set notification and ancillary events (SCTP_EVENTS) * * This socket option is used to specify various notifications and * ancillary data the user wishes to receive. */ static int sctp_getsockopt_events(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_event_subscribe subscribe; __u8 *sn_type = (__u8 *)&subscribe; int i; if (len == 0) return -EINVAL; if (len > sizeof(struct sctp_event_subscribe)) len = sizeof(struct sctp_event_subscribe); if (put_user(len, optlen)) return -EFAULT; for (i = 0; i < len; i++) sn_type[i] = sctp_ulpevent_type_enabled(sctp_sk(sk)->subscribe, SCTP_SN_TYPE_BASE + i); if (copy_to_user(optval, &subscribe, len)) return -EFAULT; return 0; } /* 7.1.8 Automatic Close of associations (SCTP_AUTOCLOSE) * * This socket option is applicable to the UDP-style socket only. When * set it will cause associations that are idle for more than the * specified number of seconds to automatically close. An association * being idle is defined an association that has NOT sent or received * user data. The special value of '0' indicates that no automatic * close of any associations should be performed. The option expects an * integer defining the number of seconds of idle time before an * association is closed. */ static int sctp_getsockopt_autoclose(struct sock *sk, int len, char __user *optval, int __user *optlen) { /* Applicable to UDP-style socket only */ if (sctp_style(sk, TCP)) return -EOPNOTSUPP; if (len < sizeof(int)) return -EINVAL; len = sizeof(int); if (put_user(len, optlen)) return -EFAULT; if (put_user(sctp_sk(sk)->autoclose, (int __user *)optval)) return -EFAULT; return 0; } /* Helper routine to branch off an association to a new socket. */ int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp) { struct sctp_association *asoc = sctp_id2assoc(sk, id); struct sctp_sock *sp = sctp_sk(sk); struct socket *sock; int err = 0; /* Do not peel off from one netns to another one. */ if (!net_eq(current->nsproxy->net_ns, sock_net(sk))) return -EINVAL; if (!asoc) return -EINVAL; /* An association cannot be branched off from an already peeled-off * socket, nor is this supported for tcp style sockets. */ if (!sctp_style(sk, UDP)) return -EINVAL; /* Create a new socket. */ err = sock_create(sk->sk_family, SOCK_SEQPACKET, IPPROTO_SCTP, &sock); if (err < 0) return err; sctp_copy_sock(sock->sk, sk, asoc); /* Make peeled-off sockets more like 1-1 accepted sockets. * Set the daddr and initialize id to something more random and also * copy over any ip options. */ sp->pf->to_sk_daddr(&asoc->peer.primary_addr, sock->sk); sp->pf->copy_ip_options(sk, sock->sk); /* Populate the fields of the newsk from the oldsk and migrate the * asoc to the newsk. */ err = sctp_sock_migrate(sk, sock->sk, asoc, SCTP_SOCKET_UDP_HIGH_BANDWIDTH); if (err) { sock_release(sock); sock = NULL; } *sockp = sock; return err; } EXPORT_SYMBOL(sctp_do_peeloff); static int sctp_getsockopt_peeloff_common(struct sock *sk, sctp_peeloff_arg_t *peeloff, struct file **newfile, unsigned flags) { struct socket *newsock; int retval; retval = sctp_do_peeloff(sk, peeloff->associd, &newsock); if (retval < 0) goto out; /* Map the socket to an unused fd that can be returned to the user. */ retval = get_unused_fd_flags(flags & SOCK_CLOEXEC); if (retval < 0) { sock_release(newsock); goto out; } *newfile = sock_alloc_file(newsock, 0, NULL); if (IS_ERR(*newfile)) { put_unused_fd(retval); retval = PTR_ERR(*newfile); *newfile = NULL; return retval; } pr_debug("%s: sk:%p, newsk:%p, sd:%d\n", __func__, sk, newsock->sk, retval); peeloff->sd = retval; if (flags & SOCK_NONBLOCK) (*newfile)->f_flags |= O_NONBLOCK; out: return retval; } static int sctp_getsockopt_peeloff(struct sock *sk, int len, char __user *optval, int __user *optlen) { sctp_peeloff_arg_t peeloff; struct file *newfile = NULL; int retval = 0; if (len < sizeof(sctp_peeloff_arg_t)) return -EINVAL; len = sizeof(sctp_peeloff_arg_t); if (copy_from_user(&peeloff, optval, len)) return -EFAULT; retval = sctp_getsockopt_peeloff_common(sk, &peeloff, &newfile, 0); if (retval < 0) goto out; /* Return the fd mapped to the new socket. */ if (put_user(len, optlen)) { fput(newfile); put_unused_fd(retval); return -EFAULT; } if (copy_to_user(optval, &peeloff, len)) { fput(newfile); put_unused_fd(retval); return -EFAULT; } fd_install(retval, newfile); out: return retval; } static int sctp_getsockopt_peeloff_flags(struct sock *sk, int len, char __user *optval, int __user *optlen) { sctp_peeloff_flags_arg_t peeloff; struct file *newfile = NULL; int retval = 0; if (len < sizeof(sctp_peeloff_flags_arg_t)) return -EINVAL; len = sizeof(sctp_peeloff_flags_arg_t); if (copy_from_user(&peeloff, optval, len)) return -EFAULT; retval = sctp_getsockopt_peeloff_common(sk, &peeloff.p_arg, &newfile, peeloff.flags); if (retval < 0) goto out; /* Return the fd mapped to the new socket. */ if (put_user(len, optlen)) { fput(newfile); put_unused_fd(retval); return -EFAULT; } if (copy_to_user(optval, &peeloff, len)) { fput(newfile); put_unused_fd(retval); return -EFAULT; } fd_install(retval, newfile); out: return retval; } /* 7.1.13 Peer Address Parameters (SCTP_PEER_ADDR_PARAMS) * * Applications can enable or disable heartbeats for any peer address of * an association, modify an address's heartbeat interval, force a * heartbeat to be sent immediately, and adjust the address's maximum * number of retransmissions sent before an address is considered * unreachable. The following structure is used to access and modify an * address's parameters: * * struct sctp_paddrparams { * sctp_assoc_t spp_assoc_id; * struct sockaddr_storage spp_address; * uint32_t spp_hbinterval; * uint16_t spp_pathmaxrxt; * uint32_t spp_pathmtu; * uint32_t spp_sackdelay; * uint32_t spp_flags; * }; * * spp_assoc_id - (one-to-many style socket) This is filled in the * application, and identifies the association for * this query. * spp_address - This specifies which address is of interest. * spp_hbinterval - This contains the value of the heartbeat interval, * in milliseconds. If a value of zero * is present in this field then no changes are to * be made to this parameter. * spp_pathmaxrxt - This contains the maximum number of * retransmissions before this address shall be * considered unreachable. If a value of zero * is present in this field then no changes are to * be made to this parameter. * spp_pathmtu - When Path MTU discovery is disabled the value * specified here will be the "fixed" path mtu. * Note that if the spp_address field is empty * then all associations on this address will * have this fixed path mtu set upon them. * * spp_sackdelay - When delayed sack is enabled, this value specifies * the number of milliseconds that sacks will be delayed * for. This value will apply to all addresses of an * association if the spp_address field is empty. Note * also, that if delayed sack is enabled and this * value is set to 0, no change is made to the last * recorded delayed sack timer value. * * spp_flags - These flags are used to control various features * on an association. The flag field may contain * zero or more of the following options. * * SPP_HB_ENABLE - Enable heartbeats on the * specified address. Note that if the address * field is empty all addresses for the association * have heartbeats enabled upon them. * * SPP_HB_DISABLE - Disable heartbeats on the * speicifed address. Note that if the address * field is empty all addresses for the association * will have their heartbeats disabled. Note also * that SPP_HB_ENABLE and SPP_HB_DISABLE are * mutually exclusive, only one of these two should * be specified. Enabling both fields will have * undetermined results. * * SPP_HB_DEMAND - Request a user initiated heartbeat * to be made immediately. * * SPP_PMTUD_ENABLE - This field will enable PMTU * discovery upon the specified address. Note that * if the address feild is empty then all addresses * on the association are effected. * * SPP_PMTUD_DISABLE - This field will disable PMTU * discovery upon the specified address. Note that * if the address feild is empty then all addresses * on the association are effected. Not also that * SPP_PMTUD_ENABLE and SPP_PMTUD_DISABLE are mutually * exclusive. Enabling both will have undetermined * results. * * SPP_SACKDELAY_ENABLE - Setting this flag turns * on delayed sack. The time specified in spp_sackdelay * is used to specify the sack delay for this address. Note * that if spp_address is empty then all addresses will * enable delayed sack and take on the sack delay * value specified in spp_sackdelay. * SPP_SACKDELAY_DISABLE - Setting this flag turns * off delayed sack. If the spp_address field is blank then * delayed sack is disabled for the entire association. Note * also that this field is mutually exclusive to * SPP_SACKDELAY_ENABLE, setting both will have undefined * results. * * SPP_IPV6_FLOWLABEL: Setting this flag enables the * setting of the IPV6 flow label value. The value is * contained in the spp_ipv6_flowlabel field. * Upon retrieval, this flag will be set to indicate that * the spp_ipv6_flowlabel field has a valid value returned. * If a specific destination address is set (in the * spp_address field), then the value returned is that of * the address. If just an association is specified (and * no address), then the association's default flow label * is returned. If neither an association nor a destination * is specified, then the socket's default flow label is * returned. For non-IPv6 sockets, this flag will be left * cleared. * * SPP_DSCP: Setting this flag enables the setting of the * Differentiated Services Code Point (DSCP) value * associated with either the association or a specific * address. The value is obtained in the spp_dscp field. * Upon retrieval, this flag will be set to indicate that * the spp_dscp field has a valid value returned. If a * specific destination address is set when called (in the * spp_address field), then that specific destination * address's DSCP value is returned. If just an association * is specified, then the association's default DSCP is * returned. If neither an association nor a destination is * specified, then the socket's default DSCP is returned. * * spp_ipv6_flowlabel * - This field is used in conjunction with the * SPP_IPV6_FLOWLABEL flag and contains the IPv6 flow label. * The 20 least significant bits are used for the flow * label. This setting has precedence over any IPv6-layer * setting. * * spp_dscp - This field is used in conjunction with the SPP_DSCP flag * and contains the DSCP. The 6 most significant bits are * used for the DSCP. This setting has precedence over any * IPv4- or IPv6- layer setting. */ static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_paddrparams params; struct sctp_transport *trans = NULL; struct sctp_association *asoc = NULL; struct sctp_sock *sp = sctp_sk(sk); if (len >= sizeof(params)) len = sizeof(params); else if (len >= ALIGN(offsetof(struct sctp_paddrparams, spp_ipv6_flowlabel), 4)) len = ALIGN(offsetof(struct sctp_paddrparams, spp_ipv6_flowlabel), 4); else return -EINVAL; if (copy_from_user(¶ms, optval, len)) return -EFAULT; /* If an address other than INADDR_ANY is specified, and * no transport is found, then the request is invalid. */ if (!sctp_is_any(sk, (union sctp_addr *)¶ms.spp_address)) { trans = sctp_addr_id2transport(sk, ¶ms.spp_address, params.spp_assoc_id); if (!trans) { pr_debug("%s: failed no transport\n", __func__); return -EINVAL; } } /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the * socket is a one to many style socket, and an association * was not found, then the id was invalid. */ asoc = sctp_id2assoc(sk, params.spp_assoc_id); if (!asoc && params.spp_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) { pr_debug("%s: failed no association\n", __func__); return -EINVAL; } if (trans) { /* Fetch transport values. */ params.spp_hbinterval = jiffies_to_msecs(trans->hbinterval); params.spp_pathmtu = trans->pathmtu; params.spp_pathmaxrxt = trans->pathmaxrxt; params.spp_sackdelay = jiffies_to_msecs(trans->sackdelay); /*draft-11 doesn't say what to return in spp_flags*/ params.spp_flags = trans->param_flags; if (trans->flowlabel & SCTP_FLOWLABEL_SET_MASK) { params.spp_ipv6_flowlabel = trans->flowlabel & SCTP_FLOWLABEL_VAL_MASK; params.spp_flags |= SPP_IPV6_FLOWLABEL; } if (trans->dscp & SCTP_DSCP_SET_MASK) { params.spp_dscp = trans->dscp & SCTP_DSCP_VAL_MASK; params.spp_flags |= SPP_DSCP; } } else if (asoc) { /* Fetch association values. */ params.spp_hbinterval = jiffies_to_msecs(asoc->hbinterval); params.spp_pathmtu = asoc->pathmtu; params.spp_pathmaxrxt = asoc->pathmaxrxt; params.spp_sackdelay = jiffies_to_msecs(asoc->sackdelay); /*draft-11 doesn't say what to return in spp_flags*/ params.spp_flags = asoc->param_flags; if (asoc->flowlabel & SCTP_FLOWLABEL_SET_MASK) { params.spp_ipv6_flowlabel = asoc->flowlabel & SCTP_FLOWLABEL_VAL_MASK; params.spp_flags |= SPP_IPV6_FLOWLABEL; } if (asoc->dscp & SCTP_DSCP_SET_MASK) { params.spp_dscp = asoc->dscp & SCTP_DSCP_VAL_MASK; params.spp_flags |= SPP_DSCP; } } else { /* Fetch socket values. */ params.spp_hbinterval = sp->hbinterval; params.spp_pathmtu = sp->pathmtu; params.spp_sackdelay = sp->sackdelay; params.spp_pathmaxrxt = sp->pathmaxrxt; /*draft-11 doesn't say what to return in spp_flags*/ params.spp_flags = sp->param_flags; if (sp->flowlabel & SCTP_FLOWLABEL_SET_MASK) { params.spp_ipv6_flowlabel = sp->flowlabel & SCTP_FLOWLABEL_VAL_MASK; params.spp_flags |= SPP_IPV6_FLOWLABEL; } if (sp->dscp & SCTP_DSCP_SET_MASK) { params.spp_dscp = sp->dscp & SCTP_DSCP_VAL_MASK; params.spp_flags |= SPP_DSCP; } } if (copy_to_user(optval, ¶ms, len)) return -EFAULT; if (put_user(len, optlen)) return -EFAULT; return 0; } /* * 7.1.23. Get or set delayed ack timer (SCTP_DELAYED_SACK) * * This option will effect the way delayed acks are performed. This * option allows you to get or set the delayed ack time, in * milliseconds. It also allows changing the delayed ack frequency. * Changing the frequency to 1 disables the delayed sack algorithm. If * the assoc_id is 0, then this sets or gets the endpoints default * values. If the assoc_id field is non-zero, then the set or get * effects the specified association for the one to many model (the * assoc_id field is ignored by the one to one model). Note that if * sack_delay or sack_freq are 0 when setting this option, then the * current values will remain unchanged. * * struct sctp_sack_info { * sctp_assoc_t sack_assoc_id; * uint32_t sack_delay; * uint32_t sack_freq; * }; * * sack_assoc_id - This parameter, indicates which association the user * is performing an action upon. Note that if this field's value is * zero then the endpoints default value is changed (effecting future * associations only). * * sack_delay - This parameter contains the number of milliseconds that * the user is requesting the delayed ACK timer be set to. Note that * this value is defined in the standard to be between 200 and 500 * milliseconds. * * sack_freq - This parameter contains the number of packets that must * be received before a sack is sent without waiting for the delay * timer to expire. The default value for this is 2, setting this * value to 1 will disable the delayed sack algorithm. */ static int sctp_getsockopt_delayed_ack(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_sack_info params; struct sctp_association *asoc = NULL; struct sctp_sock *sp = sctp_sk(sk); if (len >= sizeof(struct sctp_sack_info)) { len = sizeof(struct sctp_sack_info); if (copy_from_user(¶ms, optval, len)) return -EFAULT; } else if (len == sizeof(struct sctp_assoc_value)) { pr_warn_ratelimited(DEPRECATED "%s (pid %d) " "Use of struct sctp_assoc_value in delayed_ack socket option.\n" "Use struct sctp_sack_info instead\n", current->comm, task_pid_nr(current)); if (copy_from_user(¶ms, optval, len)) return -EFAULT; } else return -EINVAL; /* Get association, if sack_assoc_id != SCTP_FUTURE_ASSOC and the * socket is a one to many style socket, and an association * was not found, then the id was invalid. */ asoc = sctp_id2assoc(sk, params.sack_assoc_id); if (!asoc && params.sack_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) { /* Fetch association values. */ if (asoc->param_flags & SPP_SACKDELAY_ENABLE) { params.sack_delay = jiffies_to_msecs(asoc->sackdelay); params.sack_freq = asoc->sackfreq; } else { params.sack_delay = 0; params.sack_freq = 1; } } else { /* Fetch socket values. */ if (sp->param_flags & SPP_SACKDELAY_ENABLE) { params.sack_delay = sp->sackdelay; params.sack_freq = sp->sackfreq; } else { params.sack_delay = 0; params.sack_freq = 1; } } if (copy_to_user(optval, ¶ms, len)) return -EFAULT; if (put_user(len, optlen)) return -EFAULT; return 0; } /* 7.1.3 Initialization Parameters (SCTP_INITMSG) * * Applications can specify protocol parameters for the default association * initialization. The option name argument to setsockopt() and getsockopt() * is SCTP_INITMSG. * * Setting initialization parameters is effective only on an unconnected * socket (for UDP-style sockets only future associations are effected * by the change). With TCP-style sockets, this option is inherited by * sockets derived from a listener socket. */ static int sctp_getsockopt_initmsg(struct sock *sk, int len, char __user *optval, int __user *optlen) { if (len < sizeof(struct sctp_initmsg)) return -EINVAL; len = sizeof(struct sctp_initmsg); if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &sctp_sk(sk)->initmsg, len)) return -EFAULT; return 0; } static int sctp_getsockopt_peer_addrs(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_association *asoc; int cnt = 0; struct sctp_getaddrs getaddrs; struct sctp_transport *from; void __user *to; union sctp_addr temp; struct sctp_sock *sp = sctp_sk(sk); int addrlen; size_t space_left; int bytes_copied; if (len < sizeof(struct sctp_getaddrs)) return -EINVAL; if (copy_from_user(&getaddrs, optval, sizeof(struct sctp_getaddrs))) return -EFAULT; /* For UDP-style sockets, id specifies the association to query. */ asoc = sctp_id2assoc(sk, getaddrs.assoc_id); if (!asoc) return -EINVAL; to = optval + offsetof(struct sctp_getaddrs, addrs); space_left = len - offsetof(struct sctp_getaddrs, addrs); list_for_each_entry(from, &asoc->peer.transport_addr_list, transports) { memcpy(&temp, &from->ipaddr, sizeof(temp)); addrlen = sctp_get_pf_specific(sk->sk_family) ->addr_to_user(sp, &temp); if (space_left < addrlen) return -ENOMEM; if (copy_to_user(to, &temp, addrlen)) return -EFAULT; to += addrlen; cnt++; space_left -= addrlen; } if (put_user(cnt, &((struct sctp_getaddrs __user *)optval)->addr_num)) return -EFAULT; bytes_copied = ((char __user *)to) - optval; if (put_user(bytes_copied, optlen)) return -EFAULT; return 0; } static int sctp_copy_laddrs(struct sock *sk, __u16 port, void *to, size_t space_left, int *bytes_copied) { struct sctp_sockaddr_entry *addr; union sctp_addr temp; int cnt = 0; int addrlen; struct net *net = sock_net(sk); rcu_read_lock(); list_for_each_entry_rcu(addr, &net->sctp.local_addr_list, list) { if (!addr->valid) continue; if ((PF_INET == sk->sk_family) && (AF_INET6 == addr->a.sa.sa_family)) continue; if ((PF_INET6 == sk->sk_family) && inet_v6_ipv6only(sk) && (AF_INET == addr->a.sa.sa_family)) continue; memcpy(&temp, &addr->a, sizeof(temp)); if (!temp.v4.sin_port) temp.v4.sin_port = htons(port); addrlen = sctp_get_pf_specific(sk->sk_family) ->addr_to_user(sctp_sk(sk), &temp); if (space_left < addrlen) { cnt = -ENOMEM; break; } memcpy(to, &temp, addrlen); to += addrlen; cnt++; space_left -= addrlen; *bytes_copied += addrlen; } rcu_read_unlock(); return cnt; } static int sctp_getsockopt_local_addrs(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_bind_addr *bp; struct sctp_association *asoc; int cnt = 0; struct sctp_getaddrs getaddrs; struct sctp_sockaddr_entry *addr; void __user *to; union sctp_addr temp; struct sctp_sock *sp = sctp_sk(sk); int addrlen; int err = 0; size_t space_left; int bytes_copied = 0; void *addrs; void *buf; if (len < sizeof(struct sctp_getaddrs)) return -EINVAL; if (copy_from_user(&getaddrs, optval, sizeof(struct sctp_getaddrs))) return -EFAULT; /* * For UDP-style sockets, id specifies the association to query. * If the id field is set to the value '0' then the locally bound * addresses are returned without regard to any particular * association. */ if (0 == getaddrs.assoc_id) { bp = &sctp_sk(sk)->ep->base.bind_addr; } else { asoc = sctp_id2assoc(sk, getaddrs.assoc_id); if (!asoc) return -EINVAL; bp = &asoc->base.bind_addr; } to = optval + offsetof(struct sctp_getaddrs, addrs); space_left = len - offsetof(struct sctp_getaddrs, addrs); addrs = kmalloc(space_left, GFP_USER | __GFP_NOWARN); if (!addrs) return -ENOMEM; /* If the endpoint is bound to 0.0.0.0 or ::0, get the valid * addresses from the global local address list. */ if (sctp_list_single_entry(&bp->address_list)) { addr = list_entry(bp->address_list.next, struct sctp_sockaddr_entry, list); if (sctp_is_any(sk, &addr->a)) { cnt = sctp_copy_laddrs(sk, bp->port, addrs, space_left, &bytes_copied); if (cnt < 0) { err = cnt; goto out; } goto copy_getaddrs; } } buf = addrs; /* Protection on the bound address list is not needed since * in the socket option context we hold a socket lock and * thus the bound address list can't change. */ list_for_each_entry(addr, &bp->address_list, list) { memcpy(&temp, &addr->a, sizeof(temp)); addrlen = sctp_get_pf_specific(sk->sk_family) ->addr_to_user(sp, &temp); if (space_left < addrlen) { err = -ENOMEM; /*fixme: right error?*/ goto out; } memcpy(buf, &temp, addrlen); buf += addrlen; bytes_copied += addrlen; cnt++; space_left -= addrlen; } copy_getaddrs: if (copy_to_user(to, addrs, bytes_copied)) { err = -EFAULT; goto out; } if (put_user(cnt, &((struct sctp_getaddrs __user *)optval)->addr_num)) { err = -EFAULT; goto out; } /* XXX: We should have accounted for sizeof(struct sctp_getaddrs) too, * but we can't change it anymore. */ if (put_user(bytes_copied, optlen)) err = -EFAULT; out: kfree(addrs); return err; } /* 7.1.10 Set Primary Address (SCTP_PRIMARY_ADDR) * * Requests that the local SCTP stack use the enclosed peer address as * the association primary. The enclosed address must be one of the * association peer's addresses. */ static int sctp_getsockopt_primary_addr(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_prim prim; struct sctp_association *asoc; struct sctp_sock *sp = sctp_sk(sk); if (len < sizeof(struct sctp_prim)) return -EINVAL; len = sizeof(struct sctp_prim); if (copy_from_user(&prim, optval, len)) return -EFAULT; asoc = sctp_id2assoc(sk, prim.ssp_assoc_id); if (!asoc) return -EINVAL; if (!asoc->peer.primary_path) return -ENOTCONN; memcpy(&prim.ssp_addr, &asoc->peer.primary_path->ipaddr, asoc->peer.primary_path->af_specific->sockaddr_len); sctp_get_pf_specific(sk->sk_family)->addr_to_user(sp, (union sctp_addr *)&prim.ssp_addr); if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &prim, len)) return -EFAULT; return 0; } /* * 7.1.11 Set Adaptation Layer Indicator (SCTP_ADAPTATION_LAYER) * * Requests that the local endpoint set the specified Adaptation Layer * Indication parameter for all future INIT and INIT-ACK exchanges. */ static int sctp_getsockopt_adaptation_layer(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_setadaptation adaptation; if (len < sizeof(struct sctp_setadaptation)) return -EINVAL; len = sizeof(struct sctp_setadaptation); adaptation.ssb_adaptation_ind = sctp_sk(sk)->adaptation_ind; if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &adaptation, len)) return -EFAULT; return 0; } /* * * 7.1.14 Set default send parameters (SCTP_DEFAULT_SEND_PARAM) * * Applications that wish to use the sendto() system call may wish to * specify a default set of parameters that would normally be supplied * through the inclusion of ancillary data. This socket option allows * such an application to set the default sctp_sndrcvinfo structure. * The application that wishes to use this socket option simply passes * in to this call the sctp_sndrcvinfo structure defined in Section * 5.2.2) The input parameters accepted by this call include * sinfo_stream, sinfo_flags, sinfo_ppid, sinfo_context, * sinfo_timetolive. The user must provide the sinfo_assoc_id field in * to this call if the caller is using the UDP model. * * For getsockopt, it get the default sctp_sndrcvinfo structure. */ static int sctp_getsockopt_default_send_param(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; struct sctp_sndrcvinfo info; if (len < sizeof(info)) return -EINVAL; len = sizeof(info); if (copy_from_user(&info, optval, len)) return -EFAULT; asoc = sctp_id2assoc(sk, info.sinfo_assoc_id); if (!asoc && info.sinfo_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) { info.sinfo_stream = asoc->default_stream; info.sinfo_flags = asoc->default_flags; info.sinfo_ppid = asoc->default_ppid; info.sinfo_context = asoc->default_context; info.sinfo_timetolive = asoc->default_timetolive; } else { info.sinfo_stream = sp->default_stream; info.sinfo_flags = sp->default_flags; info.sinfo_ppid = sp->default_ppid; info.sinfo_context = sp->default_context; info.sinfo_timetolive = sp->default_timetolive; } if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &info, len)) return -EFAULT; return 0; } /* RFC6458, Section 8.1.31. Set/get Default Send Parameters * (SCTP_DEFAULT_SNDINFO) */ static int sctp_getsockopt_default_sndinfo(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; struct sctp_sndinfo info; if (len < sizeof(info)) return -EINVAL; len = sizeof(info); if (copy_from_user(&info, optval, len)) return -EFAULT; asoc = sctp_id2assoc(sk, info.snd_assoc_id); if (!asoc && info.snd_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) { info.snd_sid = asoc->default_stream; info.snd_flags = asoc->default_flags; info.snd_ppid = asoc->default_ppid; info.snd_context = asoc->default_context; } else { info.snd_sid = sp->default_stream; info.snd_flags = sp->default_flags; info.snd_ppid = sp->default_ppid; info.snd_context = sp->default_context; } if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &info, len)) return -EFAULT; return 0; } /* * * 7.1.5 SCTP_NODELAY * * Turn on/off any Nagle-like algorithm. This means that packets are * generally sent as soon as possible and no unnecessary delays are * introduced, at the cost of more packets in the network. Expects an * integer boolean flag. */ static int sctp_getsockopt_nodelay(struct sock *sk, int len, char __user *optval, int __user *optlen) { int val; if (len < sizeof(int)) return -EINVAL; len = sizeof(int); val = (sctp_sk(sk)->nodelay == 1); if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } /* * * 7.1.1 SCTP_RTOINFO * * The protocol parameters used to initialize and bound retransmission * timeout (RTO) are tunable. sctp_rtoinfo structure is used to access * and modify these parameters. * All parameters are time values, in milliseconds. A value of 0, when * modifying the parameters, indicates that the current value should not * be changed. * */ static int sctp_getsockopt_rtoinfo(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_rtoinfo rtoinfo; struct sctp_association *asoc; if (len < sizeof (struct sctp_rtoinfo)) return -EINVAL; len = sizeof(struct sctp_rtoinfo); if (copy_from_user(&rtoinfo, optval, len)) return -EFAULT; asoc = sctp_id2assoc(sk, rtoinfo.srto_assoc_id); if (!asoc && rtoinfo.srto_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; /* Values corresponding to the specific association. */ if (asoc) { rtoinfo.srto_initial = jiffies_to_msecs(asoc->rto_initial); rtoinfo.srto_max = jiffies_to_msecs(asoc->rto_max); rtoinfo.srto_min = jiffies_to_msecs(asoc->rto_min); } else { /* Values corresponding to the endpoint. */ struct sctp_sock *sp = sctp_sk(sk); rtoinfo.srto_initial = sp->rtoinfo.srto_initial; rtoinfo.srto_max = sp->rtoinfo.srto_max; rtoinfo.srto_min = sp->rtoinfo.srto_min; } if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &rtoinfo, len)) return -EFAULT; return 0; } /* * * 7.1.2 SCTP_ASSOCINFO * * This option is used to tune the maximum retransmission attempts * of the association. * Returns an error if the new association retransmission value is * greater than the sum of the retransmission value of the peer. * See [SCTP] for more information. * */ static int sctp_getsockopt_associnfo(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assocparams assocparams; struct sctp_association *asoc; struct list_head *pos; int cnt = 0; if (len < sizeof (struct sctp_assocparams)) return -EINVAL; len = sizeof(struct sctp_assocparams); if (copy_from_user(&assocparams, optval, len)) return -EFAULT; asoc = sctp_id2assoc(sk, assocparams.sasoc_assoc_id); if (!asoc && assocparams.sasoc_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; /* Values correspoinding to the specific association */ if (asoc) { assocparams.sasoc_asocmaxrxt = asoc->max_retrans; assocparams.sasoc_peer_rwnd = asoc->peer.rwnd; assocparams.sasoc_local_rwnd = asoc->a_rwnd; assocparams.sasoc_cookie_life = ktime_to_ms(asoc->cookie_life); list_for_each(pos, &asoc->peer.transport_addr_list) { cnt++; } assocparams.sasoc_number_peer_destinations = cnt; } else { /* Values corresponding to the endpoint */ struct sctp_sock *sp = sctp_sk(sk); assocparams.sasoc_asocmaxrxt = sp->assocparams.sasoc_asocmaxrxt; assocparams.sasoc_peer_rwnd = sp->assocparams.sasoc_peer_rwnd; assocparams.sasoc_local_rwnd = sp->assocparams.sasoc_local_rwnd; assocparams.sasoc_cookie_life = sp->assocparams.sasoc_cookie_life; assocparams.sasoc_number_peer_destinations = sp->assocparams. sasoc_number_peer_destinations; } if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &assocparams, len)) return -EFAULT; return 0; } /* * 7.1.16 Set/clear IPv4 mapped addresses (SCTP_I_WANT_MAPPED_V4_ADDR) * * This socket option is a boolean flag which turns on or off mapped V4 * addresses. If this option is turned on and the socket is type * PF_INET6, then IPv4 addresses will be mapped to V6 representation. * If this option is turned off, then no mapping will be done of V4 * addresses and a user will receive both PF_INET6 and PF_INET type * addresses on the socket. */ static int sctp_getsockopt_mappedv4(struct sock *sk, int len, char __user *optval, int __user *optlen) { int val; struct sctp_sock *sp = sctp_sk(sk); if (len < sizeof(int)) return -EINVAL; len = sizeof(int); val = sp->v4mapped; if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } /* * 7.1.29. Set or Get the default context (SCTP_CONTEXT) * (chapter and verse is quoted at sctp_setsockopt_context()) */ static int sctp_getsockopt_context(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assoc_value params; struct sctp_association *asoc; if (len < sizeof(struct sctp_assoc_value)) return -EINVAL; len = sizeof(struct sctp_assoc_value); if (copy_from_user(¶ms, optval, len)) return -EFAULT; asoc = sctp_id2assoc(sk, params.assoc_id); if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; params.assoc_value = asoc ? asoc->default_rcv_context : sctp_sk(sk)->default_rcv_context; if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, ¶ms, len)) return -EFAULT; return 0; } /* * 8.1.16. Get or Set the Maximum Fragmentation Size (SCTP_MAXSEG) * This option will get or set the maximum size to put in any outgoing * SCTP DATA chunk. If a message is larger than this size it will be * fragmented by SCTP into the specified size. Note that the underlying * SCTP implementation may fragment into smaller sized chunks when the * PMTU of the underlying association is smaller than the value set by * the user. The default value for this option is '0' which indicates * the user is NOT limiting fragmentation and only the PMTU will effect * SCTP's choice of DATA chunk size. Note also that values set larger * than the maximum size of an IP datagram will effectively let SCTP * control fragmentation (i.e. the same as setting this option to 0). * * The following structure is used to access and modify this parameter: * * struct sctp_assoc_value { * sctp_assoc_t assoc_id; * uint32_t assoc_value; * }; * * assoc_id: This parameter is ignored for one-to-one style sockets. * For one-to-many style sockets this parameter indicates which * association the user is performing an action upon. Note that if * this field's value is zero then the endpoints default value is * changed (effecting future associations only). * assoc_value: This parameter specifies the maximum size in bytes. */ static int sctp_getsockopt_maxseg(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assoc_value params; struct sctp_association *asoc; if (len == sizeof(int)) { pr_warn_ratelimited(DEPRECATED "%s (pid %d) " "Use of int in maxseg socket option.\n" "Use struct sctp_assoc_value instead\n", current->comm, task_pid_nr(current)); params.assoc_id = SCTP_FUTURE_ASSOC; } else if (len >= sizeof(struct sctp_assoc_value)) { len = sizeof(struct sctp_assoc_value); if (copy_from_user(¶ms, optval, len)) return -EFAULT; } else return -EINVAL; asoc = sctp_id2assoc(sk, params.assoc_id); if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) params.assoc_value = asoc->frag_point; else params.assoc_value = sctp_sk(sk)->user_frag; if (put_user(len, optlen)) return -EFAULT; if (len == sizeof(int)) { if (copy_to_user(optval, ¶ms.assoc_value, len)) return -EFAULT; } else { if (copy_to_user(optval, ¶ms, len)) return -EFAULT; } return 0; } /* * 7.1.24. Get or set fragmented interleave (SCTP_FRAGMENT_INTERLEAVE) * (chapter and verse is quoted at sctp_setsockopt_fragment_interleave()) */ static int sctp_getsockopt_fragment_interleave(struct sock *sk, int len, char __user *optval, int __user *optlen) { int val; if (len < sizeof(int)) return -EINVAL; len = sizeof(int); val = sctp_sk(sk)->frag_interleave; if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } /* * 7.1.25. Set or Get the sctp partial delivery point * (chapter and verse is quoted at sctp_setsockopt_partial_delivery_point()) */ static int sctp_getsockopt_partial_delivery_point(struct sock *sk, int len, char __user *optval, int __user *optlen) { u32 val; if (len < sizeof(u32)) return -EINVAL; len = sizeof(u32); val = sctp_sk(sk)->pd_point; if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } /* * 7.1.28. Set or Get the maximum burst (SCTP_MAX_BURST) * (chapter and verse is quoted at sctp_setsockopt_maxburst()) */ static int sctp_getsockopt_maxburst(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assoc_value params; struct sctp_association *asoc; if (len == sizeof(int)) { pr_warn_ratelimited(DEPRECATED "%s (pid %d) " "Use of int in max_burst socket option.\n" "Use struct sctp_assoc_value instead\n", current->comm, task_pid_nr(current)); params.assoc_id = SCTP_FUTURE_ASSOC; } else if (len >= sizeof(struct sctp_assoc_value)) { len = sizeof(struct sctp_assoc_value); if (copy_from_user(¶ms, optval, len)) return -EFAULT; } else return -EINVAL; asoc = sctp_id2assoc(sk, params.assoc_id); if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; params.assoc_value = asoc ? asoc->max_burst : sctp_sk(sk)->max_burst; if (len == sizeof(int)) { if (copy_to_user(optval, ¶ms.assoc_value, len)) return -EFAULT; } else { if (copy_to_user(optval, ¶ms, len)) return -EFAULT; } return 0; } static int sctp_getsockopt_hmac_ident(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_hmacalgo __user *p = (void __user *)optval; struct sctp_hmac_algo_param *hmacs; __u16 data_len = 0; u32 num_idents; int i; if (!ep->auth_enable) return -EACCES; hmacs = ep->auth_hmacs_list; data_len = ntohs(hmacs->param_hdr.length) - sizeof(struct sctp_paramhdr); if (len < sizeof(struct sctp_hmacalgo) + data_len) return -EINVAL; len = sizeof(struct sctp_hmacalgo) + data_len; num_idents = data_len / sizeof(u16); if (put_user(len, optlen)) return -EFAULT; if (put_user(num_idents, &p->shmac_num_idents)) return -EFAULT; for (i = 0; i < num_idents; i++) { __u16 hmacid = ntohs(hmacs->hmac_ids[i]); if (copy_to_user(&p->shmac_idents[i], &hmacid, sizeof(__u16))) return -EFAULT; } return 0; } static int sctp_getsockopt_active_key(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_authkeyid val; struct sctp_association *asoc; if (len < sizeof(struct sctp_authkeyid)) return -EINVAL; len = sizeof(struct sctp_authkeyid); if (copy_from_user(&val, optval, len)) return -EFAULT; asoc = sctp_id2assoc(sk, val.scact_assoc_id); if (!asoc && val.scact_assoc_id && sctp_style(sk, UDP)) return -EINVAL; if (asoc) { if (!asoc->peer.auth_capable) return -EACCES; val.scact_keynumber = asoc->active_key_id; } else { if (!ep->auth_enable) return -EACCES; val.scact_keynumber = ep->active_key_id; } if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } static int sctp_getsockopt_peer_auth_chunks(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_authchunks __user *p = (void __user *)optval; struct sctp_authchunks val; struct sctp_association *asoc; struct sctp_chunks_param *ch; u32 num_chunks = 0; char __user *to; if (len < sizeof(struct sctp_authchunks)) return -EINVAL; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; to = p->gauth_chunks; asoc = sctp_id2assoc(sk, val.gauth_assoc_id); if (!asoc) return -EINVAL; if (!asoc->peer.auth_capable) return -EACCES; ch = asoc->peer.peer_chunks; if (!ch) goto num; /* See if the user provided enough room for all the data */ num_chunks = ntohs(ch->param_hdr.length) - sizeof(struct sctp_paramhdr); if (len < num_chunks) return -EINVAL; if (copy_to_user(to, ch->chunks, num_chunks)) return -EFAULT; num: len = sizeof(struct sctp_authchunks) + num_chunks; if (put_user(len, optlen)) return -EFAULT; if (put_user(num_chunks, &p->gauth_number_of_chunks)) return -EFAULT; return 0; } static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_authchunks __user *p = (void __user *)optval; struct sctp_authchunks val; struct sctp_association *asoc; struct sctp_chunks_param *ch; u32 num_chunks = 0; char __user *to; if (len < sizeof(struct sctp_authchunks)) return -EINVAL; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; to = p->gauth_chunks; asoc = sctp_id2assoc(sk, val.gauth_assoc_id); if (!asoc && val.gauth_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) { if (!asoc->peer.auth_capable) return -EACCES; ch = (struct sctp_chunks_param *)asoc->c.auth_chunks; } else { if (!ep->auth_enable) return -EACCES; ch = ep->auth_chunk_list; } if (!ch) goto num; num_chunks = ntohs(ch->param_hdr.length) - sizeof(struct sctp_paramhdr); if (len < sizeof(struct sctp_authchunks) + num_chunks) return -EINVAL; if (copy_to_user(to, ch->chunks, num_chunks)) return -EFAULT; num: len = sizeof(struct sctp_authchunks) + num_chunks; if (put_user(len, optlen)) return -EFAULT; if (put_user(num_chunks, &p->gauth_number_of_chunks)) return -EFAULT; return 0; } /* * 8.2.5. Get the Current Number of Associations (SCTP_GET_ASSOC_NUMBER) * This option gets the current number of associations that are attached * to a one-to-many style socket. The option value is an uint32_t. */ static int sctp_getsockopt_assoc_number(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; u32 val = 0; if (sctp_style(sk, TCP)) return -EOPNOTSUPP; if (len < sizeof(u32)) return -EINVAL; len = sizeof(u32); list_for_each_entry(asoc, &(sp->ep->asocs), asocs) { val++; } if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } /* * 8.1.23 SCTP_AUTO_ASCONF * See the corresponding setsockopt entry as description */ static int sctp_getsockopt_auto_asconf(struct sock *sk, int len, char __user *optval, int __user *optlen) { int val = 0; if (len < sizeof(int)) return -EINVAL; len = sizeof(int); if (sctp_sk(sk)->do_auto_asconf && sctp_is_ep_boundall(sk)) val = 1; if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } /* * 8.2.6. Get the Current Identifiers of Associations * (SCTP_GET_ASSOC_ID_LIST) * * This option gets the current list of SCTP association identifiers of * the SCTP associations handled by a one-to-many style socket. */ static int sctp_getsockopt_assoc_ids(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; struct sctp_assoc_ids *ids; size_t ids_size; u32 num = 0; if (sctp_style(sk, TCP)) return -EOPNOTSUPP; if (len < sizeof(struct sctp_assoc_ids)) return -EINVAL; list_for_each_entry(asoc, &(sp->ep->asocs), asocs) { num++; } ids_size = struct_size(ids, gaids_assoc_id, num); if (len < ids_size) return -EINVAL; len = ids_size; ids = kmalloc(len, GFP_USER | __GFP_NOWARN); if (unlikely(!ids)) return -ENOMEM; ids->gaids_number_of_ids = num; num = 0; list_for_each_entry(asoc, &(sp->ep->asocs), asocs) { ids->gaids_assoc_id[num++] = asoc->assoc_id; } if (put_user(len, optlen) || copy_to_user(optval, ids, len)) { kfree(ids); return -EFAULT; } kfree(ids); return 0; } /* * SCTP_PEER_ADDR_THLDS * * This option allows us to fetch the partially failed threshold for one or all * transports in an association. See Section 6.1 of: * http://www.ietf.org/id/draft-nishida-tsvwg-sctp-failover-05.txt */ static int sctp_getsockopt_paddr_thresholds(struct sock *sk, char __user *optval, int len, int __user *optlen, bool v2) { struct sctp_paddrthlds_v2 val; struct sctp_transport *trans; struct sctp_association *asoc; int min; min = v2 ? sizeof(val) : sizeof(struct sctp_paddrthlds); if (len < min) return -EINVAL; len = min; if (copy_from_user(&val, optval, len)) return -EFAULT; if (!sctp_is_any(sk, (const union sctp_addr *)&val.spt_address)) { trans = sctp_addr_id2transport(sk, &val.spt_address, val.spt_assoc_id); if (!trans) return -ENOENT; val.spt_pathmaxrxt = trans->pathmaxrxt; val.spt_pathpfthld = trans->pf_retrans; val.spt_pathcpthld = trans->ps_retrans; goto out; } asoc = sctp_id2assoc(sk, val.spt_assoc_id); if (!asoc && val.spt_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) { val.spt_pathpfthld = asoc->pf_retrans; val.spt_pathmaxrxt = asoc->pathmaxrxt; val.spt_pathcpthld = asoc->ps_retrans; } else { struct sctp_sock *sp = sctp_sk(sk); val.spt_pathpfthld = sp->pf_retrans; val.spt_pathmaxrxt = sp->pathmaxrxt; val.spt_pathcpthld = sp->ps_retrans; } out: if (put_user(len, optlen) || copy_to_user(optval, &val, len)) return -EFAULT; return 0; } /* * SCTP_GET_ASSOC_STATS * * This option retrieves local per endpoint statistics. It is modeled * after OpenSolaris' implementation */ static int sctp_getsockopt_assoc_stats(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assoc_stats sas; struct sctp_association *asoc = NULL; /* User must provide at least the assoc id */ if (len < sizeof(sctp_assoc_t)) return -EINVAL; /* Allow the struct to grow and fill in as much as possible */ len = min_t(size_t, len, sizeof(sas)); if (copy_from_user(&sas, optval, len)) return -EFAULT; asoc = sctp_id2assoc(sk, sas.sas_assoc_id); if (!asoc) return -EINVAL; sas.sas_rtxchunks = asoc->stats.rtxchunks; sas.sas_gapcnt = asoc->stats.gapcnt; sas.sas_outofseqtsns = asoc->stats.outofseqtsns; sas.sas_osacks = asoc->stats.osacks; sas.sas_isacks = asoc->stats.isacks; sas.sas_octrlchunks = asoc->stats.octrlchunks; sas.sas_ictrlchunks = asoc->stats.ictrlchunks; sas.sas_oodchunks = asoc->stats.oodchunks; sas.sas_iodchunks = asoc->stats.iodchunks; sas.sas_ouodchunks = asoc->stats.ouodchunks; sas.sas_iuodchunks = asoc->stats.iuodchunks; sas.sas_idupchunks = asoc->stats.idupchunks; sas.sas_opackets = asoc->stats.opackets; sas.sas_ipackets = asoc->stats.ipackets; /* New high max rto observed, will return 0 if not a single * RTO update took place. obs_rto_ipaddr will be bogus * in such a case */ sas.sas_maxrto = asoc->stats.max_obs_rto; memcpy(&sas.sas_obs_rto_ipaddr, &asoc->stats.obs_rto_ipaddr, sizeof(struct sockaddr_storage)); /* Mark beginning of a new observation period */ asoc->stats.max_obs_rto = asoc->rto_min; if (put_user(len, optlen)) return -EFAULT; pr_debug("%s: len:%d, assoc_id:%d\n", __func__, len, sas.sas_assoc_id); if (copy_to_user(optval, &sas, len)) return -EFAULT; return 0; } static int sctp_getsockopt_recvrcvinfo(struct sock *sk, int len, char __user *optval, int __user *optlen) { int val = 0; if (len < sizeof(int)) return -EINVAL; len = sizeof(int); if (sctp_sk(sk)->recvrcvinfo) val = 1; if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } static int sctp_getsockopt_recvnxtinfo(struct sock *sk, int len, char __user *optval, int __user *optlen) { int val = 0; if (len < sizeof(int)) return -EINVAL; len = sizeof(int); if (sctp_sk(sk)->recvnxtinfo) val = 1; if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } static int sctp_getsockopt_pr_supported(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assoc_value params; struct sctp_association *asoc; int retval = -EFAULT; if (len < sizeof(params)) { retval = -EINVAL; goto out; } len = sizeof(params); if (copy_from_user(¶ms, optval, len)) goto out; asoc = sctp_id2assoc(sk, params.assoc_id); if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } params.assoc_value = asoc ? asoc->peer.prsctp_capable : sctp_sk(sk)->ep->prsctp_enable; if (put_user(len, optlen)) goto out; if (copy_to_user(optval, ¶ms, len)) goto out; retval = 0; out: return retval; } static int sctp_getsockopt_default_prinfo(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_default_prinfo info; struct sctp_association *asoc; int retval = -EFAULT; if (len < sizeof(info)) { retval = -EINVAL; goto out; } len = sizeof(info); if (copy_from_user(&info, optval, len)) goto out; asoc = sctp_id2assoc(sk, info.pr_assoc_id); if (!asoc && info.pr_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } if (asoc) { info.pr_policy = SCTP_PR_POLICY(asoc->default_flags); info.pr_value = asoc->default_timetolive; } else { struct sctp_sock *sp = sctp_sk(sk); info.pr_policy = SCTP_PR_POLICY(sp->default_flags); info.pr_value = sp->default_timetolive; } if (put_user(len, optlen)) goto out; if (copy_to_user(optval, &info, len)) goto out; retval = 0; out: return retval; } static int sctp_getsockopt_pr_assocstatus(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_prstatus params; struct sctp_association *asoc; int policy; int retval = -EINVAL; if (len < sizeof(params)) goto out; len = sizeof(params); if (copy_from_user(¶ms, optval, len)) { retval = -EFAULT; goto out; } policy = params.sprstat_policy; if (!policy || (policy & ~(SCTP_PR_SCTP_MASK | SCTP_PR_SCTP_ALL)) || ((policy & SCTP_PR_SCTP_ALL) && (policy & SCTP_PR_SCTP_MASK))) goto out; asoc = sctp_id2assoc(sk, params.sprstat_assoc_id); if (!asoc) goto out; if (policy == SCTP_PR_SCTP_ALL) { params.sprstat_abandoned_unsent = 0; params.sprstat_abandoned_sent = 0; for (policy = 0; policy <= SCTP_PR_INDEX(MAX); policy++) { params.sprstat_abandoned_unsent += asoc->abandoned_unsent[policy]; params.sprstat_abandoned_sent += asoc->abandoned_sent[policy]; } } else { params.sprstat_abandoned_unsent = asoc->abandoned_unsent[__SCTP_PR_INDEX(policy)]; params.sprstat_abandoned_sent = asoc->abandoned_sent[__SCTP_PR_INDEX(policy)]; } if (put_user(len, optlen)) { retval = -EFAULT; goto out; } if (copy_to_user(optval, ¶ms, len)) { retval = -EFAULT; goto out; } retval = 0; out: return retval; } static int sctp_getsockopt_pr_streamstatus(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_stream_out_ext *streamoute; struct sctp_association *asoc; struct sctp_prstatus params; int retval = -EINVAL; int policy; if (len < sizeof(params)) goto out; len = sizeof(params); if (copy_from_user(¶ms, optval, len)) { retval = -EFAULT; goto out; } policy = params.sprstat_policy; if (!policy || (policy & ~(SCTP_PR_SCTP_MASK | SCTP_PR_SCTP_ALL)) || ((policy & SCTP_PR_SCTP_ALL) && (policy & SCTP_PR_SCTP_MASK))) goto out; asoc = sctp_id2assoc(sk, params.sprstat_assoc_id); if (!asoc || params.sprstat_sid >= asoc->stream.outcnt) goto out; streamoute = SCTP_SO(&asoc->stream, params.sprstat_sid)->ext; if (!streamoute) { /* Not allocated yet, means all stats are 0 */ params.sprstat_abandoned_unsent = 0; params.sprstat_abandoned_sent = 0; retval = 0; goto out; } if (policy == SCTP_PR_SCTP_ALL) { params.sprstat_abandoned_unsent = 0; params.sprstat_abandoned_sent = 0; for (policy = 0; policy <= SCTP_PR_INDEX(MAX); policy++) { params.sprstat_abandoned_unsent += streamoute->abandoned_unsent[policy]; params.sprstat_abandoned_sent += streamoute->abandoned_sent[policy]; } } else { params.sprstat_abandoned_unsent = streamoute->abandoned_unsent[__SCTP_PR_INDEX(policy)]; params.sprstat_abandoned_sent = streamoute->abandoned_sent[__SCTP_PR_INDEX(policy)]; } if (put_user(len, optlen) || copy_to_user(optval, ¶ms, len)) { retval = -EFAULT; goto out; } retval = 0; out: return retval; } static int sctp_getsockopt_reconfig_supported(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assoc_value params; struct sctp_association *asoc; int retval = -EFAULT; if (len < sizeof(params)) { retval = -EINVAL; goto out; } len = sizeof(params); if (copy_from_user(¶ms, optval, len)) goto out; asoc = sctp_id2assoc(sk, params.assoc_id); if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } params.assoc_value = asoc ? asoc->peer.reconf_capable : sctp_sk(sk)->ep->reconf_enable; if (put_user(len, optlen)) goto out; if (copy_to_user(optval, ¶ms, len)) goto out; retval = 0; out: return retval; } static int sctp_getsockopt_enable_strreset(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assoc_value params; struct sctp_association *asoc; int retval = -EFAULT; if (len < sizeof(params)) { retval = -EINVAL; goto out; } len = sizeof(params); if (copy_from_user(¶ms, optval, len)) goto out; asoc = sctp_id2assoc(sk, params.assoc_id); if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } params.assoc_value = asoc ? asoc->strreset_enable : sctp_sk(sk)->ep->strreset_enable; if (put_user(len, optlen)) goto out; if (copy_to_user(optval, ¶ms, len)) goto out; retval = 0; out: return retval; } static int sctp_getsockopt_scheduler(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assoc_value params; struct sctp_association *asoc; int retval = -EFAULT; if (len < sizeof(params)) { retval = -EINVAL; goto out; } len = sizeof(params); if (copy_from_user(¶ms, optval, len)) goto out; asoc = sctp_id2assoc(sk, params.assoc_id); if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } params.assoc_value = asoc ? sctp_sched_get_sched(asoc) : sctp_sk(sk)->default_ss; if (put_user(len, optlen)) goto out; if (copy_to_user(optval, ¶ms, len)) goto out; retval = 0; out: return retval; } static int sctp_getsockopt_scheduler_value(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_stream_value params; struct sctp_association *asoc; int retval = -EFAULT; if (len < sizeof(params)) { retval = -EINVAL; goto out; } len = sizeof(params); if (copy_from_user(¶ms, optval, len)) goto out; asoc = sctp_id2assoc(sk, params.assoc_id); if (!asoc) { retval = -EINVAL; goto out; } retval = sctp_sched_get_value(asoc, params.stream_id, ¶ms.stream_value); if (retval) goto out; if (put_user(len, optlen)) { retval = -EFAULT; goto out; } if (copy_to_user(optval, ¶ms, len)) { retval = -EFAULT; goto out; } out: return retval; } static int sctp_getsockopt_interleaving_supported(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assoc_value params; struct sctp_association *asoc; int retval = -EFAULT; if (len < sizeof(params)) { retval = -EINVAL; goto out; } len = sizeof(params); if (copy_from_user(¶ms, optval, len)) goto out; asoc = sctp_id2assoc(sk, params.assoc_id); if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } params.assoc_value = asoc ? asoc->peer.intl_capable : sctp_sk(sk)->ep->intl_enable; if (put_user(len, optlen)) goto out; if (copy_to_user(optval, ¶ms, len)) goto out; retval = 0; out: return retval; } static int sctp_getsockopt_reuse_port(struct sock *sk, int len, char __user *optval, int __user *optlen) { int val; if (len < sizeof(int)) return -EINVAL; len = sizeof(int); val = sctp_sk(sk)->reuse; if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } static int sctp_getsockopt_event(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_association *asoc; struct sctp_event param; __u16 subscribe; if (len < sizeof(param)) return -EINVAL; len = sizeof(param); if (copy_from_user(¶m, optval, len)) return -EFAULT; if (param.se_type < SCTP_SN_TYPE_BASE || param.se_type > SCTP_SN_TYPE_MAX) return -EINVAL; asoc = sctp_id2assoc(sk, param.se_assoc_id); if (!asoc && param.se_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; subscribe = asoc ? asoc->subscribe : sctp_sk(sk)->subscribe; param.se_on = sctp_ulpevent_type_enabled(subscribe, param.se_type); if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, ¶m, len)) return -EFAULT; return 0; } static int sctp_getsockopt_asconf_supported(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assoc_value params; struct sctp_association *asoc; int retval = -EFAULT; if (len < sizeof(params)) { retval = -EINVAL; goto out; } len = sizeof(params); if (copy_from_user(¶ms, optval, len)) goto out; asoc = sctp_id2assoc(sk, params.assoc_id); if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } params.assoc_value = asoc ? asoc->peer.asconf_capable : sctp_sk(sk)->ep->asconf_enable; if (put_user(len, optlen)) goto out; if (copy_to_user(optval, ¶ms, len)) goto out; retval = 0; out: return retval; } static int sctp_getsockopt_auth_supported(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assoc_value params; struct sctp_association *asoc; int retval = -EFAULT; if (len < sizeof(params)) { retval = -EINVAL; goto out; } len = sizeof(params); if (copy_from_user(¶ms, optval, len)) goto out; asoc = sctp_id2assoc(sk, params.assoc_id); if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } params.assoc_value = asoc ? asoc->peer.auth_capable : sctp_sk(sk)->ep->auth_enable; if (put_user(len, optlen)) goto out; if (copy_to_user(optval, ¶ms, len)) goto out; retval = 0; out: return retval; } static int sctp_getsockopt_ecn_supported(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assoc_value params; struct sctp_association *asoc; int retval = -EFAULT; if (len < sizeof(params)) { retval = -EINVAL; goto out; } len = sizeof(params); if (copy_from_user(¶ms, optval, len)) goto out; asoc = sctp_id2assoc(sk, params.assoc_id); if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } params.assoc_value = asoc ? asoc->peer.ecn_capable : sctp_sk(sk)->ep->ecn_enable; if (put_user(len, optlen)) goto out; if (copy_to_user(optval, ¶ms, len)) goto out; retval = 0; out: return retval; } static int sctp_getsockopt_pf_expose(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assoc_value params; struct sctp_association *asoc; int retval = -EFAULT; if (len < sizeof(params)) { retval = -EINVAL; goto out; } len = sizeof(params); if (copy_from_user(¶ms, optval, len)) goto out; asoc = sctp_id2assoc(sk, params.assoc_id); if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } params.assoc_value = asoc ? asoc->pf_expose : sctp_sk(sk)->pf_expose; if (put_user(len, optlen)) goto out; if (copy_to_user(optval, ¶ms, len)) goto out; retval = 0; out: return retval; } static int sctp_getsockopt_encap_port(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_association *asoc; struct sctp_udpencaps encap; struct sctp_transport *t; __be16 encap_port; if (len < sizeof(encap)) return -EINVAL; len = sizeof(encap); if (copy_from_user(&encap, optval, len)) return -EFAULT; /* If an address other than INADDR_ANY is specified, and * no transport is found, then the request is invalid. */ if (!sctp_is_any(sk, (union sctp_addr *)&encap.sue_address)) { t = sctp_addr_id2transport(sk, &encap.sue_address, encap.sue_assoc_id); if (!t) { pr_debug("%s: failed no transport\n", __func__); return -EINVAL; } encap_port = t->encap_port; goto out; } /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the * socket is a one to many style socket, and an association * was not found, then the id was invalid. */ asoc = sctp_id2assoc(sk, encap.sue_assoc_id); if (!asoc && encap.sue_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) { pr_debug("%s: failed no association\n", __func__); return -EINVAL; } if (asoc) { encap_port = asoc->encap_port; goto out; } encap_port = sctp_sk(sk)->encap_port; out: encap.sue_port = (__force uint16_t)encap_port; if (copy_to_user(optval, &encap, len)) return -EFAULT; if (put_user(len, optlen)) return -EFAULT; return 0; } static int sctp_getsockopt_probe_interval(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_probeinterval params; struct sctp_association *asoc; struct sctp_transport *t; __u32 probe_interval; if (len < sizeof(params)) return -EINVAL; len = sizeof(params); if (copy_from_user(¶ms, optval, len)) return -EFAULT; /* If an address other than INADDR_ANY is specified, and * no transport is found, then the request is invalid. */ if (!sctp_is_any(sk, (union sctp_addr *)¶ms.spi_address)) { t = sctp_addr_id2transport(sk, ¶ms.spi_address, params.spi_assoc_id); if (!t) { pr_debug("%s: failed no transport\n", __func__); return -EINVAL; } probe_interval = jiffies_to_msecs(t->probe_interval); goto out; } /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the * socket is a one to many style socket, and an association * was not found, then the id was invalid. */ asoc = sctp_id2assoc(sk, params.spi_assoc_id); if (!asoc && params.spi_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) { pr_debug("%s: failed no association\n", __func__); return -EINVAL; } if (asoc) { probe_interval = jiffies_to_msecs(asoc->probe_interval); goto out; } probe_interval = sctp_sk(sk)->probe_interval; out: params.spi_interval = probe_interval; if (copy_to_user(optval, ¶ms, len)) return -EFAULT; if (put_user(len, optlen)) return -EFAULT; return 0; } static int sctp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { int retval = 0; int len; pr_debug("%s: sk:%p, optname:%d\n", __func__, sk, optname); /* I can hardly begin to describe how wrong this is. This is * so broken as to be worse than useless. The API draft * REALLY is NOT helpful here... I am not convinced that the * semantics of getsockopt() with a level OTHER THAN SOL_SCTP * are at all well-founded. */ if (level != SOL_SCTP) { struct sctp_af *af = sctp_sk(sk)->pf->af; retval = af->getsockopt(sk, level, optname, optval, optlen); return retval; } if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; lock_sock(sk); switch (optname) { case SCTP_STATUS: retval = sctp_getsockopt_sctp_status(sk, len, optval, optlen); break; case SCTP_DISABLE_FRAGMENTS: retval = sctp_getsockopt_disable_fragments(sk, len, optval, optlen); break; case SCTP_EVENTS: retval = sctp_getsockopt_events(sk, len, optval, optlen); break; case SCTP_AUTOCLOSE: retval = sctp_getsockopt_autoclose(sk, len, optval, optlen); break; case SCTP_SOCKOPT_PEELOFF: retval = sctp_getsockopt_peeloff(sk, len, optval, optlen); break; case SCTP_SOCKOPT_PEELOFF_FLAGS: retval = sctp_getsockopt_peeloff_flags(sk, len, optval, optlen); break; case SCTP_PEER_ADDR_PARAMS: retval = sctp_getsockopt_peer_addr_params(sk, len, optval, optlen); break; case SCTP_DELAYED_SACK: retval = sctp_getsockopt_delayed_ack(sk, len, optval, optlen); break; case SCTP_INITMSG: retval = sctp_getsockopt_initmsg(sk, len, optval, optlen); break; case SCTP_GET_PEER_ADDRS: retval = sctp_getsockopt_peer_addrs(sk, len, optval, optlen); break; case SCTP_GET_LOCAL_ADDRS: retval = sctp_getsockopt_local_addrs(sk, len, optval, optlen); break; case SCTP_SOCKOPT_CONNECTX3: retval = sctp_getsockopt_connectx3(sk, len, optval, optlen); break; case SCTP_DEFAULT_SEND_PARAM: retval = sctp_getsockopt_default_send_param(sk, len, optval, optlen); break; case SCTP_DEFAULT_SNDINFO: retval = sctp_getsockopt_default_sndinfo(sk, len, optval, optlen); break; case SCTP_PRIMARY_ADDR: retval = sctp_getsockopt_primary_addr(sk, len, optval, optlen); break; case SCTP_NODELAY: retval = sctp_getsockopt_nodelay(sk, len, optval, optlen); break; case SCTP_RTOINFO: retval = sctp_getsockopt_rtoinfo(sk, len, optval, optlen); break; case SCTP_ASSOCINFO: retval = sctp_getsockopt_associnfo(sk, len, optval, optlen); break; case SCTP_I_WANT_MAPPED_V4_ADDR: retval = sctp_getsockopt_mappedv4(sk, len, optval, optlen); break; case SCTP_MAXSEG: retval = sctp_getsockopt_maxseg(sk, len, optval, optlen); break; case SCTP_GET_PEER_ADDR_INFO: retval = sctp_getsockopt_peer_addr_info(sk, len, optval, optlen); break; case SCTP_ADAPTATION_LAYER: retval = sctp_getsockopt_adaptation_layer(sk, len, optval, optlen); break; case SCTP_CONTEXT: retval = sctp_getsockopt_context(sk, len, optval, optlen); break; case SCTP_FRAGMENT_INTERLEAVE: retval = sctp_getsockopt_fragment_interleave(sk, len, optval, optlen); break; case SCTP_PARTIAL_DELIVERY_POINT: retval = sctp_getsockopt_partial_delivery_point(sk, len, optval, optlen); break; case SCTP_MAX_BURST: retval = sctp_getsockopt_maxburst(sk, len, optval, optlen); break; case SCTP_AUTH_KEY: case SCTP_AUTH_CHUNK: case SCTP_AUTH_DELETE_KEY: case SCTP_AUTH_DEACTIVATE_KEY: retval = -EOPNOTSUPP; break; case SCTP_HMAC_IDENT: retval = sctp_getsockopt_hmac_ident(sk, len, optval, optlen); break; case SCTP_AUTH_ACTIVE_KEY: retval = sctp_getsockopt_active_key(sk, len, optval, optlen); break; case SCTP_PEER_AUTH_CHUNKS: retval = sctp_getsockopt_peer_auth_chunks(sk, len, optval, optlen); break; case SCTP_LOCAL_AUTH_CHUNKS: retval = sctp_getsockopt_local_auth_chunks(sk, len, optval, optlen); break; case SCTP_GET_ASSOC_NUMBER: retval = sctp_getsockopt_assoc_number(sk, len, optval, optlen); break; case SCTP_GET_ASSOC_ID_LIST: retval = sctp_getsockopt_assoc_ids(sk, len, optval, optlen); break; case SCTP_AUTO_ASCONF: retval = sctp_getsockopt_auto_asconf(sk, len, optval, optlen); break; case SCTP_PEER_ADDR_THLDS: retval = sctp_getsockopt_paddr_thresholds(sk, optval, len, optlen, false); break; case SCTP_PEER_ADDR_THLDS_V2: retval = sctp_getsockopt_paddr_thresholds(sk, optval, len, optlen, true); break; case SCTP_GET_ASSOC_STATS: retval = sctp_getsockopt_assoc_stats(sk, len, optval, optlen); break; case SCTP_RECVRCVINFO: retval = sctp_getsockopt_recvrcvinfo(sk, len, optval, optlen); break; case SCTP_RECVNXTINFO: retval = sctp_getsockopt_recvnxtinfo(sk, len, optval, optlen); break; case SCTP_PR_SUPPORTED: retval = sctp_getsockopt_pr_supported(sk, len, optval, optlen); break; case SCTP_DEFAULT_PRINFO: retval = sctp_getsockopt_default_prinfo(sk, len, optval, optlen); break; case SCTP_PR_ASSOC_STATUS: retval = sctp_getsockopt_pr_assocstatus(sk, len, optval, optlen); break; case SCTP_PR_STREAM_STATUS: retval = sctp_getsockopt_pr_streamstatus(sk, len, optval, optlen); break; case SCTP_RECONFIG_SUPPORTED: retval = sctp_getsockopt_reconfig_supported(sk, len, optval, optlen); break; case SCTP_ENABLE_STREAM_RESET: retval = sctp_getsockopt_enable_strreset(sk, len, optval, optlen); break; case SCTP_STREAM_SCHEDULER: retval = sctp_getsockopt_scheduler(sk, len, optval, optlen); break; case SCTP_STREAM_SCHEDULER_VALUE: retval = sctp_getsockopt_scheduler_value(sk, len, optval, optlen); break; case SCTP_INTERLEAVING_SUPPORTED: retval = sctp_getsockopt_interleaving_supported(sk, len, optval, optlen); break; case SCTP_REUSE_PORT: retval = sctp_getsockopt_reuse_port(sk, len, optval, optlen); break; case SCTP_EVENT: retval = sctp_getsockopt_event(sk, len, optval, optlen); break; case SCTP_ASCONF_SUPPORTED: retval = sctp_getsockopt_asconf_supported(sk, len, optval, optlen); break; case SCTP_AUTH_SUPPORTED: retval = sctp_getsockopt_auth_supported(sk, len, optval, optlen); break; case SCTP_ECN_SUPPORTED: retval = sctp_getsockopt_ecn_supported(sk, len, optval, optlen); break; case SCTP_EXPOSE_POTENTIALLY_FAILED_STATE: retval = sctp_getsockopt_pf_expose(sk, len, optval, optlen); break; case SCTP_REMOTE_UDP_ENCAPS_PORT: retval = sctp_getsockopt_encap_port(sk, len, optval, optlen); break; case SCTP_PLPMTUD_PROBE_INTERVAL: retval = sctp_getsockopt_probe_interval(sk, len, optval, optlen); break; default: retval = -ENOPROTOOPT; break; } release_sock(sk); return retval; } static bool sctp_bpf_bypass_getsockopt(int level, int optname) { if (level == SOL_SCTP) { switch (optname) { case SCTP_SOCKOPT_PEELOFF: case SCTP_SOCKOPT_PEELOFF_FLAGS: case SCTP_SOCKOPT_CONNECTX3: return true; default: return false; } } return false; } static int sctp_hash(struct sock *sk) { /* STUB */ return 0; } static void sctp_unhash(struct sock *sk) { /* STUB */ } /* Check if port is acceptable. Possibly find first available port. * * The port hash table (contained in the 'global' SCTP protocol storage * returned by struct sctp_protocol *sctp_get_protocol()). The hash * table is an array of 4096 lists (sctp_bind_hashbucket). Each * list (the list number is the port number hashed out, so as you * would expect from a hash function, all the ports in a given list have * such a number that hashes out to the same list number; you were * expecting that, right?); so each list has a set of ports, with a * link to the socket (struct sock) that uses it, the port number and * a fastreuse flag (FIXME: NPI ipg). */ static struct sctp_bind_bucket *sctp_bucket_create( struct sctp_bind_hashbucket *head, struct net *, unsigned short snum); static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr) { struct sctp_sock *sp = sctp_sk(sk); bool reuse = (sk->sk_reuse || sp->reuse); struct sctp_bind_hashbucket *head; /* hash list */ struct net *net = sock_net(sk); kuid_t uid = sock_i_uid(sk); struct sctp_bind_bucket *pp; unsigned short snum; int ret; snum = ntohs(addr->v4.sin_port); pr_debug("%s: begins, snum:%d\n", __func__, snum); if (snum == 0) { /* Search for an available port. */ int low, high, remaining, index; unsigned int rover; inet_sk_get_local_port_range(sk, &low, &high); remaining = (high - low) + 1; rover = get_random_u32_below(remaining) + low; do { rover++; if ((rover < low) || (rover > high)) rover = low; if (inet_is_local_reserved_port(net, rover)) continue; index = sctp_phashfn(net, rover); head = &sctp_port_hashtable[index]; spin_lock_bh(&head->lock); sctp_for_each_hentry(pp, &head->chain) if ((pp->port == rover) && net_eq(net, pp->net)) goto next; break; next: spin_unlock_bh(&head->lock); cond_resched(); } while (--remaining > 0); /* Exhausted local port range during search? */ ret = 1; if (remaining <= 0) return ret; /* OK, here is the one we will use. HEAD (the port * hash table list entry) is non-NULL and we hold it's * mutex. */ snum = rover; } else { /* We are given an specific port number; we verify * that it is not being used. If it is used, we will * exahust the search in the hash list corresponding * to the port number (snum) - we detect that with the * port iterator, pp being NULL. */ head = &sctp_port_hashtable[sctp_phashfn(net, snum)]; spin_lock_bh(&head->lock); sctp_for_each_hentry(pp, &head->chain) { if ((pp->port == snum) && net_eq(pp->net, net)) goto pp_found; } } pp = NULL; goto pp_not_found; pp_found: if (!hlist_empty(&pp->owner)) { /* We had a port hash table hit - there is an * available port (pp != NULL) and it is being * used by other socket (pp->owner not empty); that other * socket is going to be sk2. */ struct sock *sk2; pr_debug("%s: found a possible match\n", __func__); if ((pp->fastreuse && reuse && sk->sk_state != SCTP_SS_LISTENING) || (pp->fastreuseport && sk->sk_reuseport && uid_eq(pp->fastuid, uid))) goto success; /* Run through the list of sockets bound to the port * (pp->port) [via the pointers bind_next and * bind_pprev in the struct sock *sk2 (pp->sk)]. On each one, * we get the endpoint they describe and run through * the endpoint's list of IP (v4 or v6) addresses, * comparing each of the addresses with the address of * the socket sk. If we find a match, then that means * that this port/socket (sk) combination are already * in an endpoint. */ sk_for_each_bound(sk2, &pp->owner) { int bound_dev_if2 = READ_ONCE(sk2->sk_bound_dev_if); struct sctp_sock *sp2 = sctp_sk(sk2); struct sctp_endpoint *ep2 = sp2->ep; if (sk == sk2 || (reuse && (sk2->sk_reuse || sp2->reuse) && sk2->sk_state != SCTP_SS_LISTENING) || (sk->sk_reuseport && sk2->sk_reuseport && uid_eq(uid, sock_i_uid(sk2)))) continue; if ((!sk->sk_bound_dev_if || !bound_dev_if2 || sk->sk_bound_dev_if == bound_dev_if2) && sctp_bind_addr_conflict(&ep2->base.bind_addr, addr, sp2, sp)) { ret = 1; goto fail_unlock; } } pr_debug("%s: found a match\n", __func__); } pp_not_found: /* If there was a hash table miss, create a new port. */ ret = 1; if (!pp && !(pp = sctp_bucket_create(head, net, snum))) goto fail_unlock; /* In either case (hit or miss), make sure fastreuse is 1 only * if sk->sk_reuse is too (that is, if the caller requested * SO_REUSEADDR on this socket -sk-). */ if (hlist_empty(&pp->owner)) { if (reuse && sk->sk_state != SCTP_SS_LISTENING) pp->fastreuse = 1; else pp->fastreuse = 0; if (sk->sk_reuseport) { pp->fastreuseport = 1; pp->fastuid = uid; } else { pp->fastreuseport = 0; } } else { if (pp->fastreuse && (!reuse || sk->sk_state == SCTP_SS_LISTENING)) pp->fastreuse = 0; if (pp->fastreuseport && (!sk->sk_reuseport || !uid_eq(pp->fastuid, uid))) pp->fastreuseport = 0; } /* We are set, so fill up all the data in the hash table * entry, tie the socket list information with the rest of the * sockets FIXME: Blurry, NPI (ipg). */ success: if (!sp->bind_hash) { inet_sk(sk)->inet_num = snum; sk_add_bind_node(sk, &pp->owner); sp->bind_hash = pp; } ret = 0; fail_unlock: spin_unlock_bh(&head->lock); return ret; } /* Assign a 'snum' port to the socket. If snum == 0, an ephemeral * port is requested. */ static int sctp_get_port(struct sock *sk, unsigned short snum) { union sctp_addr addr; struct sctp_af *af = sctp_sk(sk)->pf->af; /* Set up a dummy address struct from the sk. */ af->from_sk(&addr, sk); addr.v4.sin_port = htons(snum); /* Note: sk->sk_num gets filled in if ephemeral port request. */ return sctp_get_port_local(sk, &addr); } /* * Move a socket to LISTENING state. */ static int sctp_listen_start(struct sock *sk, int backlog) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_endpoint *ep = sp->ep; struct crypto_shash *tfm = NULL; char alg[32]; int err; /* Allocate HMAC for generating cookie. */ if (!sp->hmac && sp->sctp_hmac_alg) { sprintf(alg, "hmac(%s)", sp->sctp_hmac_alg); tfm = crypto_alloc_shash(alg, 0, 0); if (IS_ERR(tfm)) { net_info_ratelimited("failed to load transform for %s: %ld\n", sp->sctp_hmac_alg, PTR_ERR(tfm)); return -ENOSYS; } sctp_sk(sk)->hmac = tfm; } /* * If a bind() or sctp_bindx() is not called prior to a listen() * call that allows new associations to be accepted, the system * picks an ephemeral port and will choose an address set equivalent * to binding with a wildcard address. * * This is not currently spelled out in the SCTP sockets * extensions draft, but follows the practice as seen in TCP * sockets. * */ inet_sk_set_state(sk, SCTP_SS_LISTENING); if (!ep->base.bind_addr.port) { if (sctp_autobind(sk)) { err = -EAGAIN; goto err; } } else { if (sctp_get_port(sk, inet_sk(sk)->inet_num)) { err = -EADDRINUSE; goto err; } } WRITE_ONCE(sk->sk_max_ack_backlog, backlog); err = sctp_hash_endpoint(ep); if (err) goto err; return 0; err: inet_sk_set_state(sk, SCTP_SS_CLOSED); return err; } /* * 4.1.3 / 5.1.3 listen() * * By default, new associations are not accepted for UDP style sockets. * An application uses listen() to mark a socket as being able to * accept new associations. * * On TCP style sockets, applications use listen() to ready the SCTP * endpoint for accepting inbound associations. * * On both types of endpoints a backlog of '0' disables listening. * * Move a socket to LISTENING state. */ int sctp_inet_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; struct sctp_endpoint *ep = sctp_sk(sk)->ep; int err = -EINVAL; if (unlikely(backlog < 0)) return err; lock_sock(sk); /* Peeled-off sockets are not allowed to listen(). */ if (sctp_style(sk, UDP_HIGH_BANDWIDTH)) goto out; if (sock->state != SS_UNCONNECTED) goto out; if (!sctp_sstate(sk, LISTENING) && !sctp_sstate(sk, CLOSED)) goto out; /* If backlog is zero, disable listening. */ if (!backlog) { if (sctp_sstate(sk, CLOSED)) goto out; err = 0; sctp_unhash_endpoint(ep); sk->sk_state = SCTP_SS_CLOSED; if (sk->sk_reuse || sctp_sk(sk)->reuse) sctp_sk(sk)->bind_hash->fastreuse = 1; goto out; } /* If we are already listening, just update the backlog */ if (sctp_sstate(sk, LISTENING)) WRITE_ONCE(sk->sk_max_ack_backlog, backlog); else { err = sctp_listen_start(sk, backlog); if (err) goto out; } err = 0; out: release_sock(sk); return err; } /* * This function is done by modeling the current datagram_poll() and the * tcp_poll(). Note that, based on these implementations, we don't * lock the socket in this function, even though it seems that, * ideally, locking or some other mechanisms can be used to ensure * the integrity of the counters (sndbuf and wmem_alloc) used * in this place. We assume that we don't need locks either until proven * otherwise. * * Another thing to note is that we include the Async I/O support * here, again, by modeling the current TCP/UDP code. We don't have * a good way to test with it yet. */ __poll_t sctp_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; struct sctp_sock *sp = sctp_sk(sk); __poll_t mask; poll_wait(file, sk_sleep(sk), wait); sock_rps_record_flow(sk); /* A TCP-style listening socket becomes readable when the accept queue * is not empty. */ if (sctp_style(sk, TCP) && sctp_sstate(sk, LISTENING)) return (!list_empty(&sp->ep->asocs)) ? (EPOLLIN | EPOLLRDNORM) : 0; mask = 0; /* Is there any exceptional events? */ if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR | (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); if (sk->sk_shutdown & RCV_SHUTDOWN) mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; if (sk->sk_shutdown == SHUTDOWN_MASK) mask |= EPOLLHUP; /* Is it readable? Reconsider this code with TCP-style support. */ if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; /* The association is either gone or not ready. */ if (!sctp_style(sk, UDP) && sctp_sstate(sk, CLOSED)) return mask; /* Is it writable? */ if (sctp_writeable(sk)) { mask |= EPOLLOUT | EPOLLWRNORM; } else { sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); /* * Since the socket is not locked, the buffer * might be made available after the writeable check and * before the bit is set. This could cause a lost I/O * signal. tcp_poll() has a race breaker for this race * condition. Based on their implementation, we put * in the following code to cover it as well. */ if (sctp_writeable(sk)) mask |= EPOLLOUT | EPOLLWRNORM; } return mask; } /******************************************************************** * 2nd Level Abstractions ********************************************************************/ static struct sctp_bind_bucket *sctp_bucket_create( struct sctp_bind_hashbucket *head, struct net *net, unsigned short snum) { struct sctp_bind_bucket *pp; pp = kmem_cache_alloc(sctp_bucket_cachep, GFP_ATOMIC); if (pp) { SCTP_DBG_OBJCNT_INC(bind_bucket); pp->port = snum; pp->fastreuse = 0; INIT_HLIST_HEAD(&pp->owner); pp->net = net; hlist_add_head(&pp->node, &head->chain); } return pp; } /* Caller must hold hashbucket lock for this tb with local BH disabled */ static void sctp_bucket_destroy(struct sctp_bind_bucket *pp) { if (pp && hlist_empty(&pp->owner)) { __hlist_del(&pp->node); kmem_cache_free(sctp_bucket_cachep, pp); SCTP_DBG_OBJCNT_DEC(bind_bucket); } } /* Release this socket's reference to a local port. */ static inline void __sctp_put_port(struct sock *sk) { struct sctp_bind_hashbucket *head = &sctp_port_hashtable[sctp_phashfn(sock_net(sk), inet_sk(sk)->inet_num)]; struct sctp_bind_bucket *pp; spin_lock(&head->lock); pp = sctp_sk(sk)->bind_hash; __sk_del_bind_node(sk); sctp_sk(sk)->bind_hash = NULL; inet_sk(sk)->inet_num = 0; sctp_bucket_destroy(pp); spin_unlock(&head->lock); } void sctp_put_port(struct sock *sk) { local_bh_disable(); __sctp_put_port(sk); local_bh_enable(); } /* * The system picks an ephemeral port and choose an address set equivalent * to binding with a wildcard address. * One of those addresses will be the primary address for the association. * This automatically enables the multihoming capability of SCTP. */ static int sctp_autobind(struct sock *sk) { union sctp_addr autoaddr; struct sctp_af *af; __be16 port; /* Initialize a local sockaddr structure to INADDR_ANY. */ af = sctp_sk(sk)->pf->af; port = htons(inet_sk(sk)->inet_num); af->inaddr_any(&autoaddr, port); return sctp_do_bind(sk, &autoaddr, af->sockaddr_len); } /* Parse out IPPROTO_SCTP CMSG headers. Perform only minimal validation. * * From RFC 2292 * 4.2 The cmsghdr Structure * * * When ancillary data is sent or received, any number of ancillary data * objects can be specified by the msg_control and msg_controllen members of * the msghdr structure, because each object is preceded by * a cmsghdr structure defining the object's length (the cmsg_len member). * Historically Berkeley-derived implementations have passed only one object * at a time, but this API allows multiple objects to be * passed in a single call to sendmsg() or recvmsg(). The following example * shows two ancillary data objects in a control buffer. * * |<--------------------------- msg_controllen -------------------------->| * | | * * |<----- ancillary data object ----->|<----- ancillary data object ----->| * * |<---------- CMSG_SPACE() --------->|<---------- CMSG_SPACE() --------->| * | | | * * |<---------- cmsg_len ---------->| |<--------- cmsg_len ----------->| | * * |<--------- CMSG_LEN() --------->| |<-------- CMSG_LEN() ---------->| | * | | | | | * * +-----+-----+-----+--+-----------+--+-----+-----+-----+--+-----------+--+ * |cmsg_|cmsg_|cmsg_|XX| |XX|cmsg_|cmsg_|cmsg_|XX| |XX| * * |len |level|type |XX|cmsg_data[]|XX|len |level|type |XX|cmsg_data[]|XX| * * +-----+-----+-----+--+-----------+--+-----+-----+-----+--+-----------+--+ * ^ * | * * msg_control * points here */ static int sctp_msghdr_parse(const struct msghdr *msg, struct sctp_cmsgs *cmsgs) { struct msghdr *my_msg = (struct msghdr *)msg; struct cmsghdr *cmsg; for_each_cmsghdr(cmsg, my_msg) { if (!CMSG_OK(my_msg, cmsg)) return -EINVAL; /* Should we parse this header or ignore? */ if (cmsg->cmsg_level != IPPROTO_SCTP) continue; /* Strictly check lengths following example in SCM code. */ switch (cmsg->cmsg_type) { case SCTP_INIT: /* SCTP Socket API Extension * 5.3.1 SCTP Initiation Structure (SCTP_INIT) * * This cmsghdr structure provides information for * initializing new SCTP associations with sendmsg(). * The SCTP_INITMSG socket option uses this same data * structure. This structure is not used for * recvmsg(). * * cmsg_level cmsg_type cmsg_data[] * ------------ ------------ ---------------------- * IPPROTO_SCTP SCTP_INIT struct sctp_initmsg */ if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct sctp_initmsg))) return -EINVAL; cmsgs->init = CMSG_DATA(cmsg); break; case SCTP_SNDRCV: /* SCTP Socket API Extension * 5.3.2 SCTP Header Information Structure(SCTP_SNDRCV) * * This cmsghdr structure specifies SCTP options for * sendmsg() and describes SCTP header information * about a received message through recvmsg(). * * cmsg_level cmsg_type cmsg_data[] * ------------ ------------ ---------------------- * IPPROTO_SCTP SCTP_SNDRCV struct sctp_sndrcvinfo */ if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct sctp_sndrcvinfo))) return -EINVAL; cmsgs->srinfo = CMSG_DATA(cmsg); if (cmsgs->srinfo->sinfo_flags & ~(SCTP_UNORDERED | SCTP_ADDR_OVER | SCTP_SACK_IMMEDIATELY | SCTP_SENDALL | SCTP_PR_SCTP_MASK | SCTP_ABORT | SCTP_EOF)) return -EINVAL; break; case SCTP_SNDINFO: /* SCTP Socket API Extension * 5.3.4 SCTP Send Information Structure (SCTP_SNDINFO) * * This cmsghdr structure specifies SCTP options for * sendmsg(). This structure and SCTP_RCVINFO replaces * SCTP_SNDRCV which has been deprecated. * * cmsg_level cmsg_type cmsg_data[] * ------------ ------------ --------------------- * IPPROTO_SCTP SCTP_SNDINFO struct sctp_sndinfo */ if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct sctp_sndinfo))) return -EINVAL; cmsgs->sinfo = CMSG_DATA(cmsg); if (cmsgs->sinfo->snd_flags & ~(SCTP_UNORDERED | SCTP_ADDR_OVER | SCTP_SACK_IMMEDIATELY | SCTP_SENDALL | SCTP_PR_SCTP_MASK | SCTP_ABORT | SCTP_EOF)) return -EINVAL; break; case SCTP_PRINFO: /* SCTP Socket API Extension * 5.3.7 SCTP PR-SCTP Information Structure (SCTP_PRINFO) * * This cmsghdr structure specifies SCTP options for sendmsg(). * * cmsg_level cmsg_type cmsg_data[] * ------------ ------------ --------------------- * IPPROTO_SCTP SCTP_PRINFO struct sctp_prinfo */ if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct sctp_prinfo))) return -EINVAL; cmsgs->prinfo = CMSG_DATA(cmsg); if (cmsgs->prinfo->pr_policy & ~SCTP_PR_SCTP_MASK) return -EINVAL; if (cmsgs->prinfo->pr_policy == SCTP_PR_SCTP_NONE) cmsgs->prinfo->pr_value = 0; break; case SCTP_AUTHINFO: /* SCTP Socket API Extension * 5.3.8 SCTP AUTH Information Structure (SCTP_AUTHINFO) * * This cmsghdr structure specifies SCTP options for sendmsg(). * * cmsg_level cmsg_type cmsg_data[] * ------------ ------------ --------------------- * IPPROTO_SCTP SCTP_AUTHINFO struct sctp_authinfo */ if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct sctp_authinfo))) return -EINVAL; cmsgs->authinfo = CMSG_DATA(cmsg); break; case SCTP_DSTADDRV4: case SCTP_DSTADDRV6: /* SCTP Socket API Extension * 5.3.9/10 SCTP Destination IPv4/6 Address Structure (SCTP_DSTADDRV4/6) * * This cmsghdr structure specifies SCTP options for sendmsg(). * * cmsg_level cmsg_type cmsg_data[] * ------------ ------------ --------------------- * IPPROTO_SCTP SCTP_DSTADDRV4 struct in_addr * ------------ ------------ --------------------- * IPPROTO_SCTP SCTP_DSTADDRV6 struct in6_addr */ cmsgs->addrs_msg = my_msg; break; default: return -EINVAL; } } return 0; } /* * Wait for a packet.. * Note: This function is the same function as in core/datagram.c * with a few modifications to make lksctp work. */ static int sctp_wait_for_packet(struct sock *sk, int *err, long *timeo_p) { int error; DEFINE_WAIT(wait); prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); /* Socket errors? */ error = sock_error(sk); if (error) goto out; if (!skb_queue_empty(&sk->sk_receive_queue)) goto ready; /* Socket shut down? */ if (sk->sk_shutdown & RCV_SHUTDOWN) goto out; /* Sequenced packets can come disconnected. If so we report the * problem. */ error = -ENOTCONN; /* Is there a good reason to think that we may receive some data? */ if (list_empty(&sctp_sk(sk)->ep->asocs) && !sctp_sstate(sk, LISTENING)) goto out; /* Handle signals. */ if (signal_pending(current)) goto interrupted; /* Let another process have a go. Since we are going to sleep * anyway. Note: This may cause odd behaviors if the message * does not fit in the user's buffer, but this seems to be the * only way to honor MSG_DONTWAIT realistically. */ release_sock(sk); *timeo_p = schedule_timeout(*timeo_p); lock_sock(sk); ready: finish_wait(sk_sleep(sk), &wait); return 0; interrupted: error = sock_intr_errno(*timeo_p); out: finish_wait(sk_sleep(sk), &wait); *err = error; return error; } /* Receive a datagram. * Note: This is pretty much the same routine as in core/datagram.c * with a few changes to make lksctp work. */ struct sk_buff *sctp_skb_recv_datagram(struct sock *sk, int flags, int *err) { int error; struct sk_buff *skb; long timeo; timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); pr_debug("%s: timeo:%ld, max:%ld\n", __func__, timeo, MAX_SCHEDULE_TIMEOUT); do { /* Again only user level code calls this function, * so nothing interrupt level * will suddenly eat the receive_queue. * * Look at current nfs client by the way... * However, this function was correct in any case. 8) */ if (flags & MSG_PEEK) { skb = skb_peek(&sk->sk_receive_queue); if (skb) refcount_inc(&skb->users); } else { skb = __skb_dequeue(&sk->sk_receive_queue); } if (skb) return skb; /* Caller is allowed not to check sk->sk_err before calling. */ error = sock_error(sk); if (error) goto no_packet; if (sk->sk_shutdown & RCV_SHUTDOWN) break; /* User doesn't want to wait. */ error = -EAGAIN; if (!timeo) goto no_packet; } while (sctp_wait_for_packet(sk, err, &timeo) == 0); return NULL; no_packet: *err = error; return NULL; } /* If sndbuf has changed, wake up per association sndbuf waiters. */ static void __sctp_write_space(struct sctp_association *asoc) { struct sock *sk = asoc->base.sk; if (sctp_wspace(asoc) <= 0) return; if (waitqueue_active(&asoc->wait)) wake_up_interruptible(&asoc->wait); if (sctp_writeable(sk)) { struct socket_wq *wq; rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (wq) { if (waitqueue_active(&wq->wait)) wake_up_interruptible(&wq->wait); /* Note that we try to include the Async I/O support * here by modeling from the current TCP/UDP code. * We have not tested with it yet. */ if (!(sk->sk_shutdown & SEND_SHUTDOWN)) sock_wake_async(wq, SOCK_WAKE_SPACE, POLL_OUT); } rcu_read_unlock(); } } static void sctp_wake_up_waiters(struct sock *sk, struct sctp_association *asoc) { struct sctp_association *tmp = asoc; /* We do accounting for the sndbuf space per association, * so we only need to wake our own association. */ if (asoc->ep->sndbuf_policy) return __sctp_write_space(asoc); /* If association goes down and is just flushing its * outq, then just normally notify others. */ if (asoc->base.dead) return sctp_write_space(sk); /* Accounting for the sndbuf space is per socket, so we * need to wake up others, try to be fair and in case of * other associations, let them have a go first instead * of just doing a sctp_write_space() call. * * Note that we reach sctp_wake_up_waiters() only when * associations free up queued chunks, thus we are under * lock and the list of associations on a socket is * guaranteed not to change. */ for (tmp = list_next_entry(tmp, asocs); 1; tmp = list_next_entry(tmp, asocs)) { /* Manually skip the head element. */ if (&tmp->asocs == &((sctp_sk(sk))->ep->asocs)) continue; /* Wake up association. */ __sctp_write_space(tmp); /* We've reached the end. */ if (tmp == asoc) break; } } /* Do accounting for the sndbuf space. * Decrement the used sndbuf space of the corresponding association by the * data size which was just transmitted(freed). */ static void sctp_wfree(struct sk_buff *skb) { struct sctp_chunk *chunk = skb_shinfo(skb)->destructor_arg; struct sctp_association *asoc = chunk->asoc; struct sock *sk = asoc->base.sk; sk_mem_uncharge(sk, skb->truesize); sk_wmem_queued_add(sk, -(skb->truesize + sizeof(struct sctp_chunk))); asoc->sndbuf_used -= skb->truesize + sizeof(struct sctp_chunk); WARN_ON(refcount_sub_and_test(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc)); if (chunk->shkey) { struct sctp_shared_key *shkey = chunk->shkey; /* refcnt == 2 and !list_empty mean after this release, it's * not being used anywhere, and it's time to notify userland * that this shkey can be freed if it's been deactivated. */ if (shkey->deactivated && !list_empty(&shkey->key_list) && refcount_read(&shkey->refcnt) == 2) { struct sctp_ulpevent *ev; ev = sctp_ulpevent_make_authkey(asoc, shkey->key_id, SCTP_AUTH_FREE_KEY, GFP_KERNEL); if (ev) asoc->stream.si->enqueue_event(&asoc->ulpq, ev); } sctp_auth_shkey_release(chunk->shkey); } sock_wfree(skb); sctp_wake_up_waiters(sk, asoc); sctp_association_put(asoc); } /* Do accounting for the receive space on the socket. * Accounting for the association is done in ulpevent.c * We set this as a destructor for the cloned data skbs so that * accounting is done at the correct time. */ void sctp_sock_rfree(struct sk_buff *skb) { struct sock *sk = skb->sk; struct sctp_ulpevent *event = sctp_skb2event(skb); atomic_sub(event->rmem_len, &sk->sk_rmem_alloc); /* * Mimic the behavior of sock_rfree */ sk_mem_uncharge(sk, event->rmem_len); } /* Helper function to wait for space in the sndbuf. */ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, size_t msg_len) { struct sock *sk = asoc->base.sk; long current_timeo = *timeo_p; DEFINE_WAIT(wait); int err = 0; pr_debug("%s: asoc:%p, timeo:%ld, msg_len:%zu\n", __func__, asoc, *timeo_p, msg_len); /* Increment the association's refcnt. */ sctp_association_hold(asoc); /* Wait on the association specific sndbuf space. */ for (;;) { prepare_to_wait_exclusive(&asoc->wait, &wait, TASK_INTERRUPTIBLE); if (asoc->base.dead) goto do_dead; if (!*timeo_p) goto do_nonblock; if (sk->sk_err || asoc->state >= SCTP_STATE_SHUTDOWN_PENDING) goto do_error; if (signal_pending(current)) goto do_interrupted; if ((int)msg_len <= sctp_wspace(asoc) && sk_wmem_schedule(sk, msg_len)) break; /* Let another process have a go. Since we are going * to sleep anyway. */ release_sock(sk); current_timeo = schedule_timeout(current_timeo); lock_sock(sk); if (sk != asoc->base.sk) goto do_error; *timeo_p = current_timeo; } out: finish_wait(&asoc->wait, &wait); /* Release the association's refcnt. */ sctp_association_put(asoc); return err; do_dead: err = -ESRCH; goto out; do_error: err = -EPIPE; goto out; do_interrupted: err = sock_intr_errno(*timeo_p); goto out; do_nonblock: err = -EAGAIN; goto out; } void sctp_data_ready(struct sock *sk) { struct socket_wq *wq; trace_sk_data_ready(sk); rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | EPOLLRDNORM | EPOLLRDBAND); sk_wake_async_rcu(sk, SOCK_WAKE_WAITD, POLL_IN); rcu_read_unlock(); } /* If socket sndbuf has changed, wake up all per association waiters. */ void sctp_write_space(struct sock *sk) { struct sctp_association *asoc; /* Wake up the tasks in each wait queue. */ list_for_each_entry(asoc, &((sctp_sk(sk))->ep->asocs), asocs) { __sctp_write_space(asoc); } } /* Is there any sndbuf space available on the socket? * * Note that sk_wmem_alloc is the sum of the send buffers on all of the * associations on the same socket. For a UDP-style socket with * multiple associations, it is possible for it to be "unwriteable" * prematurely. I assume that this is acceptable because * a premature "unwriteable" is better than an accidental "writeable" which * would cause an unwanted block under certain circumstances. For the 1-1 * UDP-style sockets or TCP-style sockets, this code should work. * - Daisy */ static bool sctp_writeable(const struct sock *sk) { return READ_ONCE(sk->sk_sndbuf) > READ_ONCE(sk->sk_wmem_queued); } /* Wait for an association to go into ESTABLISHED state. If timeout is 0, * returns immediately with EINPROGRESS. */ static int sctp_wait_for_connect(struct sctp_association *asoc, long *timeo_p) { struct sock *sk = asoc->base.sk; int err = 0; long current_timeo = *timeo_p; DEFINE_WAIT(wait); pr_debug("%s: asoc:%p, timeo:%ld\n", __func__, asoc, *timeo_p); /* Increment the association's refcnt. */ sctp_association_hold(asoc); for (;;) { prepare_to_wait_exclusive(&asoc->wait, &wait, TASK_INTERRUPTIBLE); if (!*timeo_p) goto do_nonblock; if (sk->sk_shutdown & RCV_SHUTDOWN) break; if (sk->sk_err || asoc->state >= SCTP_STATE_SHUTDOWN_PENDING || asoc->base.dead) goto do_error; if (signal_pending(current)) goto do_interrupted; if (sctp_state(asoc, ESTABLISHED)) break; /* Let another process have a go. Since we are going * to sleep anyway. */ release_sock(sk); current_timeo = schedule_timeout(current_timeo); lock_sock(sk); *timeo_p = current_timeo; } out: finish_wait(&asoc->wait, &wait); /* Release the association's refcnt. */ sctp_association_put(asoc); return err; do_error: if (asoc->init_err_counter + 1 > asoc->max_init_attempts) err = -ETIMEDOUT; else err = -ECONNREFUSED; goto out; do_interrupted: err = sock_intr_errno(*timeo_p); goto out; do_nonblock: err = -EINPROGRESS; goto out; } static int sctp_wait_for_accept(struct sock *sk, long timeo) { struct sctp_endpoint *ep; int err = 0; DEFINE_WAIT(wait); ep = sctp_sk(sk)->ep; for (;;) { prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (list_empty(&ep->asocs)) { release_sock(sk); timeo = schedule_timeout(timeo); lock_sock(sk); } err = -EINVAL; if (!sctp_sstate(sk, LISTENING) || (sk->sk_shutdown & RCV_SHUTDOWN)) break; err = 0; if (!list_empty(&ep->asocs)) break; err = sock_intr_errno(timeo); if (signal_pending(current)) break; err = -EAGAIN; if (!timeo) break; } finish_wait(sk_sleep(sk), &wait); return err; } static void sctp_wait_for_close(struct sock *sk, long timeout) { DEFINE_WAIT(wait); do { prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (list_empty(&sctp_sk(sk)->ep->asocs)) break; release_sock(sk); timeout = schedule_timeout(timeout); lock_sock(sk); } while (!signal_pending(current) && timeout); finish_wait(sk_sleep(sk), &wait); } static void sctp_skb_set_owner_r_frag(struct sk_buff *skb, struct sock *sk) { struct sk_buff *frag; if (!skb->data_len) goto done; /* Don't forget the fragments. */ skb_walk_frags(skb, frag) sctp_skb_set_owner_r_frag(frag, sk); done: sctp_skb_set_owner_r(skb, sk); } void sctp_copy_sock(struct sock *newsk, struct sock *sk, struct sctp_association *asoc) { struct inet_sock *inet = inet_sk(sk); struct inet_sock *newinet; struct sctp_sock *sp = sctp_sk(sk); newsk->sk_type = sk->sk_type; newsk->sk_bound_dev_if = sk->sk_bound_dev_if; newsk->sk_flags = sk->sk_flags; newsk->sk_tsflags = sk->sk_tsflags; newsk->sk_no_check_tx = sk->sk_no_check_tx; newsk->sk_no_check_rx = sk->sk_no_check_rx; newsk->sk_reuse = sk->sk_reuse; sctp_sk(newsk)->reuse = sp->reuse; newsk->sk_shutdown = sk->sk_shutdown; newsk->sk_destruct = sk->sk_destruct; newsk->sk_family = sk->sk_family; newsk->sk_protocol = IPPROTO_SCTP; newsk->sk_backlog_rcv = sk->sk_prot->backlog_rcv; newsk->sk_sndbuf = sk->sk_sndbuf; newsk->sk_rcvbuf = sk->sk_rcvbuf; newsk->sk_lingertime = sk->sk_lingertime; newsk->sk_rcvtimeo = sk->sk_rcvtimeo; newsk->sk_sndtimeo = sk->sk_sndtimeo; newsk->sk_rxhash = sk->sk_rxhash; newinet = inet_sk(newsk); /* Initialize sk's sport, dport, rcv_saddr and daddr for * getsockname() and getpeername() */ newinet->inet_sport = inet->inet_sport; newinet->inet_saddr = inet->inet_saddr; newinet->inet_rcv_saddr = inet->inet_rcv_saddr; newinet->inet_dport = htons(asoc->peer.port); newinet->pmtudisc = inet->pmtudisc; atomic_set(&newinet->inet_id, get_random_u16()); newinet->uc_ttl = inet->uc_ttl; inet_set_bit(MC_LOOP, newsk); newinet->mc_ttl = 1; newinet->mc_index = 0; newinet->mc_list = NULL; if (newsk->sk_flags & SK_FLAGS_TIMESTAMP) net_enable_timestamp(); /* Set newsk security attributes from original sk and connection * security attribute from asoc. */ security_sctp_sk_clone(asoc, sk, newsk); } static inline void sctp_copy_descendant(struct sock *sk_to, const struct sock *sk_from) { size_t ancestor_size = sizeof(struct inet_sock); ancestor_size += sk_from->sk_prot->obj_size; ancestor_size -= offsetof(struct sctp_sock, pd_lobby); __inet_sk_copy_descendant(sk_to, sk_from, ancestor_size); } /* Populate the fields of the newsk from the oldsk and migrate the assoc * and its messages to the newsk. */ static int sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, struct sctp_association *assoc, enum sctp_socket_type type) { struct sctp_sock *oldsp = sctp_sk(oldsk); struct sctp_sock *newsp = sctp_sk(newsk); struct sctp_bind_bucket *pp; /* hash list port iterator */ struct sctp_endpoint *newep = newsp->ep; struct sk_buff *skb, *tmp; struct sctp_ulpevent *event; struct sctp_bind_hashbucket *head; int err; /* Migrate socket buffer sizes and all the socket level options to the * new socket. */ newsk->sk_sndbuf = oldsk->sk_sndbuf; newsk->sk_rcvbuf = oldsk->sk_rcvbuf; /* Brute force copy old sctp opt. */ sctp_copy_descendant(newsk, oldsk); /* Restore the ep value that was overwritten with the above structure * copy. */ newsp->ep = newep; newsp->hmac = NULL; /* Hook this new socket in to the bind_hash list. */ head = &sctp_port_hashtable[sctp_phashfn(sock_net(oldsk), inet_sk(oldsk)->inet_num)]; spin_lock_bh(&head->lock); pp = sctp_sk(oldsk)->bind_hash; sk_add_bind_node(newsk, &pp->owner); sctp_sk(newsk)->bind_hash = pp; inet_sk(newsk)->inet_num = inet_sk(oldsk)->inet_num; spin_unlock_bh(&head->lock); /* Copy the bind_addr list from the original endpoint to the new * endpoint so that we can handle restarts properly */ err = sctp_bind_addr_dup(&newsp->ep->base.bind_addr, &oldsp->ep->base.bind_addr, GFP_KERNEL); if (err) return err; /* New ep's auth_hmacs should be set if old ep's is set, in case * that net->sctp.auth_enable has been changed to 0 by users and * new ep's auth_hmacs couldn't be set in sctp_endpoint_init(). */ if (oldsp->ep->auth_hmacs) { err = sctp_auth_init_hmacs(newsp->ep, GFP_KERNEL); if (err) return err; } sctp_auto_asconf_init(newsp); /* Move any messages in the old socket's receive queue that are for the * peeled off association to the new socket's receive queue. */ sctp_skb_for_each(skb, &oldsk->sk_receive_queue, tmp) { event = sctp_skb2event(skb); if (event->asoc == assoc) { __skb_unlink(skb, &oldsk->sk_receive_queue); __skb_queue_tail(&newsk->sk_receive_queue, skb); sctp_skb_set_owner_r_frag(skb, newsk); } } /* Clean up any messages pending delivery due to partial * delivery. Three cases: * 1) No partial deliver; no work. * 2) Peeling off partial delivery; keep pd_lobby in new pd_lobby. * 3) Peeling off non-partial delivery; move pd_lobby to receive_queue. */ atomic_set(&sctp_sk(newsk)->pd_mode, assoc->ulpq.pd_mode); if (atomic_read(&sctp_sk(oldsk)->pd_mode)) { struct sk_buff_head *queue; /* Decide which queue to move pd_lobby skbs to. */ if (assoc->ulpq.pd_mode) { queue = &newsp->pd_lobby; } else queue = &newsk->sk_receive_queue; /* Walk through the pd_lobby, looking for skbs that * need moved to the new socket. */ sctp_skb_for_each(skb, &oldsp->pd_lobby, tmp) { event = sctp_skb2event(skb); if (event->asoc == assoc) { __skb_unlink(skb, &oldsp->pd_lobby); __skb_queue_tail(queue, skb); sctp_skb_set_owner_r_frag(skb, newsk); } } /* Clear up any skbs waiting for the partial * delivery to finish. */ if (assoc->ulpq.pd_mode) sctp_clear_pd(oldsk, NULL); } sctp_for_each_rx_skb(assoc, newsk, sctp_skb_set_owner_r_frag); /* Set the type of socket to indicate that it is peeled off from the * original UDP-style socket or created with the accept() call on a * TCP-style socket.. */ newsp->type = type; /* Mark the new socket "in-use" by the user so that any packets * that may arrive on the association after we've moved it are * queued to the backlog. This prevents a potential race between * backlog processing on the old socket and new-packet processing * on the new socket. * * The caller has just allocated newsk so we can guarantee that other * paths won't try to lock it and then oldsk. */ lock_sock_nested(newsk, SINGLE_DEPTH_NESTING); sctp_for_each_tx_datachunk(assoc, true, sctp_clear_owner_w); sctp_assoc_migrate(assoc, newsk); sctp_for_each_tx_datachunk(assoc, false, sctp_set_owner_w); /* If the association on the newsk is already closed before accept() * is called, set RCV_SHUTDOWN flag. */ if (sctp_state(assoc, CLOSED) && sctp_style(newsk, TCP)) { inet_sk_set_state(newsk, SCTP_SS_CLOSED); newsk->sk_shutdown |= RCV_SHUTDOWN; } else { inet_sk_set_state(newsk, SCTP_SS_ESTABLISHED); } release_sock(newsk); return 0; } /* This proto struct describes the ULP interface for SCTP. */ struct proto sctp_prot = { .name = "SCTP", .owner = THIS_MODULE, .close = sctp_close, .disconnect = sctp_disconnect, .accept = sctp_accept, .ioctl = sctp_ioctl, .init = sctp_init_sock, .destroy = sctp_destroy_sock, .shutdown = sctp_shutdown, .setsockopt = sctp_setsockopt, .getsockopt = sctp_getsockopt, .bpf_bypass_getsockopt = sctp_bpf_bypass_getsockopt, .sendmsg = sctp_sendmsg, .recvmsg = sctp_recvmsg, .bind = sctp_bind, .bind_add = sctp_bind_add, .backlog_rcv = sctp_backlog_rcv, .hash = sctp_hash, .unhash = sctp_unhash, .no_autobind = true, .obj_size = sizeof(struct sctp_sock), .useroffset = offsetof(struct sctp_sock, subscribe), .usersize = offsetof(struct sctp_sock, initmsg) - offsetof(struct sctp_sock, subscribe) + sizeof_field(struct sctp_sock, initmsg), .sysctl_mem = sysctl_sctp_mem, .sysctl_rmem = sysctl_sctp_rmem, .sysctl_wmem = sysctl_sctp_wmem, .memory_pressure = &sctp_memory_pressure, .enter_memory_pressure = sctp_enter_memory_pressure, .memory_allocated = &sctp_memory_allocated, .per_cpu_fw_alloc = &sctp_memory_per_cpu_fw_alloc, .sockets_allocated = &sctp_sockets_allocated, }; #if IS_ENABLED(CONFIG_IPV6) static void sctp_v6_destruct_sock(struct sock *sk) { sctp_destruct_common(sk); inet6_sock_destruct(sk); } static int sctp_v6_init_sock(struct sock *sk) { int ret = sctp_init_sock(sk); if (!ret) sk->sk_destruct = sctp_v6_destruct_sock; return ret; } struct proto sctpv6_prot = { .name = "SCTPv6", .owner = THIS_MODULE, .close = sctp_close, .disconnect = sctp_disconnect, .accept = sctp_accept, .ioctl = sctp_ioctl, .init = sctp_v6_init_sock, .destroy = sctp_destroy_sock, .shutdown = sctp_shutdown, .setsockopt = sctp_setsockopt, .getsockopt = sctp_getsockopt, .bpf_bypass_getsockopt = sctp_bpf_bypass_getsockopt, .sendmsg = sctp_sendmsg, .recvmsg = sctp_recvmsg, .bind = sctp_bind, .bind_add = sctp_bind_add, .backlog_rcv = sctp_backlog_rcv, .hash = sctp_hash, .unhash = sctp_unhash, .no_autobind = true, .obj_size = sizeof(struct sctp6_sock), .ipv6_pinfo_offset = offsetof(struct sctp6_sock, inet6), .useroffset = offsetof(struct sctp6_sock, sctp.subscribe), .usersize = offsetof(struct sctp6_sock, sctp.initmsg) - offsetof(struct sctp6_sock, sctp.subscribe) + sizeof_field(struct sctp6_sock, sctp.initmsg), .sysctl_mem = sysctl_sctp_mem, .sysctl_rmem = sysctl_sctp_rmem, .sysctl_wmem = sysctl_sctp_wmem, .memory_pressure = &sctp_memory_pressure, .enter_memory_pressure = sctp_enter_memory_pressure, .memory_allocated = &sctp_memory_allocated, .per_cpu_fw_alloc = &sctp_memory_per_cpu_fw_alloc, .sockets_allocated = &sctp_sockets_allocated, }; #endif /* IS_ENABLED(CONFIG_IPV6) */ |
| 5 45 13 1 6 4 5 5 9 15 9 6 1 1 9 8 1 1 5 5 1 4 4 1 3 2 1 17 2 3 5 5 5 5 5 3 3 1 2 1 1 1 1 2 5 1 2 9 9 6 8 8 8 8 8 1 1 6 6 6 5 1 5 1 8 15 15 2 1 12 10 2 15 3 2 1 1 1 3 6 2 4 15 10 10 1 7 4 17 20 20 6 1 24 5 20 21 21 21 1 1 2 1 1 1 1 1 21 21 21 21 21 10 10 3 10 88 90 2 1 2 2 1 1 1 1 4 1 23 85 10 9 4 29 1 2 12 11 11 11 11 55 51 1 3 2 50 26 24 30 19 36 1 11 35 8 2 2 11 1 2 1 1 1 5 2 3 1 4 2 32 2 7 17 11 26 2 1 27 15 13 1 26 1 13 11 22 2 21 1 2 14 1 8 1 20 1 20 1 1 21 21 5 1 28 10 10 1 10 10 9 3 1 5 7 1 6 2 6 1 8 3 2 3 46 17 3 17 81 2 76 16 17 17 1 3 80 75 28 881 877 40 39 14 1 2 1 1 2 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2007 Patrick McHardy <kaber@trash.net> * * The code this is based on carried the following copyright notice: * --- * (C) Copyright 2001-2006 * Alex Zeffertt, Cambridge Broadband Ltd, ajz@cambridgebroadband.com * Re-worked by Ben Greear <greearb@candelatech.com> * --- */ #include <linux/kernel.h> #include <linux/types.h> #include <linux/module.h> #include <linux/init.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/rculist.h> #include <linux/notifier.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/net_tstamp.h> #include <linux/ethtool.h> #include <linux/if_arp.h> #include <linux/if_vlan.h> #include <linux/if_link.h> #include <linux/if_macvlan.h> #include <linux/hash.h> #include <linux/workqueue.h> #include <net/rtnetlink.h> #include <net/xfrm.h> #include <linux/netpoll.h> #include <linux/phy.h> #define MACVLAN_HASH_BITS 8 #define MACVLAN_HASH_SIZE (1<<MACVLAN_HASH_BITS) #define MACVLAN_DEFAULT_BC_QUEUE_LEN 1000 #define MACVLAN_F_PASSTHRU 1 #define MACVLAN_F_ADDRCHANGE 2 struct macvlan_port { struct net_device *dev; struct hlist_head vlan_hash[MACVLAN_HASH_SIZE]; struct list_head vlans; struct sk_buff_head bc_queue; struct work_struct bc_work; u32 bc_queue_len_used; int bc_cutoff; u32 flags; int count; struct hlist_head vlan_source_hash[MACVLAN_HASH_SIZE]; DECLARE_BITMAP(bc_filter, MACVLAN_MC_FILTER_SZ); DECLARE_BITMAP(mc_filter, MACVLAN_MC_FILTER_SZ); unsigned char perm_addr[ETH_ALEN]; }; struct macvlan_source_entry { struct hlist_node hlist; struct macvlan_dev *vlan; unsigned char addr[6+2] __aligned(sizeof(u16)); struct rcu_head rcu; }; struct macvlan_skb_cb { const struct macvlan_dev *src; }; #define MACVLAN_SKB_CB(__skb) ((struct macvlan_skb_cb *)&((__skb)->cb[0])) static void macvlan_port_destroy(struct net_device *dev); static void update_port_bc_queue_len(struct macvlan_port *port); static inline bool macvlan_passthru(const struct macvlan_port *port) { return port->flags & MACVLAN_F_PASSTHRU; } static inline void macvlan_set_passthru(struct macvlan_port *port) { port->flags |= MACVLAN_F_PASSTHRU; } static inline bool macvlan_addr_change(const struct macvlan_port *port) { return port->flags & MACVLAN_F_ADDRCHANGE; } static inline void macvlan_set_addr_change(struct macvlan_port *port) { port->flags |= MACVLAN_F_ADDRCHANGE; } static inline void macvlan_clear_addr_change(struct macvlan_port *port) { port->flags &= ~MACVLAN_F_ADDRCHANGE; } /* Hash Ethernet address */ static u32 macvlan_eth_hash(const unsigned char *addr) { u64 value = get_unaligned((u64 *)addr); /* only want 6 bytes */ #ifdef __BIG_ENDIAN value >>= 16; #else value <<= 16; #endif return hash_64(value, MACVLAN_HASH_BITS); } static struct macvlan_port *macvlan_port_get_rcu(const struct net_device *dev) { return rcu_dereference(dev->rx_handler_data); } static struct macvlan_port *macvlan_port_get_rtnl(const struct net_device *dev) { return rtnl_dereference(dev->rx_handler_data); } static struct macvlan_dev *macvlan_hash_lookup(const struct macvlan_port *port, const unsigned char *addr) { struct macvlan_dev *vlan; u32 idx = macvlan_eth_hash(addr); hlist_for_each_entry_rcu(vlan, &port->vlan_hash[idx], hlist, lockdep_rtnl_is_held()) { if (ether_addr_equal_64bits(vlan->dev->dev_addr, addr)) return vlan; } return NULL; } static struct macvlan_source_entry *macvlan_hash_lookup_source( const struct macvlan_dev *vlan, const unsigned char *addr) { struct macvlan_source_entry *entry; u32 idx = macvlan_eth_hash(addr); struct hlist_head *h = &vlan->port->vlan_source_hash[idx]; hlist_for_each_entry_rcu(entry, h, hlist, lockdep_rtnl_is_held()) { if (ether_addr_equal_64bits(entry->addr, addr) && entry->vlan == vlan) return entry; } return NULL; } static int macvlan_hash_add_source(struct macvlan_dev *vlan, const unsigned char *addr) { struct macvlan_port *port = vlan->port; struct macvlan_source_entry *entry; struct hlist_head *h; entry = macvlan_hash_lookup_source(vlan, addr); if (entry) return 0; entry = kmalloc(sizeof(*entry), GFP_KERNEL); if (!entry) return -ENOMEM; ether_addr_copy(entry->addr, addr); entry->vlan = vlan; h = &port->vlan_source_hash[macvlan_eth_hash(addr)]; hlist_add_head_rcu(&entry->hlist, h); vlan->macaddr_count++; return 0; } static void macvlan_hash_add(struct macvlan_dev *vlan) { struct macvlan_port *port = vlan->port; const unsigned char *addr = vlan->dev->dev_addr; u32 idx = macvlan_eth_hash(addr); hlist_add_head_rcu(&vlan->hlist, &port->vlan_hash[idx]); } static void macvlan_hash_del_source(struct macvlan_source_entry *entry) { hlist_del_rcu(&entry->hlist); kfree_rcu(entry, rcu); } static void macvlan_hash_del(struct macvlan_dev *vlan, bool sync) { hlist_del_rcu(&vlan->hlist); if (sync) synchronize_rcu(); } static void macvlan_hash_change_addr(struct macvlan_dev *vlan, const unsigned char *addr) { macvlan_hash_del(vlan, true); /* Now that we are unhashed it is safe to change the device * address without confusing packet delivery. */ eth_hw_addr_set(vlan->dev, addr); macvlan_hash_add(vlan); } static bool macvlan_addr_busy(const struct macvlan_port *port, const unsigned char *addr) { /* Test to see if the specified address is * currently in use by the underlying device or * another macvlan. */ if (!macvlan_passthru(port) && !macvlan_addr_change(port) && ether_addr_equal_64bits(port->dev->dev_addr, addr)) return true; if (macvlan_hash_lookup(port, addr)) return true; return false; } static int macvlan_broadcast_one(struct sk_buff *skb, const struct macvlan_dev *vlan, const struct ethhdr *eth, bool local) { struct net_device *dev = vlan->dev; if (local) return __dev_forward_skb(dev, skb); skb->dev = dev; if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast)) skb->pkt_type = PACKET_BROADCAST; else skb->pkt_type = PACKET_MULTICAST; return 0; } static u32 macvlan_hash_mix(const struct macvlan_dev *vlan) { return (u32)(((unsigned long)vlan) >> L1_CACHE_SHIFT); } static unsigned int mc_hash(const struct macvlan_dev *vlan, const unsigned char *addr) { u32 val = __get_unaligned_cpu32(addr + 2); val ^= macvlan_hash_mix(vlan); return hash_32(val, MACVLAN_MC_FILTER_BITS); } static void macvlan_broadcast(struct sk_buff *skb, const struct macvlan_port *port, struct net_device *src, enum macvlan_mode mode) { const struct ethhdr *eth = eth_hdr(skb); const struct macvlan_dev *vlan; struct sk_buff *nskb; unsigned int i; int err; unsigned int hash; if (skb->protocol == htons(ETH_P_PAUSE)) return; hash_for_each_rcu(port->vlan_hash, i, vlan, hlist) { if (vlan->dev == src || !(vlan->mode & mode)) continue; hash = mc_hash(vlan, eth->h_dest); if (!test_bit(hash, vlan->mc_filter)) continue; err = NET_RX_DROP; nskb = skb_clone(skb, GFP_ATOMIC); if (likely(nskb)) err = macvlan_broadcast_one(nskb, vlan, eth, mode == MACVLAN_MODE_BRIDGE) ?: netif_rx(nskb); macvlan_count_rx(vlan, skb->len + ETH_HLEN, err == NET_RX_SUCCESS, true); } } static void macvlan_multicast_rx(const struct macvlan_port *port, const struct macvlan_dev *src, struct sk_buff *skb) { if (!src) /* frame comes from an external address */ macvlan_broadcast(skb, port, NULL, MACVLAN_MODE_PRIVATE | MACVLAN_MODE_VEPA | MACVLAN_MODE_PASSTHRU| MACVLAN_MODE_BRIDGE); else if (src->mode == MACVLAN_MODE_VEPA) /* flood to everyone except source */ macvlan_broadcast(skb, port, src->dev, MACVLAN_MODE_VEPA | MACVLAN_MODE_BRIDGE); else /* * flood only to VEPA ports, bridge ports * already saw the frame on the way out. */ macvlan_broadcast(skb, port, src->dev, MACVLAN_MODE_VEPA); } static void macvlan_process_broadcast(struct work_struct *w) { struct macvlan_port *port = container_of(w, struct macvlan_port, bc_work); struct sk_buff *skb; struct sk_buff_head list; __skb_queue_head_init(&list); spin_lock_bh(&port->bc_queue.lock); skb_queue_splice_tail_init(&port->bc_queue, &list); spin_unlock_bh(&port->bc_queue.lock); while ((skb = __skb_dequeue(&list))) { const struct macvlan_dev *src = MACVLAN_SKB_CB(skb)->src; rcu_read_lock(); macvlan_multicast_rx(port, src, skb); rcu_read_unlock(); if (src) dev_put(src->dev); consume_skb(skb); cond_resched(); } } static void macvlan_broadcast_enqueue(struct macvlan_port *port, const struct macvlan_dev *src, struct sk_buff *skb) { struct sk_buff *nskb; int err = -ENOMEM; nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) goto err; MACVLAN_SKB_CB(nskb)->src = src; spin_lock(&port->bc_queue.lock); if (skb_queue_len(&port->bc_queue) < port->bc_queue_len_used) { if (src) dev_hold(src->dev); __skb_queue_tail(&port->bc_queue, nskb); err = 0; } spin_unlock(&port->bc_queue.lock); queue_work(system_unbound_wq, &port->bc_work); if (err) goto free_nskb; return; free_nskb: kfree_skb(nskb); err: dev_core_stats_rx_dropped_inc(skb->dev); } static void macvlan_flush_sources(struct macvlan_port *port, struct macvlan_dev *vlan) { struct macvlan_source_entry *entry; struct hlist_node *next; int i; hash_for_each_safe(port->vlan_source_hash, i, next, entry, hlist) if (entry->vlan == vlan) macvlan_hash_del_source(entry); vlan->macaddr_count = 0; } static void macvlan_forward_source_one(struct sk_buff *skb, struct macvlan_dev *vlan) { struct sk_buff *nskb; struct net_device *dev; int len; int ret; dev = vlan->dev; if (unlikely(!(dev->flags & IFF_UP))) return; nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return; len = nskb->len + ETH_HLEN; nskb->dev = dev; if (ether_addr_equal_64bits(eth_hdr(skb)->h_dest, dev->dev_addr)) nskb->pkt_type = PACKET_HOST; ret = __netif_rx(nskb); macvlan_count_rx(vlan, len, ret == NET_RX_SUCCESS, false); } static bool macvlan_forward_source(struct sk_buff *skb, struct macvlan_port *port, const unsigned char *addr) { struct macvlan_source_entry *entry; u32 idx = macvlan_eth_hash(addr); struct hlist_head *h = &port->vlan_source_hash[idx]; bool consume = false; hlist_for_each_entry_rcu(entry, h, hlist) { if (ether_addr_equal_64bits(entry->addr, addr)) { if (entry->vlan->flags & MACVLAN_FLAG_NODST) consume = true; macvlan_forward_source_one(skb, entry->vlan); } } return consume; } /* called under rcu_read_lock() from netif_receive_skb */ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb) { struct macvlan_port *port; struct sk_buff *skb = *pskb; const struct ethhdr *eth = eth_hdr(skb); const struct macvlan_dev *vlan; const struct macvlan_dev *src; struct net_device *dev; unsigned int len = 0; int ret; rx_handler_result_t handle_res; /* Packets from dev_loopback_xmit() do not have L2 header, bail out */ if (unlikely(skb->pkt_type == PACKET_LOOPBACK)) return RX_HANDLER_PASS; port = macvlan_port_get_rcu(skb->dev); if (is_multicast_ether_addr(eth->h_dest)) { unsigned int hash; skb = ip_check_defrag(dev_net(skb->dev), skb, IP_DEFRAG_MACVLAN); if (!skb) return RX_HANDLER_CONSUMED; *pskb = skb; eth = eth_hdr(skb); if (macvlan_forward_source(skb, port, eth->h_source)) { kfree_skb(skb); return RX_HANDLER_CONSUMED; } src = macvlan_hash_lookup(port, eth->h_source); if (src && src->mode != MACVLAN_MODE_VEPA && src->mode != MACVLAN_MODE_BRIDGE) { /* forward to original port. */ vlan = src; ret = macvlan_broadcast_one(skb, vlan, eth, 0) ?: __netif_rx(skb); handle_res = RX_HANDLER_CONSUMED; goto out; } hash = mc_hash(NULL, eth->h_dest); if (test_bit(hash, port->bc_filter)) macvlan_broadcast_enqueue(port, src, skb); else if (test_bit(hash, port->mc_filter)) macvlan_multicast_rx(port, src, skb); return RX_HANDLER_PASS; } if (macvlan_forward_source(skb, port, eth->h_source)) { kfree_skb(skb); return RX_HANDLER_CONSUMED; } if (macvlan_passthru(port)) vlan = list_first_or_null_rcu(&port->vlans, struct macvlan_dev, list); else vlan = macvlan_hash_lookup(port, eth->h_dest); if (!vlan || vlan->mode == MACVLAN_MODE_SOURCE) return RX_HANDLER_PASS; dev = vlan->dev; if (unlikely(!(dev->flags & IFF_UP))) { kfree_skb(skb); return RX_HANDLER_CONSUMED; } len = skb->len + ETH_HLEN; skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) { ret = NET_RX_DROP; handle_res = RX_HANDLER_CONSUMED; goto out; } *pskb = skb; skb->dev = dev; skb->pkt_type = PACKET_HOST; ret = NET_RX_SUCCESS; handle_res = RX_HANDLER_ANOTHER; out: macvlan_count_rx(vlan, len, ret == NET_RX_SUCCESS, false); return handle_res; } static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev) { const struct macvlan_dev *vlan = netdev_priv(dev); const struct macvlan_port *port = vlan->port; const struct macvlan_dev *dest; if (vlan->mode == MACVLAN_MODE_BRIDGE) { const struct ethhdr *eth = skb_eth_hdr(skb); /* send to other bridge ports directly */ if (is_multicast_ether_addr(eth->h_dest)) { skb_reset_mac_header(skb); macvlan_broadcast(skb, port, dev, MACVLAN_MODE_BRIDGE); goto xmit_world; } dest = macvlan_hash_lookup(port, eth->h_dest); if (dest && dest->mode == MACVLAN_MODE_BRIDGE) { /* send to lowerdev first for its network taps */ dev_forward_skb(vlan->lowerdev, skb); return NET_XMIT_SUCCESS; } } xmit_world: skb->dev = vlan->lowerdev; return dev_queue_xmit_accel(skb, netdev_get_sb_channel(dev) ? dev : NULL); } static inline netdev_tx_t macvlan_netpoll_send_skb(struct macvlan_dev *vlan, struct sk_buff *skb) { #ifdef CONFIG_NET_POLL_CONTROLLER return netpoll_send_skb(vlan->netpoll, skb); #else BUG(); return NETDEV_TX_OK; #endif } static netdev_tx_t macvlan_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); unsigned int len = skb->len; int ret; if (unlikely(netpoll_tx_running(dev))) return macvlan_netpoll_send_skb(vlan, skb); ret = macvlan_queue_xmit(skb, dev); if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { struct vlan_pcpu_stats *pcpu_stats; pcpu_stats = this_cpu_ptr(vlan->pcpu_stats); u64_stats_update_begin(&pcpu_stats->syncp); u64_stats_inc(&pcpu_stats->tx_packets); u64_stats_add(&pcpu_stats->tx_bytes, len); u64_stats_update_end(&pcpu_stats->syncp); } else { this_cpu_inc(vlan->pcpu_stats->tx_dropped); } return ret; } static int macvlan_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned len) { const struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; return dev_hard_header(skb, lowerdev, type, daddr, saddr ? : dev->dev_addr, len); } static const struct header_ops macvlan_hard_header_ops = { .create = macvlan_hard_header, .parse = eth_header_parse, .cache = eth_header_cache, .cache_update = eth_header_cache_update, .parse_protocol = eth_header_parse_protocol, }; static int macvlan_open(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; int err; if (macvlan_passthru(vlan->port)) { if (!(vlan->flags & MACVLAN_FLAG_NOPROMISC)) { err = dev_set_promiscuity(lowerdev, 1); if (err < 0) goto out; } goto hash_add; } err = -EADDRINUSE; if (macvlan_addr_busy(vlan->port, dev->dev_addr)) goto out; /* Attempt to populate accel_priv which is used to offload the L2 * forwarding requests for unicast packets. */ if (lowerdev->features & NETIF_F_HW_L2FW_DOFFLOAD) vlan->accel_priv = lowerdev->netdev_ops->ndo_dfwd_add_station(lowerdev, dev); /* If earlier attempt to offload failed, or accel_priv is not * populated we must add the unicast address to the lower device. */ if (IS_ERR_OR_NULL(vlan->accel_priv)) { vlan->accel_priv = NULL; err = dev_uc_add(lowerdev, dev->dev_addr); if (err < 0) goto out; } if (dev->flags & IFF_ALLMULTI) { err = dev_set_allmulti(lowerdev, 1); if (err < 0) goto del_unicast; } if (dev->flags & IFF_PROMISC) { err = dev_set_promiscuity(lowerdev, 1); if (err < 0) goto clear_multi; } hash_add: macvlan_hash_add(vlan); return 0; clear_multi: if (dev->flags & IFF_ALLMULTI) dev_set_allmulti(lowerdev, -1); del_unicast: if (vlan->accel_priv) { lowerdev->netdev_ops->ndo_dfwd_del_station(lowerdev, vlan->accel_priv); vlan->accel_priv = NULL; } else { dev_uc_del(lowerdev, dev->dev_addr); } out: return err; } static int macvlan_stop(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; if (vlan->accel_priv) { lowerdev->netdev_ops->ndo_dfwd_del_station(lowerdev, vlan->accel_priv); vlan->accel_priv = NULL; } dev_uc_unsync(lowerdev, dev); dev_mc_unsync(lowerdev, dev); if (macvlan_passthru(vlan->port)) { if (!(vlan->flags & MACVLAN_FLAG_NOPROMISC)) dev_set_promiscuity(lowerdev, -1); goto hash_del; } if (dev->flags & IFF_ALLMULTI) dev_set_allmulti(lowerdev, -1); if (dev->flags & IFF_PROMISC) dev_set_promiscuity(lowerdev, -1); dev_uc_del(lowerdev, dev->dev_addr); hash_del: macvlan_hash_del(vlan, !dev->dismantle); return 0; } static int macvlan_sync_address(struct net_device *dev, const unsigned char *addr) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; struct macvlan_port *port = vlan->port; int err; if (!(dev->flags & IFF_UP)) { /* Just copy in the new address */ eth_hw_addr_set(dev, addr); } else { /* Rehash and update the device filters */ if (macvlan_addr_busy(vlan->port, addr)) return -EADDRINUSE; if (!macvlan_passthru(port)) { err = dev_uc_add(lowerdev, addr); if (err) return err; dev_uc_del(lowerdev, dev->dev_addr); } macvlan_hash_change_addr(vlan, addr); } if (macvlan_passthru(port) && !macvlan_addr_change(port)) { /* Since addr_change isn't set, we are here due to lower * device change. Save the lower-dev address so we can * restore it later. */ ether_addr_copy(vlan->port->perm_addr, lowerdev->dev_addr); } macvlan_clear_addr_change(port); return 0; } static int macvlan_set_mac_address(struct net_device *dev, void *p) { struct macvlan_dev *vlan = netdev_priv(dev); struct sockaddr *addr = p; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; /* If the addresses are the same, this is a no-op */ if (ether_addr_equal(dev->dev_addr, addr->sa_data)) return 0; if (vlan->mode == MACVLAN_MODE_PASSTHRU) { macvlan_set_addr_change(vlan->port); return dev_set_mac_address(vlan->lowerdev, addr, NULL); } if (macvlan_addr_busy(vlan->port, addr->sa_data)) return -EADDRINUSE; return macvlan_sync_address(dev, addr->sa_data); } static void macvlan_change_rx_flags(struct net_device *dev, int change) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; if (dev->flags & IFF_UP) { if (change & IFF_ALLMULTI) dev_set_allmulti(lowerdev, dev->flags & IFF_ALLMULTI ? 1 : -1); if (!macvlan_passthru(vlan->port) && change & IFF_PROMISC) dev_set_promiscuity(lowerdev, dev->flags & IFF_PROMISC ? 1 : -1); } } static void macvlan_compute_filter(unsigned long *mc_filter, struct net_device *dev, struct macvlan_dev *vlan, int cutoff) { if (dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) { bitmap_fill(mc_filter, MACVLAN_MC_FILTER_SZ); } else { DECLARE_BITMAP(filter, MACVLAN_MC_FILTER_SZ); struct netdev_hw_addr *ha; bitmap_zero(filter, MACVLAN_MC_FILTER_SZ); netdev_for_each_mc_addr(ha, dev) { if (!vlan && ha->synced <= cutoff) continue; __set_bit(mc_hash(vlan, ha->addr), filter); } __set_bit(mc_hash(vlan, dev->broadcast), filter); bitmap_copy(mc_filter, filter, MACVLAN_MC_FILTER_SZ); } } static void macvlan_recompute_bc_filter(struct macvlan_dev *vlan) { if (vlan->port->bc_cutoff < 0) { bitmap_zero(vlan->port->bc_filter, MACVLAN_MC_FILTER_SZ); return; } macvlan_compute_filter(vlan->port->bc_filter, vlan->lowerdev, NULL, vlan->port->bc_cutoff); } static void macvlan_set_mac_lists(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); macvlan_compute_filter(vlan->mc_filter, dev, vlan, 0); dev_uc_sync(vlan->lowerdev, dev); dev_mc_sync(vlan->lowerdev, dev); /* This is slightly inaccurate as we're including the subscription * list of vlan->lowerdev too. * * Bug alert: This only works if everyone has the same broadcast * address as lowerdev. As soon as someone changes theirs this * will break. * * However, this is already broken as when you change your broadcast * address we don't get called. * * The solution is to maintain a list of broadcast addresses like * we do for uc/mc, if you care. */ macvlan_compute_filter(vlan->port->mc_filter, vlan->lowerdev, NULL, 0); macvlan_recompute_bc_filter(vlan); } static void update_port_bc_cutoff(struct macvlan_dev *vlan, int cutoff) { if (vlan->port->bc_cutoff == cutoff) return; vlan->port->bc_cutoff = cutoff; macvlan_recompute_bc_filter(vlan); } static int macvlan_change_mtu(struct net_device *dev, int new_mtu) { struct macvlan_dev *vlan = netdev_priv(dev); if (vlan->lowerdev->mtu < new_mtu) return -EINVAL; WRITE_ONCE(dev->mtu, new_mtu); return 0; } static int macvlan_hwtstamp_get(struct net_device *dev, struct kernel_hwtstamp_config *cfg) { struct net_device *real_dev = macvlan_dev_real_dev(dev); return generic_hwtstamp_get_lower(real_dev, cfg); } static int macvlan_hwtstamp_set(struct net_device *dev, struct kernel_hwtstamp_config *cfg, struct netlink_ext_ack *extack) { struct net_device *real_dev = macvlan_dev_real_dev(dev); if (!net_eq(dev_net(dev), &init_net)) return -EOPNOTSUPP; return generic_hwtstamp_set_lower(real_dev, cfg, extack); } /* * macvlan network devices have devices nesting below it and are a special * "super class" of normal network devices; split their locks off into a * separate class since they always nest. */ static struct lock_class_key macvlan_netdev_addr_lock_key; #define ALWAYS_ON_OFFLOADS \ (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE | \ NETIF_F_GSO_ROBUST | NETIF_F_GSO_ENCAP_ALL) #define ALWAYS_ON_FEATURES ALWAYS_ON_OFFLOADS #define MACVLAN_FEATURES \ (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \ NETIF_F_GSO | NETIF_F_TSO | NETIF_F_LRO | \ NETIF_F_TSO_ECN | NETIF_F_TSO6 | NETIF_F_GRO | NETIF_F_RXCSUM | \ NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER) #define MACVLAN_STATE_MASK \ ((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT)) static void macvlan_set_lockdep_class(struct net_device *dev) { netdev_lockdep_set_classes(dev); lockdep_set_class(&dev->addr_list_lock, &macvlan_netdev_addr_lock_key); } static int macvlan_init(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; struct macvlan_port *port = vlan->port; dev->state = (dev->state & ~MACVLAN_STATE_MASK) | (lowerdev->state & MACVLAN_STATE_MASK); dev->features = lowerdev->features & MACVLAN_FEATURES; dev->features |= ALWAYS_ON_FEATURES; dev->hw_features |= NETIF_F_LRO; dev->vlan_features = lowerdev->vlan_features & MACVLAN_FEATURES; dev->vlan_features |= ALWAYS_ON_OFFLOADS; dev->hw_enc_features |= dev->features; dev->lltx = true; netif_inherit_tso_max(dev, lowerdev); dev->hard_header_len = lowerdev->hard_header_len; macvlan_set_lockdep_class(dev); vlan->pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats); if (!vlan->pcpu_stats) return -ENOMEM; port->count += 1; /* Get macvlan's reference to lowerdev */ netdev_hold(lowerdev, &vlan->dev_tracker, GFP_KERNEL); return 0; } static void macvlan_uninit(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); struct macvlan_port *port = vlan->port; free_percpu(vlan->pcpu_stats); macvlan_flush_sources(port, vlan); port->count -= 1; if (!port->count) macvlan_port_destroy(port->dev); } static void macvlan_dev_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct macvlan_dev *vlan = netdev_priv(dev); if (vlan->pcpu_stats) { struct vlan_pcpu_stats *p; u64 rx_packets, rx_bytes, rx_multicast, tx_packets, tx_bytes; u32 rx_errors = 0, tx_dropped = 0; unsigned int start; int i; for_each_possible_cpu(i) { p = per_cpu_ptr(vlan->pcpu_stats, i); do { start = u64_stats_fetch_begin(&p->syncp); rx_packets = u64_stats_read(&p->rx_packets); rx_bytes = u64_stats_read(&p->rx_bytes); rx_multicast = u64_stats_read(&p->rx_multicast); tx_packets = u64_stats_read(&p->tx_packets); tx_bytes = u64_stats_read(&p->tx_bytes); } while (u64_stats_fetch_retry(&p->syncp, start)); stats->rx_packets += rx_packets; stats->rx_bytes += rx_bytes; stats->multicast += rx_multicast; stats->tx_packets += tx_packets; stats->tx_bytes += tx_bytes; /* rx_errors & tx_dropped are u32, updated * without syncp protection. */ rx_errors += READ_ONCE(p->rx_errors); tx_dropped += READ_ONCE(p->tx_dropped); } stats->rx_errors = rx_errors; stats->rx_dropped = rx_errors; stats->tx_dropped = tx_dropped; } } static int macvlan_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; return vlan_vid_add(lowerdev, proto, vid); } static int macvlan_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; vlan_vid_del(lowerdev, proto, vid); return 0; } static int macvlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u16 flags, bool *notified, struct netlink_ext_ack *extack) { struct macvlan_dev *vlan = netdev_priv(dev); int err = -EINVAL; /* Support unicast filter only on passthru devices. * Multicast filter should be allowed on all devices. */ if (!macvlan_passthru(vlan->port) && is_unicast_ether_addr(addr)) return -EOPNOTSUPP; if (flags & NLM_F_REPLACE) return -EOPNOTSUPP; if (is_unicast_ether_addr(addr)) err = dev_uc_add_excl(dev, addr); else if (is_multicast_ether_addr(addr)) err = dev_mc_add_excl(dev, addr); return err; } static int macvlan_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, bool *notified, struct netlink_ext_ack *extack) { struct macvlan_dev *vlan = netdev_priv(dev); int err = -EINVAL; /* Support unicast filter only on passthru devices. * Multicast filter should be allowed on all devices. */ if (!macvlan_passthru(vlan->port) && is_unicast_ether_addr(addr)) return -EOPNOTSUPP; if (is_unicast_ether_addr(addr)) err = dev_uc_del(dev, addr); else if (is_multicast_ether_addr(addr)) err = dev_mc_del(dev, addr); return err; } static void macvlan_ethtool_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->driver, "macvlan", sizeof(drvinfo->driver)); strscpy(drvinfo->version, "0.1", sizeof(drvinfo->version)); } static int macvlan_ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { const struct macvlan_dev *vlan = netdev_priv(dev); return __ethtool_get_link_ksettings(vlan->lowerdev, cmd); } static int macvlan_ethtool_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info) { struct net_device *real_dev = macvlan_dev_real_dev(dev); return ethtool_get_ts_info_by_layer(real_dev, info); } static netdev_features_t macvlan_fix_features(struct net_device *dev, netdev_features_t features) { struct macvlan_dev *vlan = netdev_priv(dev); netdev_features_t lowerdev_features = vlan->lowerdev->features; netdev_features_t mask; features |= NETIF_F_ALL_FOR_ALL; features &= (vlan->set_features | ~MACVLAN_FEATURES); mask = features; lowerdev_features &= (features | ~NETIF_F_LRO); features = netdev_increment_features(lowerdev_features, features, mask); features |= ALWAYS_ON_FEATURES; features &= (ALWAYS_ON_FEATURES | MACVLAN_FEATURES); return features; } #ifdef CONFIG_NET_POLL_CONTROLLER static void macvlan_dev_poll_controller(struct net_device *dev) { return; } static int macvlan_dev_netpoll_setup(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *real_dev = vlan->lowerdev; struct netpoll *netpoll; int err; netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL); err = -ENOMEM; if (!netpoll) goto out; err = __netpoll_setup(netpoll, real_dev); if (err) { kfree(netpoll); goto out; } vlan->netpoll = netpoll; out: return err; } static void macvlan_dev_netpoll_cleanup(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); struct netpoll *netpoll = vlan->netpoll; if (!netpoll) return; vlan->netpoll = NULL; __netpoll_free(netpoll); } #endif /* CONFIG_NET_POLL_CONTROLLER */ static int macvlan_dev_get_iflink(const struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); return READ_ONCE(vlan->lowerdev->ifindex); } static const struct ethtool_ops macvlan_ethtool_ops = { .get_link = ethtool_op_get_link, .get_link_ksettings = macvlan_ethtool_get_link_ksettings, .get_drvinfo = macvlan_ethtool_get_drvinfo, .get_ts_info = macvlan_ethtool_get_ts_info, }; static const struct net_device_ops macvlan_netdev_ops = { .ndo_init = macvlan_init, .ndo_uninit = macvlan_uninit, .ndo_open = macvlan_open, .ndo_stop = macvlan_stop, .ndo_start_xmit = macvlan_start_xmit, .ndo_change_mtu = macvlan_change_mtu, .ndo_fix_features = macvlan_fix_features, .ndo_change_rx_flags = macvlan_change_rx_flags, .ndo_set_mac_address = macvlan_set_mac_address, .ndo_set_rx_mode = macvlan_set_mac_lists, .ndo_get_stats64 = macvlan_dev_get_stats64, .ndo_validate_addr = eth_validate_addr, .ndo_vlan_rx_add_vid = macvlan_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = macvlan_vlan_rx_kill_vid, .ndo_fdb_add = macvlan_fdb_add, .ndo_fdb_del = macvlan_fdb_del, .ndo_fdb_dump = ndo_dflt_fdb_dump, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = macvlan_dev_poll_controller, .ndo_netpoll_setup = macvlan_dev_netpoll_setup, .ndo_netpoll_cleanup = macvlan_dev_netpoll_cleanup, #endif .ndo_get_iflink = macvlan_dev_get_iflink, .ndo_features_check = passthru_features_check, .ndo_hwtstamp_get = macvlan_hwtstamp_get, .ndo_hwtstamp_set = macvlan_hwtstamp_set, }; static void macvlan_dev_free(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); /* Get rid of the macvlan's reference to lowerdev */ netdev_put(vlan->lowerdev, &vlan->dev_tracker); } void macvlan_common_setup(struct net_device *dev) { ether_setup(dev); /* ether_setup() has set dev->min_mtu to ETH_MIN_MTU. */ dev->max_mtu = ETH_MAX_MTU; dev->priv_flags &= ~IFF_TX_SKB_SHARING; netif_keep_dst(dev); dev->priv_flags |= IFF_UNICAST_FLT; dev->change_proto_down = true; dev->netdev_ops = &macvlan_netdev_ops; dev->needs_free_netdev = true; dev->priv_destructor = macvlan_dev_free; dev->header_ops = &macvlan_hard_header_ops; dev->ethtool_ops = &macvlan_ethtool_ops; } EXPORT_SYMBOL_GPL(macvlan_common_setup); static void macvlan_setup(struct net_device *dev) { macvlan_common_setup(dev); dev->priv_flags |= IFF_NO_QUEUE; } static int macvlan_port_create(struct net_device *dev) { struct macvlan_port *port; unsigned int i; int err; if (dev->type != ARPHRD_ETHER || dev->flags & IFF_LOOPBACK) return -EINVAL; if (netdev_is_rx_handler_busy(dev)) return -EBUSY; port = kzalloc(sizeof(*port), GFP_KERNEL); if (port == NULL) return -ENOMEM; port->dev = dev; ether_addr_copy(port->perm_addr, dev->dev_addr); INIT_LIST_HEAD(&port->vlans); for (i = 0; i < MACVLAN_HASH_SIZE; i++) INIT_HLIST_HEAD(&port->vlan_hash[i]); for (i = 0; i < MACVLAN_HASH_SIZE; i++) INIT_HLIST_HEAD(&port->vlan_source_hash[i]); port->bc_queue_len_used = 0; port->bc_cutoff = 1; skb_queue_head_init(&port->bc_queue); INIT_WORK(&port->bc_work, macvlan_process_broadcast); err = netdev_rx_handler_register(dev, macvlan_handle_frame, port); if (err) kfree(port); else dev->priv_flags |= IFF_MACVLAN_PORT; return err; } static void macvlan_port_destroy(struct net_device *dev) { struct macvlan_port *port = macvlan_port_get_rtnl(dev); struct sk_buff *skb; dev->priv_flags &= ~IFF_MACVLAN_PORT; netdev_rx_handler_unregister(dev); /* After this point, no packet can schedule bc_work anymore, * but we need to cancel it and purge left skbs if any. */ cancel_work_sync(&port->bc_work); while ((skb = __skb_dequeue(&port->bc_queue))) { const struct macvlan_dev *src = MACVLAN_SKB_CB(skb)->src; if (src) dev_put(src->dev); kfree_skb(skb); } /* If the lower device address has been changed by passthru * macvlan, put it back. */ if (macvlan_passthru(port) && !ether_addr_equal(port->dev->dev_addr, port->perm_addr)) { struct sockaddr sa; sa.sa_family = port->dev->type; memcpy(&sa.sa_data, port->perm_addr, port->dev->addr_len); dev_set_mac_address(port->dev, &sa, NULL); } kfree(port); } static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct nlattr *nla, *head; int rem, len; if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) return -EADDRNOTAVAIL; } if (!data) return 0; if (data[IFLA_MACVLAN_FLAGS] && nla_get_u16(data[IFLA_MACVLAN_FLAGS]) & ~(MACVLAN_FLAG_NOPROMISC | MACVLAN_FLAG_NODST)) return -EINVAL; if (data[IFLA_MACVLAN_MODE]) { switch (nla_get_u32(data[IFLA_MACVLAN_MODE])) { case MACVLAN_MODE_PRIVATE: case MACVLAN_MODE_VEPA: case MACVLAN_MODE_BRIDGE: case MACVLAN_MODE_PASSTHRU: case MACVLAN_MODE_SOURCE: break; default: return -EINVAL; } } if (data[IFLA_MACVLAN_MACADDR_MODE]) { switch (nla_get_u32(data[IFLA_MACVLAN_MACADDR_MODE])) { case MACVLAN_MACADDR_ADD: case MACVLAN_MACADDR_DEL: case MACVLAN_MACADDR_FLUSH: case MACVLAN_MACADDR_SET: break; default: return -EINVAL; } } if (data[IFLA_MACVLAN_MACADDR]) { if (nla_len(data[IFLA_MACVLAN_MACADDR]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(data[IFLA_MACVLAN_MACADDR]))) return -EADDRNOTAVAIL; } if (data[IFLA_MACVLAN_MACADDR_DATA]) { head = nla_data(data[IFLA_MACVLAN_MACADDR_DATA]); len = nla_len(data[IFLA_MACVLAN_MACADDR_DATA]); nla_for_each_attr(nla, head, len, rem) { if (nla_type(nla) != IFLA_MACVLAN_MACADDR || nla_len(nla) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(nla))) return -EADDRNOTAVAIL; } } if (data[IFLA_MACVLAN_MACADDR_COUNT]) return -EINVAL; return 0; } /* * reconfigure list of remote source mac address * (only for macvlan devices in source mode) * Note regarding alignment: all netlink data is aligned to 4 Byte, which * suffices for both ether_addr_copy and ether_addr_equal_64bits usage. */ static int macvlan_changelink_sources(struct macvlan_dev *vlan, u32 mode, struct nlattr *data[]) { char *addr = NULL; int ret, rem, len; struct nlattr *nla, *head; struct macvlan_source_entry *entry; if (data[IFLA_MACVLAN_MACADDR]) addr = nla_data(data[IFLA_MACVLAN_MACADDR]); if (mode == MACVLAN_MACADDR_ADD) { if (!addr) return -EINVAL; return macvlan_hash_add_source(vlan, addr); } else if (mode == MACVLAN_MACADDR_DEL) { if (!addr) return -EINVAL; entry = macvlan_hash_lookup_source(vlan, addr); if (entry) { macvlan_hash_del_source(entry); vlan->macaddr_count--; } } else if (mode == MACVLAN_MACADDR_FLUSH) { macvlan_flush_sources(vlan->port, vlan); } else if (mode == MACVLAN_MACADDR_SET) { macvlan_flush_sources(vlan->port, vlan); if (addr) { ret = macvlan_hash_add_source(vlan, addr); if (ret) return ret; } if (!data[IFLA_MACVLAN_MACADDR_DATA]) return 0; head = nla_data(data[IFLA_MACVLAN_MACADDR_DATA]); len = nla_len(data[IFLA_MACVLAN_MACADDR_DATA]); nla_for_each_attr(nla, head, len, rem) { addr = nla_data(nla); ret = macvlan_hash_add_source(vlan, addr); if (ret) return ret; } } else { return -EINVAL; } return 0; } int macvlan_common_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct macvlan_dev *vlan = netdev_priv(dev); struct macvlan_port *port; struct net_device *lowerdev; int err; int macmode; bool create = false; if (!tb[IFLA_LINK]) return -EINVAL; lowerdev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK])); if (lowerdev == NULL) return -ENODEV; /* When creating macvlans or macvtaps on top of other macvlans - use * the real device as the lowerdev. */ if (netif_is_macvlan(lowerdev)) lowerdev = macvlan_dev_real_dev(lowerdev); if (!tb[IFLA_MTU]) dev->mtu = lowerdev->mtu; else if (dev->mtu > lowerdev->mtu) return -EINVAL; /* MTU range: 68 - lowerdev->max_mtu */ dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = lowerdev->max_mtu; if (!tb[IFLA_ADDRESS]) eth_hw_addr_random(dev); if (!netif_is_macvlan_port(lowerdev)) { err = macvlan_port_create(lowerdev); if (err < 0) return err; create = true; } port = macvlan_port_get_rtnl(lowerdev); /* Only 1 macvlan device can be created in passthru mode */ if (macvlan_passthru(port)) { /* The macvlan port must be not created this time, * still goto destroy_macvlan_port for readability. */ err = -EINVAL; goto destroy_macvlan_port; } vlan->lowerdev = lowerdev; vlan->dev = dev; vlan->port = port; vlan->set_features = MACVLAN_FEATURES; vlan->mode = MACVLAN_MODE_VEPA; if (data && data[IFLA_MACVLAN_MODE]) vlan->mode = nla_get_u32(data[IFLA_MACVLAN_MODE]); if (data && data[IFLA_MACVLAN_FLAGS]) vlan->flags = nla_get_u16(data[IFLA_MACVLAN_FLAGS]); if (vlan->mode == MACVLAN_MODE_PASSTHRU) { if (port->count) { err = -EINVAL; goto destroy_macvlan_port; } macvlan_set_passthru(port); eth_hw_addr_inherit(dev, lowerdev); } if (data && data[IFLA_MACVLAN_MACADDR_MODE]) { if (vlan->mode != MACVLAN_MODE_SOURCE) { err = -EINVAL; goto destroy_macvlan_port; } macmode = nla_get_u32(data[IFLA_MACVLAN_MACADDR_MODE]); err = macvlan_changelink_sources(vlan, macmode, data); if (err) goto destroy_macvlan_port; } vlan->bc_queue_len_req = MACVLAN_DEFAULT_BC_QUEUE_LEN; if (data && data[IFLA_MACVLAN_BC_QUEUE_LEN]) vlan->bc_queue_len_req = nla_get_u32(data[IFLA_MACVLAN_BC_QUEUE_LEN]); if (data && data[IFLA_MACVLAN_BC_CUTOFF]) update_port_bc_cutoff( vlan, nla_get_s32(data[IFLA_MACVLAN_BC_CUTOFF])); err = register_netdevice(dev); if (err < 0) goto destroy_macvlan_port; dev->priv_flags |= IFF_MACVLAN; err = netdev_upper_dev_link(lowerdev, dev, extack); if (err) goto unregister_netdev; list_add_tail_rcu(&vlan->list, &port->vlans); update_port_bc_queue_len(vlan->port); netif_stacked_transfer_operstate(lowerdev, dev); linkwatch_fire_event(dev); return 0; unregister_netdev: /* macvlan_uninit would free the macvlan port */ unregister_netdevice(dev); return err; destroy_macvlan_port: /* the macvlan port may be freed by macvlan_uninit when fail to register. * so we destroy the macvlan port only when it's valid. */ if (create && macvlan_port_get_rtnl(lowerdev)) { macvlan_flush_sources(port, vlan); macvlan_port_destroy(port->dev); } return err; } EXPORT_SYMBOL_GPL(macvlan_common_newlink); static int macvlan_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { return macvlan_common_newlink(src_net, dev, tb, data, extack); } void macvlan_dellink(struct net_device *dev, struct list_head *head) { struct macvlan_dev *vlan = netdev_priv(dev); if (vlan->mode == MACVLAN_MODE_SOURCE) macvlan_flush_sources(vlan->port, vlan); list_del_rcu(&vlan->list); update_port_bc_queue_len(vlan->port); unregister_netdevice_queue(dev, head); netdev_upper_dev_unlink(vlan->lowerdev, dev); } EXPORT_SYMBOL_GPL(macvlan_dellink); static int macvlan_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct macvlan_dev *vlan = netdev_priv(dev); enum macvlan_mode mode; bool set_mode = false; enum macvlan_macaddr_mode macmode; int ret; /* Validate mode, but don't set yet: setting flags may fail. */ if (data && data[IFLA_MACVLAN_MODE]) { set_mode = true; mode = nla_get_u32(data[IFLA_MACVLAN_MODE]); /* Passthrough mode can't be set or cleared dynamically */ if ((mode == MACVLAN_MODE_PASSTHRU) != (vlan->mode == MACVLAN_MODE_PASSTHRU)) return -EINVAL; if (vlan->mode == MACVLAN_MODE_SOURCE && vlan->mode != mode) macvlan_flush_sources(vlan->port, vlan); } if (data && data[IFLA_MACVLAN_FLAGS]) { __u16 flags = nla_get_u16(data[IFLA_MACVLAN_FLAGS]); bool promisc = (flags ^ vlan->flags) & MACVLAN_FLAG_NOPROMISC; if (macvlan_passthru(vlan->port) && promisc) { int err; if (flags & MACVLAN_FLAG_NOPROMISC) err = dev_set_promiscuity(vlan->lowerdev, -1); else err = dev_set_promiscuity(vlan->lowerdev, 1); if (err < 0) return err; } vlan->flags = flags; } if (data && data[IFLA_MACVLAN_BC_QUEUE_LEN]) { vlan->bc_queue_len_req = nla_get_u32(data[IFLA_MACVLAN_BC_QUEUE_LEN]); update_port_bc_queue_len(vlan->port); } if (data && data[IFLA_MACVLAN_BC_CUTOFF]) update_port_bc_cutoff( vlan, nla_get_s32(data[IFLA_MACVLAN_BC_CUTOFF])); if (set_mode) vlan->mode = mode; if (data && data[IFLA_MACVLAN_MACADDR_MODE]) { if (vlan->mode != MACVLAN_MODE_SOURCE) return -EINVAL; macmode = nla_get_u32(data[IFLA_MACVLAN_MACADDR_MODE]); ret = macvlan_changelink_sources(vlan, macmode, data); if (ret) return ret; } return 0; } static size_t macvlan_get_size_mac(const struct macvlan_dev *vlan) { if (vlan->macaddr_count == 0) return 0; return nla_total_size(0) /* IFLA_MACVLAN_MACADDR_DATA */ + vlan->macaddr_count * nla_total_size(sizeof(u8) * ETH_ALEN); } static size_t macvlan_get_size(const struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); return (0 + nla_total_size(4) /* IFLA_MACVLAN_MODE */ + nla_total_size(2) /* IFLA_MACVLAN_FLAGS */ + nla_total_size(4) /* IFLA_MACVLAN_MACADDR_COUNT */ + macvlan_get_size_mac(vlan) /* IFLA_MACVLAN_MACADDR */ + nla_total_size(4) /* IFLA_MACVLAN_BC_QUEUE_LEN */ + nla_total_size(4) /* IFLA_MACVLAN_BC_QUEUE_LEN_USED */ ); } static int macvlan_fill_info_macaddr(struct sk_buff *skb, const struct macvlan_dev *vlan, const int i) { struct hlist_head *h = &vlan->port->vlan_source_hash[i]; struct macvlan_source_entry *entry; hlist_for_each_entry_rcu(entry, h, hlist, lockdep_rtnl_is_held()) { if (entry->vlan != vlan) continue; if (nla_put(skb, IFLA_MACVLAN_MACADDR, ETH_ALEN, entry->addr)) return 1; } return 0; } static int macvlan_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); struct macvlan_port *port = vlan->port; int i; struct nlattr *nest; if (nla_put_u32(skb, IFLA_MACVLAN_MODE, vlan->mode)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_MACVLAN_FLAGS, vlan->flags)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_MACVLAN_MACADDR_COUNT, vlan->macaddr_count)) goto nla_put_failure; if (vlan->macaddr_count > 0) { nest = nla_nest_start_noflag(skb, IFLA_MACVLAN_MACADDR_DATA); if (nest == NULL) goto nla_put_failure; for (i = 0; i < MACVLAN_HASH_SIZE; i++) { if (macvlan_fill_info_macaddr(skb, vlan, i)) goto nla_put_failure; } nla_nest_end(skb, nest); } if (nla_put_u32(skb, IFLA_MACVLAN_BC_QUEUE_LEN, vlan->bc_queue_len_req)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_MACVLAN_BC_QUEUE_LEN_USED, port->bc_queue_len_used)) goto nla_put_failure; if (port->bc_cutoff != 1 && nla_put_s32(skb, IFLA_MACVLAN_BC_CUTOFF, port->bc_cutoff)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static const struct nla_policy macvlan_policy[IFLA_MACVLAN_MAX + 1] = { [IFLA_MACVLAN_MODE] = { .type = NLA_U32 }, [IFLA_MACVLAN_FLAGS] = { .type = NLA_U16 }, [IFLA_MACVLAN_MACADDR_MODE] = { .type = NLA_U32 }, [IFLA_MACVLAN_MACADDR] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN }, [IFLA_MACVLAN_MACADDR_DATA] = { .type = NLA_NESTED }, [IFLA_MACVLAN_MACADDR_COUNT] = { .type = NLA_U32 }, [IFLA_MACVLAN_BC_QUEUE_LEN] = { .type = NLA_U32 }, [IFLA_MACVLAN_BC_QUEUE_LEN_USED] = { .type = NLA_REJECT }, [IFLA_MACVLAN_BC_CUTOFF] = { .type = NLA_S32 }, }; int macvlan_link_register(struct rtnl_link_ops *ops) { /* common fields */ ops->validate = macvlan_validate; ops->maxtype = IFLA_MACVLAN_MAX; ops->policy = macvlan_policy; ops->changelink = macvlan_changelink; ops->get_size = macvlan_get_size; ops->fill_info = macvlan_fill_info; return rtnl_link_register(ops); }; EXPORT_SYMBOL_GPL(macvlan_link_register); static struct net *macvlan_get_link_net(const struct net_device *dev) { return dev_net(macvlan_dev_real_dev(dev)); } static struct rtnl_link_ops macvlan_link_ops = { .kind = "macvlan", .setup = macvlan_setup, .newlink = macvlan_newlink, .dellink = macvlan_dellink, .get_link_net = macvlan_get_link_net, .priv_size = sizeof(struct macvlan_dev), }; static void update_port_bc_queue_len(struct macvlan_port *port) { u32 max_bc_queue_len_req = 0; struct macvlan_dev *vlan; list_for_each_entry(vlan, &port->vlans, list) { if (vlan->bc_queue_len_req > max_bc_queue_len_req) max_bc_queue_len_req = vlan->bc_queue_len_req; } port->bc_queue_len_used = max_bc_queue_len_req; } static int macvlan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct macvlan_dev *vlan, *next; struct macvlan_port *port; LIST_HEAD(list_kill); if (!netif_is_macvlan_port(dev)) return NOTIFY_DONE; port = macvlan_port_get_rtnl(dev); switch (event) { case NETDEV_UP: case NETDEV_DOWN: case NETDEV_CHANGE: list_for_each_entry(vlan, &port->vlans, list) netif_stacked_transfer_operstate(vlan->lowerdev, vlan->dev); break; case NETDEV_FEAT_CHANGE: list_for_each_entry(vlan, &port->vlans, list) { netif_inherit_tso_max(vlan->dev, dev); netdev_update_features(vlan->dev); } break; case NETDEV_CHANGEMTU: list_for_each_entry(vlan, &port->vlans, list) { if (vlan->dev->mtu <= dev->mtu) continue; dev_set_mtu(vlan->dev, dev->mtu); } break; case NETDEV_CHANGEADDR: if (!macvlan_passthru(port)) return NOTIFY_DONE; vlan = list_first_entry_or_null(&port->vlans, struct macvlan_dev, list); if (vlan && macvlan_sync_address(vlan->dev, dev->dev_addr)) return NOTIFY_BAD; break; case NETDEV_UNREGISTER: /* twiddle thumbs on netns device moves */ if (dev->reg_state != NETREG_UNREGISTERING) break; list_for_each_entry_safe(vlan, next, &port->vlans, list) vlan->dev->rtnl_link_ops->dellink(vlan->dev, &list_kill); unregister_netdevice_many(&list_kill); break; case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlying device to change its type. */ return NOTIFY_BAD; case NETDEV_NOTIFY_PEERS: case NETDEV_BONDING_FAILOVER: case NETDEV_RESEND_IGMP: /* Propagate to all vlans */ list_for_each_entry(vlan, &port->vlans, list) call_netdevice_notifiers(event, vlan->dev); } return NOTIFY_DONE; } static struct notifier_block macvlan_notifier_block __read_mostly = { .notifier_call = macvlan_device_event, }; static int __init macvlan_init_module(void) { int err; register_netdevice_notifier(&macvlan_notifier_block); err = macvlan_link_register(&macvlan_link_ops); if (err < 0) goto err1; return 0; err1: unregister_netdevice_notifier(&macvlan_notifier_block); return err; } static void __exit macvlan_cleanup_module(void) { rtnl_link_unregister(&macvlan_link_ops); unregister_netdevice_notifier(&macvlan_notifier_block); } module_init(macvlan_init_module); module_exit(macvlan_cleanup_module); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_DESCRIPTION("Driver for MAC address based VLANs"); MODULE_ALIAS_RTNL_LINK("macvlan"); |
| 4 91 95 97 20 8 8 42 14 9 9 56 1 2 4 43 41 3 24 11 11 17 42 10 16 47 756 574 1 1 12 189 19 266 12 259 256 258 1 112 62 69 111 1 258 3 3 1 3 2 3 5 5 5 1 97 98 96 97 97 97 97 96 97 98 2 97 97 96 97 97 1 96 97 2 2 1 1 1 1 92 90 93 92 73 27 93 5 1 4 4 1 4 93 27 71 95 4 29 9 9 1 1 7 1 2 3 3 1 3 3 1 1 2 2 1 2 3 3 1 8 8 8 1 1 6 5 1 2 2 1 1 2 1 1 1 1 1 14 14 14 29 27 1 27 1 27 27 27 25 9 25 6 5 1 21 5 2 24 25 2 26 20 24 3 26 25 9 17 16 17 16 5 15 16 10 22 1 3 2 1 1 11 9 14 14 21 7 26 27 20 20 2 4 8 6 6 71 68 1 70 71 69 69 69 3 1 8 8 1 29 20 879 785 68 20 206 204 25 216 218 172 63 202 36 194 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Neighbour Discovery for IPv6 * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * Mike Shaver <shaver@ingenia.com> */ /* * Changes: * * Alexey I. Froloff : RFC6106 (DNSSL) support * Pierre Ynard : export userland ND options * through netlink (RDNSS support) * Lars Fenneberg : fixed MTU setting on receipt * of an RA. * Janos Farkas : kmalloc failure checks * Alexey Kuznetsov : state machine reworked * and moved to net/core. * Pekka Savola : RFC2461 validation * YOSHIFUJI Hideaki @USAGI : Verify ND options properly */ #define pr_fmt(fmt) "ICMPv6: " fmt #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/sched.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/route.h> #include <linux/init.h> #include <linux/rcupdate.h> #include <linux/slab.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <linux/if_addr.h> #include <linux/if_ether.h> #include <linux/if_arp.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> #include <linux/jhash.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/ndisc.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/icmp.h> #include <net/netlink.h> #include <linux/rtnetlink.h> #include <net/flow.h> #include <net/ip6_checksum.h> #include <net/inet_common.h> #include <linux/proc_fs.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> static u32 ndisc_hash(const void *pkey, const struct net_device *dev, __u32 *hash_rnd); static bool ndisc_key_eq(const struct neighbour *neigh, const void *pkey); static bool ndisc_allow_add(const struct net_device *dev, struct netlink_ext_ack *extack); static int ndisc_constructor(struct neighbour *neigh); static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb); static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb); static int pndisc_constructor(struct pneigh_entry *n); static void pndisc_destructor(struct pneigh_entry *n); static void pndisc_redo(struct sk_buff *skb); static int ndisc_is_multicast(const void *pkey); static const struct neigh_ops ndisc_generic_ops = { .family = AF_INET6, .solicit = ndisc_solicit, .error_report = ndisc_error_report, .output = neigh_resolve_output, .connected_output = neigh_connected_output, }; static const struct neigh_ops ndisc_hh_ops = { .family = AF_INET6, .solicit = ndisc_solicit, .error_report = ndisc_error_report, .output = neigh_resolve_output, .connected_output = neigh_resolve_output, }; static const struct neigh_ops ndisc_direct_ops = { .family = AF_INET6, .output = neigh_direct_output, .connected_output = neigh_direct_output, }; struct neigh_table nd_tbl = { .family = AF_INET6, .key_len = sizeof(struct in6_addr), .protocol = cpu_to_be16(ETH_P_IPV6), .hash = ndisc_hash, .key_eq = ndisc_key_eq, .constructor = ndisc_constructor, .pconstructor = pndisc_constructor, .pdestructor = pndisc_destructor, .proxy_redo = pndisc_redo, .is_multicast = ndisc_is_multicast, .allow_add = ndisc_allow_add, .id = "ndisc_cache", .parms = { .tbl = &nd_tbl, .reachable_time = ND_REACHABLE_TIME, .data = { [NEIGH_VAR_MCAST_PROBES] = 3, [NEIGH_VAR_UCAST_PROBES] = 3, [NEIGH_VAR_RETRANS_TIME] = ND_RETRANS_TIMER, [NEIGH_VAR_BASE_REACHABLE_TIME] = ND_REACHABLE_TIME, [NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ, [NEIGH_VAR_INTERVAL_PROBE_TIME_MS] = 5 * HZ, [NEIGH_VAR_GC_STALETIME] = 60 * HZ, [NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_MAX, [NEIGH_VAR_PROXY_QLEN] = 64, [NEIGH_VAR_ANYCAST_DELAY] = 1 * HZ, [NEIGH_VAR_PROXY_DELAY] = (8 * HZ) / 10, }, }, .gc_interval = 30 * HZ, .gc_thresh1 = 128, .gc_thresh2 = 512, .gc_thresh3 = 1024, }; EXPORT_SYMBOL_GPL(nd_tbl); void __ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data, int data_len, int pad) { int space = __ndisc_opt_addr_space(data_len, pad); u8 *opt = skb_put(skb, space); opt[0] = type; opt[1] = space>>3; memset(opt + 2, 0, pad); opt += pad; space -= pad; memcpy(opt+2, data, data_len); data_len += 2; opt += data_len; space -= data_len; if (space > 0) memset(opt, 0, space); } EXPORT_SYMBOL_GPL(__ndisc_fill_addr_option); static inline void ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data, u8 icmp6_type) { __ndisc_fill_addr_option(skb, type, data, skb->dev->addr_len, ndisc_addr_option_pad(skb->dev->type)); ndisc_ops_fill_addr_option(skb->dev, skb, icmp6_type); } static inline void ndisc_fill_redirect_addr_option(struct sk_buff *skb, void *ha, const u8 *ops_data) { ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR, ha, NDISC_REDIRECT); ndisc_ops_fill_redirect_addr_option(skb->dev, skb, ops_data); } static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur, struct nd_opt_hdr *end) { int type; if (!cur || !end || cur >= end) return NULL; type = cur->nd_opt_type; do { cur = ((void *)cur) + (cur->nd_opt_len << 3); } while (cur < end && cur->nd_opt_type != type); return cur <= end && cur->nd_opt_type == type ? cur : NULL; } static inline int ndisc_is_useropt(const struct net_device *dev, struct nd_opt_hdr *opt) { return opt->nd_opt_type == ND_OPT_PREFIX_INFO || opt->nd_opt_type == ND_OPT_RDNSS || opt->nd_opt_type == ND_OPT_DNSSL || opt->nd_opt_type == ND_OPT_6CO || opt->nd_opt_type == ND_OPT_CAPTIVE_PORTAL || opt->nd_opt_type == ND_OPT_PREF64; } static struct nd_opt_hdr *ndisc_next_useropt(const struct net_device *dev, struct nd_opt_hdr *cur, struct nd_opt_hdr *end) { if (!cur || !end || cur >= end) return NULL; do { cur = ((void *)cur) + (cur->nd_opt_len << 3); } while (cur < end && !ndisc_is_useropt(dev, cur)); return cur <= end && ndisc_is_useropt(dev, cur) ? cur : NULL; } struct ndisc_options *ndisc_parse_options(const struct net_device *dev, u8 *opt, int opt_len, struct ndisc_options *ndopts) { struct nd_opt_hdr *nd_opt = (struct nd_opt_hdr *)opt; if (!nd_opt || opt_len < 0 || !ndopts) return NULL; memset(ndopts, 0, sizeof(*ndopts)); while (opt_len) { bool unknown = false; int l; if (opt_len < sizeof(struct nd_opt_hdr)) return NULL; l = nd_opt->nd_opt_len << 3; if (opt_len < l || l == 0) return NULL; if (ndisc_ops_parse_options(dev, nd_opt, ndopts)) goto next_opt; switch (nd_opt->nd_opt_type) { case ND_OPT_SOURCE_LL_ADDR: case ND_OPT_TARGET_LL_ADDR: case ND_OPT_MTU: case ND_OPT_NONCE: case ND_OPT_REDIRECT_HDR: if (ndopts->nd_opt_array[nd_opt->nd_opt_type]) { ND_PRINTK(2, warn, "%s: duplicated ND6 option found: type=%d\n", __func__, nd_opt->nd_opt_type); } else { ndopts->nd_opt_array[nd_opt->nd_opt_type] = nd_opt; } break; case ND_OPT_PREFIX_INFO: ndopts->nd_opts_pi_end = nd_opt; if (!ndopts->nd_opt_array[nd_opt->nd_opt_type]) ndopts->nd_opt_array[nd_opt->nd_opt_type] = nd_opt; break; #ifdef CONFIG_IPV6_ROUTE_INFO case ND_OPT_ROUTE_INFO: ndopts->nd_opts_ri_end = nd_opt; if (!ndopts->nd_opts_ri) ndopts->nd_opts_ri = nd_opt; break; #endif default: unknown = true; } if (ndisc_is_useropt(dev, nd_opt)) { ndopts->nd_useropts_end = nd_opt; if (!ndopts->nd_useropts) ndopts->nd_useropts = nd_opt; } else if (unknown) { /* * Unknown options must be silently ignored, * to accommodate future extension to the * protocol. */ ND_PRINTK(2, notice, "%s: ignored unsupported option; type=%d, len=%d\n", __func__, nd_opt->nd_opt_type, nd_opt->nd_opt_len); } next_opt: opt_len -= l; nd_opt = ((void *)nd_opt) + l; } return ndopts; } int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev, int dir) { switch (dev->type) { case ARPHRD_ETHER: case ARPHRD_IEEE802: /* Not sure. Check it later. --ANK */ case ARPHRD_FDDI: ipv6_eth_mc_map(addr, buf); return 0; case ARPHRD_ARCNET: ipv6_arcnet_mc_map(addr, buf); return 0; case ARPHRD_INFINIBAND: ipv6_ib_mc_map(addr, dev->broadcast, buf); return 0; case ARPHRD_IPGRE: return ipv6_ipgre_mc_map(addr, dev->broadcast, buf); default: if (dir) { memcpy(buf, dev->broadcast, dev->addr_len); return 0; } } return -EINVAL; } EXPORT_SYMBOL(ndisc_mc_map); static u32 ndisc_hash(const void *pkey, const struct net_device *dev, __u32 *hash_rnd) { return ndisc_hashfn(pkey, dev, hash_rnd); } static bool ndisc_key_eq(const struct neighbour *n, const void *pkey) { return neigh_key_eq128(n, pkey); } static int ndisc_constructor(struct neighbour *neigh) { struct in6_addr *addr = (struct in6_addr *)&neigh->primary_key; struct net_device *dev = neigh->dev; struct inet6_dev *in6_dev; struct neigh_parms *parms; bool is_multicast = ipv6_addr_is_multicast(addr); in6_dev = in6_dev_get(dev); if (!in6_dev) { return -EINVAL; } parms = in6_dev->nd_parms; __neigh_parms_put(neigh->parms); neigh->parms = neigh_parms_clone(parms); neigh->type = is_multicast ? RTN_MULTICAST : RTN_UNICAST; if (!dev->header_ops) { neigh->nud_state = NUD_NOARP; neigh->ops = &ndisc_direct_ops; neigh->output = neigh_direct_output; } else { if (is_multicast) { neigh->nud_state = NUD_NOARP; ndisc_mc_map(addr, neigh->ha, dev, 1); } else if (dev->flags&(IFF_NOARP|IFF_LOOPBACK)) { neigh->nud_state = NUD_NOARP; memcpy(neigh->ha, dev->dev_addr, dev->addr_len); if (dev->flags&IFF_LOOPBACK) neigh->type = RTN_LOCAL; } else if (dev->flags&IFF_POINTOPOINT) { neigh->nud_state = NUD_NOARP; memcpy(neigh->ha, dev->broadcast, dev->addr_len); } if (dev->header_ops->cache) neigh->ops = &ndisc_hh_ops; else neigh->ops = &ndisc_generic_ops; if (neigh->nud_state&NUD_VALID) neigh->output = neigh->ops->connected_output; else neigh->output = neigh->ops->output; } in6_dev_put(in6_dev); return 0; } static int pndisc_constructor(struct pneigh_entry *n) { struct in6_addr *addr = (struct in6_addr *)&n->key; struct in6_addr maddr; struct net_device *dev = n->dev; if (!dev || !__in6_dev_get(dev)) return -EINVAL; addrconf_addr_solict_mult(addr, &maddr); ipv6_dev_mc_inc(dev, &maddr); return 0; } static void pndisc_destructor(struct pneigh_entry *n) { struct in6_addr *addr = (struct in6_addr *)&n->key; struct in6_addr maddr; struct net_device *dev = n->dev; if (!dev || !__in6_dev_get(dev)) return; addrconf_addr_solict_mult(addr, &maddr); ipv6_dev_mc_dec(dev, &maddr); } /* called with rtnl held */ static bool ndisc_allow_add(const struct net_device *dev, struct netlink_ext_ack *extack) { struct inet6_dev *idev = __in6_dev_get(dev); if (!idev || idev->cnf.disable_ipv6) { NL_SET_ERR_MSG(extack, "IPv6 is disabled on this device"); return false; } return true; } static struct sk_buff *ndisc_alloc_skb(struct net_device *dev, int len) { int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; struct sock *sk = dev_net(dev)->ipv6.ndisc_sk; struct sk_buff *skb; skb = alloc_skb(hlen + sizeof(struct ipv6hdr) + len + tlen, GFP_ATOMIC); if (!skb) { ND_PRINTK(0, err, "ndisc: %s failed to allocate an skb\n", __func__); return NULL; } skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; skb_reserve(skb, hlen + sizeof(struct ipv6hdr)); skb_reset_transport_header(skb); /* Manually assign socket ownership as we avoid calling * sock_alloc_send_pskb() to bypass wmem buffer limits */ skb_set_owner_w(skb, sk); return skb; } static void ip6_nd_hdr(struct sk_buff *skb, const struct in6_addr *saddr, const struct in6_addr *daddr, int hop_limit, int len) { struct ipv6hdr *hdr; struct inet6_dev *idev; unsigned tclass; rcu_read_lock(); idev = __in6_dev_get(skb->dev); tclass = idev ? READ_ONCE(idev->cnf.ndisc_tclass) : 0; rcu_read_unlock(); skb_push(skb, sizeof(*hdr)); skb_reset_network_header(skb); hdr = ipv6_hdr(skb); ip6_flow_hdr(hdr, tclass, 0); hdr->payload_len = htons(len); hdr->nexthdr = IPPROTO_ICMPV6; hdr->hop_limit = hop_limit; hdr->saddr = *saddr; hdr->daddr = *daddr; } void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr, const struct in6_addr *saddr) { struct dst_entry *dst = skb_dst(skb); struct net *net = dev_net(skb->dev); struct sock *sk = net->ipv6.ndisc_sk; struct inet6_dev *idev; int err; struct icmp6hdr *icmp6h = icmp6_hdr(skb); u8 type; type = icmp6h->icmp6_type; if (!dst) { struct flowi6 fl6; int oif = skb->dev->ifindex; icmpv6_flow_init(sk, &fl6, type, saddr, daddr, oif); dst = icmp6_dst_alloc(skb->dev, &fl6); if (IS_ERR(dst)) { kfree_skb(skb); return; } skb_dst_set(skb, dst); } icmp6h->icmp6_cksum = csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_ICMPV6, csum_partial(icmp6h, skb->len, 0)); ip6_nd_hdr(skb, saddr, daddr, READ_ONCE(inet6_sk(sk)->hop_limit), skb->len); rcu_read_lock(); idev = __in6_dev_get(dst->dev); IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, dst->dev, dst_output); if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } rcu_read_unlock(); } EXPORT_SYMBOL(ndisc_send_skb); void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr, const struct in6_addr *solicited_addr, bool router, bool solicited, bool override, bool inc_opt) { struct sk_buff *skb; struct in6_addr tmpaddr; struct inet6_ifaddr *ifp; const struct in6_addr *src_addr; struct nd_msg *msg; int optlen = 0; /* for anycast or proxy, solicited_addr != src_addr */ ifp = ipv6_get_ifaddr(dev_net(dev), solicited_addr, dev, 1); if (ifp) { src_addr = solicited_addr; if (ifp->flags & IFA_F_OPTIMISTIC) override = false; inc_opt |= READ_ONCE(ifp->idev->cnf.force_tllao); in6_ifa_put(ifp); } else { if (ipv6_dev_get_saddr(dev_net(dev), dev, daddr, inet6_sk(dev_net(dev)->ipv6.ndisc_sk)->srcprefs, &tmpaddr)) return; src_addr = &tmpaddr; } if (!dev->addr_len) inc_opt = false; if (inc_opt) optlen += ndisc_opt_addr_space(dev, NDISC_NEIGHBOUR_ADVERTISEMENT); skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); if (!skb) return; msg = skb_put(skb, sizeof(*msg)); *msg = (struct nd_msg) { .icmph = { .icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT, .icmp6_router = router, .icmp6_solicited = solicited, .icmp6_override = override, }, .target = *solicited_addr, }; if (inc_opt) ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR, dev->dev_addr, NDISC_NEIGHBOUR_ADVERTISEMENT); ndisc_send_skb(skb, daddr, src_addr); } static void ndisc_send_unsol_na(struct net_device *dev) { struct inet6_dev *idev; struct inet6_ifaddr *ifa; idev = in6_dev_get(dev); if (!idev) return; read_lock_bh(&idev->lock); list_for_each_entry(ifa, &idev->addr_list, if_list) { /* skip tentative addresses until dad completes */ if (ifa->flags & IFA_F_TENTATIVE && !(ifa->flags & IFA_F_OPTIMISTIC)) continue; ndisc_send_na(dev, &in6addr_linklocal_allnodes, &ifa->addr, /*router=*/ !!idev->cnf.forwarding, /*solicited=*/ false, /*override=*/ true, /*inc_opt=*/ true); } read_unlock_bh(&idev->lock); in6_dev_put(idev); } struct sk_buff *ndisc_ns_create(struct net_device *dev, const struct in6_addr *solicit, const struct in6_addr *saddr, u64 nonce) { int inc_opt = dev->addr_len; struct sk_buff *skb; struct nd_msg *msg; int optlen = 0; if (!saddr) return NULL; if (ipv6_addr_any(saddr)) inc_opt = false; if (inc_opt) optlen += ndisc_opt_addr_space(dev, NDISC_NEIGHBOUR_SOLICITATION); if (nonce != 0) optlen += 8; skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); if (!skb) return NULL; msg = skb_put(skb, sizeof(*msg)); *msg = (struct nd_msg) { .icmph = { .icmp6_type = NDISC_NEIGHBOUR_SOLICITATION, }, .target = *solicit, }; if (inc_opt) ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR, dev->dev_addr, NDISC_NEIGHBOUR_SOLICITATION); if (nonce != 0) { u8 *opt = skb_put(skb, 8); opt[0] = ND_OPT_NONCE; opt[1] = 8 >> 3; memcpy(opt + 2, &nonce, 6); } return skb; } EXPORT_SYMBOL(ndisc_ns_create); void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit, const struct in6_addr *daddr, const struct in6_addr *saddr, u64 nonce) { struct in6_addr addr_buf; struct sk_buff *skb; if (!saddr) { if (ipv6_get_lladdr(dev, &addr_buf, (IFA_F_TENTATIVE | IFA_F_OPTIMISTIC))) return; saddr = &addr_buf; } skb = ndisc_ns_create(dev, solicit, saddr, nonce); if (skb) ndisc_send_skb(skb, daddr, saddr); } void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr) { struct sk_buff *skb; struct rs_msg *msg; int send_sllao = dev->addr_len; int optlen = 0; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD /* * According to section 2.2 of RFC 4429, we must not * send router solicitations with a sllao from * optimistic addresses, but we may send the solicitation * if we don't include the sllao. So here we check * if our address is optimistic, and if so, we * suppress the inclusion of the sllao. */ if (send_sllao) { struct inet6_ifaddr *ifp = ipv6_get_ifaddr(dev_net(dev), saddr, dev, 1); if (ifp) { if (ifp->flags & IFA_F_OPTIMISTIC) { send_sllao = 0; } in6_ifa_put(ifp); } else { send_sllao = 0; } } #endif if (send_sllao) optlen += ndisc_opt_addr_space(dev, NDISC_ROUTER_SOLICITATION); skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); if (!skb) return; msg = skb_put(skb, sizeof(*msg)); *msg = (struct rs_msg) { .icmph = { .icmp6_type = NDISC_ROUTER_SOLICITATION, }, }; if (send_sllao) ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR, dev->dev_addr, NDISC_ROUTER_SOLICITATION); ndisc_send_skb(skb, daddr, saddr); } static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb) { /* * "The sender MUST return an ICMP * destination unreachable" */ dst_link_failure(skb); kfree_skb(skb); } /* Called with locked neigh: either read or both */ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb) { struct in6_addr *saddr = NULL; struct in6_addr mcaddr; struct net_device *dev = neigh->dev; struct in6_addr *target = (struct in6_addr *)&neigh->primary_key; int probes = atomic_read(&neigh->probes); if (skb && ipv6_chk_addr_and_flags(dev_net(dev), &ipv6_hdr(skb)->saddr, dev, false, 1, IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)) saddr = &ipv6_hdr(skb)->saddr; probes -= NEIGH_VAR(neigh->parms, UCAST_PROBES); if (probes < 0) { if (!(READ_ONCE(neigh->nud_state) & NUD_VALID)) { ND_PRINTK(1, dbg, "%s: trying to ucast probe in NUD_INVALID: %pI6\n", __func__, target); } ndisc_send_ns(dev, target, target, saddr, 0); } else if ((probes -= NEIGH_VAR(neigh->parms, APP_PROBES)) < 0) { neigh_app_ns(neigh); } else { addrconf_addr_solict_mult(target, &mcaddr); ndisc_send_ns(dev, target, &mcaddr, saddr, 0); } } static int pndisc_is_router(const void *pkey, struct net_device *dev) { struct pneigh_entry *n; int ret = -1; read_lock_bh(&nd_tbl.lock); n = __pneigh_lookup(&nd_tbl, dev_net(dev), pkey, dev); if (n) ret = !!(n->flags & NTF_ROUTER); read_unlock_bh(&nd_tbl.lock); return ret; } void ndisc_update(const struct net_device *dev, struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u8 icmp6_type, struct ndisc_options *ndopts) { neigh_update(neigh, lladdr, new, flags, 0); /* report ndisc ops about neighbour update */ ndisc_ops_update(dev, neigh, flags, icmp6_type, ndopts); } static enum skb_drop_reason ndisc_recv_ns(struct sk_buff *skb) { struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb); const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr; u8 *lladdr = NULL; u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + offsetof(struct nd_msg, opt)); struct ndisc_options ndopts; struct net_device *dev = skb->dev; struct inet6_ifaddr *ifp; struct inet6_dev *idev = NULL; struct neighbour *neigh; int dad = ipv6_addr_any(saddr); int is_router = -1; SKB_DR(reason); u64 nonce = 0; bool inc; if (skb->len < sizeof(struct nd_msg)) return SKB_DROP_REASON_PKT_TOO_SMALL; if (ipv6_addr_is_multicast(&msg->target)) { ND_PRINTK(2, warn, "NS: multicast target address\n"); return reason; } /* * RFC2461 7.1.1: * DAD has to be destined for solicited node multicast address. */ if (dad && !ipv6_addr_is_solict_mult(daddr)) { ND_PRINTK(2, warn, "NS: bad DAD packet (wrong destination)\n"); return reason; } if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts)) return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS; if (ndopts.nd_opts_src_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr, dev); if (!lladdr) { ND_PRINTK(2, warn, "NS: invalid link-layer address length\n"); return reason; } /* RFC2461 7.1.1: * If the IP source address is the unspecified address, * there MUST NOT be source link-layer address option * in the message. */ if (dad) { ND_PRINTK(2, warn, "NS: bad DAD packet (link-layer address option)\n"); return reason; } } if (ndopts.nd_opts_nonce && ndopts.nd_opts_nonce->nd_opt_len == 1) memcpy(&nonce, (u8 *)(ndopts.nd_opts_nonce + 1), 6); inc = ipv6_addr_is_multicast(daddr); ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1); if (ifp) { have_ifp: if (ifp->flags & (IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)) { if (dad) { if (nonce != 0 && ifp->dad_nonce == nonce) { u8 *np = (u8 *)&nonce; /* Matching nonce if looped back */ ND_PRINTK(2, notice, "%s: IPv6 DAD loopback for address %pI6c nonce %pM ignored\n", ifp->idev->dev->name, &ifp->addr, np); goto out; } /* * We are colliding with another node * who is doing DAD * so fail our DAD process */ addrconf_dad_failure(skb, ifp); return reason; } else { /* * This is not a dad solicitation. * If we are an optimistic node, * we should respond. * Otherwise, we should ignore it. */ if (!(ifp->flags & IFA_F_OPTIMISTIC)) goto out; } } idev = ifp->idev; } else { struct net *net = dev_net(dev); /* perhaps an address on the master device */ if (netif_is_l3_slave(dev)) { struct net_device *mdev; mdev = netdev_master_upper_dev_get_rcu(dev); if (mdev) { ifp = ipv6_get_ifaddr(net, &msg->target, mdev, 1); if (ifp) goto have_ifp; } } idev = in6_dev_get(dev); if (!idev) { /* XXX: count this drop? */ return reason; } if (ipv6_chk_acast_addr(net, dev, &msg->target) || (READ_ONCE(idev->cnf.forwarding) && (READ_ONCE(net->ipv6.devconf_all->proxy_ndp) || READ_ONCE(idev->cnf.proxy_ndp)) && (is_router = pndisc_is_router(&msg->target, dev)) >= 0)) { if (!(NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED) && skb->pkt_type != PACKET_HOST && inc && NEIGH_VAR(idev->nd_parms, PROXY_DELAY) != 0) { /* * for anycast or proxy, * sender should delay its response * by a random time between 0 and * MAX_ANYCAST_DELAY_TIME seconds. * (RFC2461) -- yoshfuji */ struct sk_buff *n = skb_clone(skb, GFP_ATOMIC); if (n) pneigh_enqueue(&nd_tbl, idev->nd_parms, n); goto out; } } else { SKB_DR_SET(reason, IPV6_NDISC_NS_OTHERHOST); goto out; } } if (is_router < 0) is_router = READ_ONCE(idev->cnf.forwarding); if (dad) { ndisc_send_na(dev, &in6addr_linklocal_allnodes, &msg->target, !!is_router, false, (ifp != NULL), true); goto out; } if (inc) NEIGH_CACHE_STAT_INC(&nd_tbl, rcv_probes_mcast); else NEIGH_CACHE_STAT_INC(&nd_tbl, rcv_probes_ucast); /* * update / create cache entry * for the source address */ neigh = __neigh_lookup(&nd_tbl, saddr, dev, !inc || lladdr || !dev->addr_len); if (neigh) ndisc_update(dev, neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE, NDISC_NEIGHBOUR_SOLICITATION, &ndopts); if (neigh || !dev->header_ops) { ndisc_send_na(dev, saddr, &msg->target, !!is_router, true, (ifp != NULL && inc), inc); if (neigh) neigh_release(neigh); reason = SKB_CONSUMED; } out: if (ifp) in6_ifa_put(ifp); else in6_dev_put(idev); return reason; } static int accept_untracked_na(struct net_device *dev, struct in6_addr *saddr) { struct inet6_dev *idev = __in6_dev_get(dev); switch (READ_ONCE(idev->cnf.accept_untracked_na)) { case 0: /* Don't accept untracked na (absent in neighbor cache) */ return 0; case 1: /* Create new entries from na if currently untracked */ return 1; case 2: /* Create new entries from untracked na only if saddr is in the * same subnet as an address configured on the interface that * received the na */ return !!ipv6_chk_prefix(saddr, dev); default: return 0; } } static enum skb_drop_reason ndisc_recv_na(struct sk_buff *skb) { struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb); struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr; u8 *lladdr = NULL; u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + offsetof(struct nd_msg, opt)); struct ndisc_options ndopts; struct net_device *dev = skb->dev; struct inet6_dev *idev = __in6_dev_get(dev); struct inet6_ifaddr *ifp; struct neighbour *neigh; SKB_DR(reason); u8 new_state; if (skb->len < sizeof(struct nd_msg)) return SKB_DROP_REASON_PKT_TOO_SMALL; if (ipv6_addr_is_multicast(&msg->target)) { ND_PRINTK(2, warn, "NA: target address is multicast\n"); return reason; } if (ipv6_addr_is_multicast(daddr) && msg->icmph.icmp6_solicited) { ND_PRINTK(2, warn, "NA: solicited NA is multicasted\n"); return reason; } /* For some 802.11 wireless deployments (and possibly other networks), * there will be a NA proxy and unsolicitd packets are attacks * and thus should not be accepted. * drop_unsolicited_na takes precedence over accept_untracked_na */ if (!msg->icmph.icmp6_solicited && idev && READ_ONCE(idev->cnf.drop_unsolicited_na)) return reason; if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts)) return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS; if (ndopts.nd_opts_tgt_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_tgt_lladdr, dev); if (!lladdr) { ND_PRINTK(2, warn, "NA: invalid link-layer address length\n"); return reason; } } ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1); if (ifp) { if (skb->pkt_type != PACKET_LOOPBACK && (ifp->flags & IFA_F_TENTATIVE)) { addrconf_dad_failure(skb, ifp); return reason; } /* What should we make now? The advertisement is invalid, but ndisc specs say nothing about it. It could be misconfiguration, or an smart proxy agent tries to help us :-) We should not print the error if NA has been received from loopback - it is just our own unsolicited advertisement. */ if (skb->pkt_type != PACKET_LOOPBACK) ND_PRINTK(1, warn, "NA: %pM advertised our address %pI6c on %s!\n", eth_hdr(skb)->h_source, &ifp->addr, ifp->idev->dev->name); in6_ifa_put(ifp); return reason; } neigh = neigh_lookup(&nd_tbl, &msg->target, dev); /* RFC 9131 updates original Neighbour Discovery RFC 4861. * NAs with Target LL Address option without a corresponding * entry in the neighbour cache can now create a STALE neighbour * cache entry on routers. * * entry accept fwding solicited behaviour * ------- ------ ------ --------- ---------------------- * present X X 0 Set state to STALE * present X X 1 Set state to REACHABLE * absent 0 X X Do nothing * absent 1 0 X Do nothing * absent 1 1 X Add a new STALE entry * * Note that we don't do a (daddr == all-routers-mcast) check. */ new_state = msg->icmph.icmp6_solicited ? NUD_REACHABLE : NUD_STALE; if (!neigh && lladdr && idev && READ_ONCE(idev->cnf.forwarding)) { if (accept_untracked_na(dev, saddr)) { neigh = neigh_create(&nd_tbl, &msg->target, dev); new_state = NUD_STALE; } } if (neigh && !IS_ERR(neigh)) { u8 old_flags = neigh->flags; struct net *net = dev_net(dev); if (READ_ONCE(neigh->nud_state) & NUD_FAILED) goto out; /* * Don't update the neighbor cache entry on a proxy NA from * ourselves because either the proxied node is off link or it * has already sent a NA to us. */ if (lladdr && !memcmp(lladdr, dev->dev_addr, dev->addr_len) && READ_ONCE(net->ipv6.devconf_all->forwarding) && READ_ONCE(net->ipv6.devconf_all->proxy_ndp) && pneigh_lookup(&nd_tbl, net, &msg->target, dev, 0)) { /* XXX: idev->cnf.proxy_ndp */ goto out; } ndisc_update(dev, neigh, lladdr, new_state, NEIGH_UPDATE_F_WEAK_OVERRIDE| (msg->icmph.icmp6_override ? NEIGH_UPDATE_F_OVERRIDE : 0)| NEIGH_UPDATE_F_OVERRIDE_ISROUTER| (msg->icmph.icmp6_router ? NEIGH_UPDATE_F_ISROUTER : 0), NDISC_NEIGHBOUR_ADVERTISEMENT, &ndopts); if ((old_flags & ~neigh->flags) & NTF_ROUTER) { /* * Change: router to host */ rt6_clean_tohost(dev_net(dev), saddr); } reason = SKB_CONSUMED; out: neigh_release(neigh); } return reason; } static enum skb_drop_reason ndisc_recv_rs(struct sk_buff *skb) { struct rs_msg *rs_msg = (struct rs_msg *)skb_transport_header(skb); unsigned long ndoptlen = skb->len - sizeof(*rs_msg); struct neighbour *neigh; struct inet6_dev *idev; const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; struct ndisc_options ndopts; u8 *lladdr = NULL; SKB_DR(reason); if (skb->len < sizeof(*rs_msg)) return SKB_DROP_REASON_PKT_TOO_SMALL; idev = __in6_dev_get(skb->dev); if (!idev) { ND_PRINTK(1, err, "RS: can't find in6 device\n"); return reason; } /* Don't accept RS if we're not in router mode */ if (!READ_ONCE(idev->cnf.forwarding)) goto out; /* * Don't update NCE if src = ::; * this implies that the source node has no ip address assigned yet. */ if (ipv6_addr_any(saddr)) goto out; /* Parse ND options */ if (!ndisc_parse_options(skb->dev, rs_msg->opt, ndoptlen, &ndopts)) return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS; if (ndopts.nd_opts_src_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr, skb->dev); if (!lladdr) goto out; } neigh = __neigh_lookup(&nd_tbl, saddr, skb->dev, 1); if (neigh) { ndisc_update(skb->dev, neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE_ISROUTER, NDISC_ROUTER_SOLICITATION, &ndopts); neigh_release(neigh); reason = SKB_CONSUMED; } out: return reason; } static void ndisc_ra_useropt(struct sk_buff *ra, struct nd_opt_hdr *opt) { struct icmp6hdr *icmp6h = (struct icmp6hdr *)skb_transport_header(ra); struct sk_buff *skb; struct nlmsghdr *nlh; struct nduseroptmsg *ndmsg; struct net *net = dev_net(ra->dev); int err; int base_size = NLMSG_ALIGN(sizeof(struct nduseroptmsg) + (opt->nd_opt_len << 3)); size_t msg_size = base_size + nla_total_size(sizeof(struct in6_addr)); skb = nlmsg_new(msg_size, GFP_ATOMIC); if (!skb) { err = -ENOBUFS; goto errout; } nlh = nlmsg_put(skb, 0, 0, RTM_NEWNDUSEROPT, base_size, 0); if (!nlh) { goto nla_put_failure; } ndmsg = nlmsg_data(nlh); ndmsg->nduseropt_family = AF_INET6; ndmsg->nduseropt_ifindex = ra->dev->ifindex; ndmsg->nduseropt_icmp_type = icmp6h->icmp6_type; ndmsg->nduseropt_icmp_code = icmp6h->icmp6_code; ndmsg->nduseropt_opts_len = opt->nd_opt_len << 3; memcpy(ndmsg + 1, opt, opt->nd_opt_len << 3); if (nla_put_in6_addr(skb, NDUSEROPT_SRCADDR, &ipv6_hdr(ra)->saddr)) goto nla_put_failure; nlmsg_end(skb, nlh); rtnl_notify(skb, net, 0, RTNLGRP_ND_USEROPT, NULL, GFP_ATOMIC); return; nla_put_failure: nlmsg_free(skb); err = -EMSGSIZE; errout: rtnl_set_sk_err(net, RTNLGRP_ND_USEROPT, err); } static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb) { struct ra_msg *ra_msg = (struct ra_msg *)skb_transport_header(skb); bool send_ifinfo_notify = false; struct neighbour *neigh = NULL; struct ndisc_options ndopts; struct fib6_info *rt = NULL; struct inet6_dev *in6_dev; struct fib6_table *table; u32 defrtr_usr_metric; unsigned int pref = 0; __u32 old_if_flags; struct net *net; SKB_DR(reason); int lifetime; int optlen; __u8 *opt = (__u8 *)(ra_msg + 1); optlen = (skb_tail_pointer(skb) - skb_transport_header(skb)) - sizeof(struct ra_msg); ND_PRINTK(2, info, "RA: %s, dev: %s\n", __func__, skb->dev->name); if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) { ND_PRINTK(2, warn, "RA: source address is not link-local\n"); return reason; } if (optlen < 0) return SKB_DROP_REASON_PKT_TOO_SMALL; #ifdef CONFIG_IPV6_NDISC_NODETYPE if (skb->ndisc_nodetype == NDISC_NODETYPE_HOST) { ND_PRINTK(2, warn, "RA: from host or unauthorized router\n"); return reason; } #endif in6_dev = __in6_dev_get(skb->dev); if (!in6_dev) { ND_PRINTK(0, err, "RA: can't find inet6 device for %s\n", skb->dev->name); return reason; } if (!ndisc_parse_options(skb->dev, opt, optlen, &ndopts)) return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS; if (!ipv6_accept_ra(in6_dev)) { ND_PRINTK(2, info, "RA: %s, did not accept ra for dev: %s\n", __func__, skb->dev->name); goto skip_linkparms; } #ifdef CONFIG_IPV6_NDISC_NODETYPE /* skip link-specific parameters from interior routers */ if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) { ND_PRINTK(2, info, "RA: %s, nodetype is NODEFAULT, dev: %s\n", __func__, skb->dev->name); goto skip_linkparms; } #endif if (in6_dev->if_flags & IF_RS_SENT) { /* * flag that an RA was received after an RS was sent * out on this interface. */ in6_dev->if_flags |= IF_RA_RCVD; } /* * Remember the managed/otherconf flags from most recently * received RA message (RFC 2462) -- yoshfuji */ old_if_flags = in6_dev->if_flags; in6_dev->if_flags = (in6_dev->if_flags & ~(IF_RA_MANAGED | IF_RA_OTHERCONF)) | (ra_msg->icmph.icmp6_addrconf_managed ? IF_RA_MANAGED : 0) | (ra_msg->icmph.icmp6_addrconf_other ? IF_RA_OTHERCONF : 0); if (old_if_flags != in6_dev->if_flags) send_ifinfo_notify = true; if (!READ_ONCE(in6_dev->cnf.accept_ra_defrtr)) { ND_PRINTK(2, info, "RA: %s, defrtr is false for dev: %s\n", __func__, skb->dev->name); goto skip_defrtr; } lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime); if (lifetime != 0 && lifetime < READ_ONCE(in6_dev->cnf.accept_ra_min_lft)) { ND_PRINTK(2, info, "RA: router lifetime (%ds) is too short: %s\n", lifetime, skb->dev->name); goto skip_defrtr; } /* Do not accept RA with source-addr found on local machine unless * accept_ra_from_local is set to true. */ net = dev_net(in6_dev->dev); if (!READ_ONCE(in6_dev->cnf.accept_ra_from_local) && ipv6_chk_addr(net, &ipv6_hdr(skb)->saddr, in6_dev->dev, 0)) { ND_PRINTK(2, info, "RA from local address detected on dev: %s: default router ignored\n", skb->dev->name); goto skip_defrtr; } #ifdef CONFIG_IPV6_ROUTER_PREF pref = ra_msg->icmph.icmp6_router_pref; /* 10b is handled as if it were 00b (medium) */ if (pref == ICMPV6_ROUTER_PREF_INVALID || !READ_ONCE(in6_dev->cnf.accept_ra_rtr_pref)) pref = ICMPV6_ROUTER_PREF_MEDIUM; #endif /* routes added from RAs do not use nexthop objects */ rt = rt6_get_dflt_router(net, &ipv6_hdr(skb)->saddr, skb->dev); if (rt) { neigh = ip6_neigh_lookup(&rt->fib6_nh->fib_nh_gw6, rt->fib6_nh->fib_nh_dev, NULL, &ipv6_hdr(skb)->saddr); if (!neigh) { ND_PRINTK(0, err, "RA: %s got default router without neighbour\n", __func__); fib6_info_release(rt); return reason; } } /* Set default route metric as specified by user */ defrtr_usr_metric = in6_dev->cnf.ra_defrtr_metric; /* delete the route if lifetime is 0 or if metric needs change */ if (rt && (lifetime == 0 || rt->fib6_metric != defrtr_usr_metric)) { ip6_del_rt(net, rt, false); rt = NULL; } ND_PRINTK(3, info, "RA: rt: %p lifetime: %d, metric: %d, for dev: %s\n", rt, lifetime, defrtr_usr_metric, skb->dev->name); if (!rt && lifetime) { ND_PRINTK(3, info, "RA: adding default router\n"); if (neigh) neigh_release(neigh); rt = rt6_add_dflt_router(net, &ipv6_hdr(skb)->saddr, skb->dev, pref, defrtr_usr_metric, lifetime); if (!rt) { ND_PRINTK(0, err, "RA: %s failed to add default route\n", __func__); return reason; } neigh = ip6_neigh_lookup(&rt->fib6_nh->fib_nh_gw6, rt->fib6_nh->fib_nh_dev, NULL, &ipv6_hdr(skb)->saddr); if (!neigh) { ND_PRINTK(0, err, "RA: %s got default router without neighbour\n", __func__); fib6_info_release(rt); return reason; } neigh->flags |= NTF_ROUTER; } else if (rt && IPV6_EXTRACT_PREF(rt->fib6_flags) != pref) { struct nl_info nlinfo = { .nl_net = net, }; rt->fib6_flags = (rt->fib6_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); inet6_rt_notify(RTM_NEWROUTE, rt, &nlinfo, NLM_F_REPLACE); } if (rt) { table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); fib6_set_expires(rt, jiffies + (HZ * lifetime)); fib6_add_gc_list(rt); spin_unlock_bh(&table->tb6_lock); } if (READ_ONCE(in6_dev->cnf.accept_ra_min_hop_limit) < 256 && ra_msg->icmph.icmp6_hop_limit) { if (READ_ONCE(in6_dev->cnf.accept_ra_min_hop_limit) <= ra_msg->icmph.icmp6_hop_limit) { WRITE_ONCE(in6_dev->cnf.hop_limit, ra_msg->icmph.icmp6_hop_limit); fib6_metric_set(rt, RTAX_HOPLIMIT, ra_msg->icmph.icmp6_hop_limit); } else { ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than minimum\n"); } } skip_defrtr: /* * Update Reachable Time and Retrans Timer */ if (in6_dev->nd_parms) { unsigned long rtime = ntohl(ra_msg->retrans_timer); if (rtime && rtime/1000 < MAX_SCHEDULE_TIMEOUT/HZ) { rtime = (rtime*HZ)/1000; if (rtime < HZ/100) rtime = HZ/100; NEIGH_VAR_SET(in6_dev->nd_parms, RETRANS_TIME, rtime); in6_dev->tstamp = jiffies; send_ifinfo_notify = true; } rtime = ntohl(ra_msg->reachable_time); if (rtime && rtime/1000 < MAX_SCHEDULE_TIMEOUT/(3*HZ)) { rtime = (rtime*HZ)/1000; if (rtime < HZ/10) rtime = HZ/10; if (rtime != NEIGH_VAR(in6_dev->nd_parms, BASE_REACHABLE_TIME)) { NEIGH_VAR_SET(in6_dev->nd_parms, BASE_REACHABLE_TIME, rtime); NEIGH_VAR_SET(in6_dev->nd_parms, GC_STALETIME, 3 * rtime); in6_dev->nd_parms->reachable_time = neigh_rand_reach_time(rtime); in6_dev->tstamp = jiffies; send_ifinfo_notify = true; } } } skip_linkparms: /* * Process options. */ if (!neigh) neigh = __neigh_lookup(&nd_tbl, &ipv6_hdr(skb)->saddr, skb->dev, 1); if (neigh) { u8 *lladdr = NULL; if (ndopts.nd_opts_src_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr, skb->dev); if (!lladdr) { ND_PRINTK(2, warn, "RA: invalid link-layer address length\n"); goto out; } } ndisc_update(skb->dev, neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE_ISROUTER| NEIGH_UPDATE_F_ISROUTER, NDISC_ROUTER_ADVERTISEMENT, &ndopts); reason = SKB_CONSUMED; } if (!ipv6_accept_ra(in6_dev)) { ND_PRINTK(2, info, "RA: %s, accept_ra is false for dev: %s\n", __func__, skb->dev->name); goto out; } #ifdef CONFIG_IPV6_ROUTE_INFO if (!READ_ONCE(in6_dev->cnf.accept_ra_from_local) && ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, in6_dev->dev, 0)) { ND_PRINTK(2, info, "RA from local address detected on dev: %s: router info ignored.\n", skb->dev->name); goto skip_routeinfo; } if (READ_ONCE(in6_dev->cnf.accept_ra_rtr_pref) && ndopts.nd_opts_ri) { struct nd_opt_hdr *p; for (p = ndopts.nd_opts_ri; p; p = ndisc_next_option(p, ndopts.nd_opts_ri_end)) { struct route_info *ri = (struct route_info *)p; #ifdef CONFIG_IPV6_NDISC_NODETYPE if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT && ri->prefix_len == 0) continue; #endif if (ri->prefix_len == 0 && !READ_ONCE(in6_dev->cnf.accept_ra_defrtr)) continue; if (ri->lifetime != 0 && ntohl(ri->lifetime) < READ_ONCE(in6_dev->cnf.accept_ra_min_lft)) continue; if (ri->prefix_len < READ_ONCE(in6_dev->cnf.accept_ra_rt_info_min_plen)) continue; if (ri->prefix_len > READ_ONCE(in6_dev->cnf.accept_ra_rt_info_max_plen)) continue; rt6_route_rcv(skb->dev, (u8 *)p, (p->nd_opt_len) << 3, &ipv6_hdr(skb)->saddr); } } skip_routeinfo: #endif #ifdef CONFIG_IPV6_NDISC_NODETYPE /* skip link-specific ndopts from interior routers */ if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) { ND_PRINTK(2, info, "RA: %s, nodetype is NODEFAULT (interior routes), dev: %s\n", __func__, skb->dev->name); goto out; } #endif if (READ_ONCE(in6_dev->cnf.accept_ra_pinfo) && ndopts.nd_opts_pi) { struct nd_opt_hdr *p; for (p = ndopts.nd_opts_pi; p; p = ndisc_next_option(p, ndopts.nd_opts_pi_end)) { addrconf_prefix_rcv(skb->dev, (u8 *)p, (p->nd_opt_len) << 3, ndopts.nd_opts_src_lladdr != NULL); } } if (ndopts.nd_opts_mtu && READ_ONCE(in6_dev->cnf.accept_ra_mtu)) { __be32 n; u32 mtu; memcpy(&n, ((u8 *)(ndopts.nd_opts_mtu+1))+2, sizeof(mtu)); mtu = ntohl(n); if (in6_dev->ra_mtu != mtu) { in6_dev->ra_mtu = mtu; send_ifinfo_notify = true; } if (mtu < IPV6_MIN_MTU || mtu > skb->dev->mtu) { ND_PRINTK(2, warn, "RA: invalid mtu: %d\n", mtu); } else if (READ_ONCE(in6_dev->cnf.mtu6) != mtu) { WRITE_ONCE(in6_dev->cnf.mtu6, mtu); fib6_metric_set(rt, RTAX_MTU, mtu); rt6_mtu_change(skb->dev, mtu); } } if (ndopts.nd_useropts) { struct nd_opt_hdr *p; for (p = ndopts.nd_useropts; p; p = ndisc_next_useropt(skb->dev, p, ndopts.nd_useropts_end)) { ndisc_ra_useropt(skb, p); } } if (ndopts.nd_opts_tgt_lladdr || ndopts.nd_opts_rh) { ND_PRINTK(2, warn, "RA: invalid RA options\n"); } out: /* Send a notify if RA changed managed/otherconf flags or * timer settings or ra_mtu value */ if (send_ifinfo_notify) inet6_ifinfo_notify(RTM_NEWLINK, in6_dev); fib6_info_release(rt); if (neigh) neigh_release(neigh); return reason; } static enum skb_drop_reason ndisc_redirect_rcv(struct sk_buff *skb) { struct rd_msg *msg = (struct rd_msg *)skb_transport_header(skb); u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + offsetof(struct rd_msg, opt)); struct ndisc_options ndopts; SKB_DR(reason); u8 *hdr; #ifdef CONFIG_IPV6_NDISC_NODETYPE switch (skb->ndisc_nodetype) { case NDISC_NODETYPE_HOST: case NDISC_NODETYPE_NODEFAULT: ND_PRINTK(2, warn, "Redirect: from host or unauthorized router\n"); return reason; } #endif if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) { ND_PRINTK(2, warn, "Redirect: source address is not link-local\n"); return reason; } if (!ndisc_parse_options(skb->dev, msg->opt, ndoptlen, &ndopts)) return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS; if (!ndopts.nd_opts_rh) { ip6_redirect_no_header(skb, dev_net(skb->dev), skb->dev->ifindex); return reason; } hdr = (u8 *)ndopts.nd_opts_rh; hdr += 8; if (!pskb_pull(skb, hdr - skb_transport_header(skb))) return SKB_DROP_REASON_PKT_TOO_SMALL; return icmpv6_notify(skb, NDISC_REDIRECT, 0, 0); } static void ndisc_fill_redirect_hdr_option(struct sk_buff *skb, struct sk_buff *orig_skb, int rd_len) { u8 *opt = skb_put(skb, rd_len); memset(opt, 0, 8); *(opt++) = ND_OPT_REDIRECT_HDR; *(opt++) = (rd_len >> 3); opt += 6; skb_copy_bits(orig_skb, skb_network_offset(orig_skb), opt, rd_len - 8); } void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) { struct net_device *dev = skb->dev; struct net *net = dev_net(dev); struct sock *sk = net->ipv6.ndisc_sk; int optlen = 0; struct inet_peer *peer; struct sk_buff *buff; struct rd_msg *msg; struct in6_addr saddr_buf; struct rt6_info *rt; struct dst_entry *dst; struct flowi6 fl6; int rd_len; u8 ha_buf[MAX_ADDR_LEN], *ha = NULL, ops_data_buf[NDISC_OPS_REDIRECT_DATA_SPACE], *ops_data = NULL; bool ret; if (netif_is_l3_master(skb->dev)) { dev = __dev_get_by_index(dev_net(skb->dev), IPCB(skb)->iif); if (!dev) return; } if (ipv6_get_lladdr(dev, &saddr_buf, IFA_F_TENTATIVE)) { ND_PRINTK(2, warn, "Redirect: no link-local address on %s\n", dev->name); return; } if (!ipv6_addr_equal(&ipv6_hdr(skb)->daddr, target) && ipv6_addr_type(target) != (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) { ND_PRINTK(2, warn, "Redirect: target address is not link-local unicast\n"); return; } icmpv6_flow_init(sk, &fl6, NDISC_REDIRECT, &saddr_buf, &ipv6_hdr(skb)->saddr, dev->ifindex); dst = ip6_route_output(net, NULL, &fl6); if (dst->error) { dst_release(dst); return; } dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0); if (IS_ERR(dst)) return; rt = dst_rt6_info(dst); if (rt->rt6i_flags & RTF_GATEWAY) { ND_PRINTK(2, warn, "Redirect: destination is not a neighbour\n"); goto release; } peer = inet_getpeer_v6(net->ipv6.peers, &ipv6_hdr(skb)->saddr, 1); ret = inet_peer_xrlim_allow(peer, 1*HZ); if (peer) inet_putpeer(peer); if (!ret) goto release; if (dev->addr_len) { struct neighbour *neigh = dst_neigh_lookup(skb_dst(skb), target); if (!neigh) { ND_PRINTK(2, warn, "Redirect: no neigh for target address\n"); goto release; } read_lock_bh(&neigh->lock); if (neigh->nud_state & NUD_VALID) { memcpy(ha_buf, neigh->ha, dev->addr_len); read_unlock_bh(&neigh->lock); ha = ha_buf; optlen += ndisc_redirect_opt_addr_space(dev, neigh, ops_data_buf, &ops_data); } else read_unlock_bh(&neigh->lock); neigh_release(neigh); } rd_len = min_t(unsigned int, IPV6_MIN_MTU - sizeof(struct ipv6hdr) - sizeof(*msg) - optlen, skb->len + 8); rd_len &= ~0x7; optlen += rd_len; buff = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); if (!buff) goto release; msg = skb_put(buff, sizeof(*msg)); *msg = (struct rd_msg) { .icmph = { .icmp6_type = NDISC_REDIRECT, }, .target = *target, .dest = ipv6_hdr(skb)->daddr, }; /* * include target_address option */ if (ha) ndisc_fill_redirect_addr_option(buff, ha, ops_data); /* * build redirect option and copy skb over to the new packet. */ if (rd_len) ndisc_fill_redirect_hdr_option(buff, skb, rd_len); skb_dst_set(buff, dst); ndisc_send_skb(buff, &ipv6_hdr(skb)->saddr, &saddr_buf); return; release: dst_release(dst); } static void pndisc_redo(struct sk_buff *skb) { enum skb_drop_reason reason = ndisc_recv_ns(skb); kfree_skb_reason(skb, reason); } static int ndisc_is_multicast(const void *pkey) { return ipv6_addr_is_multicast((struct in6_addr *)pkey); } static bool ndisc_suppress_frag_ndisc(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); if (!idev) return true; if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED && READ_ONCE(idev->cnf.suppress_frag_ndisc)) { net_warn_ratelimited("Received fragmented ndisc packet. Carefully consider disabling suppress_frag_ndisc.\n"); return true; } return false; } enum skb_drop_reason ndisc_rcv(struct sk_buff *skb) { struct nd_msg *msg; SKB_DR(reason); if (ndisc_suppress_frag_ndisc(skb)) return SKB_DROP_REASON_IPV6_NDISC_FRAG; if (skb_linearize(skb)) return SKB_DROP_REASON_NOMEM; msg = (struct nd_msg *)skb_transport_header(skb); __skb_push(skb, skb->data - skb_transport_header(skb)); if (ipv6_hdr(skb)->hop_limit != 255) { ND_PRINTK(2, warn, "NDISC: invalid hop-limit: %d\n", ipv6_hdr(skb)->hop_limit); return SKB_DROP_REASON_IPV6_NDISC_HOP_LIMIT; } if (msg->icmph.icmp6_code != 0) { ND_PRINTK(2, warn, "NDISC: invalid ICMPv6 code: %d\n", msg->icmph.icmp6_code); return SKB_DROP_REASON_IPV6_NDISC_BAD_CODE; } switch (msg->icmph.icmp6_type) { case NDISC_NEIGHBOUR_SOLICITATION: memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb)); reason = ndisc_recv_ns(skb); break; case NDISC_NEIGHBOUR_ADVERTISEMENT: reason = ndisc_recv_na(skb); break; case NDISC_ROUTER_SOLICITATION: reason = ndisc_recv_rs(skb); break; case NDISC_ROUTER_ADVERTISEMENT: reason = ndisc_router_discovery(skb); break; case NDISC_REDIRECT: reason = ndisc_redirect_rcv(skb); break; } return reason; } static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netdev_notifier_change_info *change_info; struct net *net = dev_net(dev); struct inet6_dev *idev; bool evict_nocarrier; switch (event) { case NETDEV_CHANGEADDR: neigh_changeaddr(&nd_tbl, dev); fib6_run_gc(0, net, false); fallthrough; case NETDEV_UP: idev = in6_dev_get(dev); if (!idev) break; if (READ_ONCE(idev->cnf.ndisc_notify) || READ_ONCE(net->ipv6.devconf_all->ndisc_notify)) ndisc_send_unsol_na(dev); in6_dev_put(idev); break; case NETDEV_CHANGE: idev = in6_dev_get(dev); if (!idev) evict_nocarrier = true; else { evict_nocarrier = READ_ONCE(idev->cnf.ndisc_evict_nocarrier) && READ_ONCE(net->ipv6.devconf_all->ndisc_evict_nocarrier); in6_dev_put(idev); } change_info = ptr; if (change_info->flags_changed & IFF_NOARP) neigh_changeaddr(&nd_tbl, dev); if (evict_nocarrier && !netif_carrier_ok(dev)) neigh_carrier_down(&nd_tbl, dev); break; case NETDEV_DOWN: neigh_ifdown(&nd_tbl, dev); fib6_run_gc(0, net, false); break; case NETDEV_NOTIFY_PEERS: ndisc_send_unsol_na(dev); break; default: break; } return NOTIFY_DONE; } static struct notifier_block ndisc_netdev_notifier = { .notifier_call = ndisc_netdev_event, .priority = ADDRCONF_NOTIFY_PRIORITY - 5, }; #ifdef CONFIG_SYSCTL static void ndisc_warn_deprecated_sysctl(const struct ctl_table *ctl, const char *func, const char *dev_name) { static char warncomm[TASK_COMM_LEN]; static int warned; if (strcmp(warncomm, current->comm) && warned < 5) { strscpy(warncomm, current->comm); pr_warn("process `%s' is using deprecated sysctl (%s) net.ipv6.neigh.%s.%s - use net.ipv6.neigh.%s.%s_ms instead\n", warncomm, func, dev_name, ctl->procname, dev_name, ctl->procname); warned++; } } int ndisc_ifinfo_sysctl_change(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net_device *dev = ctl->extra1; struct inet6_dev *idev; int ret; if ((strcmp(ctl->procname, "retrans_time") == 0) || (strcmp(ctl->procname, "base_reachable_time") == 0)) ndisc_warn_deprecated_sysctl(ctl, "syscall", dev ? dev->name : "default"); if (strcmp(ctl->procname, "retrans_time") == 0) ret = neigh_proc_dointvec(ctl, write, buffer, lenp, ppos); else if (strcmp(ctl->procname, "base_reachable_time") == 0) ret = neigh_proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos); else if ((strcmp(ctl->procname, "retrans_time_ms") == 0) || (strcmp(ctl->procname, "base_reachable_time_ms") == 0)) ret = neigh_proc_dointvec_ms_jiffies(ctl, write, buffer, lenp, ppos); else ret = -1; if (write && ret == 0 && dev && (idev = in6_dev_get(dev)) != NULL) { if (ctl->data == &NEIGH_VAR(idev->nd_parms, BASE_REACHABLE_TIME)) idev->nd_parms->reachable_time = neigh_rand_reach_time(NEIGH_VAR(idev->nd_parms, BASE_REACHABLE_TIME)); WRITE_ONCE(idev->tstamp, jiffies); inet6_ifinfo_notify(RTM_NEWLINK, idev); in6_dev_put(idev); } return ret; } #endif static int __net_init ndisc_net_init(struct net *net) { struct ipv6_pinfo *np; struct sock *sk; int err; err = inet_ctl_sock_create(&sk, PF_INET6, SOCK_RAW, IPPROTO_ICMPV6, net); if (err < 0) { ND_PRINTK(0, err, "NDISC: Failed to initialize the control socket (err %d)\n", err); return err; } net->ipv6.ndisc_sk = sk; np = inet6_sk(sk); np->hop_limit = 255; /* Do not loopback ndisc messages */ inet6_clear_bit(MC6_LOOP, sk); return 0; } static void __net_exit ndisc_net_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv6.ndisc_sk); } static struct pernet_operations ndisc_net_ops = { .init = ndisc_net_init, .exit = ndisc_net_exit, }; int __init ndisc_init(void) { int err; err = register_pernet_subsys(&ndisc_net_ops); if (err) return err; /* * Initialize the neighbour table */ neigh_table_init(NEIGH_ND_TABLE, &nd_tbl); #ifdef CONFIG_SYSCTL err = neigh_sysctl_register(NULL, &nd_tbl.parms, ndisc_ifinfo_sysctl_change); if (err) goto out_unregister_pernet; out: #endif return err; #ifdef CONFIG_SYSCTL out_unregister_pernet: unregister_pernet_subsys(&ndisc_net_ops); goto out; #endif } int __init ndisc_late_init(void) { return register_netdevice_notifier(&ndisc_netdev_notifier); } void ndisc_late_cleanup(void) { unregister_netdevice_notifier(&ndisc_netdev_notifier); } void ndisc_cleanup(void) { #ifdef CONFIG_SYSCTL neigh_sysctl_unregister(&nd_tbl.parms); #endif neigh_table_clear(NEIGH_ND_TABLE, &nd_tbl); unregister_pernet_subsys(&ndisc_net_ops); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_RTNETLINK_H #define __NET_RTNETLINK_H #include <linux/rtnetlink.h> #include <linux/srcu.h> #include <net/netlink.h> typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *, struct netlink_ext_ack *); typedef int (*rtnl_dumpit_func)(struct sk_buff *, struct netlink_callback *); enum rtnl_link_flags { RTNL_FLAG_DOIT_UNLOCKED = BIT(0), #define RTNL_FLAG_DOIT_PERNET RTNL_FLAG_DOIT_UNLOCKED #define RTNL_FLAG_DOIT_PERNET_WIP RTNL_FLAG_DOIT_UNLOCKED RTNL_FLAG_BULK_DEL_SUPPORTED = BIT(1), RTNL_FLAG_DUMP_UNLOCKED = BIT(2), RTNL_FLAG_DUMP_SPLIT_NLM_DONE = BIT(3), /* legacy behavior */ }; enum rtnl_kinds { RTNL_KIND_NEW, RTNL_KIND_DEL, RTNL_KIND_GET, RTNL_KIND_SET }; #define RTNL_KIND_MASK 0x3 static inline enum rtnl_kinds rtnl_msgtype_kind(int msgtype) { return msgtype & RTNL_KIND_MASK; } /** * struct rtnl_msg_handler - rtnetlink message type and handlers * * @owner: NULL for built-in, THIS_MODULE for module * @protocol: Protocol family or PF_UNSPEC * @msgtype: rtnetlink message type * @doit: Function pointer called for each request message * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message * @flags: rtnl_link_flags to modify behaviour of doit/dumpit functions */ struct rtnl_msg_handler { struct module *owner; int protocol; int msgtype; rtnl_doit_func doit; rtnl_dumpit_func dumpit; int flags; }; void rtnl_unregister_all(int protocol); int __rtnl_register_many(const struct rtnl_msg_handler *handlers, int n); void __rtnl_unregister_many(const struct rtnl_msg_handler *handlers, int n); #define rtnl_register_many(handlers) \ __rtnl_register_many(handlers, ARRAY_SIZE(handlers)) #define rtnl_unregister_many(handlers) \ __rtnl_unregister_many(handlers, ARRAY_SIZE(handlers)) static inline int rtnl_msg_family(const struct nlmsghdr *nlh) { if (nlmsg_len(nlh) >= sizeof(struct rtgenmsg)) return ((struct rtgenmsg *) nlmsg_data(nlh))->rtgen_family; else return AF_UNSPEC; } /** * struct rtnl_link_ops - rtnetlink link operations * * @list: Used internally, protected by link_ops_mutex and SRCU * @srcu: Used internally * @kind: Identifier * @netns_refund: Physical device, move to init_net on netns exit * @peer_type: Peer device specific netlink attribute number (e.g. VETH_INFO_PEER) * @maxtype: Highest device specific netlink attribute number * @policy: Netlink policy for device specific attribute validation * @validate: Optional validation function for netlink/changelink parameters * @alloc: netdev allocation function, can be %NULL and is then used * in place of alloc_netdev_mqs(), in this case @priv_size * and @setup are unused. Returns a netdev or ERR_PTR(). * @priv_size: sizeof net_device private space * @setup: net_device setup function * @newlink: Function for configuring and registering a new device * @changelink: Function for changing parameters of an existing device * @dellink: Function to remove a device * @get_size: Function to calculate required room for dumping device * specific netlink attributes * @fill_info: Function to dump device specific netlink attributes * @get_xstats_size: Function to calculate required room for dumping device * specific statistics * @fill_xstats: Function to dump device specific statistics * @get_num_tx_queues: Function to determine number of transmit queues * to create when creating a new device. * @get_num_rx_queues: Function to determine number of receive queues * to create when creating a new device. * @get_link_net: Function to get the i/o netns of the device * @get_linkxstats_size: Function to calculate the required room for * dumping device-specific extended link stats * @fill_linkxstats: Function to dump device-specific extended link stats */ struct rtnl_link_ops { struct list_head list; struct srcu_struct srcu; const char *kind; size_t priv_size; struct net_device *(*alloc)(struct nlattr *tb[], const char *ifname, unsigned char name_assign_type, unsigned int num_tx_queues, unsigned int num_rx_queues); void (*setup)(struct net_device *dev); bool netns_refund; const u16 peer_type; unsigned int maxtype; const struct nla_policy *policy; int (*validate)(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack); int (*newlink)(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack); int (*changelink)(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack); void (*dellink)(struct net_device *dev, struct list_head *head); size_t (*get_size)(const struct net_device *dev); int (*fill_info)(struct sk_buff *skb, const struct net_device *dev); size_t (*get_xstats_size)(const struct net_device *dev); int (*fill_xstats)(struct sk_buff *skb, const struct net_device *dev); unsigned int (*get_num_tx_queues)(void); unsigned int (*get_num_rx_queues)(void); unsigned int slave_maxtype; const struct nla_policy *slave_policy; int (*slave_changelink)(struct net_device *dev, struct net_device *slave_dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack); size_t (*get_slave_size)(const struct net_device *dev, const struct net_device *slave_dev); int (*fill_slave_info)(struct sk_buff *skb, const struct net_device *dev, const struct net_device *slave_dev); struct net *(*get_link_net)(const struct net_device *dev); size_t (*get_linkxstats_size)(const struct net_device *dev, int attr); int (*fill_linkxstats)(struct sk_buff *skb, const struct net_device *dev, int *prividx, int attr); }; int rtnl_link_register(struct rtnl_link_ops *ops); void rtnl_link_unregister(struct rtnl_link_ops *ops); /** * struct rtnl_af_ops - rtnetlink address family operations * * @list: Used internally, protected by RTNL and SRCU * @srcu: Used internally * @family: Address family * @fill_link_af: Function to fill IFLA_AF_SPEC with address family * specific netlink attributes. * @get_link_af_size: Function to calculate size of address family specific * netlink attributes. * @validate_link_af: Validate a IFLA_AF_SPEC attribute, must check attr * for invalid configuration settings. * @set_link_af: Function to parse a IFLA_AF_SPEC attribute and modify * net_device accordingly. */ struct rtnl_af_ops { struct list_head list; struct srcu_struct srcu; int family; int (*fill_link_af)(struct sk_buff *skb, const struct net_device *dev, u32 ext_filter_mask); size_t (*get_link_af_size)(const struct net_device *dev, u32 ext_filter_mask); int (*validate_link_af)(const struct net_device *dev, const struct nlattr *attr, struct netlink_ext_ack *extack); int (*set_link_af)(struct net_device *dev, const struct nlattr *attr, struct netlink_ext_ack *extack); int (*fill_stats_af)(struct sk_buff *skb, const struct net_device *dev); size_t (*get_stats_af_size)(const struct net_device *dev); }; int rtnl_af_register(struct rtnl_af_ops *ops); void rtnl_af_unregister(struct rtnl_af_ops *ops); struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]); struct net_device *rtnl_create_link(struct net *net, const char *ifname, unsigned char name_assign_type, const struct rtnl_link_ops *ops, struct nlattr *tb[], struct netlink_ext_ack *extack); int rtnl_delete_link(struct net_device *dev, u32 portid, const struct nlmsghdr *nlh); int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm, u32 portid, const struct nlmsghdr *nlh); int rtnl_nla_parse_ifinfomsg(struct nlattr **tb, const struct nlattr *nla_peer, struct netlink_ext_ack *exterr); struct net *rtnl_get_net_ns_capable(struct sock *sk, int netnsid); #define MODULE_ALIAS_RTNL_LINK(kind) MODULE_ALIAS("rtnl-link-" kind) #endif |
| 5 2 2 1 35 18 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 | // SPDX-License-Identifier: GPL-2.0-only /* * IEEE 802.1Q GARP VLAN Registration Protocol (GVRP) * * Copyright (c) 2008 Patrick McHardy <kaber@trash.net> */ #include <linux/types.h> #include <linux/if_vlan.h> #include <net/garp.h> #include "vlan.h" #define GARP_GVRP_ADDRESS { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x21 } enum gvrp_attributes { GVRP_ATTR_INVALID, GVRP_ATTR_VID, __GVRP_ATTR_MAX }; #define GVRP_ATTR_MAX (__GVRP_ATTR_MAX - 1) static struct garp_application vlan_gvrp_app __read_mostly = { .proto.group_address = GARP_GVRP_ADDRESS, .maxattr = GVRP_ATTR_MAX, .type = GARP_APPLICATION_GVRP, }; int vlan_gvrp_request_join(const struct net_device *dev) { const struct vlan_dev_priv *vlan = vlan_dev_priv(dev); __be16 vlan_id = htons(vlan->vlan_id); if (vlan->vlan_proto != htons(ETH_P_8021Q)) return 0; return garp_request_join(vlan->real_dev, &vlan_gvrp_app, &vlan_id, sizeof(vlan_id), GVRP_ATTR_VID); } void vlan_gvrp_request_leave(const struct net_device *dev) { const struct vlan_dev_priv *vlan = vlan_dev_priv(dev); __be16 vlan_id = htons(vlan->vlan_id); if (vlan->vlan_proto != htons(ETH_P_8021Q)) return; garp_request_leave(vlan->real_dev, &vlan_gvrp_app, &vlan_id, sizeof(vlan_id), GVRP_ATTR_VID); } int vlan_gvrp_init_applicant(struct net_device *dev) { return garp_init_applicant(dev, &vlan_gvrp_app); } void vlan_gvrp_uninit_applicant(struct net_device *dev) { garp_uninit_applicant(dev, &vlan_gvrp_app); } int __init vlan_gvrp_init(void) { return garp_register_application(&vlan_gvrp_app); } void vlan_gvrp_uninit(void) { garp_unregister_application(&vlan_gvrp_app); } |
| 1 1 1 1 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 | // SPDX-License-Identifier: GPL-2.0 /* * thermal.c - Generic Thermal Management Sysfs support. * * Copyright (C) 2008 Intel Corp * Copyright (C) 2008 Zhang Rui <rui.zhang@intel.com> * Copyright (C) 2008 Sujith Thomas <sujith.thomas@intel.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/device.h> #include <linux/err.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/kdev_t.h> #include <linux/idr.h> #include <linux/thermal.h> #include <linux/reboot.h> #include <linux/string.h> #include <linux/of.h> #include <linux/suspend.h> #define CREATE_TRACE_POINTS #include "thermal_trace.h" #include "thermal_core.h" #include "thermal_hwmon.h" static DEFINE_IDA(thermal_tz_ida); static DEFINE_IDA(thermal_cdev_ida); static LIST_HEAD(thermal_tz_list); static LIST_HEAD(thermal_cdev_list); static LIST_HEAD(thermal_governor_list); static DEFINE_MUTEX(thermal_list_lock); static DEFINE_MUTEX(thermal_governor_lock); static struct thermal_governor *def_governor; static bool thermal_pm_suspended; /* * Governor section: set of functions to handle thermal governors * * Functions to help in the life cycle of thermal governors within * the thermal core and by the thermal governor code. */ static struct thermal_governor *__find_governor(const char *name) { struct thermal_governor *pos; if (!name || !name[0]) return def_governor; list_for_each_entry(pos, &thermal_governor_list, governor_list) if (!strncasecmp(name, pos->name, THERMAL_NAME_LENGTH)) return pos; return NULL; } /** * bind_previous_governor() - bind the previous governor of the thermal zone * @tz: a valid pointer to a struct thermal_zone_device * @failed_gov_name: the name of the governor that failed to register * * Register the previous governor of the thermal zone after a new * governor has failed to be bound. */ static void bind_previous_governor(struct thermal_zone_device *tz, const char *failed_gov_name) { if (tz->governor && tz->governor->bind_to_tz) { if (tz->governor->bind_to_tz(tz)) { dev_err(&tz->device, "governor %s failed to bind and the previous one (%s) failed to bind again, thermal zone %s has no governor\n", failed_gov_name, tz->governor->name, tz->type); tz->governor = NULL; } } } /** * thermal_set_governor() - Switch to another governor * @tz: a valid pointer to a struct thermal_zone_device * @new_gov: pointer to the new governor * * Change the governor of thermal zone @tz. * * Return: 0 on success, an error if the new governor's bind_to_tz() failed. */ static int thermal_set_governor(struct thermal_zone_device *tz, struct thermal_governor *new_gov) { int ret = 0; if (tz->governor && tz->governor->unbind_from_tz) tz->governor->unbind_from_tz(tz); if (new_gov && new_gov->bind_to_tz) { ret = new_gov->bind_to_tz(tz); if (ret) { bind_previous_governor(tz, new_gov->name); return ret; } } tz->governor = new_gov; return ret; } int thermal_register_governor(struct thermal_governor *governor) { int err; const char *name; struct thermal_zone_device *pos; if (!governor) return -EINVAL; guard(mutex)(&thermal_governor_lock); err = -EBUSY; if (!__find_governor(governor->name)) { bool match_default; err = 0; list_add(&governor->governor_list, &thermal_governor_list); match_default = !strncmp(governor->name, DEFAULT_THERMAL_GOVERNOR, THERMAL_NAME_LENGTH); if (!def_governor && match_default) def_governor = governor; } guard(mutex)(&thermal_list_lock); list_for_each_entry(pos, &thermal_tz_list, node) { /* * only thermal zones with specified tz->tzp->governor_name * may run with tz->govenor unset */ if (pos->governor) continue; name = pos->tzp->governor_name; if (!strncasecmp(name, governor->name, THERMAL_NAME_LENGTH)) { int ret; ret = thermal_set_governor(pos, governor); if (ret) dev_err(&pos->device, "Failed to set governor %s for thermal zone %s: %d\n", governor->name, pos->type, ret); } } return err; } void thermal_unregister_governor(struct thermal_governor *governor) { struct thermal_zone_device *pos; if (!governor) return; guard(mutex)(&thermal_governor_lock); if (!__find_governor(governor->name)) return; list_del(&governor->governor_list); guard(mutex)(&thermal_list_lock); list_for_each_entry(pos, &thermal_tz_list, node) { if (!strncasecmp(pos->governor->name, governor->name, THERMAL_NAME_LENGTH)) thermal_set_governor(pos, NULL); } } int thermal_zone_device_set_policy(struct thermal_zone_device *tz, char *policy) { struct thermal_governor *gov; int ret = -EINVAL; guard(mutex)(&thermal_governor_lock); guard(thermal_zone)(tz); gov = __find_governor(strim(policy)); if (gov) ret = thermal_set_governor(tz, gov); thermal_notify_tz_gov_change(tz, policy); return ret; } int thermal_build_list_of_policies(char *buf) { struct thermal_governor *pos; ssize_t count = 0; guard(mutex)(&thermal_governor_lock); list_for_each_entry(pos, &thermal_governor_list, governor_list) { count += sysfs_emit_at(buf, count, "%s ", pos->name); } count += sysfs_emit_at(buf, count, "\n"); return count; } static void __init thermal_unregister_governors(void) { struct thermal_governor **governor; for_each_governor_table(governor) thermal_unregister_governor(*governor); } static int __init thermal_register_governors(void) { int ret = 0; struct thermal_governor **governor; for_each_governor_table(governor) { ret = thermal_register_governor(*governor); if (ret) { pr_err("Failed to register governor: '%s'", (*governor)->name); break; } pr_info("Registered thermal governor '%s'", (*governor)->name); } if (ret) { struct thermal_governor **gov; for_each_governor_table(gov) { if (gov == governor) break; thermal_unregister_governor(*gov); } } return ret; } static int __thermal_zone_device_set_mode(struct thermal_zone_device *tz, enum thermal_device_mode mode) { if (tz->ops.change_mode) { int ret; ret = tz->ops.change_mode(tz, mode); if (ret) return ret; } tz->mode = mode; return 0; } static void thermal_zone_broken_disable(struct thermal_zone_device *tz) { struct thermal_trip_desc *td; dev_err(&tz->device, "Unable to get temperature, disabling!\n"); /* * This function only runs for enabled thermal zones, so no need to * check for the current mode. */ __thermal_zone_device_set_mode(tz, THERMAL_DEVICE_DISABLED); thermal_notify_tz_disable(tz); for_each_trip_desc(tz, td) { if (td->trip.type == THERMAL_TRIP_CRITICAL && td->trip.temperature > THERMAL_TEMP_INVALID) { dev_crit(&tz->device, "Disabled thermal zone with critical trip point\n"); return; } } } /* * Zone update section: main control loop applied to each zone while monitoring * in polling mode. The monitoring is done using a workqueue. * Same update may be done on a zone by calling thermal_zone_device_update(). * * An update means: * - Non-critical trips will invoke the governor responsible for that zone; * - Hot trips will produce a notification to userspace; * - Critical trip point will cause a system shutdown. */ static void thermal_zone_device_set_polling(struct thermal_zone_device *tz, unsigned long delay) { if (delay > HZ) delay = round_jiffies_relative(delay); mod_delayed_work(system_freezable_power_efficient_wq, &tz->poll_queue, delay); } static void thermal_zone_recheck(struct thermal_zone_device *tz, int error) { if (error == -EAGAIN) { thermal_zone_device_set_polling(tz, THERMAL_RECHECK_DELAY); return; } /* * Print the message once to reduce log noise. It will be followed by * another one if the temperature cannot be determined after multiple * attempts. */ if (tz->recheck_delay_jiffies == THERMAL_RECHECK_DELAY) dev_info(&tz->device, "Temperature check failed (%d)\n", error); thermal_zone_device_set_polling(tz, tz->recheck_delay_jiffies); tz->recheck_delay_jiffies += max(tz->recheck_delay_jiffies >> 1, 1ULL); if (tz->recheck_delay_jiffies > THERMAL_MAX_RECHECK_DELAY) { thermal_zone_broken_disable(tz); /* * Restore the original recheck delay value to allow the thermal * zone to try to recover when it is reenabled by user space. */ tz->recheck_delay_jiffies = THERMAL_RECHECK_DELAY; } } static void monitor_thermal_zone(struct thermal_zone_device *tz) { if (tz->passive > 0 && tz->passive_delay_jiffies) thermal_zone_device_set_polling(tz, tz->passive_delay_jiffies); else if (tz->polling_delay_jiffies) thermal_zone_device_set_polling(tz, tz->polling_delay_jiffies); } static struct thermal_governor *thermal_get_tz_governor(struct thermal_zone_device *tz) { if (tz->governor) return tz->governor; return def_governor; } void thermal_governor_update_tz(struct thermal_zone_device *tz, enum thermal_notify_event reason) { if (!tz->governor || !tz->governor->update_tz) return; tz->governor->update_tz(tz, reason); } static void thermal_zone_device_halt(struct thermal_zone_device *tz, bool shutdown) { /* * poweroff_delay_ms must be a carefully profiled positive value. * Its a must for forced_emergency_poweroff_work to be scheduled. */ int poweroff_delay_ms = CONFIG_THERMAL_EMERGENCY_POWEROFF_DELAY_MS; const char *msg = "Temperature too high"; dev_emerg(&tz->device, "%s: critical temperature reached\n", tz->type); if (shutdown) hw_protection_shutdown(msg, poweroff_delay_ms); else hw_protection_reboot(msg, poweroff_delay_ms); } void thermal_zone_device_critical(struct thermal_zone_device *tz) { thermal_zone_device_halt(tz, true); } EXPORT_SYMBOL(thermal_zone_device_critical); void thermal_zone_device_critical_reboot(struct thermal_zone_device *tz) { thermal_zone_device_halt(tz, false); } static void handle_critical_trips(struct thermal_zone_device *tz, const struct thermal_trip *trip) { trace_thermal_zone_trip(tz, thermal_zone_trip_id(tz, trip), trip->type); if (trip->type == THERMAL_TRIP_CRITICAL) tz->ops.critical(tz); else if (tz->ops.hot) tz->ops.hot(tz); } static void move_trip_to_sorted_list(struct thermal_trip_desc *td, struct list_head *list) { struct thermal_trip_desc *entry; /* * Delete upfront and then add to make relocation within the same list * work. */ list_del(&td->list_node); /* Assume that the new entry is likely to be the last one. */ list_for_each_entry_reverse(entry, list, list_node) { if (entry->threshold <= td->threshold) { list_add(&td->list_node, &entry->list_node); return; } } list_add(&td->list_node, list); } static void move_to_trips_high(struct thermal_zone_device *tz, struct thermal_trip_desc *td) { td->threshold = td->trip.temperature; move_trip_to_sorted_list(td, &tz->trips_high); } static void move_to_trips_reached(struct thermal_zone_device *tz, struct thermal_trip_desc *td) { td->threshold = td->trip.temperature - td->trip.hysteresis; move_trip_to_sorted_list(td, &tz->trips_reached); } static void move_to_trips_invalid(struct thermal_zone_device *tz, struct thermal_trip_desc *td) { td->threshold = INT_MAX; list_move(&td->list_node, &tz->trips_invalid); } static void thermal_governor_trip_crossed(struct thermal_governor *governor, struct thermal_zone_device *tz, const struct thermal_trip *trip, bool crossed_up) { if (trip->type == THERMAL_TRIP_HOT || trip->type == THERMAL_TRIP_CRITICAL) return; if (governor->trip_crossed) governor->trip_crossed(tz, trip, crossed_up); } static void thermal_trip_crossed(struct thermal_zone_device *tz, struct thermal_trip_desc *td, struct thermal_governor *governor, bool crossed_up) { const struct thermal_trip *trip = &td->trip; if (crossed_up) { if (trip->type == THERMAL_TRIP_PASSIVE) tz->passive++; else if (trip->type == THERMAL_TRIP_CRITICAL || trip->type == THERMAL_TRIP_HOT) handle_critical_trips(tz, trip); thermal_notify_tz_trip_up(tz, trip); thermal_debug_tz_trip_up(tz, trip); } else { if (trip->type == THERMAL_TRIP_PASSIVE) { tz->passive--; WARN_ON(tz->passive < 0); } thermal_notify_tz_trip_down(tz, trip); thermal_debug_tz_trip_down(tz, trip); } thermal_governor_trip_crossed(governor, tz, trip, crossed_up); } void thermal_zone_set_trip_hyst(struct thermal_zone_device *tz, struct thermal_trip *trip, int hyst) { struct thermal_trip_desc *td = trip_to_trip_desc(trip); WRITE_ONCE(trip->hysteresis, hyst); thermal_notify_tz_trip_change(tz, trip); /* * If the zone temperature is above or at the trip tmperature, the trip * is in the trips_reached list and its threshold is equal to its low * temperature. It needs to stay in that list, but its threshold needs * to be updated and the list ordering may need to be restored. */ if (tz->temperature >= td->threshold) move_to_trips_reached(tz, td); } void thermal_zone_set_trip_temp(struct thermal_zone_device *tz, struct thermal_trip *trip, int temp) { struct thermal_trip_desc *td = trip_to_trip_desc(trip); int old_temp = trip->temperature; if (old_temp == temp) return; WRITE_ONCE(trip->temperature, temp); thermal_notify_tz_trip_change(tz, trip); if (old_temp == THERMAL_TEMP_INVALID) { /* * The trip was invalid before the change, so move it to the * trips_high list regardless of the new temperature value * because there is no mitigation under way for it. If a * mitigation needs to be started, the trip will be moved to the * trips_reached list later. */ move_to_trips_high(tz, td); return; } if (temp == THERMAL_TEMP_INVALID) { /* * If the trip is in the trips_reached list, mitigation is under * way for it and it needs to be stopped because the trip is * effectively going away. */ if (tz->temperature >= td->threshold) thermal_trip_crossed(tz, td, thermal_get_tz_governor(tz), false); move_to_trips_invalid(tz, td); return; } /* * The trip stays on its current list, but its threshold needs to be * updated due to the temperature change and the list ordering may need * to be restored. */ if (tz->temperature >= td->threshold) move_to_trips_reached(tz, td); else move_to_trips_high(tz, td); } EXPORT_SYMBOL_GPL(thermal_zone_set_trip_temp); static void thermal_zone_handle_trips(struct thermal_zone_device *tz, struct thermal_governor *governor, int *low, int *high) { struct thermal_trip_desc *td, *next; LIST_HEAD(way_down_list); /* Check the trips that were below or at the zone temperature. */ list_for_each_entry_safe_reverse(td, next, &tz->trips_reached, list_node) { if (td->threshold <= tz->temperature) break; thermal_trip_crossed(tz, td, governor, false); /* * The current trips_high list needs to be processed before * adding new entries to it, so put them on a temporary list. */ list_move(&td->list_node, &way_down_list); } /* Check the trips that were previously above the zone temperature. */ list_for_each_entry_safe(td, next, &tz->trips_high, list_node) { if (td->threshold > tz->temperature) break; thermal_trip_crossed(tz, td, governor, true); move_to_trips_reached(tz, td); } /* Move all of the trips from the temporary list to trips_high. */ list_for_each_entry_safe(td, next, &way_down_list, list_node) move_to_trips_high(tz, td); if (!list_empty(&tz->trips_reached)) { td = list_last_entry(&tz->trips_reached, struct thermal_trip_desc, list_node); /* * Set the "low" value below the current trip threshold in case * the zone temperature is at that threshold and stays there, * which would trigger a new interrupt immediately in vain. */ *low = td->threshold - 1; } if (!list_empty(&tz->trips_high)) { td = list_first_entry(&tz->trips_high, struct thermal_trip_desc, list_node); *high = td->threshold; } } void __thermal_zone_device_update(struct thermal_zone_device *tz, enum thermal_notify_event event) { struct thermal_governor *governor = thermal_get_tz_governor(tz); int low = -INT_MAX, high = INT_MAX; int temp, ret; if (tz->state != TZ_STATE_READY || tz->mode != THERMAL_DEVICE_ENABLED) return; ret = __thermal_zone_get_temp(tz, &temp); if (ret) { thermal_zone_recheck(tz, ret); return; } else if (temp <= THERMAL_TEMP_INVALID) { /* * Special case: No valid temperature value is available, but * the zone owner does not want the core to do anything about * it. Continue regular zone polling if needed, so that this * function can be called again, but skip everything else. */ goto monitor; } tz->recheck_delay_jiffies = THERMAL_RECHECK_DELAY; tz->last_temperature = tz->temperature; tz->temperature = temp; trace_thermal_temperature(tz); thermal_genl_sampling_temp(tz->id, temp); tz->notify_event = event; thermal_zone_handle_trips(tz, governor, &low, &high); thermal_thresholds_handle(tz, &low, &high); thermal_zone_set_trips(tz, low, high); if (governor->manage) governor->manage(tz); thermal_debug_update_trip_stats(tz); monitor: monitor_thermal_zone(tz); } static int thermal_zone_device_set_mode(struct thermal_zone_device *tz, enum thermal_device_mode mode) { int ret; guard(thermal_zone)(tz); /* do nothing if mode isn't changing */ if (mode == tz->mode) return 0; ret = __thermal_zone_device_set_mode(tz, mode); if (ret) return ret; __thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED); if (mode == THERMAL_DEVICE_ENABLED) thermal_notify_tz_enable(tz); else thermal_notify_tz_disable(tz); return 0; } int thermal_zone_device_enable(struct thermal_zone_device *tz) { return thermal_zone_device_set_mode(tz, THERMAL_DEVICE_ENABLED); } EXPORT_SYMBOL_GPL(thermal_zone_device_enable); int thermal_zone_device_disable(struct thermal_zone_device *tz) { return thermal_zone_device_set_mode(tz, THERMAL_DEVICE_DISABLED); } EXPORT_SYMBOL_GPL(thermal_zone_device_disable); static bool thermal_zone_is_present(struct thermal_zone_device *tz) { return !list_empty(&tz->node); } void thermal_zone_device_update(struct thermal_zone_device *tz, enum thermal_notify_event event) { guard(thermal_zone)(tz); if (thermal_zone_is_present(tz)) __thermal_zone_device_update(tz, event); } EXPORT_SYMBOL_GPL(thermal_zone_device_update); int for_each_thermal_governor(int (*cb)(struct thermal_governor *, void *), void *data) { struct thermal_governor *gov; guard(mutex)(&thermal_governor_lock); list_for_each_entry(gov, &thermal_governor_list, governor_list) { int ret; ret = cb(gov, data); if (ret) return ret; } return 0; } int for_each_thermal_cooling_device(int (*cb)(struct thermal_cooling_device *, void *), void *data) { struct thermal_cooling_device *cdev; guard(mutex)(&thermal_list_lock); list_for_each_entry(cdev, &thermal_cdev_list, node) { int ret; ret = cb(cdev, data); if (ret) return ret; } return 0; } int for_each_thermal_zone(int (*cb)(struct thermal_zone_device *, void *), void *data) { struct thermal_zone_device *tz; guard(mutex)(&thermal_list_lock); list_for_each_entry(tz, &thermal_tz_list, node) { int ret; ret = cb(tz, data); if (ret) return ret; } return 0; } struct thermal_zone_device *thermal_zone_get_by_id(int id) { struct thermal_zone_device *tz; guard(mutex)(&thermal_list_lock); list_for_each_entry(tz, &thermal_tz_list, node) { if (tz->id == id) { get_device(&tz->device); return tz; } } return NULL; } /* * Device management section: cooling devices, zones devices, and binding * * Set of functions provided by the thermal core for: * - cooling devices lifecycle: registration, unregistration, * binding, and unbinding. * - thermal zone devices lifecycle: registration, unregistration, * binding, and unbinding. */ static int thermal_instance_add(struct thermal_instance *new_instance, struct thermal_cooling_device *cdev, struct thermal_trip_desc *td) { struct thermal_instance *instance; list_for_each_entry(instance, &td->thermal_instances, trip_node) { if (instance->cdev == cdev) return -EEXIST; } list_add_tail(&new_instance->trip_node, &td->thermal_instances); guard(cooling_dev)(cdev); list_add_tail(&new_instance->cdev_node, &cdev->thermal_instances); return 0; } /** * thermal_bind_cdev_to_trip - bind a cooling device to a thermal zone * @tz: pointer to struct thermal_zone_device * @td: descriptor of the trip point to bind @cdev to * @cdev: pointer to struct thermal_cooling_device * @cool_spec: cooling specification for the trip point and @cdev * * This interface function bind a thermal cooling device to the certain trip * point of a thermal zone device. * This function is usually called in the thermal zone device .bind callback. * * Return: 0 on success, the proper error value otherwise. */ static int thermal_bind_cdev_to_trip(struct thermal_zone_device *tz, struct thermal_trip_desc *td, struct thermal_cooling_device *cdev, struct cooling_spec *cool_spec) { struct thermal_instance *dev; bool upper_no_limit; int result; /* lower default 0, upper default max_state */ if (cool_spec->lower == THERMAL_NO_LIMIT) cool_spec->lower = 0; if (cool_spec->upper == THERMAL_NO_LIMIT) { cool_spec->upper = cdev->max_state; upper_no_limit = true; } else { upper_no_limit = false; } if (cool_spec->lower > cool_spec->upper || cool_spec->upper > cdev->max_state) return -EINVAL; dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) return -ENOMEM; dev->cdev = cdev; dev->trip = &td->trip; dev->upper = cool_spec->upper; dev->upper_no_limit = upper_no_limit; dev->lower = cool_spec->lower; dev->target = THERMAL_NO_TARGET; dev->weight = cool_spec->weight; result = ida_alloc(&tz->ida, GFP_KERNEL); if (result < 0) goto free_mem; dev->id = result; sprintf(dev->name, "cdev%d", dev->id); result = sysfs_create_link(&tz->device.kobj, &cdev->device.kobj, dev->name); if (result) goto release_ida; snprintf(dev->attr_name, sizeof(dev->attr_name), "cdev%d_trip_point", dev->id); sysfs_attr_init(&dev->attr.attr); dev->attr.attr.name = dev->attr_name; dev->attr.attr.mode = 0444; dev->attr.show = trip_point_show; result = device_create_file(&tz->device, &dev->attr); if (result) goto remove_symbol_link; snprintf(dev->weight_attr_name, sizeof(dev->weight_attr_name), "cdev%d_weight", dev->id); sysfs_attr_init(&dev->weight_attr.attr); dev->weight_attr.attr.name = dev->weight_attr_name; dev->weight_attr.attr.mode = S_IWUSR | S_IRUGO; dev->weight_attr.show = weight_show; dev->weight_attr.store = weight_store; result = device_create_file(&tz->device, &dev->weight_attr); if (result) goto remove_trip_file; result = thermal_instance_add(dev, cdev, td); if (result) goto remove_weight_file; thermal_governor_update_tz(tz, THERMAL_TZ_BIND_CDEV); return 0; remove_weight_file: device_remove_file(&tz->device, &dev->weight_attr); remove_trip_file: device_remove_file(&tz->device, &dev->attr); remove_symbol_link: sysfs_remove_link(&tz->device.kobj, dev->name); release_ida: ida_free(&tz->ida, dev->id); free_mem: kfree(dev); return result; } static void thermal_instance_delete(struct thermal_instance *instance) { list_del(&instance->trip_node); guard(cooling_dev)(instance->cdev); list_del(&instance->cdev_node); } /** * thermal_unbind_cdev_from_trip - unbind a cooling device from a thermal zone. * @tz: pointer to a struct thermal_zone_device. * @td: descriptor of the trip point to unbind @cdev from * @cdev: pointer to a struct thermal_cooling_device. * * This interface function unbind a thermal cooling device from the certain * trip point of a thermal zone device. * This function is usually called in the thermal zone device .unbind callback. */ static void thermal_unbind_cdev_from_trip(struct thermal_zone_device *tz, struct thermal_trip_desc *td, struct thermal_cooling_device *cdev) { struct thermal_instance *pos, *next; list_for_each_entry_safe(pos, next, &td->thermal_instances, trip_node) { if (pos->cdev == cdev) { thermal_instance_delete(pos); goto unbind; } } return; unbind: thermal_governor_update_tz(tz, THERMAL_TZ_UNBIND_CDEV); device_remove_file(&tz->device, &pos->weight_attr); device_remove_file(&tz->device, &pos->attr); sysfs_remove_link(&tz->device.kobj, pos->name); ida_free(&tz->ida, pos->id); kfree(pos); } static void thermal_release(struct device *dev) { struct thermal_zone_device *tz; struct thermal_cooling_device *cdev; if (!strncmp(dev_name(dev), "thermal_zone", sizeof("thermal_zone") - 1)) { tz = to_thermal_zone(dev); thermal_zone_destroy_device_groups(tz); mutex_destroy(&tz->lock); complete(&tz->removal); } else if (!strncmp(dev_name(dev), "cooling_device", sizeof("cooling_device") - 1)) { cdev = to_cooling_device(dev); thermal_cooling_device_destroy_sysfs(cdev); kfree_const(cdev->type); ida_free(&thermal_cdev_ida, cdev->id); kfree(cdev); } } static struct class *thermal_class; static inline void print_bind_err_msg(struct thermal_zone_device *tz, const struct thermal_trip_desc *td, struct thermal_cooling_device *cdev, int ret) { dev_err(&tz->device, "binding cdev %s to trip %d failed: %d\n", cdev->type, thermal_zone_trip_id(tz, &td->trip), ret); } static bool __thermal_zone_cdev_bind(struct thermal_zone_device *tz, struct thermal_cooling_device *cdev) { struct thermal_trip_desc *td; bool update_tz = false; if (!tz->ops.should_bind) return false; for_each_trip_desc(tz, td) { struct cooling_spec c = { .upper = THERMAL_NO_LIMIT, .lower = THERMAL_NO_LIMIT, .weight = THERMAL_WEIGHT_DEFAULT }; int ret; if (!tz->ops.should_bind(tz, &td->trip, cdev, &c)) continue; ret = thermal_bind_cdev_to_trip(tz, td, cdev, &c); if (ret) { print_bind_err_msg(tz, td, cdev, ret); continue; } update_tz = true; } return update_tz; } static void thermal_zone_cdev_bind(struct thermal_zone_device *tz, struct thermal_cooling_device *cdev) { guard(thermal_zone)(tz); if (__thermal_zone_cdev_bind(tz, cdev)) __thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED); } static void thermal_cooling_device_init_complete(struct thermal_cooling_device *cdev) { struct thermal_zone_device *tz; guard(mutex)(&thermal_list_lock); list_add(&cdev->node, &thermal_cdev_list); list_for_each_entry(tz, &thermal_tz_list, node) thermal_zone_cdev_bind(tz, cdev); } /** * __thermal_cooling_device_register() - register a new thermal cooling device * @np: a pointer to a device tree node. * @type: the thermal cooling device type. * @devdata: device private data. * @ops: standard thermal cooling devices callbacks. * * This interface function adds a new thermal cooling device (fan/processor/...) * to /sys/class/thermal/ folder as cooling_device[0-*]. It tries to bind itself * to all the thermal zone devices registered at the same time. * It also gives the opportunity to link the cooling device to a device tree * node, so that it can be bound to a thermal zone created out of device tree. * * Return: a pointer to the created struct thermal_cooling_device or an * ERR_PTR. Caller must check return value with IS_ERR*() helpers. */ static struct thermal_cooling_device * __thermal_cooling_device_register(struct device_node *np, const char *type, void *devdata, const struct thermal_cooling_device_ops *ops) { struct thermal_cooling_device *cdev; unsigned long current_state; int id, ret; if (!ops || !ops->get_max_state || !ops->get_cur_state || !ops->set_cur_state) return ERR_PTR(-EINVAL); if (!thermal_class) return ERR_PTR(-ENODEV); cdev = kzalloc(sizeof(*cdev), GFP_KERNEL); if (!cdev) return ERR_PTR(-ENOMEM); ret = ida_alloc(&thermal_cdev_ida, GFP_KERNEL); if (ret < 0) goto out_kfree_cdev; cdev->id = ret; id = ret; cdev->type = kstrdup_const(type ? type : "", GFP_KERNEL); if (!cdev->type) { ret = -ENOMEM; goto out_ida_remove; } mutex_init(&cdev->lock); INIT_LIST_HEAD(&cdev->thermal_instances); cdev->np = np; cdev->ops = ops; cdev->updated = false; cdev->device.class = thermal_class; cdev->devdata = devdata; ret = cdev->ops->get_max_state(cdev, &cdev->max_state); if (ret) goto out_cdev_type; /* * The cooling device's current state is only needed for debug * initialization below, so a failure to get it does not cause * the entire cooling device initialization to fail. However, * the debug will not work for the device if its initial state * cannot be determined and drivers are responsible for ensuring * that this will not happen. */ ret = cdev->ops->get_cur_state(cdev, ¤t_state); if (ret) current_state = ULONG_MAX; thermal_cooling_device_setup_sysfs(cdev); ret = dev_set_name(&cdev->device, "cooling_device%d", cdev->id); if (ret) goto out_cooling_dev; ret = device_register(&cdev->device); if (ret) { /* thermal_release() handles rest of the cleanup */ put_device(&cdev->device); return ERR_PTR(ret); } if (current_state <= cdev->max_state) thermal_debug_cdev_add(cdev, current_state); thermal_cooling_device_init_complete(cdev); return cdev; out_cooling_dev: thermal_cooling_device_destroy_sysfs(cdev); out_cdev_type: kfree_const(cdev->type); out_ida_remove: ida_free(&thermal_cdev_ida, id); out_kfree_cdev: kfree(cdev); return ERR_PTR(ret); } /** * thermal_cooling_device_register() - register a new thermal cooling device * @type: the thermal cooling device type. * @devdata: device private data. * @ops: standard thermal cooling devices callbacks. * * This interface function adds a new thermal cooling device (fan/processor/...) * to /sys/class/thermal/ folder as cooling_device[0-*]. It tries to bind itself * to all the thermal zone devices registered at the same time. * * Return: a pointer to the created struct thermal_cooling_device or an * ERR_PTR. Caller must check return value with IS_ERR*() helpers. */ struct thermal_cooling_device * thermal_cooling_device_register(const char *type, void *devdata, const struct thermal_cooling_device_ops *ops) { return __thermal_cooling_device_register(NULL, type, devdata, ops); } EXPORT_SYMBOL_GPL(thermal_cooling_device_register); /** * thermal_of_cooling_device_register() - register an OF thermal cooling device * @np: a pointer to a device tree node. * @type: the thermal cooling device type. * @devdata: device private data. * @ops: standard thermal cooling devices callbacks. * * This function will register a cooling device with device tree node reference. * This interface function adds a new thermal cooling device (fan/processor/...) * to /sys/class/thermal/ folder as cooling_device[0-*]. It tries to bind itself * to all the thermal zone devices registered at the same time. * * Return: a pointer to the created struct thermal_cooling_device or an * ERR_PTR. Caller must check return value with IS_ERR*() helpers. */ struct thermal_cooling_device * thermal_of_cooling_device_register(struct device_node *np, const char *type, void *devdata, const struct thermal_cooling_device_ops *ops) { return __thermal_cooling_device_register(np, type, devdata, ops); } EXPORT_SYMBOL_GPL(thermal_of_cooling_device_register); static void thermal_cooling_device_release(struct device *dev, void *res) { thermal_cooling_device_unregister( *(struct thermal_cooling_device **)res); } /** * devm_thermal_of_cooling_device_register() - register an OF thermal cooling * device * @dev: a valid struct device pointer of a sensor device. * @np: a pointer to a device tree node. * @type: the thermal cooling device type. * @devdata: device private data. * @ops: standard thermal cooling devices callbacks. * * This function will register a cooling device with device tree node reference. * This interface function adds a new thermal cooling device (fan/processor/...) * to /sys/class/thermal/ folder as cooling_device[0-*]. It tries to bind itself * to all the thermal zone devices registered at the same time. * * Return: a pointer to the created struct thermal_cooling_device or an * ERR_PTR. Caller must check return value with IS_ERR*() helpers. */ struct thermal_cooling_device * devm_thermal_of_cooling_device_register(struct device *dev, struct device_node *np, const char *type, void *devdata, const struct thermal_cooling_device_ops *ops) { struct thermal_cooling_device **ptr, *tcd; ptr = devres_alloc(thermal_cooling_device_release, sizeof(*ptr), GFP_KERNEL); if (!ptr) return ERR_PTR(-ENOMEM); tcd = __thermal_cooling_device_register(np, type, devdata, ops); if (IS_ERR(tcd)) { devres_free(ptr); return tcd; } *ptr = tcd; devres_add(dev, ptr); return tcd; } EXPORT_SYMBOL_GPL(devm_thermal_of_cooling_device_register); static bool thermal_cooling_device_present(struct thermal_cooling_device *cdev) { struct thermal_cooling_device *pos = NULL; list_for_each_entry(pos, &thermal_cdev_list, node) { if (pos == cdev) return true; } return false; } /** * thermal_cooling_device_update - Update a cooling device object * @cdev: Target cooling device. * * Update @cdev to reflect a change of the underlying hardware or platform. * * Must be called when the maximum cooling state of @cdev becomes invalid and so * its .get_max_state() callback needs to be run to produce the new maximum * cooling state value. */ void thermal_cooling_device_update(struct thermal_cooling_device *cdev) { struct thermal_instance *ti; unsigned long state; if (IS_ERR_OR_NULL(cdev)) return; /* * Hold thermal_list_lock throughout the update to prevent the device * from going away while being updated. */ guard(mutex)(&thermal_list_lock); if (!thermal_cooling_device_present(cdev)) return; /* * Update under the cdev lock to prevent the state from being set beyond * the new limit concurrently. */ guard(cooling_dev)(cdev); if (cdev->ops->get_max_state(cdev, &cdev->max_state)) return; thermal_cooling_device_stats_reinit(cdev); list_for_each_entry(ti, &cdev->thermal_instances, cdev_node) { if (ti->upper == cdev->max_state) continue; if (ti->upper < cdev->max_state) { if (ti->upper_no_limit) ti->upper = cdev->max_state; continue; } ti->upper = cdev->max_state; if (ti->lower > ti->upper) ti->lower = ti->upper; if (ti->target == THERMAL_NO_TARGET) continue; if (ti->target > ti->upper) ti->target = ti->upper; } if (cdev->ops->get_cur_state(cdev, &state) || state > cdev->max_state) return; thermal_cooling_device_stats_update(cdev, state); } EXPORT_SYMBOL_GPL(thermal_cooling_device_update); static void __thermal_zone_cdev_unbind(struct thermal_zone_device *tz, struct thermal_cooling_device *cdev) { struct thermal_trip_desc *td; for_each_trip_desc(tz, td) thermal_unbind_cdev_from_trip(tz, td, cdev); } static void thermal_zone_cdev_unbind(struct thermal_zone_device *tz, struct thermal_cooling_device *cdev) { guard(thermal_zone)(tz); __thermal_zone_cdev_unbind(tz, cdev); } static bool thermal_cooling_device_exit(struct thermal_cooling_device *cdev) { struct thermal_zone_device *tz; guard(mutex)(&thermal_list_lock); if (!thermal_cooling_device_present(cdev)) return false; list_del(&cdev->node); list_for_each_entry(tz, &thermal_tz_list, node) thermal_zone_cdev_unbind(tz, cdev); return true; } /** * thermal_cooling_device_unregister() - removes a thermal cooling device * @cdev: Thermal cooling device to remove. */ void thermal_cooling_device_unregister(struct thermal_cooling_device *cdev) { if (!cdev) return; thermal_debug_cdev_remove(cdev); if (thermal_cooling_device_exit(cdev)) device_unregister(&cdev->device); } EXPORT_SYMBOL_GPL(thermal_cooling_device_unregister); int thermal_zone_get_crit_temp(struct thermal_zone_device *tz, int *temp) { const struct thermal_trip_desc *td; int ret = -EINVAL; if (tz->ops.get_crit_temp) return tz->ops.get_crit_temp(tz, temp); guard(thermal_zone)(tz); for_each_trip_desc(tz, td) { const struct thermal_trip *trip = &td->trip; if (trip->type == THERMAL_TRIP_CRITICAL) { *temp = trip->temperature; ret = 0; break; } } return ret; } EXPORT_SYMBOL_GPL(thermal_zone_get_crit_temp); static void thermal_zone_device_check(struct work_struct *work) { struct thermal_zone_device *tz = container_of(work, struct thermal_zone_device, poll_queue.work); thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED); } static void thermal_zone_device_init(struct thermal_zone_device *tz) { struct thermal_trip_desc *td, *next; INIT_DELAYED_WORK(&tz->poll_queue, thermal_zone_device_check); tz->temperature = THERMAL_TEMP_INIT; tz->passive = 0; tz->prev_low_trip = -INT_MAX; tz->prev_high_trip = INT_MAX; for_each_trip_desc(tz, td) { struct thermal_instance *instance; list_for_each_entry(instance, &td->thermal_instances, trip_node) instance->initialized = false; } /* * At this point, all valid trips need to be moved to trips_high so that * mitigation can be started if the zone temperature is above them. */ list_for_each_entry_safe(td, next, &tz->trips_invalid, list_node) { if (td->trip.temperature != THERMAL_TEMP_INVALID) move_to_trips_high(tz, td); } /* The trips_reached list may not be empty during system resume. */ list_for_each_entry_safe(td, next, &tz->trips_reached, list_node) { if (td->trip.temperature == THERMAL_TEMP_INVALID) move_to_trips_invalid(tz, td); else move_to_trips_high(tz, td); } } static int thermal_zone_init_governor(struct thermal_zone_device *tz) { struct thermal_governor *governor; guard(mutex)(&thermal_governor_lock); if (tz->tzp) governor = __find_governor(tz->tzp->governor_name); else governor = def_governor; return thermal_set_governor(tz, governor); } static void thermal_zone_init_complete(struct thermal_zone_device *tz) { struct thermal_cooling_device *cdev; guard(mutex)(&thermal_list_lock); list_add_tail(&tz->node, &thermal_tz_list); guard(thermal_zone)(tz); /* Bind cooling devices for this zone. */ list_for_each_entry(cdev, &thermal_cdev_list, node) __thermal_zone_cdev_bind(tz, cdev); tz->state &= ~TZ_STATE_FLAG_INIT; /* * If system suspend or resume is in progress at this point, the * new thermal zone needs to be marked as suspended because * thermal_pm_notify() has run already. */ if (thermal_pm_suspended) tz->state |= TZ_STATE_FLAG_SUSPENDED; __thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED); } /** * thermal_zone_device_register_with_trips() - register a new thermal zone device * @type: the thermal zone device type * @trips: a pointer to an array of thermal trips * @num_trips: the number of trip points the thermal zone support * @devdata: private device data * @ops: standard thermal zone device callbacks * @tzp: thermal zone platform parameters * @passive_delay: number of milliseconds to wait between polls when * performing passive cooling * @polling_delay: number of milliseconds to wait between polls when checking * whether trip points have been crossed (0 for interrupt * driven systems) * * This interface function adds a new thermal zone device (sensor) to * /sys/class/thermal folder as thermal_zone[0-*]. It tries to bind all the * thermal cooling devices registered at the same time. * thermal_zone_device_unregister() must be called when the device is no * longer needed. The passive cooling depends on the .get_trend() return value. * * Return: a pointer to the created struct thermal_zone_device or an * in case of error, an ERR_PTR. Caller must check return value with * IS_ERR*() helpers. */ struct thermal_zone_device * thermal_zone_device_register_with_trips(const char *type, const struct thermal_trip *trips, int num_trips, void *devdata, const struct thermal_zone_device_ops *ops, const struct thermal_zone_params *tzp, unsigned int passive_delay, unsigned int polling_delay) { const struct thermal_trip *trip = trips; struct thermal_zone_device *tz; struct thermal_trip_desc *td; int id; int result; if (!type || strlen(type) == 0) { pr_err("No thermal zone type defined\n"); return ERR_PTR(-EINVAL); } if (strlen(type) >= THERMAL_NAME_LENGTH) { pr_err("Thermal zone name (%s) too long, should be under %d chars\n", type, THERMAL_NAME_LENGTH); return ERR_PTR(-EINVAL); } if (num_trips < 0) { pr_err("Incorrect number of thermal trips\n"); return ERR_PTR(-EINVAL); } if (!ops || !ops->get_temp) { pr_err("Thermal zone device ops not defined or invalid\n"); return ERR_PTR(-EINVAL); } if (num_trips > 0 && !trips) return ERR_PTR(-EINVAL); if (polling_delay && passive_delay > polling_delay) return ERR_PTR(-EINVAL); if (!thermal_class) return ERR_PTR(-ENODEV); tz = kzalloc(struct_size(tz, trips, num_trips), GFP_KERNEL); if (!tz) return ERR_PTR(-ENOMEM); if (tzp) { tz->tzp = kmemdup(tzp, sizeof(*tzp), GFP_KERNEL); if (!tz->tzp) { result = -ENOMEM; goto free_tz; } } INIT_LIST_HEAD(&tz->node); INIT_LIST_HEAD(&tz->trips_high); INIT_LIST_HEAD(&tz->trips_reached); INIT_LIST_HEAD(&tz->trips_invalid); ida_init(&tz->ida); mutex_init(&tz->lock); init_completion(&tz->removal); init_completion(&tz->resume); id = ida_alloc(&thermal_tz_ida, GFP_KERNEL); if (id < 0) { result = id; goto free_tzp; } tz->id = id; strscpy(tz->type, type, sizeof(tz->type)); tz->ops = *ops; if (!tz->ops.critical) tz->ops.critical = thermal_zone_device_critical; tz->device.class = thermal_class; tz->devdata = devdata; tz->num_trips = num_trips; for_each_trip_desc(tz, td) { td->trip = *trip++; INIT_LIST_HEAD(&td->thermal_instances); INIT_LIST_HEAD(&td->list_node); /* * Mark all thresholds as invalid to start with even though * this only matters for the trips that start as invalid and * become valid later. */ move_to_trips_invalid(tz, td); } tz->polling_delay_jiffies = msecs_to_jiffies(polling_delay); tz->passive_delay_jiffies = msecs_to_jiffies(passive_delay); tz->recheck_delay_jiffies = THERMAL_RECHECK_DELAY; tz->state = TZ_STATE_FLAG_INIT; /* sys I/F */ /* Add nodes that are always present via .groups */ result = thermal_zone_create_device_groups(tz); if (result) goto remove_id; result = dev_set_name(&tz->device, "thermal_zone%d", tz->id); if (result) { thermal_zone_destroy_device_groups(tz); goto remove_id; } thermal_zone_device_init(tz); result = device_register(&tz->device); if (result) goto release_device; result = thermal_zone_init_governor(tz); if (result) goto unregister; if (!tz->tzp || !tz->tzp->no_hwmon) { result = thermal_add_hwmon_sysfs(tz); if (result) goto unregister; } result = thermal_thresholds_init(tz); if (result) goto remove_hwmon; thermal_zone_init_complete(tz); thermal_notify_tz_create(tz); thermal_debug_tz_add(tz); return tz; remove_hwmon: thermal_remove_hwmon_sysfs(tz); unregister: device_del(&tz->device); release_device: put_device(&tz->device); remove_id: ida_free(&thermal_tz_ida, id); free_tzp: kfree(tz->tzp); free_tz: kfree(tz); return ERR_PTR(result); } EXPORT_SYMBOL_GPL(thermal_zone_device_register_with_trips); struct thermal_zone_device *thermal_tripless_zone_device_register( const char *type, void *devdata, const struct thermal_zone_device_ops *ops, const struct thermal_zone_params *tzp) { return thermal_zone_device_register_with_trips(type, NULL, 0, devdata, ops, tzp, 0, 0); } EXPORT_SYMBOL_GPL(thermal_tripless_zone_device_register); void *thermal_zone_device_priv(struct thermal_zone_device *tzd) { return tzd->devdata; } EXPORT_SYMBOL_GPL(thermal_zone_device_priv); const char *thermal_zone_device_type(struct thermal_zone_device *tzd) { return tzd->type; } EXPORT_SYMBOL_GPL(thermal_zone_device_type); int thermal_zone_device_id(struct thermal_zone_device *tzd) { return tzd->id; } EXPORT_SYMBOL_GPL(thermal_zone_device_id); struct device *thermal_zone_device(struct thermal_zone_device *tzd) { return &tzd->device; } EXPORT_SYMBOL_GPL(thermal_zone_device); static bool thermal_zone_exit(struct thermal_zone_device *tz) { struct thermal_cooling_device *cdev; guard(mutex)(&thermal_list_lock); if (list_empty(&tz->node)) return false; guard(thermal_zone)(tz); tz->state |= TZ_STATE_FLAG_EXIT; list_del_init(&tz->node); /* Unbind all cdevs associated with this thermal zone. */ list_for_each_entry(cdev, &thermal_cdev_list, node) __thermal_zone_cdev_unbind(tz, cdev); return true; } /** * thermal_zone_device_unregister - removes the registered thermal zone device * @tz: the thermal zone device to remove */ void thermal_zone_device_unregister(struct thermal_zone_device *tz) { if (!tz) return; thermal_debug_tz_remove(tz); if (!thermal_zone_exit(tz)) return; cancel_delayed_work_sync(&tz->poll_queue); thermal_set_governor(tz, NULL); thermal_thresholds_exit(tz); thermal_remove_hwmon_sysfs(tz); ida_free(&thermal_tz_ida, tz->id); ida_destroy(&tz->ida); device_del(&tz->device); put_device(&tz->device); thermal_notify_tz_delete(tz); wait_for_completion(&tz->removal); kfree(tz->tzp); kfree(tz); } EXPORT_SYMBOL_GPL(thermal_zone_device_unregister); /** * thermal_zone_get_zone_by_name() - search for a zone and returns its ref * @name: thermal zone name to fetch the temperature * * When only one zone is found with the passed name, returns a reference to it. * * Return: On success returns a reference to an unique thermal zone with * matching name equals to @name, an ERR_PTR otherwise (-EINVAL for invalid * paramenters, -ENODEV for not found and -EEXIST for multiple matches). */ struct thermal_zone_device *thermal_zone_get_zone_by_name(const char *name) { struct thermal_zone_device *pos = NULL, *ref = ERR_PTR(-EINVAL); unsigned int found = 0; if (!name) return ERR_PTR(-EINVAL); guard(mutex)(&thermal_list_lock); list_for_each_entry(pos, &thermal_tz_list, node) if (!strncasecmp(name, pos->type, THERMAL_NAME_LENGTH)) { found++; ref = pos; } if (!found) return ERR_PTR(-ENODEV); /* Success only when one zone is found. */ if (found > 1) return ERR_PTR(-EEXIST); return ref; } EXPORT_SYMBOL_GPL(thermal_zone_get_zone_by_name); static void thermal_zone_device_resume(struct work_struct *work) { struct thermal_zone_device *tz; tz = container_of(work, struct thermal_zone_device, poll_queue.work); guard(thermal_zone)(tz); tz->state &= ~(TZ_STATE_FLAG_SUSPENDED | TZ_STATE_FLAG_RESUMING); thermal_debug_tz_resume(tz); thermal_zone_device_init(tz); thermal_governor_update_tz(tz, THERMAL_TZ_RESUME); __thermal_zone_device_update(tz, THERMAL_TZ_RESUME); complete(&tz->resume); } static void thermal_zone_pm_prepare(struct thermal_zone_device *tz) { guard(thermal_zone)(tz); if (tz->state & TZ_STATE_FLAG_RESUMING) { /* * thermal_zone_device_resume() queued up for this zone has not * acquired the lock yet, so release it to let the function run * and wait util it has done the work. */ scoped_guard(thermal_zone_reverse, tz) { wait_for_completion(&tz->resume); } } tz->state |= TZ_STATE_FLAG_SUSPENDED; } static void thermal_pm_notify_prepare(void) { struct thermal_zone_device *tz; guard(mutex)(&thermal_list_lock); thermal_pm_suspended = true; list_for_each_entry(tz, &thermal_tz_list, node) thermal_zone_pm_prepare(tz); } static void thermal_zone_pm_complete(struct thermal_zone_device *tz) { guard(thermal_zone)(tz); cancel_delayed_work(&tz->poll_queue); reinit_completion(&tz->resume); tz->state |= TZ_STATE_FLAG_RESUMING; /* * Replace the work function with the resume one, which will restore the * original work function and schedule the polling work if needed. */ INIT_DELAYED_WORK(&tz->poll_queue, thermal_zone_device_resume); /* Queue up the work without a delay. */ mod_delayed_work(system_freezable_power_efficient_wq, &tz->poll_queue, 0); } static void thermal_pm_notify_complete(void) { struct thermal_zone_device *tz; guard(mutex)(&thermal_list_lock); thermal_pm_suspended = false; list_for_each_entry(tz, &thermal_tz_list, node) thermal_zone_pm_complete(tz); } static int thermal_pm_notify(struct notifier_block *nb, unsigned long mode, void *_unused) { switch (mode) { case PM_HIBERNATION_PREPARE: case PM_RESTORE_PREPARE: case PM_SUSPEND_PREPARE: thermal_pm_notify_prepare(); break; case PM_POST_HIBERNATION: case PM_POST_RESTORE: case PM_POST_SUSPEND: thermal_pm_notify_complete(); break; default: break; } return 0; } static struct notifier_block thermal_pm_nb = { .notifier_call = thermal_pm_notify, /* * Run at the lowest priority to avoid interference between the thermal * zone resume work items spawned by thermal_pm_notify() and the other * PM notifiers. */ .priority = INT_MIN, }; static int __init thermal_init(void) { int result; thermal_debug_init(); result = thermal_netlink_init(); if (result) goto error; result = thermal_register_governors(); if (result) goto unregister_netlink; thermal_class = kzalloc(sizeof(*thermal_class), GFP_KERNEL); if (!thermal_class) { result = -ENOMEM; goto unregister_governors; } thermal_class->name = "thermal"; thermal_class->dev_release = thermal_release; result = class_register(thermal_class); if (result) { kfree(thermal_class); thermal_class = NULL; goto unregister_governors; } result = register_pm_notifier(&thermal_pm_nb); if (result) pr_warn("Thermal: Can not register suspend notifier, return %d\n", result); return 0; unregister_governors: thermal_unregister_governors(); unregister_netlink: thermal_netlink_exit(); error: mutex_destroy(&thermal_list_lock); mutex_destroy(&thermal_governor_lock); return result; } postcore_initcall(thermal_init); |
| 71 | 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 | /* * include/linux/topology.h * * Written by: Matthew Dobson, IBM Corporation * * Copyright (C) 2002, IBM Corp. * * All rights reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * This program is distributed in the hope that it will be useful, but * WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or * NON INFRINGEMENT. See the GNU General Public License for more * details. * * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. * * Send feedback to <colpatch@us.ibm.com> */ #ifndef _LINUX_TOPOLOGY_H #define _LINUX_TOPOLOGY_H #include <linux/arch_topology.h> #include <linux/cpumask.h> #include <linux/bitops.h> #include <linux/mmzone.h> #include <linux/smp.h> #include <linux/percpu.h> #include <asm/topology.h> #ifndef nr_cpus_node #define nr_cpus_node(node) cpumask_weight(cpumask_of_node(node)) #endif #define for_each_node_with_cpus(node) \ for_each_online_node(node) \ if (nr_cpus_node(node)) int arch_update_cpu_topology(void); /* Conform to ACPI 2.0 SLIT distance definitions */ #define LOCAL_DISTANCE 10 #define REMOTE_DISTANCE 20 #define DISTANCE_BITS 8 #ifndef node_distance #define node_distance(from,to) ((from) == (to) ? LOCAL_DISTANCE : REMOTE_DISTANCE) #endif #ifndef RECLAIM_DISTANCE /* * If the distance between nodes in a system is larger than RECLAIM_DISTANCE * (in whatever arch specific measurement units returned by node_distance()) * and node_reclaim_mode is enabled then the VM will only call node_reclaim() * on nodes within this distance. */ #define RECLAIM_DISTANCE 30 #endif /* * The following tunable allows platforms to override the default node * reclaim distance (RECLAIM_DISTANCE) if remote memory accesses are * sufficiently fast that the default value actually hurts * performance. * * AMD EPYC machines use this because even though the 2-hop distance * is 32 (3.2x slower than a local memory access) performance actually * *improves* if allowed to reclaim memory and load balance tasks * between NUMA nodes 2-hops apart. */ extern int __read_mostly node_reclaim_distance; #ifndef PENALTY_FOR_NODE_WITH_CPUS #define PENALTY_FOR_NODE_WITH_CPUS (1) #endif #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID DECLARE_PER_CPU(int, numa_node); #ifndef numa_node_id /* Returns the number of the current Node. */ static inline int numa_node_id(void) { return raw_cpu_read(numa_node); } #endif #ifndef cpu_to_node static inline int cpu_to_node(int cpu) { return per_cpu(numa_node, cpu); } #endif #ifndef set_numa_node static inline void set_numa_node(int node) { this_cpu_write(numa_node, node); } #endif #ifndef set_cpu_numa_node static inline void set_cpu_numa_node(int cpu, int node) { per_cpu(numa_node, cpu) = node; } #endif #else /* !CONFIG_USE_PERCPU_NUMA_NODE_ID */ /* Returns the number of the current Node. */ #ifndef numa_node_id static inline int numa_node_id(void) { return cpu_to_node(raw_smp_processor_id()); } #endif #endif /* [!]CONFIG_USE_PERCPU_NUMA_NODE_ID */ #ifdef CONFIG_HAVE_MEMORYLESS_NODES /* * N.B., Do NOT reference the '_numa_mem_' per cpu variable directly. * It will not be defined when CONFIG_HAVE_MEMORYLESS_NODES is not defined. * Use the accessor functions set_numa_mem(), numa_mem_id() and cpu_to_mem(). */ DECLARE_PER_CPU(int, _numa_mem_); #ifndef set_numa_mem static inline void set_numa_mem(int node) { this_cpu_write(_numa_mem_, node); } #endif #ifndef numa_mem_id /* Returns the number of the nearest Node with memory */ static inline int numa_mem_id(void) { return raw_cpu_read(_numa_mem_); } #endif #ifndef cpu_to_mem static inline int cpu_to_mem(int cpu) { return per_cpu(_numa_mem_, cpu); } #endif #ifndef set_cpu_numa_mem static inline void set_cpu_numa_mem(int cpu, int node) { per_cpu(_numa_mem_, cpu) = node; } #endif #else /* !CONFIG_HAVE_MEMORYLESS_NODES */ #ifndef numa_mem_id /* Returns the number of the nearest Node with memory */ static inline int numa_mem_id(void) { return numa_node_id(); } #endif #ifndef cpu_to_mem static inline int cpu_to_mem(int cpu) { return cpu_to_node(cpu); } #endif #endif /* [!]CONFIG_HAVE_MEMORYLESS_NODES */ #if defined(topology_die_id) && defined(topology_die_cpumask) #define TOPOLOGY_DIE_SYSFS #endif #if defined(topology_cluster_id) && defined(topology_cluster_cpumask) #define TOPOLOGY_CLUSTER_SYSFS #endif #if defined(topology_book_id) && defined(topology_book_cpumask) #define TOPOLOGY_BOOK_SYSFS #endif #if defined(topology_drawer_id) && defined(topology_drawer_cpumask) #define TOPOLOGY_DRAWER_SYSFS #endif #ifndef topology_physical_package_id #define topology_physical_package_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_die_id #define topology_die_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_cluster_id #define topology_cluster_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_core_id #define topology_core_id(cpu) ((void)(cpu), 0) #endif #ifndef topology_book_id #define topology_book_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_drawer_id #define topology_drawer_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_ppin #define topology_ppin(cpu) ((void)(cpu), 0ull) #endif #ifndef topology_sibling_cpumask #define topology_sibling_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_core_cpumask #define topology_core_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_cluster_cpumask #define topology_cluster_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_die_cpumask #define topology_die_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_book_cpumask #define topology_book_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_drawer_cpumask #define topology_drawer_cpumask(cpu) cpumask_of(cpu) #endif #if defined(CONFIG_SCHED_SMT) && !defined(cpu_smt_mask) static inline const struct cpumask *cpu_smt_mask(int cpu) { return topology_sibling_cpumask(cpu); } #endif static inline const struct cpumask *cpu_cpu_mask(int cpu) { return cpumask_of_node(cpu_to_node(cpu)); } #ifdef CONFIG_NUMA int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node); extern const struct cpumask *sched_numa_hop_mask(unsigned int node, unsigned int hops); #else static __always_inline int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node) { return cpumask_nth_and(cpu, cpus, cpu_online_mask); } static inline const struct cpumask * sched_numa_hop_mask(unsigned int node, unsigned int hops) { return ERR_PTR(-EOPNOTSUPP); } #endif /* CONFIG_NUMA */ /** * for_each_numa_hop_mask - iterate over cpumasks of increasing NUMA distance * from a given node. * @mask: the iteration variable. * @node: the NUMA node to start the search from. * * Requires rcu_lock to be held. * * Yields cpu_online_mask for @node == NUMA_NO_NODE. */ #define for_each_numa_hop_mask(mask, node) \ for (unsigned int __hops = 0; \ mask = (node != NUMA_NO_NODE || __hops) ? \ sched_numa_hop_mask(node, __hops) : \ cpu_online_mask, \ !IS_ERR_OR_NULL(mask); \ __hops++) #endif /* _LINUX_TOPOLOGY_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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2020 Google LLC. */ #ifndef _LINUX_BPF_LSM_H #define _LINUX_BPF_LSM_H #include <linux/sched.h> #include <linux/bpf.h> #include <linux/bpf_verifier.h> #include <linux/lsm_hooks.h> #ifdef CONFIG_BPF_LSM #define LSM_HOOK(RET, DEFAULT, NAME, ...) \ RET bpf_lsm_##NAME(__VA_ARGS__); #include <linux/lsm_hook_defs.h> #undef LSM_HOOK struct bpf_storage_blob { struct bpf_local_storage __rcu *storage; }; extern struct lsm_blob_sizes bpf_lsm_blob_sizes; int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, const struct bpf_prog *prog); bool bpf_lsm_is_sleepable_hook(u32 btf_id); bool bpf_lsm_is_trusted(const struct bpf_prog *prog); static inline struct bpf_storage_blob *bpf_inode( const struct inode *inode) { if (unlikely(!inode->i_security)) return NULL; return inode->i_security + bpf_lsm_blob_sizes.lbs_inode; } extern const struct bpf_func_proto bpf_inode_storage_get_proto; extern const struct bpf_func_proto bpf_inode_storage_delete_proto; void bpf_inode_storage_free(struct inode *inode); void bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog, bpf_func_t *bpf_func); int bpf_lsm_get_retval_range(const struct bpf_prog *prog, struct bpf_retval_range *range); #else /* !CONFIG_BPF_LSM */ static inline bool bpf_lsm_is_sleepable_hook(u32 btf_id) { return false; } static inline bool bpf_lsm_is_trusted(const struct bpf_prog *prog) { return false; } static inline int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, const struct bpf_prog *prog) { return -EOPNOTSUPP; } static inline struct bpf_storage_blob *bpf_inode( const struct inode *inode) { return NULL; } static inline void bpf_inode_storage_free(struct inode *inode) { } static inline void bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog, bpf_func_t *bpf_func) { } static inline int bpf_lsm_get_retval_range(const struct bpf_prog *prog, struct bpf_retval_range *range) { return -EOPNOTSUPP; } #endif /* CONFIG_BPF_LSM */ #endif /* _LINUX_BPF_LSM_H */ |
| 1 1 1 1 3 3 18 18 18 18 3 3 1 3 3 3 3 3 1 1 1 1 18 18 18 18 18 35 35 35 35 34 18 18 18 18 18 18 18 18 18 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 | // SPDX-License-Identifier: GPL-2.0-only /* * IEEE 802.1D Generic Attribute Registration Protocol (GARP) * * Copyright (c) 2008 Patrick McHardy <kaber@trash.net> */ #include <linux/kernel.h> #include <linux/timer.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <linux/llc.h> #include <linux/slab.h> #include <linux/module.h> #include <net/llc.h> #include <net/llc_pdu.h> #include <net/garp.h> #include <linux/unaligned.h> static unsigned int garp_join_time __read_mostly = 200; module_param(garp_join_time, uint, 0644); MODULE_PARM_DESC(garp_join_time, "Join time in ms (default 200ms)"); MODULE_DESCRIPTION("IEEE 802.1D Generic Attribute Registration Protocol (GARP)"); MODULE_LICENSE("GPL"); static const struct garp_state_trans { u8 state; u8 action; } garp_applicant_state_table[GARP_APPLICANT_MAX + 1][GARP_EVENT_MAX + 1] = { [GARP_APPLICANT_VA] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_AA, .action = GARP_ACTION_S_JOIN_IN }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_AA }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_LA }, }, [GARP_APPLICANT_AA] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_QA, .action = GARP_ACTION_S_JOIN_IN }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QA }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_LA }, }, [GARP_APPLICANT_QA] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QA }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_LA }, }, [GARP_APPLICANT_LA] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_VO, .action = GARP_ACTION_S_LEAVE_EMPTY }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_LA }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_LA }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_LA }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_INVALID }, }, [GARP_APPLICANT_VP] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_AA, .action = GARP_ACTION_S_JOIN_IN }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_AP }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_VO }, }, [GARP_APPLICANT_AP] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_QA, .action = GARP_ACTION_S_JOIN_IN }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QP }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_AO }, }, [GARP_APPLICANT_QP] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QP }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_QO }, }, [GARP_APPLICANT_VO] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_AO }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_INVALID }, }, [GARP_APPLICANT_AO] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QO }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_AP }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_INVALID }, }, [GARP_APPLICANT_QO] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QO }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_QP }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_INVALID }, }, }; static int garp_attr_cmp(const struct garp_attr *attr, const void *data, u8 len, u8 type) { if (attr->type != type) return attr->type - type; if (attr->dlen != len) return attr->dlen - len; return memcmp(attr->data, data, len); } static struct garp_attr *garp_attr_lookup(const struct garp_applicant *app, const void *data, u8 len, u8 type) { struct rb_node *parent = app->gid.rb_node; struct garp_attr *attr; int d; while (parent) { attr = rb_entry(parent, struct garp_attr, node); d = garp_attr_cmp(attr, data, len, type); if (d > 0) parent = parent->rb_left; else if (d < 0) parent = parent->rb_right; else return attr; } return NULL; } static struct garp_attr *garp_attr_create(struct garp_applicant *app, const void *data, u8 len, u8 type) { struct rb_node *parent = NULL, **p = &app->gid.rb_node; struct garp_attr *attr; int d; while (*p) { parent = *p; attr = rb_entry(parent, struct garp_attr, node); d = garp_attr_cmp(attr, data, len, type); if (d > 0) p = &parent->rb_left; else if (d < 0) p = &parent->rb_right; else { /* The attribute already exists; re-use it. */ return attr; } } attr = kmalloc(sizeof(*attr) + len, GFP_ATOMIC); if (!attr) return attr; attr->state = GARP_APPLICANT_VO; attr->type = type; attr->dlen = len; memcpy(attr->data, data, len); rb_link_node(&attr->node, parent, p); rb_insert_color(&attr->node, &app->gid); return attr; } static void garp_attr_destroy(struct garp_applicant *app, struct garp_attr *attr) { rb_erase(&attr->node, &app->gid); kfree(attr); } static void garp_attr_destroy_all(struct garp_applicant *app) { struct rb_node *node, *next; struct garp_attr *attr; for (node = rb_first(&app->gid); next = node ? rb_next(node) : NULL, node != NULL; node = next) { attr = rb_entry(node, struct garp_attr, node); garp_attr_destroy(app, attr); } } static int garp_pdu_init(struct garp_applicant *app) { struct sk_buff *skb; struct garp_pdu_hdr *gp; #define LLC_RESERVE sizeof(struct llc_pdu_un) skb = alloc_skb(app->dev->mtu + LL_RESERVED_SPACE(app->dev), GFP_ATOMIC); if (!skb) return -ENOMEM; skb->dev = app->dev; skb->protocol = htons(ETH_P_802_2); skb_reserve(skb, LL_RESERVED_SPACE(app->dev) + LLC_RESERVE); gp = __skb_put(skb, sizeof(*gp)); put_unaligned(htons(GARP_PROTOCOL_ID), &gp->protocol); app->pdu = skb; return 0; } static int garp_pdu_append_end_mark(struct garp_applicant *app) { if (skb_tailroom(app->pdu) < sizeof(u8)) return -1; __skb_put_u8(app->pdu, GARP_END_MARK); return 0; } static void garp_pdu_queue(struct garp_applicant *app) { if (!app->pdu) return; garp_pdu_append_end_mark(app); garp_pdu_append_end_mark(app); llc_pdu_header_init(app->pdu, LLC_PDU_TYPE_U, LLC_SAP_BSPAN, LLC_SAP_BSPAN, LLC_PDU_CMD); llc_pdu_init_as_ui_cmd(app->pdu); llc_mac_hdr_init(app->pdu, app->dev->dev_addr, app->app->proto.group_address); skb_queue_tail(&app->queue, app->pdu); app->pdu = NULL; } static void garp_queue_xmit(struct garp_applicant *app) { struct sk_buff *skb; while ((skb = skb_dequeue(&app->queue))) dev_queue_xmit(skb); } static int garp_pdu_append_msg(struct garp_applicant *app, u8 attrtype) { struct garp_msg_hdr *gm; if (skb_tailroom(app->pdu) < sizeof(*gm)) return -1; gm = __skb_put(app->pdu, sizeof(*gm)); gm->attrtype = attrtype; garp_cb(app->pdu)->cur_type = attrtype; return 0; } static int garp_pdu_append_attr(struct garp_applicant *app, const struct garp_attr *attr, enum garp_attr_event event) { struct garp_attr_hdr *ga; unsigned int len; int err; again: if (!app->pdu) { err = garp_pdu_init(app); if (err < 0) return err; } if (garp_cb(app->pdu)->cur_type != attr->type) { if (garp_cb(app->pdu)->cur_type && garp_pdu_append_end_mark(app) < 0) goto queue; if (garp_pdu_append_msg(app, attr->type) < 0) goto queue; } len = sizeof(*ga) + attr->dlen; if (skb_tailroom(app->pdu) < len) goto queue; ga = __skb_put(app->pdu, len); ga->len = len; ga->event = event; memcpy(ga->data, attr->data, attr->dlen); return 0; queue: garp_pdu_queue(app); goto again; } static void garp_attr_event(struct garp_applicant *app, struct garp_attr *attr, enum garp_event event) { enum garp_applicant_state state; state = garp_applicant_state_table[attr->state][event].state; if (state == GARP_APPLICANT_INVALID) return; switch (garp_applicant_state_table[attr->state][event].action) { case GARP_ACTION_NONE: break; case GARP_ACTION_S_JOIN_IN: /* When appending the attribute fails, don't update state in * order to retry on next TRANSMIT_PDU event. */ if (garp_pdu_append_attr(app, attr, GARP_JOIN_IN) < 0) return; break; case GARP_ACTION_S_LEAVE_EMPTY: garp_pdu_append_attr(app, attr, GARP_LEAVE_EMPTY); /* As a pure applicant, sending a leave message implies that * the attribute was unregistered and can be destroyed. */ garp_attr_destroy(app, attr); return; default: WARN_ON(1); } attr->state = state; } int garp_request_join(const struct net_device *dev, const struct garp_application *appl, const void *data, u8 len, u8 type) { struct garp_port *port = rtnl_dereference(dev->garp_port); struct garp_applicant *app = rtnl_dereference(port->applicants[appl->type]); struct garp_attr *attr; spin_lock_bh(&app->lock); attr = garp_attr_create(app, data, len, type); if (!attr) { spin_unlock_bh(&app->lock); return -ENOMEM; } garp_attr_event(app, attr, GARP_EVENT_REQ_JOIN); spin_unlock_bh(&app->lock); return 0; } EXPORT_SYMBOL_GPL(garp_request_join); void garp_request_leave(const struct net_device *dev, const struct garp_application *appl, const void *data, u8 len, u8 type) { struct garp_port *port = rtnl_dereference(dev->garp_port); struct garp_applicant *app = rtnl_dereference(port->applicants[appl->type]); struct garp_attr *attr; spin_lock_bh(&app->lock); attr = garp_attr_lookup(app, data, len, type); if (!attr) { spin_unlock_bh(&app->lock); return; } garp_attr_event(app, attr, GARP_EVENT_REQ_LEAVE); spin_unlock_bh(&app->lock); } EXPORT_SYMBOL_GPL(garp_request_leave); static void garp_gid_event(struct garp_applicant *app, enum garp_event event) { struct rb_node *node, *next; struct garp_attr *attr; for (node = rb_first(&app->gid); next = node ? rb_next(node) : NULL, node != NULL; node = next) { attr = rb_entry(node, struct garp_attr, node); garp_attr_event(app, attr, event); } } static void garp_join_timer_arm(struct garp_applicant *app) { unsigned long delay; delay = get_random_u32_below(msecs_to_jiffies(garp_join_time)); mod_timer(&app->join_timer, jiffies + delay); } static void garp_join_timer(struct timer_list *t) { struct garp_applicant *app = from_timer(app, t, join_timer); spin_lock(&app->lock); garp_gid_event(app, GARP_EVENT_TRANSMIT_PDU); garp_pdu_queue(app); spin_unlock(&app->lock); garp_queue_xmit(app); garp_join_timer_arm(app); } static int garp_pdu_parse_end_mark(struct sk_buff *skb) { if (!pskb_may_pull(skb, sizeof(u8))) return -1; if (*skb->data == GARP_END_MARK) { skb_pull(skb, sizeof(u8)); return -1; } return 0; } static int garp_pdu_parse_attr(struct garp_applicant *app, struct sk_buff *skb, u8 attrtype) { const struct garp_attr_hdr *ga; struct garp_attr *attr; enum garp_event event; unsigned int dlen; if (!pskb_may_pull(skb, sizeof(*ga))) return -1; ga = (struct garp_attr_hdr *)skb->data; if (ga->len < sizeof(*ga)) return -1; if (!pskb_may_pull(skb, ga->len)) return -1; skb_pull(skb, ga->len); dlen = sizeof(*ga) - ga->len; if (attrtype > app->app->maxattr) return 0; switch (ga->event) { case GARP_LEAVE_ALL: if (dlen != 0) return -1; garp_gid_event(app, GARP_EVENT_R_LEAVE_EMPTY); return 0; case GARP_JOIN_EMPTY: event = GARP_EVENT_R_JOIN_EMPTY; break; case GARP_JOIN_IN: event = GARP_EVENT_R_JOIN_IN; break; case GARP_LEAVE_EMPTY: event = GARP_EVENT_R_LEAVE_EMPTY; break; case GARP_EMPTY: event = GARP_EVENT_R_EMPTY; break; default: return 0; } if (dlen == 0) return -1; attr = garp_attr_lookup(app, ga->data, dlen, attrtype); if (attr == NULL) return 0; garp_attr_event(app, attr, event); return 0; } static int garp_pdu_parse_msg(struct garp_applicant *app, struct sk_buff *skb) { const struct garp_msg_hdr *gm; if (!pskb_may_pull(skb, sizeof(*gm))) return -1; gm = (struct garp_msg_hdr *)skb->data; if (gm->attrtype == 0) return -1; skb_pull(skb, sizeof(*gm)); while (skb->len > 0) { if (garp_pdu_parse_attr(app, skb, gm->attrtype) < 0) return -1; if (garp_pdu_parse_end_mark(skb) < 0) break; } return 0; } static void garp_pdu_rcv(const struct stp_proto *proto, struct sk_buff *skb, struct net_device *dev) { struct garp_application *appl = proto->data; struct garp_port *port; struct garp_applicant *app; const struct garp_pdu_hdr *gp; port = rcu_dereference(dev->garp_port); if (!port) goto err; app = rcu_dereference(port->applicants[appl->type]); if (!app) goto err; if (!pskb_may_pull(skb, sizeof(*gp))) goto err; gp = (struct garp_pdu_hdr *)skb->data; if (get_unaligned(&gp->protocol) != htons(GARP_PROTOCOL_ID)) goto err; skb_pull(skb, sizeof(*gp)); spin_lock(&app->lock); while (skb->len > 0) { if (garp_pdu_parse_msg(app, skb) < 0) break; if (garp_pdu_parse_end_mark(skb) < 0) break; } spin_unlock(&app->lock); err: kfree_skb(skb); } static int garp_init_port(struct net_device *dev) { struct garp_port *port; port = kzalloc(sizeof(*port), GFP_KERNEL); if (!port) return -ENOMEM; rcu_assign_pointer(dev->garp_port, port); return 0; } static void garp_release_port(struct net_device *dev) { struct garp_port *port = rtnl_dereference(dev->garp_port); unsigned int i; for (i = 0; i <= GARP_APPLICATION_MAX; i++) { if (rtnl_dereference(port->applicants[i])) return; } RCU_INIT_POINTER(dev->garp_port, NULL); kfree_rcu(port, rcu); } int garp_init_applicant(struct net_device *dev, struct garp_application *appl) { struct garp_applicant *app; int err; ASSERT_RTNL(); if (!rtnl_dereference(dev->garp_port)) { err = garp_init_port(dev); if (err < 0) goto err1; } err = -ENOMEM; app = kzalloc(sizeof(*app), GFP_KERNEL); if (!app) goto err2; err = dev_mc_add(dev, appl->proto.group_address); if (err < 0) goto err3; app->dev = dev; app->app = appl; app->gid = RB_ROOT; spin_lock_init(&app->lock); skb_queue_head_init(&app->queue); rcu_assign_pointer(dev->garp_port->applicants[appl->type], app); timer_setup(&app->join_timer, garp_join_timer, 0); garp_join_timer_arm(app); return 0; err3: kfree(app); err2: garp_release_port(dev); err1: return err; } EXPORT_SYMBOL_GPL(garp_init_applicant); void garp_uninit_applicant(struct net_device *dev, struct garp_application *appl) { struct garp_port *port = rtnl_dereference(dev->garp_port); struct garp_applicant *app = rtnl_dereference(port->applicants[appl->type]); ASSERT_RTNL(); RCU_INIT_POINTER(port->applicants[appl->type], NULL); /* Delete timer and generate a final TRANSMIT_PDU event to flush out * all pending messages before the applicant is gone. */ timer_shutdown_sync(&app->join_timer); spin_lock_bh(&app->lock); garp_gid_event(app, GARP_EVENT_TRANSMIT_PDU); garp_attr_destroy_all(app); garp_pdu_queue(app); spin_unlock_bh(&app->lock); garp_queue_xmit(app); dev_mc_del(dev, appl->proto.group_address); kfree_rcu(app, rcu); garp_release_port(dev); } EXPORT_SYMBOL_GPL(garp_uninit_applicant); int garp_register_application(struct garp_application *appl) { appl->proto.rcv = garp_pdu_rcv; appl->proto.data = appl; return stp_proto_register(&appl->proto); } EXPORT_SYMBOL_GPL(garp_register_application); void garp_unregister_application(struct garp_application *appl) { stp_proto_unregister(&appl->proto); } EXPORT_SYMBOL_GPL(garp_unregister_application); |
| 1 1 2 2 2 2 1 8 8 8 8 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Event char devices, giving access to raw input device events. * * Copyright (c) 1999-2002 Vojtech Pavlik */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #define EVDEV_MINOR_BASE 64 #define EVDEV_MINORS 32 #define EVDEV_MIN_BUFFER_SIZE 64U #define EVDEV_BUF_PACKETS 8 #include <linux/poll.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/init.h> #include <linux/input/mt.h> #include <linux/major.h> #include <linux/device.h> #include <linux/cdev.h> #include "input-compat.h" struct evdev { int open; struct input_handle handle; struct evdev_client __rcu *grab; struct list_head client_list; spinlock_t client_lock; /* protects client_list */ struct mutex mutex; struct device dev; struct cdev cdev; bool exist; }; struct evdev_client { unsigned int head; unsigned int tail; unsigned int packet_head; /* [future] position of the first element of next packet */ spinlock_t buffer_lock; /* protects access to buffer, head and tail */ wait_queue_head_t wait; struct fasync_struct *fasync; struct evdev *evdev; struct list_head node; enum input_clock_type clk_type; bool revoked; unsigned long *evmasks[EV_CNT]; unsigned int bufsize; struct input_event buffer[] __counted_by(bufsize); }; static size_t evdev_get_mask_cnt(unsigned int type) { static const size_t counts[EV_CNT] = { /* EV_SYN==0 is EV_CNT, _not_ SYN_CNT, see EVIOCGBIT */ [EV_SYN] = EV_CNT, [EV_KEY] = KEY_CNT, [EV_REL] = REL_CNT, [EV_ABS] = ABS_CNT, [EV_MSC] = MSC_CNT, [EV_SW] = SW_CNT, [EV_LED] = LED_CNT, [EV_SND] = SND_CNT, [EV_FF] = FF_CNT, }; return (type < EV_CNT) ? counts[type] : 0; } /* requires the buffer lock to be held */ static bool __evdev_is_filtered(struct evdev_client *client, unsigned int type, unsigned int code) { unsigned long *mask; size_t cnt; /* EV_SYN and unknown codes are never filtered */ if (type == EV_SYN || type >= EV_CNT) return false; /* first test whether the type is filtered */ mask = client->evmasks[0]; if (mask && !test_bit(type, mask)) return true; /* unknown values are never filtered */ cnt = evdev_get_mask_cnt(type); if (!cnt || code >= cnt) return false; mask = client->evmasks[type]; return mask && !test_bit(code, mask); } /* flush queued events of type @type, caller must hold client->buffer_lock */ static void __evdev_flush_queue(struct evdev_client *client, unsigned int type) { unsigned int i, head, num; unsigned int mask = client->bufsize - 1; bool is_report; struct input_event *ev; BUG_ON(type == EV_SYN); head = client->tail; client->packet_head = client->tail; /* init to 1 so a leading SYN_REPORT will not be dropped */ num = 1; for (i = client->tail; i != client->head; i = (i + 1) & mask) { ev = &client->buffer[i]; is_report = ev->type == EV_SYN && ev->code == SYN_REPORT; if (ev->type == type) { /* drop matched entry */ continue; } else if (is_report && !num) { /* drop empty SYN_REPORT groups */ continue; } else if (head != i) { /* move entry to fill the gap */ client->buffer[head] = *ev; } num++; head = (head + 1) & mask; if (is_report) { num = 0; client->packet_head = head; } } client->head = head; } static void __evdev_queue_syn_dropped(struct evdev_client *client) { ktime_t *ev_time = input_get_timestamp(client->evdev->handle.dev); struct timespec64 ts = ktime_to_timespec64(ev_time[client->clk_type]); struct input_event ev; ev.input_event_sec = ts.tv_sec; ev.input_event_usec = ts.tv_nsec / NSEC_PER_USEC; ev.type = EV_SYN; ev.code = SYN_DROPPED; ev.value = 0; client->buffer[client->head++] = ev; client->head &= client->bufsize - 1; if (unlikely(client->head == client->tail)) { /* drop queue but keep our SYN_DROPPED event */ client->tail = (client->head - 1) & (client->bufsize - 1); client->packet_head = client->tail; } } static void evdev_queue_syn_dropped(struct evdev_client *client) { unsigned long flags; spin_lock_irqsave(&client->buffer_lock, flags); __evdev_queue_syn_dropped(client); spin_unlock_irqrestore(&client->buffer_lock, flags); } static int evdev_set_clk_type(struct evdev_client *client, unsigned int clkid) { unsigned long flags; enum input_clock_type clk_type; switch (clkid) { case CLOCK_REALTIME: clk_type = INPUT_CLK_REAL; break; case CLOCK_MONOTONIC: clk_type = INPUT_CLK_MONO; break; case CLOCK_BOOTTIME: clk_type = INPUT_CLK_BOOT; break; default: return -EINVAL; } if (client->clk_type != clk_type) { client->clk_type = clk_type; /* * Flush pending events and queue SYN_DROPPED event, * but only if the queue is not empty. */ spin_lock_irqsave(&client->buffer_lock, flags); if (client->head != client->tail) { client->packet_head = client->head = client->tail; __evdev_queue_syn_dropped(client); } spin_unlock_irqrestore(&client->buffer_lock, flags); } return 0; } static void __pass_event(struct evdev_client *client, const struct input_event *event) { client->buffer[client->head++] = *event; client->head &= client->bufsize - 1; if (unlikely(client->head == client->tail)) { /* * This effectively "drops" all unconsumed events, leaving * EV_SYN/SYN_DROPPED plus the newest event in the queue. */ client->tail = (client->head - 2) & (client->bufsize - 1); client->buffer[client->tail] = (struct input_event) { .input_event_sec = event->input_event_sec, .input_event_usec = event->input_event_usec, .type = EV_SYN, .code = SYN_DROPPED, .value = 0, }; client->packet_head = client->tail; } if (event->type == EV_SYN && event->code == SYN_REPORT) { client->packet_head = client->head; kill_fasync(&client->fasync, SIGIO, POLL_IN); } } static void evdev_pass_values(struct evdev_client *client, const struct input_value *vals, unsigned int count, ktime_t *ev_time) { const struct input_value *v; struct input_event event; struct timespec64 ts; bool wakeup = false; if (client->revoked) return; ts = ktime_to_timespec64(ev_time[client->clk_type]); event.input_event_sec = ts.tv_sec; event.input_event_usec = ts.tv_nsec / NSEC_PER_USEC; /* Interrupts are disabled, just acquire the lock. */ spin_lock(&client->buffer_lock); for (v = vals; v != vals + count; v++) { if (__evdev_is_filtered(client, v->type, v->code)) continue; if (v->type == EV_SYN && v->code == SYN_REPORT) { /* drop empty SYN_REPORT */ if (client->packet_head == client->head) continue; wakeup = true; } event.type = v->type; event.code = v->code; event.value = v->value; __pass_event(client, &event); } spin_unlock(&client->buffer_lock); if (wakeup) wake_up_interruptible_poll(&client->wait, EPOLLIN | EPOLLOUT | EPOLLRDNORM | EPOLLWRNORM); } /* * Pass incoming events to all connected clients. */ static unsigned int evdev_events(struct input_handle *handle, struct input_value *vals, unsigned int count) { struct evdev *evdev = handle->private; struct evdev_client *client; ktime_t *ev_time = input_get_timestamp(handle->dev); rcu_read_lock(); client = rcu_dereference(evdev->grab); if (client) evdev_pass_values(client, vals, count, ev_time); else list_for_each_entry_rcu(client, &evdev->client_list, node) evdev_pass_values(client, vals, count, ev_time); rcu_read_unlock(); return count; } static int evdev_fasync(int fd, struct file *file, int on) { struct evdev_client *client = file->private_data; return fasync_helper(fd, file, on, &client->fasync); } static void evdev_free(struct device *dev) { struct evdev *evdev = container_of(dev, struct evdev, dev); input_put_device(evdev->handle.dev); kfree(evdev); } /* * Grabs an event device (along with underlying input device). * This function is called with evdev->mutex taken. */ static int evdev_grab(struct evdev *evdev, struct evdev_client *client) { int error; if (evdev->grab) return -EBUSY; error = input_grab_device(&evdev->handle); if (error) return error; rcu_assign_pointer(evdev->grab, client); return 0; } static int evdev_ungrab(struct evdev *evdev, struct evdev_client *client) { struct evdev_client *grab = rcu_dereference_protected(evdev->grab, lockdep_is_held(&evdev->mutex)); if (grab != client) return -EINVAL; rcu_assign_pointer(evdev->grab, NULL); synchronize_rcu(); input_release_device(&evdev->handle); return 0; } static void evdev_attach_client(struct evdev *evdev, struct evdev_client *client) { spin_lock(&evdev->client_lock); list_add_tail_rcu(&client->node, &evdev->client_list); spin_unlock(&evdev->client_lock); } static void evdev_detach_client(struct evdev *evdev, struct evdev_client *client) { spin_lock(&evdev->client_lock); list_del_rcu(&client->node); spin_unlock(&evdev->client_lock); synchronize_rcu(); } static int evdev_open_device(struct evdev *evdev) { int retval; retval = mutex_lock_interruptible(&evdev->mutex); if (retval) return retval; if (!evdev->exist) retval = -ENODEV; else if (!evdev->open++) { retval = input_open_device(&evdev->handle); if (retval) evdev->open--; } mutex_unlock(&evdev->mutex); return retval; } static void evdev_close_device(struct evdev *evdev) { mutex_lock(&evdev->mutex); if (evdev->exist && !--evdev->open) input_close_device(&evdev->handle); mutex_unlock(&evdev->mutex); } /* * Wake up users waiting for IO so they can disconnect from * dead device. */ static void evdev_hangup(struct evdev *evdev) { struct evdev_client *client; spin_lock(&evdev->client_lock); list_for_each_entry(client, &evdev->client_list, node) { kill_fasync(&client->fasync, SIGIO, POLL_HUP); wake_up_interruptible_poll(&client->wait, EPOLLHUP | EPOLLERR); } spin_unlock(&evdev->client_lock); } static int evdev_release(struct inode *inode, struct file *file) { struct evdev_client *client = file->private_data; struct evdev *evdev = client->evdev; unsigned int i; mutex_lock(&evdev->mutex); if (evdev->exist && !client->revoked) input_flush_device(&evdev->handle, file); evdev_ungrab(evdev, client); mutex_unlock(&evdev->mutex); evdev_detach_client(evdev, client); for (i = 0; i < EV_CNT; ++i) bitmap_free(client->evmasks[i]); kvfree(client); evdev_close_device(evdev); return 0; } static unsigned int evdev_compute_buffer_size(struct input_dev *dev) { unsigned int n_events = max(dev->hint_events_per_packet * EVDEV_BUF_PACKETS, EVDEV_MIN_BUFFER_SIZE); return roundup_pow_of_two(n_events); } static int evdev_open(struct inode *inode, struct file *file) { struct evdev *evdev = container_of(inode->i_cdev, struct evdev, cdev); unsigned int bufsize = evdev_compute_buffer_size(evdev->handle.dev); struct evdev_client *client; int error; client = kvzalloc(struct_size(client, buffer, bufsize), GFP_KERNEL); if (!client) return -ENOMEM; init_waitqueue_head(&client->wait); client->bufsize = bufsize; spin_lock_init(&client->buffer_lock); client->evdev = evdev; evdev_attach_client(evdev, client); error = evdev_open_device(evdev); if (error) goto err_free_client; file->private_data = client; stream_open(inode, file); return 0; err_free_client: evdev_detach_client(evdev, client); kvfree(client); return error; } static ssize_t evdev_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { struct evdev_client *client = file->private_data; struct evdev *evdev = client->evdev; struct input_event event; int retval = 0; /* * Limit amount of data we inject into the input subsystem so that * we do not hold evdev->mutex for too long. 4096 bytes corresponds * to 170 input events. */ count = min(count, 4096); if (count != 0 && count < input_event_size()) return -EINVAL; retval = mutex_lock_interruptible(&evdev->mutex); if (retval) return retval; if (!evdev->exist || client->revoked) { retval = -ENODEV; goto out; } while (retval + input_event_size() <= count) { if (input_event_from_user(buffer + retval, &event)) { retval = -EFAULT; goto out; } retval += input_event_size(); input_inject_event(&evdev->handle, event.type, event.code, event.value); cond_resched(); } out: mutex_unlock(&evdev->mutex); return retval; } static int evdev_fetch_next_event(struct evdev_client *client, struct input_event *event) { int have_event; spin_lock_irq(&client->buffer_lock); have_event = client->packet_head != client->tail; if (have_event) { *event = client->buffer[client->tail++]; client->tail &= client->bufsize - 1; } spin_unlock_irq(&client->buffer_lock); return have_event; } static ssize_t evdev_read(struct file *file, char __user *buffer, size_t count, loff_t *ppos) { struct evdev_client *client = file->private_data; struct evdev *evdev = client->evdev; struct input_event event; size_t read = 0; int error; if (count != 0 && count < input_event_size()) return -EINVAL; for (;;) { if (!evdev->exist || client->revoked) return -ENODEV; if (client->packet_head == client->tail && (file->f_flags & O_NONBLOCK)) return -EAGAIN; /* * count == 0 is special - no IO is done but we check * for error conditions (see above). */ if (count == 0) break; while (read + input_event_size() <= count && evdev_fetch_next_event(client, &event)) { if (input_event_to_user(buffer + read, &event)) return -EFAULT; read += input_event_size(); } if (read) break; if (!(file->f_flags & O_NONBLOCK)) { error = wait_event_interruptible(client->wait, client->packet_head != client->tail || !evdev->exist || client->revoked); if (error) return error; } } return read; } /* No kernel lock - fine */ static __poll_t evdev_poll(struct file *file, poll_table *wait) { struct evdev_client *client = file->private_data; struct evdev *evdev = client->evdev; __poll_t mask; poll_wait(file, &client->wait, wait); if (evdev->exist && !client->revoked) mask = EPOLLOUT | EPOLLWRNORM; else mask = EPOLLHUP | EPOLLERR; if (client->packet_head != client->tail) mask |= EPOLLIN | EPOLLRDNORM; return mask; } #ifdef CONFIG_COMPAT #define BITS_PER_LONG_COMPAT (sizeof(compat_long_t) * 8) #define BITS_TO_LONGS_COMPAT(x) ((((x) - 1) / BITS_PER_LONG_COMPAT) + 1) #ifdef __BIG_ENDIAN static int bits_to_user(unsigned long *bits, unsigned int maxbit, unsigned int maxlen, void __user *p, int compat) { int len, i; if (compat) { len = BITS_TO_LONGS_COMPAT(maxbit) * sizeof(compat_long_t); if (len > maxlen) len = maxlen; for (i = 0; i < len / sizeof(compat_long_t); i++) if (copy_to_user((compat_long_t __user *) p + i, (compat_long_t *) bits + i + 1 - ((i % 2) << 1), sizeof(compat_long_t))) return -EFAULT; } else { len = BITS_TO_LONGS(maxbit) * sizeof(long); if (len > maxlen) len = maxlen; if (copy_to_user(p, bits, len)) return -EFAULT; } return len; } static int bits_from_user(unsigned long *bits, unsigned int maxbit, unsigned int maxlen, const void __user *p, int compat) { int len, i; if (compat) { if (maxlen % sizeof(compat_long_t)) return -EINVAL; len = BITS_TO_LONGS_COMPAT(maxbit) * sizeof(compat_long_t); if (len > maxlen) len = maxlen; for (i = 0; i < len / sizeof(compat_long_t); i++) if (copy_from_user((compat_long_t *) bits + i + 1 - ((i % 2) << 1), (compat_long_t __user *) p + i, sizeof(compat_long_t))) return -EFAULT; if (i % 2) *((compat_long_t *) bits + i - 1) = 0; } else { if (maxlen % sizeof(long)) return -EINVAL; len = BITS_TO_LONGS(maxbit) * sizeof(long); if (len > maxlen) len = maxlen; if (copy_from_user(bits, p, len)) return -EFAULT; } return len; } #else static int bits_to_user(unsigned long *bits, unsigned int maxbit, unsigned int maxlen, void __user *p, int compat) { int len = compat ? BITS_TO_LONGS_COMPAT(maxbit) * sizeof(compat_long_t) : BITS_TO_LONGS(maxbit) * sizeof(long); if (len > maxlen) len = maxlen; return copy_to_user(p, bits, len) ? -EFAULT : len; } static int bits_from_user(unsigned long *bits, unsigned int maxbit, unsigned int maxlen, const void __user *p, int compat) { size_t chunk_size = compat ? sizeof(compat_long_t) : sizeof(long); int len; if (maxlen % chunk_size) return -EINVAL; len = compat ? BITS_TO_LONGS_COMPAT(maxbit) : BITS_TO_LONGS(maxbit); len *= chunk_size; if (len > maxlen) len = maxlen; return copy_from_user(bits, p, len) ? -EFAULT : len; } #endif /* __BIG_ENDIAN */ #else static int bits_to_user(unsigned long *bits, unsigned int maxbit, unsigned int maxlen, void __user *p, int compat) { int len = BITS_TO_LONGS(maxbit) * sizeof(long); if (len > maxlen) len = maxlen; return copy_to_user(p, bits, len) ? -EFAULT : len; } static int bits_from_user(unsigned long *bits, unsigned int maxbit, unsigned int maxlen, const void __user *p, int compat) { int len; if (maxlen % sizeof(long)) return -EINVAL; len = BITS_TO_LONGS(maxbit) * sizeof(long); if (len > maxlen) len = maxlen; return copy_from_user(bits, p, len) ? -EFAULT : len; } #endif /* CONFIG_COMPAT */ static int str_to_user(const char *str, unsigned int maxlen, void __user *p) { int len; if (!str) return -ENOENT; len = strlen(str) + 1; if (len > maxlen) len = maxlen; return copy_to_user(p, str, len) ? -EFAULT : len; } static int handle_eviocgbit(struct input_dev *dev, unsigned int type, unsigned int size, void __user *p, int compat_mode) { unsigned long *bits; int len; switch (type) { case 0: bits = dev->evbit; len = EV_MAX; break; case EV_KEY: bits = dev->keybit; len = KEY_MAX; break; case EV_REL: bits = dev->relbit; len = REL_MAX; break; case EV_ABS: bits = dev->absbit; len = ABS_MAX; break; case EV_MSC: bits = dev->mscbit; len = MSC_MAX; break; case EV_LED: bits = dev->ledbit; len = LED_MAX; break; case EV_SND: bits = dev->sndbit; len = SND_MAX; break; case EV_FF: bits = dev->ffbit; len = FF_MAX; break; case EV_SW: bits = dev->swbit; len = SW_MAX; break; default: return -EINVAL; } return bits_to_user(bits, len, size, p, compat_mode); } static int evdev_handle_get_keycode(struct input_dev *dev, void __user *p) { struct input_keymap_entry ke = { .len = sizeof(unsigned int), .flags = 0, }; int __user *ip = (int __user *)p; int error; /* legacy case */ if (copy_from_user(ke.scancode, p, sizeof(unsigned int))) return -EFAULT; error = input_get_keycode(dev, &ke); if (error) return error; if (put_user(ke.keycode, ip + 1)) return -EFAULT; return 0; } static int evdev_handle_get_keycode_v2(struct input_dev *dev, void __user *p) { struct input_keymap_entry ke; int error; if (copy_from_user(&ke, p, sizeof(ke))) return -EFAULT; error = input_get_keycode(dev, &ke); if (error) return error; if (copy_to_user(p, &ke, sizeof(ke))) return -EFAULT; return 0; } static int evdev_handle_set_keycode(struct input_dev *dev, void __user *p) { struct input_keymap_entry ke = { .len = sizeof(unsigned int), .flags = 0, }; int __user *ip = (int __user *)p; if (copy_from_user(ke.scancode, p, sizeof(unsigned int))) return -EFAULT; if (get_user(ke.keycode, ip + 1)) return -EFAULT; return input_set_keycode(dev, &ke); } static int evdev_handle_set_keycode_v2(struct input_dev *dev, void __user *p) { struct input_keymap_entry ke; if (copy_from_user(&ke, p, sizeof(ke))) return -EFAULT; if (ke.len > sizeof(ke.scancode)) return -EINVAL; return input_set_keycode(dev, &ke); } /* * If we transfer state to the user, we should flush all pending events * of the same type from the client's queue. Otherwise, they might end up * with duplicate events, which can screw up client's state tracking. * If bits_to_user fails after flushing the queue, we queue a SYN_DROPPED * event so user-space will notice missing events. * * LOCKING: * We need to take event_lock before buffer_lock to avoid dead-locks. But we * need the even_lock only to guarantee consistent state. We can safely release * it while flushing the queue. This allows input-core to handle filters while * we flush the queue. */ static int evdev_handle_get_val(struct evdev_client *client, struct input_dev *dev, unsigned int type, unsigned long *bits, unsigned int maxbit, unsigned int maxlen, void __user *p, int compat) { int ret; unsigned long *mem; mem = bitmap_alloc(maxbit, GFP_KERNEL); if (!mem) return -ENOMEM; spin_lock_irq(&dev->event_lock); spin_lock(&client->buffer_lock); bitmap_copy(mem, bits, maxbit); spin_unlock(&dev->event_lock); __evdev_flush_queue(client, type); spin_unlock_irq(&client->buffer_lock); ret = bits_to_user(mem, maxbit, maxlen, p, compat); if (ret < 0) evdev_queue_syn_dropped(client); bitmap_free(mem); return ret; } static int evdev_handle_mt_request(struct input_dev *dev, unsigned int size, int __user *ip) { const struct input_mt *mt = dev->mt; unsigned int code; int max_slots; int i; if (get_user(code, &ip[0])) return -EFAULT; if (!mt || !input_is_mt_value(code)) return -EINVAL; max_slots = (size - sizeof(__u32)) / sizeof(__s32); for (i = 0; i < mt->num_slots && i < max_slots; i++) { int value = input_mt_get_value(&mt->slots[i], code); if (put_user(value, &ip[1 + i])) return -EFAULT; } return 0; } static int evdev_revoke(struct evdev *evdev, struct evdev_client *client, struct file *file) { client->revoked = true; evdev_ungrab(evdev, client); input_flush_device(&evdev->handle, file); wake_up_interruptible_poll(&client->wait, EPOLLHUP | EPOLLERR); return 0; } /* must be called with evdev-mutex held */ static int evdev_set_mask(struct evdev_client *client, unsigned int type, const void __user *codes, u32 codes_size, int compat) { unsigned long flags, *mask, *oldmask; size_t cnt; int error; /* we allow unknown types and 'codes_size > size' for forward-compat */ cnt = evdev_get_mask_cnt(type); if (!cnt) return 0; mask = bitmap_zalloc(cnt, GFP_KERNEL); if (!mask) return -ENOMEM; error = bits_from_user(mask, cnt - 1, codes_size, codes, compat); if (error < 0) { bitmap_free(mask); return error; } spin_lock_irqsave(&client->buffer_lock, flags); oldmask = client->evmasks[type]; client->evmasks[type] = mask; spin_unlock_irqrestore(&client->buffer_lock, flags); bitmap_free(oldmask); return 0; } /* must be called with evdev-mutex held */ static int evdev_get_mask(struct evdev_client *client, unsigned int type, void __user *codes, u32 codes_size, int compat) { unsigned long *mask; size_t cnt, size, xfer_size; int i; int error; /* we allow unknown types and 'codes_size > size' for forward-compat */ cnt = evdev_get_mask_cnt(type); size = sizeof(unsigned long) * BITS_TO_LONGS(cnt); xfer_size = min_t(size_t, codes_size, size); if (cnt > 0) { mask = client->evmasks[type]; if (mask) { error = bits_to_user(mask, cnt - 1, xfer_size, codes, compat); if (error < 0) return error; } else { /* fake mask with all bits set */ for (i = 0; i < xfer_size; i++) if (put_user(0xffU, (u8 __user *)codes + i)) return -EFAULT; } } if (xfer_size < codes_size) if (clear_user(codes + xfer_size, codes_size - xfer_size)) return -EFAULT; return 0; } static long evdev_do_ioctl(struct file *file, unsigned int cmd, void __user *p, int compat_mode) { struct evdev_client *client = file->private_data; struct evdev *evdev = client->evdev; struct input_dev *dev = evdev->handle.dev; struct input_absinfo abs; struct input_mask mask; struct ff_effect effect; int __user *ip = (int __user *)p; unsigned int i, t, u, v; unsigned int size; int error; /* First we check for fixed-length commands */ switch (cmd) { case EVIOCGVERSION: return put_user(EV_VERSION, ip); case EVIOCGID: if (copy_to_user(p, &dev->id, sizeof(struct input_id))) return -EFAULT; return 0; case EVIOCGREP: if (!test_bit(EV_REP, dev->evbit)) return -ENOSYS; if (put_user(dev->rep[REP_DELAY], ip)) return -EFAULT; if (put_user(dev->rep[REP_PERIOD], ip + 1)) return -EFAULT; return 0; case EVIOCSREP: if (!test_bit(EV_REP, dev->evbit)) return -ENOSYS; if (get_user(u, ip)) return -EFAULT; if (get_user(v, ip + 1)) return -EFAULT; input_inject_event(&evdev->handle, EV_REP, REP_DELAY, u); input_inject_event(&evdev->handle, EV_REP, REP_PERIOD, v); return 0; case EVIOCRMFF: return input_ff_erase(dev, (int)(unsigned long) p, file); case EVIOCGEFFECTS: i = test_bit(EV_FF, dev->evbit) ? dev->ff->max_effects : 0; if (put_user(i, ip)) return -EFAULT; return 0; case EVIOCGRAB: if (p) return evdev_grab(evdev, client); else return evdev_ungrab(evdev, client); case EVIOCREVOKE: if (p) return -EINVAL; else return evdev_revoke(evdev, client, file); case EVIOCGMASK: { void __user *codes_ptr; if (copy_from_user(&mask, p, sizeof(mask))) return -EFAULT; codes_ptr = (void __user *)(unsigned long)mask.codes_ptr; return evdev_get_mask(client, mask.type, codes_ptr, mask.codes_size, compat_mode); } case EVIOCSMASK: { const void __user *codes_ptr; if (copy_from_user(&mask, p, sizeof(mask))) return -EFAULT; codes_ptr = (const void __user *)(unsigned long)mask.codes_ptr; return evdev_set_mask(client, mask.type, codes_ptr, mask.codes_size, compat_mode); } case EVIOCSCLOCKID: if (copy_from_user(&i, p, sizeof(unsigned int))) return -EFAULT; return evdev_set_clk_type(client, i); case EVIOCGKEYCODE: return evdev_handle_get_keycode(dev, p); case EVIOCSKEYCODE: return evdev_handle_set_keycode(dev, p); case EVIOCGKEYCODE_V2: return evdev_handle_get_keycode_v2(dev, p); case EVIOCSKEYCODE_V2: return evdev_handle_set_keycode_v2(dev, p); } size = _IOC_SIZE(cmd); /* Now check variable-length commands */ #define EVIOC_MASK_SIZE(nr) ((nr) & ~(_IOC_SIZEMASK << _IOC_SIZESHIFT)) switch (EVIOC_MASK_SIZE(cmd)) { case EVIOCGPROP(0): return bits_to_user(dev->propbit, INPUT_PROP_MAX, size, p, compat_mode); case EVIOCGMTSLOTS(0): return evdev_handle_mt_request(dev, size, ip); case EVIOCGKEY(0): return evdev_handle_get_val(client, dev, EV_KEY, dev->key, KEY_MAX, size, p, compat_mode); case EVIOCGLED(0): return evdev_handle_get_val(client, dev, EV_LED, dev->led, LED_MAX, size, p, compat_mode); case EVIOCGSND(0): return evdev_handle_get_val(client, dev, EV_SND, dev->snd, SND_MAX, size, p, compat_mode); case EVIOCGSW(0): return evdev_handle_get_val(client, dev, EV_SW, dev->sw, SW_MAX, size, p, compat_mode); case EVIOCGNAME(0): return str_to_user(dev->name, size, p); case EVIOCGPHYS(0): return str_to_user(dev->phys, size, p); case EVIOCGUNIQ(0): return str_to_user(dev->uniq, size, p); case EVIOC_MASK_SIZE(EVIOCSFF): if (input_ff_effect_from_user(p, size, &effect)) return -EFAULT; error = input_ff_upload(dev, &effect, file); if (error) return error; if (put_user(effect.id, &(((struct ff_effect __user *)p)->id))) return -EFAULT; return 0; } /* Multi-number variable-length handlers */ if (_IOC_TYPE(cmd) != 'E') return -EINVAL; if (_IOC_DIR(cmd) == _IOC_READ) { if ((_IOC_NR(cmd) & ~EV_MAX) == _IOC_NR(EVIOCGBIT(0, 0))) return handle_eviocgbit(dev, _IOC_NR(cmd) & EV_MAX, size, p, compat_mode); if ((_IOC_NR(cmd) & ~ABS_MAX) == _IOC_NR(EVIOCGABS(0))) { if (!dev->absinfo) return -EINVAL; t = _IOC_NR(cmd) & ABS_MAX; abs = dev->absinfo[t]; if (copy_to_user(p, &abs, min_t(size_t, size, sizeof(struct input_absinfo)))) return -EFAULT; return 0; } } if (_IOC_DIR(cmd) == _IOC_WRITE) { if ((_IOC_NR(cmd) & ~ABS_MAX) == _IOC_NR(EVIOCSABS(0))) { if (!dev->absinfo) return -EINVAL; t = _IOC_NR(cmd) & ABS_MAX; if (copy_from_user(&abs, p, min_t(size_t, size, sizeof(struct input_absinfo)))) return -EFAULT; if (size < sizeof(struct input_absinfo)) abs.resolution = 0; /* We can't change number of reserved MT slots */ if (t == ABS_MT_SLOT) return -EINVAL; /* * Take event lock to ensure that we are not * changing device parameters in the middle * of event. */ spin_lock_irq(&dev->event_lock); dev->absinfo[t] = abs; spin_unlock_irq(&dev->event_lock); return 0; } } return -EINVAL; } static long evdev_ioctl_handler(struct file *file, unsigned int cmd, void __user *p, int compat_mode) { struct evdev_client *client = file->private_data; struct evdev *evdev = client->evdev; int retval; retval = mutex_lock_interruptible(&evdev->mutex); if (retval) return retval; if (!evdev->exist || client->revoked) { retval = -ENODEV; goto out; } retval = evdev_do_ioctl(file, cmd, p, compat_mode); out: mutex_unlock(&evdev->mutex); return retval; } static long evdev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return evdev_ioctl_handler(file, cmd, (void __user *)arg, 0); } #ifdef CONFIG_COMPAT static long evdev_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) { return evdev_ioctl_handler(file, cmd, compat_ptr(arg), 1); } #endif static const struct file_operations evdev_fops = { .owner = THIS_MODULE, .read = evdev_read, .write = evdev_write, .poll = evdev_poll, .open = evdev_open, .release = evdev_release, .unlocked_ioctl = evdev_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = evdev_ioctl_compat, #endif .fasync = evdev_fasync, }; /* * Mark device non-existent. This disables writes, ioctls and * prevents new users from opening the device. Already posted * blocking reads will stay, however new ones will fail. */ static void evdev_mark_dead(struct evdev *evdev) { mutex_lock(&evdev->mutex); evdev->exist = false; mutex_unlock(&evdev->mutex); } static void evdev_cleanup(struct evdev *evdev) { struct input_handle *handle = &evdev->handle; evdev_mark_dead(evdev); evdev_hangup(evdev); /* evdev is marked dead so no one else accesses evdev->open */ if (evdev->open) { input_flush_device(handle, NULL); input_close_device(handle); } } /* * Create new evdev device. Note that input core serializes calls * to connect and disconnect. */ static int evdev_connect(struct input_handler *handler, struct input_dev *dev, const struct input_device_id *id) { struct evdev *evdev; int minor; int dev_no; int error; minor = input_get_new_minor(EVDEV_MINOR_BASE, EVDEV_MINORS, true); if (minor < 0) { error = minor; pr_err("failed to reserve new minor: %d\n", error); return error; } evdev = kzalloc(sizeof(struct evdev), GFP_KERNEL); if (!evdev) { error = -ENOMEM; goto err_free_minor; } INIT_LIST_HEAD(&evdev->client_list); spin_lock_init(&evdev->client_lock); mutex_init(&evdev->mutex); evdev->exist = true; dev_no = minor; /* Normalize device number if it falls into legacy range */ if (dev_no < EVDEV_MINOR_BASE + EVDEV_MINORS) dev_no -= EVDEV_MINOR_BASE; dev_set_name(&evdev->dev, "event%d", dev_no); evdev->handle.dev = input_get_device(dev); evdev->handle.name = dev_name(&evdev->dev); evdev->handle.handler = handler; evdev->handle.private = evdev; evdev->dev.devt = MKDEV(INPUT_MAJOR, minor); evdev->dev.class = &input_class; evdev->dev.parent = &dev->dev; evdev->dev.release = evdev_free; device_initialize(&evdev->dev); error = input_register_handle(&evdev->handle); if (error) goto err_free_evdev; cdev_init(&evdev->cdev, &evdev_fops); error = cdev_device_add(&evdev->cdev, &evdev->dev); if (error) goto err_cleanup_evdev; return 0; err_cleanup_evdev: evdev_cleanup(evdev); input_unregister_handle(&evdev->handle); err_free_evdev: put_device(&evdev->dev); err_free_minor: input_free_minor(minor); return error; } static void evdev_disconnect(struct input_handle *handle) { struct evdev *evdev = handle->private; cdev_device_del(&evdev->cdev, &evdev->dev); evdev_cleanup(evdev); input_free_minor(MINOR(evdev->dev.devt)); input_unregister_handle(handle); put_device(&evdev->dev); } static const struct input_device_id evdev_ids[] = { { .driver_info = 1 }, /* Matches all devices */ { }, /* Terminating zero entry */ }; MODULE_DEVICE_TABLE(input, evdev_ids); static struct input_handler evdev_handler = { .events = evdev_events, .connect = evdev_connect, .disconnect = evdev_disconnect, .legacy_minors = true, .minor = EVDEV_MINOR_BASE, .name = "evdev", .id_table = evdev_ids, }; static int __init evdev_init(void) { return input_register_handler(&evdev_handler); } static void __exit evdev_exit(void) { input_unregister_handler(&evdev_handler); } module_init(evdev_init); module_exit(evdev_exit); MODULE_AUTHOR("Vojtech Pavlik <vojtech@ucw.cz>"); MODULE_DESCRIPTION("Input driver event char devices"); MODULE_LICENSE("GPL"); |
| 2 2 1 1 2 2 1 1 2 2 6 2 33 34 2 32 24 1 4 3 1 1 1 2 2 1 1 1 1 2 1 1 1 1 1 2 1 1 2 5 4 1 1 4 1 2 1 1 1 1 1 1 22 22 9 1 1 4 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Ioctl handler * Linux ethernet bridge * * Authors: * Lennert Buytenhek <buytenh@gnu.org> */ #include <linux/capability.h> #include <linux/compat.h> #include <linux/kernel.h> #include <linux/if_bridge.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <linux/times.h> #include <net/net_namespace.h> #include <linux/uaccess.h> #include "br_private.h" static int get_bridge_ifindices(struct net *net, int *indices, int num) { struct net_device *dev; int i = 0; rcu_read_lock(); for_each_netdev_rcu(net, dev) { if (i >= num) break; if (netif_is_bridge_master(dev)) indices[i++] = dev->ifindex; } rcu_read_unlock(); return i; } /* called with RTNL */ static void get_port_ifindices(struct net_bridge *br, int *ifindices, int num) { struct net_bridge_port *p; list_for_each_entry(p, &br->port_list, list) { if (p->port_no < num) ifindices[p->port_no] = p->dev->ifindex; } } /* * Format up to a page worth of forwarding table entries * userbuf -- where to copy result * maxnum -- maximum number of entries desired * (limited to a page for sanity) * offset -- number of records to skip */ static int get_fdb_entries(struct net_bridge *br, void __user *userbuf, unsigned long maxnum, unsigned long offset) { int num; void *buf; size_t size; /* Clamp size to PAGE_SIZE, test maxnum to avoid overflow */ if (maxnum > PAGE_SIZE/sizeof(struct __fdb_entry)) maxnum = PAGE_SIZE/sizeof(struct __fdb_entry); size = maxnum * sizeof(struct __fdb_entry); buf = kmalloc(size, GFP_USER); if (!buf) return -ENOMEM; num = br_fdb_fillbuf(br, buf, maxnum, offset); if (num > 0) { if (copy_to_user(userbuf, buf, array_size(num, sizeof(struct __fdb_entry)))) num = -EFAULT; } kfree(buf); return num; } /* called with RTNL */ static int add_del_if(struct net_bridge *br, int ifindex, int isadd) { struct net *net = dev_net(br->dev); struct net_device *dev; int ret; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; dev = __dev_get_by_index(net, ifindex); if (dev == NULL) return -EINVAL; if (isadd) ret = br_add_if(br, dev, NULL); else ret = br_del_if(br, dev); return ret; } #define BR_UARGS_MAX 4 static int br_dev_read_uargs(unsigned long *args, size_t nr_args, void __user **argp, void __user *data) { int ret; if (nr_args < 2 || nr_args > BR_UARGS_MAX) return -EINVAL; if (in_compat_syscall()) { unsigned int cargs[BR_UARGS_MAX]; int i; ret = copy_from_user(cargs, data, nr_args * sizeof(*cargs)); if (ret) goto fault; for (i = 0; i < nr_args; ++i) args[i] = cargs[i]; *argp = compat_ptr(args[1]); } else { ret = copy_from_user(args, data, nr_args * sizeof(*args)); if (ret) goto fault; *argp = (void __user *)args[1]; } return 0; fault: return -EFAULT; } /* * Legacy ioctl's through SIOCDEVPRIVATE * This interface is deprecated because it was too difficult * to do the translation for 32/64bit ioctl compatibility. */ int br_dev_siocdevprivate(struct net_device *dev, struct ifreq *rq, void __user *data, int cmd) { struct net_bridge *br = netdev_priv(dev); struct net_bridge_port *p = NULL; unsigned long args[4]; void __user *argp; int ret; ret = br_dev_read_uargs(args, ARRAY_SIZE(args), &argp, data); if (ret) return ret; switch (args[0]) { case BRCTL_ADD_IF: case BRCTL_DEL_IF: return add_del_if(br, args[1], args[0] == BRCTL_ADD_IF); case BRCTL_GET_BRIDGE_INFO: { struct __bridge_info b; memset(&b, 0, sizeof(struct __bridge_info)); rcu_read_lock(); memcpy(&b.designated_root, &br->designated_root, 8); memcpy(&b.bridge_id, &br->bridge_id, 8); b.root_path_cost = br->root_path_cost; b.max_age = jiffies_to_clock_t(br->max_age); b.hello_time = jiffies_to_clock_t(br->hello_time); b.forward_delay = br->forward_delay; b.bridge_max_age = br->bridge_max_age; b.bridge_hello_time = br->bridge_hello_time; b.bridge_forward_delay = jiffies_to_clock_t(br->bridge_forward_delay); b.topology_change = br->topology_change; b.topology_change_detected = br->topology_change_detected; b.root_port = br->root_port; b.stp_enabled = (br->stp_enabled != BR_NO_STP); b.ageing_time = jiffies_to_clock_t(br->ageing_time); b.hello_timer_value = br_timer_value(&br->hello_timer); b.tcn_timer_value = br_timer_value(&br->tcn_timer); b.topology_change_timer_value = br_timer_value(&br->topology_change_timer); b.gc_timer_value = br_timer_value(&br->gc_work.timer); rcu_read_unlock(); if (copy_to_user((void __user *)args[1], &b, sizeof(b))) return -EFAULT; return 0; } case BRCTL_GET_PORT_LIST: { int num, *indices; num = args[2]; if (num < 0) return -EINVAL; if (num == 0) num = 256; if (num > BR_MAX_PORTS) num = BR_MAX_PORTS; indices = kcalloc(num, sizeof(int), GFP_KERNEL); if (indices == NULL) return -ENOMEM; get_port_ifindices(br, indices, num); if (copy_to_user(argp, indices, array_size(num, sizeof(int)))) num = -EFAULT; kfree(indices); return num; } case BRCTL_SET_BRIDGE_FORWARD_DELAY: if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = br_set_forward_delay(br, args[1]); break; case BRCTL_SET_BRIDGE_HELLO_TIME: if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = br_set_hello_time(br, args[1]); break; case BRCTL_SET_BRIDGE_MAX_AGE: if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = br_set_max_age(br, args[1]); break; case BRCTL_SET_AGEING_TIME: if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = br_set_ageing_time(br, args[1]); break; case BRCTL_GET_PORT_INFO: { struct __port_info p; struct net_bridge_port *pt; rcu_read_lock(); if ((pt = br_get_port(br, args[2])) == NULL) { rcu_read_unlock(); return -EINVAL; } memset(&p, 0, sizeof(struct __port_info)); memcpy(&p.designated_root, &pt->designated_root, 8); memcpy(&p.designated_bridge, &pt->designated_bridge, 8); p.port_id = pt->port_id; p.designated_port = pt->designated_port; p.path_cost = pt->path_cost; p.designated_cost = pt->designated_cost; p.state = pt->state; p.top_change_ack = pt->topology_change_ack; p.config_pending = pt->config_pending; p.message_age_timer_value = br_timer_value(&pt->message_age_timer); p.forward_delay_timer_value = br_timer_value(&pt->forward_delay_timer); p.hold_timer_value = br_timer_value(&pt->hold_timer); rcu_read_unlock(); if (copy_to_user(argp, &p, sizeof(p))) return -EFAULT; return 0; } case BRCTL_SET_BRIDGE_STP_STATE: if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = br_stp_set_enabled(br, args[1], NULL); break; case BRCTL_SET_BRIDGE_PRIORITY: if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; br_stp_set_bridge_priority(br, args[1]); ret = 0; break; case BRCTL_SET_PORT_PRIORITY: { if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; spin_lock_bh(&br->lock); if ((p = br_get_port(br, args[1])) == NULL) ret = -EINVAL; else ret = br_stp_set_port_priority(p, args[2]); spin_unlock_bh(&br->lock); break; } case BRCTL_SET_PATH_COST: { if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; spin_lock_bh(&br->lock); if ((p = br_get_port(br, args[1])) == NULL) ret = -EINVAL; else ret = br_stp_set_path_cost(p, args[2]); spin_unlock_bh(&br->lock); break; } case BRCTL_GET_FDB_ENTRIES: return get_fdb_entries(br, argp, args[2], args[3]); default: ret = -EOPNOTSUPP; } if (!ret) { if (p) br_ifinfo_notify(RTM_NEWLINK, NULL, p); else netdev_state_change(br->dev); } return ret; } static int old_deviceless(struct net *net, void __user *data) { unsigned long args[3]; void __user *argp; int ret; ret = br_dev_read_uargs(args, ARRAY_SIZE(args), &argp, data); if (ret) return ret; switch (args[0]) { case BRCTL_GET_VERSION: return BRCTL_VERSION; case BRCTL_GET_BRIDGES: { int *indices; int ret = 0; if (args[2] >= 2048) return -ENOMEM; indices = kcalloc(args[2], sizeof(int), GFP_KERNEL); if (indices == NULL) return -ENOMEM; args[2] = get_bridge_ifindices(net, indices, args[2]); ret = copy_to_user(argp, indices, array_size(args[2], sizeof(int))) ? -EFAULT : args[2]; kfree(indices); return ret; } case BRCTL_ADD_BRIDGE: case BRCTL_DEL_BRIDGE: { char buf[IFNAMSIZ]; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(buf, argp, IFNAMSIZ)) return -EFAULT; buf[IFNAMSIZ-1] = 0; if (args[0] == BRCTL_ADD_BRIDGE) return br_add_bridge(net, buf); return br_del_bridge(net, buf); } } return -EOPNOTSUPP; } int br_ioctl_stub(struct net *net, struct net_bridge *br, unsigned int cmd, struct ifreq *ifr, void __user *uarg) { int ret = -EOPNOTSUPP; rtnl_lock(); switch (cmd) { case SIOCGIFBR: case SIOCSIFBR: ret = old_deviceless(net, uarg); break; case SIOCBRADDBR: case SIOCBRDELBR: { char buf[IFNAMSIZ]; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) { ret = -EPERM; break; } if (copy_from_user(buf, uarg, IFNAMSIZ)) { ret = -EFAULT; break; } buf[IFNAMSIZ-1] = 0; if (cmd == SIOCBRADDBR) ret = br_add_bridge(net, buf); else ret = br_del_bridge(net, buf); } break; case SIOCBRADDIF: case SIOCBRDELIF: ret = add_del_if(br, ifr->ifr_ifindex, cmd == SIOCBRADDIF); break; } rtnl_unlock(); return ret; } |
| 18907 933 19088 14211 14228 15596 757 15727 15742 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/memblock.h> #include <linux/mmdebug.h> #include <linux/export.h> #include <linux/mm.h> #include <asm/page.h> #include <linux/vmalloc.h> #include "physaddr.h" #ifdef CONFIG_X86_64 #ifdef CONFIG_DEBUG_VIRTUAL unsigned long __phys_addr(unsigned long x) { unsigned long y = x - __START_KERNEL_map; /* use the carry flag to determine if x was < __START_KERNEL_map */ if (unlikely(x > y)) { x = y + phys_base; VIRTUAL_BUG_ON(y >= KERNEL_IMAGE_SIZE); } else { x = y + (__START_KERNEL_map - PAGE_OFFSET); /* carry flag will be set if starting x was >= PAGE_OFFSET */ VIRTUAL_BUG_ON((x > y) || !phys_addr_valid(x)); } return x; } EXPORT_SYMBOL(__phys_addr); unsigned long __phys_addr_symbol(unsigned long x) { unsigned long y = x - __START_KERNEL_map; /* only check upper bounds since lower bounds will trigger carry */ VIRTUAL_BUG_ON(y >= KERNEL_IMAGE_SIZE); return y + phys_base; } EXPORT_SYMBOL(__phys_addr_symbol); #endif bool __virt_addr_valid(unsigned long x) { unsigned long y = x - __START_KERNEL_map; /* use the carry flag to determine if x was < __START_KERNEL_map */ if (unlikely(x > y)) { x = y + phys_base; if (y >= KERNEL_IMAGE_SIZE) return false; } else { x = y + (__START_KERNEL_map - PAGE_OFFSET); /* carry flag will be set if starting x was >= PAGE_OFFSET */ if ((x > y) || !phys_addr_valid(x)) return false; } return pfn_valid(x >> PAGE_SHIFT); } EXPORT_SYMBOL(__virt_addr_valid); #else #ifdef CONFIG_DEBUG_VIRTUAL unsigned long __phys_addr(unsigned long x) { unsigned long phys_addr = x - PAGE_OFFSET; /* VMALLOC_* aren't constants */ VIRTUAL_BUG_ON(x < PAGE_OFFSET); VIRTUAL_BUG_ON(__vmalloc_start_set && is_vmalloc_addr((void *) x)); /* max_low_pfn is set early, but not _that_ early */ if (max_low_pfn) { VIRTUAL_BUG_ON((phys_addr >> PAGE_SHIFT) > max_low_pfn); BUG_ON(slow_virt_to_phys((void *)x) != phys_addr); } return phys_addr; } EXPORT_SYMBOL(__phys_addr); #endif bool __virt_addr_valid(unsigned long x) { if (x < PAGE_OFFSET) return false; if (__vmalloc_start_set && is_vmalloc_addr((void *) x)) return false; if (x >= FIXADDR_START) return false; return pfn_valid((x - PAGE_OFFSET) >> PAGE_SHIFT); } EXPORT_SYMBOL(__virt_addr_valid); #endif /* CONFIG_X86_64 */ |
| 12 12 6 5 5 5 4 2 3 2 2 2 3 1 2 6 1 1 3 1 2 2 1 5 4 1 1 1 2 1 2 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net> * Copyright (c) 2012-2014 Pablo Neira Ayuso <pablo@netfilter.org> * * Development of this code funded by Astaro AG (http://www.astaro.com/) */ #include <linux/audit.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/ipv6.h> #include <net/ip.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_log.h> #include <linux/netdevice.h> static const char *nft_log_null_prefix = ""; struct nft_log { struct nf_loginfo loginfo; char *prefix; }; static bool audit_ip4(struct audit_buffer *ab, struct sk_buff *skb) { struct iphdr _iph; const struct iphdr *ih; ih = skb_header_pointer(skb, skb_network_offset(skb), sizeof(_iph), &_iph); if (!ih) return false; audit_log_format(ab, " saddr=%pI4 daddr=%pI4 proto=%hhu", &ih->saddr, &ih->daddr, ih->protocol); return true; } static bool audit_ip6(struct audit_buffer *ab, struct sk_buff *skb) { struct ipv6hdr _ip6h; const struct ipv6hdr *ih; u8 nexthdr; __be16 frag_off; ih = skb_header_pointer(skb, skb_network_offset(skb), sizeof(_ip6h), &_ip6h); if (!ih) return false; nexthdr = ih->nexthdr; ipv6_skip_exthdr(skb, skb_network_offset(skb) + sizeof(_ip6h), &nexthdr, &frag_off); audit_log_format(ab, " saddr=%pI6c daddr=%pI6c proto=%hhu", &ih->saddr, &ih->daddr, nexthdr); return true; } static void nft_log_eval_audit(const struct nft_pktinfo *pkt) { struct sk_buff *skb = pkt->skb; struct audit_buffer *ab; int fam = -1; if (!audit_enabled) return; ab = audit_log_start(NULL, GFP_ATOMIC, AUDIT_NETFILTER_PKT); if (!ab) return; audit_log_format(ab, "mark=%#x", skb->mark); switch (nft_pf(pkt)) { case NFPROTO_BRIDGE: switch (eth_hdr(skb)->h_proto) { case htons(ETH_P_IP): fam = audit_ip4(ab, skb) ? NFPROTO_IPV4 : -1; break; case htons(ETH_P_IPV6): fam = audit_ip6(ab, skb) ? NFPROTO_IPV6 : -1; break; } break; case NFPROTO_IPV4: fam = audit_ip4(ab, skb) ? NFPROTO_IPV4 : -1; break; case NFPROTO_IPV6: fam = audit_ip6(ab, skb) ? NFPROTO_IPV6 : -1; break; } if (fam == -1) audit_log_format(ab, " saddr=? daddr=? proto=-1"); audit_log_end(ab); } static void nft_log_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_log *priv = nft_expr_priv(expr); if (priv->loginfo.type == NF_LOG_TYPE_LOG && priv->loginfo.u.log.level == NFT_LOGLEVEL_AUDIT) { nft_log_eval_audit(pkt); return; } nf_log_packet(nft_net(pkt), nft_pf(pkt), nft_hook(pkt), pkt->skb, nft_in(pkt), nft_out(pkt), &priv->loginfo, "%s", priv->prefix); } static const struct nla_policy nft_log_policy[NFTA_LOG_MAX + 1] = { [NFTA_LOG_GROUP] = { .type = NLA_U16 }, [NFTA_LOG_PREFIX] = { .type = NLA_STRING, .len = NF_LOG_PREFIXLEN - 1 }, [NFTA_LOG_SNAPLEN] = { .type = NLA_U32 }, [NFTA_LOG_QTHRESHOLD] = { .type = NLA_U16 }, [NFTA_LOG_LEVEL] = { .type = NLA_U32 }, [NFTA_LOG_FLAGS] = { .type = NLA_U32 }, }; static int nft_log_modprobe(struct net *net, enum nf_log_type t) { switch (t) { case NF_LOG_TYPE_LOG: return nft_request_module(net, "%s", "nf_log_syslog"); case NF_LOG_TYPE_ULOG: return nft_request_module(net, "%s", "nfnetlink_log"); case NF_LOG_TYPE_MAX: break; } return -ENOENT; } static int nft_log_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_log *priv = nft_expr_priv(expr); struct nf_loginfo *li = &priv->loginfo; const struct nlattr *nla; int err; li->type = NF_LOG_TYPE_LOG; if (tb[NFTA_LOG_LEVEL] != NULL && tb[NFTA_LOG_GROUP] != NULL) return -EINVAL; if (tb[NFTA_LOG_GROUP] != NULL) { li->type = NF_LOG_TYPE_ULOG; if (tb[NFTA_LOG_FLAGS] != NULL) return -EINVAL; } nla = tb[NFTA_LOG_PREFIX]; if (nla != NULL) { priv->prefix = kmalloc(nla_len(nla) + 1, GFP_KERNEL_ACCOUNT); if (priv->prefix == NULL) return -ENOMEM; nla_strscpy(priv->prefix, nla, nla_len(nla) + 1); } else { priv->prefix = (char *)nft_log_null_prefix; } switch (li->type) { case NF_LOG_TYPE_LOG: if (tb[NFTA_LOG_LEVEL] != NULL) { li->u.log.level = ntohl(nla_get_be32(tb[NFTA_LOG_LEVEL])); } else { li->u.log.level = NFT_LOGLEVEL_WARNING; } if (li->u.log.level > NFT_LOGLEVEL_AUDIT) { err = -EINVAL; goto err1; } if (tb[NFTA_LOG_FLAGS] != NULL) { li->u.log.logflags = ntohl(nla_get_be32(tb[NFTA_LOG_FLAGS])); if (li->u.log.logflags & ~NF_LOG_MASK) { err = -EINVAL; goto err1; } } break; case NF_LOG_TYPE_ULOG: li->u.ulog.group = ntohs(nla_get_be16(tb[NFTA_LOG_GROUP])); if (tb[NFTA_LOG_SNAPLEN] != NULL) { li->u.ulog.flags |= NF_LOG_F_COPY_LEN; li->u.ulog.copy_len = ntohl(nla_get_be32(tb[NFTA_LOG_SNAPLEN])); } if (tb[NFTA_LOG_QTHRESHOLD] != NULL) { li->u.ulog.qthreshold = ntohs(nla_get_be16(tb[NFTA_LOG_QTHRESHOLD])); } break; } if (li->u.log.level == NFT_LOGLEVEL_AUDIT) return 0; err = nf_logger_find_get(ctx->family, li->type); if (err < 0) { if (nft_log_modprobe(ctx->net, li->type) == -EAGAIN) err = -EAGAIN; goto err1; } return 0; err1: if (priv->prefix != nft_log_null_prefix) kfree(priv->prefix); return err; } static void nft_log_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct nft_log *priv = nft_expr_priv(expr); struct nf_loginfo *li = &priv->loginfo; if (priv->prefix != nft_log_null_prefix) kfree(priv->prefix); if (li->u.log.level == NFT_LOGLEVEL_AUDIT) return; nf_logger_put(ctx->family, li->type); } static int nft_log_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { const struct nft_log *priv = nft_expr_priv(expr); const struct nf_loginfo *li = &priv->loginfo; if (priv->prefix != nft_log_null_prefix) if (nla_put_string(skb, NFTA_LOG_PREFIX, priv->prefix)) goto nla_put_failure; switch (li->type) { case NF_LOG_TYPE_LOG: if (nla_put_be32(skb, NFTA_LOG_LEVEL, htonl(li->u.log.level))) goto nla_put_failure; if (li->u.log.logflags) { if (nla_put_be32(skb, NFTA_LOG_FLAGS, htonl(li->u.log.logflags))) goto nla_put_failure; } break; case NF_LOG_TYPE_ULOG: if (nla_put_be16(skb, NFTA_LOG_GROUP, htons(li->u.ulog.group))) goto nla_put_failure; if (li->u.ulog.flags & NF_LOG_F_COPY_LEN) { if (nla_put_be32(skb, NFTA_LOG_SNAPLEN, htonl(li->u.ulog.copy_len))) goto nla_put_failure; } if (li->u.ulog.qthreshold) { if (nla_put_be16(skb, NFTA_LOG_QTHRESHOLD, htons(li->u.ulog.qthreshold))) goto nla_put_failure; } break; } return 0; nla_put_failure: return -1; } static struct nft_expr_type nft_log_type; static const struct nft_expr_ops nft_log_ops = { .type = &nft_log_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_log)), .eval = nft_log_eval, .init = nft_log_init, .destroy = nft_log_destroy, .dump = nft_log_dump, .reduce = NFT_REDUCE_READONLY, }; static struct nft_expr_type nft_log_type __read_mostly = { .name = "log", .ops = &nft_log_ops, .policy = nft_log_policy, .maxattr = NFTA_LOG_MAX, .owner = THIS_MODULE, }; static int __init nft_log_module_init(void) { return nft_register_expr(&nft_log_type); } static void __exit nft_log_module_exit(void) { nft_unregister_expr(&nft_log_type); } module_init(nft_log_module_init); module_exit(nft_log_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_ALIAS_NFT_EXPR("log"); MODULE_DESCRIPTION("Netfilter nf_tables log module"); |
| 9 21 70 23 24 8 17 78 23 79 12 22 23 23 23 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * sha256_base.h - core logic for SHA-256 implementations * * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org> */ #ifndef _CRYPTO_SHA256_BASE_H #define _CRYPTO_SHA256_BASE_H #include <asm/byteorder.h> #include <linux/unaligned.h> #include <crypto/internal/hash.h> #include <crypto/sha2.h> #include <linux/string.h> #include <linux/types.h> typedef void (sha256_block_fn)(struct sha256_state *sst, u8 const *src, int blocks); static inline int sha224_base_init(struct shash_desc *desc) { struct sha256_state *sctx = shash_desc_ctx(desc); sha224_init(sctx); return 0; } static inline int sha256_base_init(struct shash_desc *desc) { struct sha256_state *sctx = shash_desc_ctx(desc); sha256_init(sctx); return 0; } static inline int lib_sha256_base_do_update(struct sha256_state *sctx, const u8 *data, unsigned int len, sha256_block_fn *block_fn) { unsigned int partial = sctx->count % SHA256_BLOCK_SIZE; sctx->count += len; if (unlikely((partial + len) >= SHA256_BLOCK_SIZE)) { int blocks; if (partial) { int p = SHA256_BLOCK_SIZE - partial; memcpy(sctx->buf + partial, data, p); data += p; len -= p; block_fn(sctx, sctx->buf, 1); } blocks = len / SHA256_BLOCK_SIZE; len %= SHA256_BLOCK_SIZE; if (blocks) { block_fn(sctx, data, blocks); data += blocks * SHA256_BLOCK_SIZE; } partial = 0; } if (len) memcpy(sctx->buf + partial, data, len); return 0; } static inline int sha256_base_do_update(struct shash_desc *desc, const u8 *data, unsigned int len, sha256_block_fn *block_fn) { struct sha256_state *sctx = shash_desc_ctx(desc); return lib_sha256_base_do_update(sctx, data, len, block_fn); } static inline int lib_sha256_base_do_finalize(struct sha256_state *sctx, sha256_block_fn *block_fn) { const int bit_offset = SHA256_BLOCK_SIZE - sizeof(__be64); __be64 *bits = (__be64 *)(sctx->buf + bit_offset); unsigned int partial = sctx->count % SHA256_BLOCK_SIZE; sctx->buf[partial++] = 0x80; if (partial > bit_offset) { memset(sctx->buf + partial, 0x0, SHA256_BLOCK_SIZE - partial); partial = 0; block_fn(sctx, sctx->buf, 1); } memset(sctx->buf + partial, 0x0, bit_offset - partial); *bits = cpu_to_be64(sctx->count << 3); block_fn(sctx, sctx->buf, 1); return 0; } static inline int sha256_base_do_finalize(struct shash_desc *desc, sha256_block_fn *block_fn) { struct sha256_state *sctx = shash_desc_ctx(desc); return lib_sha256_base_do_finalize(sctx, block_fn); } static inline int lib_sha256_base_finish(struct sha256_state *sctx, u8 *out, unsigned int digest_size) { __be32 *digest = (__be32 *)out; int i; for (i = 0; digest_size > 0; i++, digest_size -= sizeof(__be32)) put_unaligned_be32(sctx->state[i], digest++); memzero_explicit(sctx, sizeof(*sctx)); return 0; } static inline int sha256_base_finish(struct shash_desc *desc, u8 *out) { unsigned int digest_size = crypto_shash_digestsize(desc->tfm); struct sha256_state *sctx = shash_desc_ctx(desc); return lib_sha256_base_finish(sctx, out, digest_size); } #endif /* _CRYPTO_SHA256_BASE_H */ |
| 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_GENERIC_SECTIONS_H_ #define _ASM_GENERIC_SECTIONS_H_ /* References to section boundaries */ #include <linux/compiler.h> #include <linux/types.h> /* * Usage guidelines: * _text, _data: architecture specific, don't use them in arch-independent code * [_stext, _etext]: contains .text.* sections, may also contain .rodata.* * and/or .init.* sections * [_sdata, _edata]: contains .data.* sections, may also contain .rodata.* * and/or .init.* sections. * [__start_rodata, __end_rodata]: contains .rodata.* sections * [__start_ro_after_init, __end_ro_after_init]: * contains .data..ro_after_init section * [__init_begin, __init_end]: contains .init.* sections, but .init.text.* * may be out of this range on some architectures. * [_sinittext, _einittext]: contains .init.text.* sections * [__bss_start, __bss_stop]: contains BSS sections * * Following global variables are optional and may be unavailable on some * architectures and/or kernel configurations. * _text, _data * __kprobes_text_start, __kprobes_text_end * __entry_text_start, __entry_text_end * __ctors_start, __ctors_end * __irqentry_text_start, __irqentry_text_end * __softirqentry_text_start, __softirqentry_text_end * __start_opd, __end_opd */ extern char _text[], _stext[], _etext[]; extern char _data[], _sdata[], _edata[]; extern char __bss_start[], __bss_stop[]; extern char __init_begin[], __init_end[]; extern char _sinittext[], _einittext[]; extern char __start_ro_after_init[], __end_ro_after_init[]; extern char _end[]; extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[]; extern char __kprobes_text_start[], __kprobes_text_end[]; extern char __entry_text_start[], __entry_text_end[]; extern char __start_rodata[], __end_rodata[]; extern char __irqentry_text_start[], __irqentry_text_end[]; extern char __softirqentry_text_start[], __softirqentry_text_end[]; extern char __start_once[], __end_once[]; /* Start and end of .ctors section - used for constructor calls. */ extern char __ctors_start[], __ctors_end[]; /* Start and end of .opd section - used for function descriptors. */ extern char __start_opd[], __end_opd[]; /* Start and end of instrumentation protected text section */ extern char __noinstr_text_start[], __noinstr_text_end[]; extern __visible const void __nosave_begin, __nosave_end; /* Function descriptor handling (if any). Override in asm/sections.h */ #ifdef CONFIG_HAVE_FUNCTION_DESCRIPTORS void *dereference_function_descriptor(void *ptr); void *dereference_kernel_function_descriptor(void *ptr); #else #define dereference_function_descriptor(p) ((void *)(p)) #define dereference_kernel_function_descriptor(p) ((void *)(p)) /* An address is simply the address of the function. */ typedef struct { unsigned long addr; } func_desc_t; #endif static inline bool have_function_descriptors(void) { return IS_ENABLED(CONFIG_HAVE_FUNCTION_DESCRIPTORS); } /** * memory_contains - checks if an object is contained within a memory region * @begin: virtual address of the beginning of the memory region * @end: virtual address of the end of the memory region * @virt: virtual address of the memory object * @size: size of the memory object * * Returns: true if the object specified by @virt and @size is entirely * contained within the memory region defined by @begin and @end, false * otherwise. */ static inline bool memory_contains(void *begin, void *end, void *virt, size_t size) { return virt >= begin && virt + size <= end; } /** * memory_intersects - checks if the region occupied by an object intersects * with another memory region * @begin: virtual address of the beginning of the memory region * @end: virtual address of the end of the memory region * @virt: virtual address of the memory object * @size: size of the memory object * * Returns: true if an object's memory region, specified by @virt and @size, * intersects with the region specified by @begin and @end, false otherwise. */ static inline bool memory_intersects(void *begin, void *end, void *virt, size_t size) { void *vend = virt + size; if (virt < end && vend > begin) return true; return false; } /** * init_section_contains - checks if an object is contained within the init * section * @virt: virtual address of the memory object * @size: size of the memory object * * Returns: true if the object specified by @virt and @size is entirely * contained within the init section, false otherwise. */ static inline bool init_section_contains(void *virt, size_t size) { return memory_contains(__init_begin, __init_end, virt, size); } /** * init_section_intersects - checks if the region occupied by an object * intersects with the init section * @virt: virtual address of the memory object * @size: size of the memory object * * Returns: true if an object's memory region, specified by @virt and @size, * intersects with the init section, false otherwise. */ static inline bool init_section_intersects(void *virt, size_t size) { return memory_intersects(__init_begin, __init_end, virt, size); } /** * is_kernel_core_data - checks if the pointer address is located in the * .data or .bss section * * @addr: address to check * * Returns: true if the address is located in .data or .bss, false otherwise. * Note: On some archs it may return true for core RODATA, and false * for others. But will always be true for core RW data. */ static inline bool is_kernel_core_data(unsigned long addr) { if (addr >= (unsigned long)_sdata && addr < (unsigned long)_edata) return true; if (addr >= (unsigned long)__bss_start && addr < (unsigned long)__bss_stop) return true; return false; } /** * is_kernel_rodata - checks if the pointer address is located in the * .rodata section * * @addr: address to check * * Returns: true if the address is located in .rodata, false otherwise. */ static inline bool is_kernel_rodata(unsigned long addr) { return addr >= (unsigned long)__start_rodata && addr < (unsigned long)__end_rodata; } static inline bool is_kernel_ro_after_init(unsigned long addr) { return addr >= (unsigned long)__start_ro_after_init && addr < (unsigned long)__end_ro_after_init; } /** * is_kernel_inittext - checks if the pointer address is located in the * .init.text section * * @addr: address to check * * Returns: true if the address is located in .init.text, false otherwise. */ static inline bool is_kernel_inittext(unsigned long addr) { return addr >= (unsigned long)_sinittext && addr < (unsigned long)_einittext; } /** * __is_kernel_text - checks if the pointer address is located in the * .text section * * @addr: address to check * * Returns: true if the address is located in .text, false otherwise. * Note: an internal helper, only check the range of _stext to _etext. */ static inline bool __is_kernel_text(unsigned long addr) { return addr >= (unsigned long)_stext && addr < (unsigned long)_etext; } /** * __is_kernel - checks if the pointer address is located in the kernel range * * @addr: address to check * * Returns: true if the address is located in the kernel range, false otherwise. * Note: an internal helper, check the range of _stext to _end, * and range from __init_begin to __init_end, which can be outside * of the _stext to _end range. */ static inline bool __is_kernel(unsigned long addr) { return ((addr >= (unsigned long)_stext && addr < (unsigned long)_end) || (addr >= (unsigned long)__init_begin && addr < (unsigned long)__init_end)); } #endif /* _ASM_GENERIC_SECTIONS_H_ */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 | // SPDX-License-Identifier: GPL-2.0 /* * BlueZ - Bluetooth protocol stack for Linux * * Copyright (C) 2022 Intel Corporation * Copyright 2023-2024 NXP */ #include <linux/module.h> #include <linux/debugfs.h> #include <linux/seq_file.h> #include <linux/sched/signal.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/iso.h> #include "eir.h" static const struct proto_ops iso_sock_ops; static struct bt_sock_list iso_sk_list = { .lock = __RW_LOCK_UNLOCKED(iso_sk_list.lock) }; /* ---- ISO connections ---- */ struct iso_conn { struct hci_conn *hcon; /* @lock: spinlock protecting changes to iso_conn fields */ spinlock_t lock; struct sock *sk; struct delayed_work timeout_work; struct sk_buff *rx_skb; __u32 rx_len; __u16 tx_sn; struct kref ref; }; #define iso_conn_lock(c) spin_lock(&(c)->lock) #define iso_conn_unlock(c) spin_unlock(&(c)->lock) static void iso_sock_close(struct sock *sk); static void iso_sock_kill(struct sock *sk); /* ----- ISO socket info ----- */ #define iso_pi(sk) ((struct iso_pinfo *)sk) #define EIR_SERVICE_DATA_LENGTH 4 #define BASE_MAX_LENGTH (HCI_MAX_PER_AD_LENGTH - EIR_SERVICE_DATA_LENGTH) #define EIR_BAA_SERVICE_UUID 0x1851 /* iso_pinfo flags values */ enum { BT_SK_BIG_SYNC, BT_SK_PA_SYNC, }; struct iso_pinfo { struct bt_sock bt; bdaddr_t src; __u8 src_type; bdaddr_t dst; __u8 dst_type; __u8 bc_sid; __u8 bc_num_bis; __u8 bc_bis[ISO_MAX_NUM_BIS]; __u16 sync_handle; unsigned long flags; struct bt_iso_qos qos; bool qos_user_set; __u8 base_len; __u8 base[BASE_MAX_LENGTH]; struct iso_conn *conn; }; static struct bt_iso_qos default_qos; static bool check_ucast_qos(struct bt_iso_qos *qos); static bool check_bcast_qos(struct bt_iso_qos *qos); static bool iso_match_sid(struct sock *sk, void *data); static bool iso_match_sync_handle(struct sock *sk, void *data); static bool iso_match_sync_handle_pa_report(struct sock *sk, void *data); static void iso_sock_disconn(struct sock *sk); typedef bool (*iso_sock_match_t)(struct sock *sk, void *data); static struct sock *iso_get_sock(bdaddr_t *src, bdaddr_t *dst, enum bt_sock_state state, iso_sock_match_t match, void *data); /* ---- ISO timers ---- */ #define ISO_CONN_TIMEOUT (HZ * 40) #define ISO_DISCONN_TIMEOUT (HZ * 2) static void iso_conn_free(struct kref *ref) { struct iso_conn *conn = container_of(ref, struct iso_conn, ref); BT_DBG("conn %p", conn); if (conn->sk) iso_pi(conn->sk)->conn = NULL; if (conn->hcon) { conn->hcon->iso_data = NULL; hci_conn_drop(conn->hcon); } /* Ensure no more work items will run since hci_conn has been dropped */ disable_delayed_work_sync(&conn->timeout_work); kfree(conn); } static void iso_conn_put(struct iso_conn *conn) { if (!conn) return; BT_DBG("conn %p refcnt %d", conn, kref_read(&conn->ref)); kref_put(&conn->ref, iso_conn_free); } static struct iso_conn *iso_conn_hold_unless_zero(struct iso_conn *conn) { if (!conn) return NULL; BT_DBG("conn %p refcnt %u", conn, kref_read(&conn->ref)); if (!kref_get_unless_zero(&conn->ref)) return NULL; return conn; } static struct sock *iso_sock_hold(struct iso_conn *conn) { if (!conn || !bt_sock_linked(&iso_sk_list, conn->sk)) return NULL; sock_hold(conn->sk); return conn->sk; } static void iso_sock_timeout(struct work_struct *work) { struct iso_conn *conn = container_of(work, struct iso_conn, timeout_work.work); struct sock *sk; conn = iso_conn_hold_unless_zero(conn); if (!conn) return; iso_conn_lock(conn); sk = iso_sock_hold(conn); iso_conn_unlock(conn); iso_conn_put(conn); if (!sk) return; BT_DBG("sock %p state %d", sk, sk->sk_state); lock_sock(sk); sk->sk_err = ETIMEDOUT; sk->sk_state_change(sk); release_sock(sk); sock_put(sk); } static void iso_sock_set_timer(struct sock *sk, long timeout) { if (!iso_pi(sk)->conn) return; BT_DBG("sock %p state %d timeout %ld", sk, sk->sk_state, timeout); cancel_delayed_work(&iso_pi(sk)->conn->timeout_work); schedule_delayed_work(&iso_pi(sk)->conn->timeout_work, timeout); } static void iso_sock_clear_timer(struct sock *sk) { if (!iso_pi(sk)->conn) return; BT_DBG("sock %p state %d", sk, sk->sk_state); cancel_delayed_work(&iso_pi(sk)->conn->timeout_work); } /* ---- ISO connections ---- */ static struct iso_conn *iso_conn_add(struct hci_conn *hcon) { struct iso_conn *conn = hcon->iso_data; conn = iso_conn_hold_unless_zero(conn); if (conn) { if (!conn->hcon) { iso_conn_lock(conn); conn->hcon = hcon; iso_conn_unlock(conn); } iso_conn_put(conn); return conn; } conn = kzalloc(sizeof(*conn), GFP_KERNEL); if (!conn) return NULL; kref_init(&conn->ref); spin_lock_init(&conn->lock); INIT_DELAYED_WORK(&conn->timeout_work, iso_sock_timeout); hcon->iso_data = conn; conn->hcon = hcon; conn->tx_sn = 0; BT_DBG("hcon %p conn %p", hcon, conn); return conn; } /* Delete channel. Must be called on the locked socket. */ static void iso_chan_del(struct sock *sk, int err) { struct iso_conn *conn; struct sock *parent; conn = iso_pi(sk)->conn; iso_pi(sk)->conn = NULL; BT_DBG("sk %p, conn %p, err %d", sk, conn, err); if (conn) { iso_conn_lock(conn); conn->sk = NULL; iso_conn_unlock(conn); iso_conn_put(conn); } sk->sk_state = BT_CLOSED; sk->sk_err = err; parent = bt_sk(sk)->parent; if (parent) { bt_accept_unlink(sk); parent->sk_data_ready(parent); } else { sk->sk_state_change(sk); } sock_set_flag(sk, SOCK_ZAPPED); } static void iso_conn_del(struct hci_conn *hcon, int err) { struct iso_conn *conn = hcon->iso_data; struct sock *sk; conn = iso_conn_hold_unless_zero(conn); if (!conn) return; BT_DBG("hcon %p conn %p, err %d", hcon, conn, err); /* Kill socket */ iso_conn_lock(conn); sk = iso_sock_hold(conn); iso_conn_unlock(conn); iso_conn_put(conn); if (!sk) { iso_conn_put(conn); return; } lock_sock(sk); iso_sock_clear_timer(sk); iso_chan_del(sk, err); release_sock(sk); sock_put(sk); } static int __iso_chan_add(struct iso_conn *conn, struct sock *sk, struct sock *parent) { BT_DBG("conn %p", conn); if (iso_pi(sk)->conn == conn && conn->sk == sk) return 0; if (conn->sk) { BT_ERR("conn->sk already set"); return -EBUSY; } iso_pi(sk)->conn = conn; conn->sk = sk; if (parent) bt_accept_enqueue(parent, sk, true); return 0; } static int iso_chan_add(struct iso_conn *conn, struct sock *sk, struct sock *parent) { int err; iso_conn_lock(conn); err = __iso_chan_add(conn, sk, parent); iso_conn_unlock(conn); return err; } static inline u8 le_addr_type(u8 bdaddr_type) { if (bdaddr_type == BDADDR_LE_PUBLIC) return ADDR_LE_DEV_PUBLIC; else return ADDR_LE_DEV_RANDOM; } static int iso_connect_bis(struct sock *sk) { struct iso_conn *conn; struct hci_conn *hcon; struct hci_dev *hdev; int err; BT_DBG("%pMR", &iso_pi(sk)->src); hdev = hci_get_route(&iso_pi(sk)->dst, &iso_pi(sk)->src, iso_pi(sk)->src_type); if (!hdev) return -EHOSTUNREACH; hci_dev_lock(hdev); if (!bis_capable(hdev)) { err = -EOPNOTSUPP; goto unlock; } /* Fail if user set invalid QoS */ if (iso_pi(sk)->qos_user_set && !check_bcast_qos(&iso_pi(sk)->qos)) { iso_pi(sk)->qos = default_qos; err = -EINVAL; goto unlock; } /* Fail if out PHYs are marked as disabled */ if (!iso_pi(sk)->qos.bcast.out.phy) { err = -EINVAL; goto unlock; } /* Just bind if DEFER_SETUP has been set */ if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { hcon = hci_bind_bis(hdev, &iso_pi(sk)->dst, &iso_pi(sk)->qos, iso_pi(sk)->base_len, iso_pi(sk)->base); if (IS_ERR(hcon)) { err = PTR_ERR(hcon); goto unlock; } } else { hcon = hci_connect_bis(hdev, &iso_pi(sk)->dst, le_addr_type(iso_pi(sk)->dst_type), &iso_pi(sk)->qos, iso_pi(sk)->base_len, iso_pi(sk)->base); if (IS_ERR(hcon)) { err = PTR_ERR(hcon); goto unlock; } } conn = iso_conn_add(hcon); if (!conn) { hci_conn_drop(hcon); err = -ENOMEM; goto unlock; } lock_sock(sk); err = iso_chan_add(conn, sk, NULL); if (err) { release_sock(sk); goto unlock; } /* Update source addr of the socket */ bacpy(&iso_pi(sk)->src, &hcon->src); if (hcon->state == BT_CONNECTED) { iso_sock_clear_timer(sk); sk->sk_state = BT_CONNECTED; } else if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { iso_sock_clear_timer(sk); sk->sk_state = BT_CONNECT; } else { sk->sk_state = BT_CONNECT; iso_sock_set_timer(sk, sk->sk_sndtimeo); } release_sock(sk); unlock: hci_dev_unlock(hdev); hci_dev_put(hdev); return err; } static int iso_connect_cis(struct sock *sk) { struct iso_conn *conn; struct hci_conn *hcon; struct hci_dev *hdev; int err; BT_DBG("%pMR -> %pMR", &iso_pi(sk)->src, &iso_pi(sk)->dst); hdev = hci_get_route(&iso_pi(sk)->dst, &iso_pi(sk)->src, iso_pi(sk)->src_type); if (!hdev) return -EHOSTUNREACH; hci_dev_lock(hdev); if (!cis_central_capable(hdev)) { err = -EOPNOTSUPP; goto unlock; } /* Fail if user set invalid QoS */ if (iso_pi(sk)->qos_user_set && !check_ucast_qos(&iso_pi(sk)->qos)) { iso_pi(sk)->qos = default_qos; err = -EINVAL; goto unlock; } /* Fail if either PHYs are marked as disabled */ if (!iso_pi(sk)->qos.ucast.in.phy && !iso_pi(sk)->qos.ucast.out.phy) { err = -EINVAL; goto unlock; } /* Just bind if DEFER_SETUP has been set */ if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { hcon = hci_bind_cis(hdev, &iso_pi(sk)->dst, le_addr_type(iso_pi(sk)->dst_type), &iso_pi(sk)->qos); if (IS_ERR(hcon)) { err = PTR_ERR(hcon); goto unlock; } } else { hcon = hci_connect_cis(hdev, &iso_pi(sk)->dst, le_addr_type(iso_pi(sk)->dst_type), &iso_pi(sk)->qos); if (IS_ERR(hcon)) { err = PTR_ERR(hcon); goto unlock; } } conn = iso_conn_add(hcon); if (!conn) { hci_conn_drop(hcon); err = -ENOMEM; goto unlock; } lock_sock(sk); err = iso_chan_add(conn, sk, NULL); if (err) { release_sock(sk); goto unlock; } /* Update source addr of the socket */ bacpy(&iso_pi(sk)->src, &hcon->src); if (hcon->state == BT_CONNECTED) { iso_sock_clear_timer(sk); sk->sk_state = BT_CONNECTED; } else if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { iso_sock_clear_timer(sk); sk->sk_state = BT_CONNECT; } else { sk->sk_state = BT_CONNECT; iso_sock_set_timer(sk, sk->sk_sndtimeo); } release_sock(sk); unlock: hci_dev_unlock(hdev); hci_dev_put(hdev); return err; } static struct bt_iso_qos *iso_sock_get_qos(struct sock *sk) { if (sk->sk_state == BT_CONNECTED || sk->sk_state == BT_CONNECT2) return &iso_pi(sk)->conn->hcon->iso_qos; return &iso_pi(sk)->qos; } static int iso_send_frame(struct sock *sk, struct sk_buff *skb) { struct iso_conn *conn = iso_pi(sk)->conn; struct bt_iso_qos *qos = iso_sock_get_qos(sk); struct hci_iso_data_hdr *hdr; int len = 0; BT_DBG("sk %p len %d", sk, skb->len); if (skb->len > qos->ucast.out.sdu) return -EMSGSIZE; len = skb->len; /* Push ISO data header */ hdr = skb_push(skb, HCI_ISO_DATA_HDR_SIZE); hdr->sn = cpu_to_le16(conn->tx_sn++); hdr->slen = cpu_to_le16(hci_iso_data_len_pack(len, HCI_ISO_STATUS_VALID)); if (sk->sk_state == BT_CONNECTED) hci_send_iso(conn->hcon, skb); else len = -ENOTCONN; return len; } static void iso_recv_frame(struct iso_conn *conn, struct sk_buff *skb) { struct sock *sk; iso_conn_lock(conn); sk = conn->sk; iso_conn_unlock(conn); if (!sk) goto drop; BT_DBG("sk %p len %d", sk, skb->len); if (sk->sk_state != BT_CONNECTED) goto drop; if (!sock_queue_rcv_skb(sk, skb)) return; drop: kfree_skb(skb); } /* -------- Socket interface ---------- */ static struct sock *__iso_get_sock_listen_by_addr(bdaddr_t *src, bdaddr_t *dst) { struct sock *sk; sk_for_each(sk, &iso_sk_list.head) { if (sk->sk_state != BT_LISTEN) continue; if (bacmp(&iso_pi(sk)->dst, dst)) continue; if (!bacmp(&iso_pi(sk)->src, src)) return sk; } return NULL; } static struct sock *__iso_get_sock_listen_by_sid(bdaddr_t *ba, bdaddr_t *bc, __u8 sid) { struct sock *sk; sk_for_each(sk, &iso_sk_list.head) { if (sk->sk_state != BT_LISTEN) continue; if (bacmp(&iso_pi(sk)->src, ba)) continue; if (bacmp(&iso_pi(sk)->dst, bc)) continue; if (iso_pi(sk)->bc_sid == sid) return sk; } return NULL; } /* Find socket in given state: * source bdaddr (Unicast) * destination bdaddr (Broadcast only) * match func - pass NULL to ignore * match func data - pass -1 to ignore * Returns closest match. */ static struct sock *iso_get_sock(bdaddr_t *src, bdaddr_t *dst, enum bt_sock_state state, iso_sock_match_t match, void *data) { struct sock *sk = NULL, *sk1 = NULL; read_lock(&iso_sk_list.lock); sk_for_each(sk, &iso_sk_list.head) { if (sk->sk_state != state) continue; /* Match Broadcast destination */ if (bacmp(dst, BDADDR_ANY) && bacmp(&iso_pi(sk)->dst, dst)) continue; /* Use Match function if provided */ if (match && !match(sk, data)) continue; /* Exact match. */ if (!bacmp(&iso_pi(sk)->src, src)) { sock_hold(sk); break; } /* Closest match */ if (!bacmp(&iso_pi(sk)->src, BDADDR_ANY)) { if (sk1) sock_put(sk1); sk1 = sk; sock_hold(sk1); } } if (sk && sk1) sock_put(sk1); read_unlock(&iso_sk_list.lock); return sk ? sk : sk1; } static struct sock *iso_get_sock_big(struct sock *match_sk, bdaddr_t *src, bdaddr_t *dst, uint8_t big) { struct sock *sk = NULL; read_lock(&iso_sk_list.lock); sk_for_each(sk, &iso_sk_list.head) { if (match_sk == sk) continue; /* Look for sockets that have already been * connected to the BIG */ if (sk->sk_state != BT_CONNECTED && sk->sk_state != BT_CONNECT) continue; /* Match Broadcast destination */ if (bacmp(&iso_pi(sk)->dst, dst)) continue; /* Match BIG handle */ if (iso_pi(sk)->qos.bcast.big != big) continue; /* Match source address */ if (bacmp(&iso_pi(sk)->src, src)) continue; sock_hold(sk); break; } read_unlock(&iso_sk_list.lock); return sk; } static void iso_sock_destruct(struct sock *sk) { BT_DBG("sk %p", sk); iso_conn_put(iso_pi(sk)->conn); skb_queue_purge(&sk->sk_receive_queue); skb_queue_purge(&sk->sk_write_queue); } static void iso_sock_cleanup_listen(struct sock *parent) { struct sock *sk; BT_DBG("parent %p", parent); /* Close not yet accepted channels */ while ((sk = bt_accept_dequeue(parent, NULL))) { iso_sock_close(sk); iso_sock_kill(sk); } /* If listening socket has a hcon, properly disconnect it */ if (iso_pi(parent)->conn && iso_pi(parent)->conn->hcon) { iso_sock_disconn(parent); return; } parent->sk_state = BT_CLOSED; sock_set_flag(parent, SOCK_ZAPPED); } /* Kill socket (only if zapped and orphan) * Must be called on unlocked socket. */ static void iso_sock_kill(struct sock *sk) { if (!sock_flag(sk, SOCK_ZAPPED) || sk->sk_socket || sock_flag(sk, SOCK_DEAD)) return; BT_DBG("sk %p state %d", sk, sk->sk_state); /* Kill poor orphan */ bt_sock_unlink(&iso_sk_list, sk); sock_set_flag(sk, SOCK_DEAD); sock_put(sk); } static void iso_sock_disconn(struct sock *sk) { struct sock *bis_sk; struct hci_conn *hcon = iso_pi(sk)->conn->hcon; if (test_bit(HCI_CONN_BIG_CREATED, &hcon->flags)) { bis_sk = iso_get_sock_big(sk, &iso_pi(sk)->src, &iso_pi(sk)->dst, iso_pi(sk)->qos.bcast.big); /* If there are any other connected sockets for the * same BIG, just delete the sk and leave the bis * hcon active, in case later rebinding is needed. */ if (bis_sk) { hcon->state = BT_OPEN; hcon->iso_data = NULL; iso_pi(sk)->conn->hcon = NULL; iso_sock_clear_timer(sk); iso_chan_del(sk, bt_to_errno(hcon->abort_reason)); sock_put(bis_sk); return; } } sk->sk_state = BT_DISCONN; iso_conn_lock(iso_pi(sk)->conn); hci_conn_drop(iso_pi(sk)->conn->hcon); iso_pi(sk)->conn->hcon = NULL; iso_conn_unlock(iso_pi(sk)->conn); } static void __iso_sock_close(struct sock *sk) { BT_DBG("sk %p state %d socket %p", sk, sk->sk_state, sk->sk_socket); switch (sk->sk_state) { case BT_LISTEN: iso_sock_cleanup_listen(sk); break; case BT_CONNECT: case BT_CONNECTED: case BT_CONFIG: if (iso_pi(sk)->conn->hcon) iso_sock_disconn(sk); else iso_chan_del(sk, ECONNRESET); break; case BT_CONNECT2: if (iso_pi(sk)->conn->hcon && (test_bit(HCI_CONN_PA_SYNC, &iso_pi(sk)->conn->hcon->flags) || test_bit(HCI_CONN_PA_SYNC_FAILED, &iso_pi(sk)->conn->hcon->flags))) iso_sock_disconn(sk); else iso_chan_del(sk, ECONNRESET); break; case BT_DISCONN: iso_chan_del(sk, ECONNRESET); break; default: sock_set_flag(sk, SOCK_ZAPPED); break; } } /* Must be called on unlocked socket. */ static void iso_sock_close(struct sock *sk) { iso_sock_clear_timer(sk); lock_sock(sk); __iso_sock_close(sk); release_sock(sk); iso_sock_kill(sk); } static void iso_sock_init(struct sock *sk, struct sock *parent) { BT_DBG("sk %p", sk); if (parent) { sk->sk_type = parent->sk_type; bt_sk(sk)->flags = bt_sk(parent)->flags; security_sk_clone(parent, sk); } } static struct proto iso_proto = { .name = "ISO", .owner = THIS_MODULE, .obj_size = sizeof(struct iso_pinfo) }; #define DEFAULT_IO_QOS \ { \ .interval = 10000u, \ .latency = 10u, \ .sdu = 40u, \ .phy = BT_ISO_PHY_2M, \ .rtn = 2u, \ } static struct bt_iso_qos default_qos = { .bcast = { .big = BT_ISO_QOS_BIG_UNSET, .bis = BT_ISO_QOS_BIS_UNSET, .sync_factor = 0x01, .packing = 0x00, .framing = 0x00, .in = DEFAULT_IO_QOS, .out = DEFAULT_IO_QOS, .encryption = 0x00, .bcode = {0x00}, .options = 0x00, .skip = 0x0000, .sync_timeout = BT_ISO_SYNC_TIMEOUT, .sync_cte_type = 0x00, .mse = 0x00, .timeout = BT_ISO_SYNC_TIMEOUT, }, }; static struct sock *iso_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio, int kern) { struct sock *sk; sk = bt_sock_alloc(net, sock, &iso_proto, proto, prio, kern); if (!sk) return NULL; sk->sk_destruct = iso_sock_destruct; sk->sk_sndtimeo = ISO_CONN_TIMEOUT; /* Set address type as public as default src address is BDADDR_ANY */ iso_pi(sk)->src_type = BDADDR_LE_PUBLIC; iso_pi(sk)->qos = default_qos; iso_pi(sk)->sync_handle = -1; bt_sock_link(&iso_sk_list, sk); return sk; } static int iso_sock_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; BT_DBG("sock %p", sock); sock->state = SS_UNCONNECTED; if (sock->type != SOCK_SEQPACKET) return -ESOCKTNOSUPPORT; sock->ops = &iso_sock_ops; sk = iso_sock_alloc(net, sock, protocol, GFP_ATOMIC, kern); if (!sk) return -ENOMEM; iso_sock_init(sk, NULL); return 0; } static int iso_sock_bind_bc(struct socket *sock, struct sockaddr *addr, int addr_len) { struct sockaddr_iso *sa = (struct sockaddr_iso *)addr; struct sock *sk = sock->sk; int i; BT_DBG("sk %p bc_sid %u bc_num_bis %u", sk, sa->iso_bc->bc_sid, sa->iso_bc->bc_num_bis); if (addr_len != sizeof(*sa) + sizeof(*sa->iso_bc)) return -EINVAL; bacpy(&iso_pi(sk)->dst, &sa->iso_bc->bc_bdaddr); /* Check if the address type is of LE type */ if (!bdaddr_type_is_le(sa->iso_bc->bc_bdaddr_type)) return -EINVAL; iso_pi(sk)->dst_type = sa->iso_bc->bc_bdaddr_type; if (sa->iso_bc->bc_sid > 0x0f) return -EINVAL; iso_pi(sk)->bc_sid = sa->iso_bc->bc_sid; if (sa->iso_bc->bc_num_bis > ISO_MAX_NUM_BIS) return -EINVAL; iso_pi(sk)->bc_num_bis = sa->iso_bc->bc_num_bis; for (i = 0; i < iso_pi(sk)->bc_num_bis; i++) if (sa->iso_bc->bc_bis[i] < 0x01 || sa->iso_bc->bc_bis[i] > 0x1f) return -EINVAL; memcpy(iso_pi(sk)->bc_bis, sa->iso_bc->bc_bis, iso_pi(sk)->bc_num_bis); return 0; } static int iso_sock_bind_pa_sk(struct sock *sk, struct sockaddr_iso *sa, int addr_len) { int err = 0; if (sk->sk_type != SOCK_SEQPACKET) { err = -EINVAL; goto done; } if (addr_len != sizeof(*sa) + sizeof(*sa->iso_bc)) { err = -EINVAL; goto done; } if (sa->iso_bc->bc_num_bis > ISO_MAX_NUM_BIS) { err = -EINVAL; goto done; } iso_pi(sk)->bc_num_bis = sa->iso_bc->bc_num_bis; for (int i = 0; i < iso_pi(sk)->bc_num_bis; i++) if (sa->iso_bc->bc_bis[i] < 0x01 || sa->iso_bc->bc_bis[i] > 0x1f) { err = -EINVAL; goto done; } memcpy(iso_pi(sk)->bc_bis, sa->iso_bc->bc_bis, iso_pi(sk)->bc_num_bis); done: return err; } static int iso_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { struct sockaddr_iso *sa = (struct sockaddr_iso *)addr; struct sock *sk = sock->sk; int err = 0; BT_DBG("sk %p %pMR type %u", sk, &sa->iso_bdaddr, sa->iso_bdaddr_type); if (!addr || addr_len < sizeof(struct sockaddr_iso) || addr->sa_family != AF_BLUETOOTH) return -EINVAL; lock_sock(sk); /* Allow the user to bind a PA sync socket to a number * of BISes to sync to. */ if ((sk->sk_state == BT_CONNECT2 || sk->sk_state == BT_CONNECTED) && test_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags)) { err = iso_sock_bind_pa_sk(sk, sa, addr_len); goto done; } if (sk->sk_state != BT_OPEN) { err = -EBADFD; goto done; } if (sk->sk_type != SOCK_SEQPACKET) { err = -EINVAL; goto done; } /* Check if the address type is of LE type */ if (!bdaddr_type_is_le(sa->iso_bdaddr_type)) { err = -EINVAL; goto done; } bacpy(&iso_pi(sk)->src, &sa->iso_bdaddr); iso_pi(sk)->src_type = sa->iso_bdaddr_type; /* Check for Broadcast address */ if (addr_len > sizeof(*sa)) { err = iso_sock_bind_bc(sock, addr, addr_len); if (err) goto done; } sk->sk_state = BT_BOUND; done: release_sock(sk); return err; } static int iso_sock_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags) { struct sockaddr_iso *sa = (struct sockaddr_iso *)addr; struct sock *sk = sock->sk; int err; BT_DBG("sk %p", sk); if (alen < sizeof(struct sockaddr_iso) || addr->sa_family != AF_BLUETOOTH) return -EINVAL; if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) return -EBADFD; if (sk->sk_type != SOCK_SEQPACKET) return -EINVAL; /* Check if the address type is of LE type */ if (!bdaddr_type_is_le(sa->iso_bdaddr_type)) return -EINVAL; lock_sock(sk); bacpy(&iso_pi(sk)->dst, &sa->iso_bdaddr); iso_pi(sk)->dst_type = sa->iso_bdaddr_type; release_sock(sk); if (bacmp(&iso_pi(sk)->dst, BDADDR_ANY)) err = iso_connect_cis(sk); else err = iso_connect_bis(sk); if (err) return err; lock_sock(sk); if (!test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { err = bt_sock_wait_state(sk, BT_CONNECTED, sock_sndtimeo(sk, flags & O_NONBLOCK)); } release_sock(sk); return err; } static int iso_listen_bis(struct sock *sk) { struct hci_dev *hdev; int err = 0; struct iso_conn *conn; struct hci_conn *hcon; BT_DBG("%pMR -> %pMR (SID 0x%2.2x)", &iso_pi(sk)->src, &iso_pi(sk)->dst, iso_pi(sk)->bc_sid); write_lock(&iso_sk_list.lock); if (__iso_get_sock_listen_by_sid(&iso_pi(sk)->src, &iso_pi(sk)->dst, iso_pi(sk)->bc_sid)) err = -EADDRINUSE; write_unlock(&iso_sk_list.lock); if (err) return err; hdev = hci_get_route(&iso_pi(sk)->dst, &iso_pi(sk)->src, iso_pi(sk)->src_type); if (!hdev) return -EHOSTUNREACH; hci_dev_lock(hdev); /* Fail if user set invalid QoS */ if (iso_pi(sk)->qos_user_set && !check_bcast_qos(&iso_pi(sk)->qos)) { iso_pi(sk)->qos = default_qos; err = -EINVAL; goto unlock; } hcon = hci_pa_create_sync(hdev, &iso_pi(sk)->dst, le_addr_type(iso_pi(sk)->dst_type), iso_pi(sk)->bc_sid, &iso_pi(sk)->qos); if (IS_ERR(hcon)) { err = PTR_ERR(hcon); goto unlock; } conn = iso_conn_add(hcon); if (!conn) { hci_conn_drop(hcon); err = -ENOMEM; goto unlock; } err = iso_chan_add(conn, sk, NULL); if (err) { hci_conn_drop(hcon); goto unlock; } hci_dev_put(hdev); unlock: hci_dev_unlock(hdev); return err; } static int iso_listen_cis(struct sock *sk) { int err = 0; BT_DBG("%pMR", &iso_pi(sk)->src); write_lock(&iso_sk_list.lock); if (__iso_get_sock_listen_by_addr(&iso_pi(sk)->src, &iso_pi(sk)->dst)) err = -EADDRINUSE; write_unlock(&iso_sk_list.lock); return err; } static int iso_sock_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; int err = 0; BT_DBG("sk %p backlog %d", sk, backlog); lock_sock(sk); if (sk->sk_state != BT_BOUND) { err = -EBADFD; goto done; } if (sk->sk_type != SOCK_SEQPACKET) { err = -EINVAL; goto done; } if (!bacmp(&iso_pi(sk)->dst, BDADDR_ANY)) err = iso_listen_cis(sk); else err = iso_listen_bis(sk); if (err) goto done; sk->sk_max_ack_backlog = backlog; sk->sk_ack_backlog = 0; sk->sk_state = BT_LISTEN; done: release_sock(sk); return err; } static int iso_sock_accept(struct socket *sock, struct socket *newsock, struct proto_accept_arg *arg) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sock *sk = sock->sk, *ch; long timeo; int err = 0; lock_sock(sk); timeo = sock_rcvtimeo(sk, arg->flags & O_NONBLOCK); BT_DBG("sk %p timeo %ld", sk, timeo); /* Wait for an incoming connection. (wake-one). */ add_wait_queue_exclusive(sk_sleep(sk), &wait); while (1) { if (sk->sk_state != BT_LISTEN) { err = -EBADFD; break; } ch = bt_accept_dequeue(sk, newsock); if (ch) break; if (!timeo) { err = -EAGAIN; break; } if (signal_pending(current)) { err = sock_intr_errno(timeo); break; } release_sock(sk); timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); lock_sock(sk); } remove_wait_queue(sk_sleep(sk), &wait); if (err) goto done; newsock->state = SS_CONNECTED; BT_DBG("new socket %p", ch); done: release_sock(sk); return err; } static int iso_sock_getname(struct socket *sock, struct sockaddr *addr, int peer) { struct sockaddr_iso *sa = (struct sockaddr_iso *)addr; struct sock *sk = sock->sk; BT_DBG("sock %p, sk %p", sock, sk); addr->sa_family = AF_BLUETOOTH; if (peer) { bacpy(&sa->iso_bdaddr, &iso_pi(sk)->dst); sa->iso_bdaddr_type = iso_pi(sk)->dst_type; } else { bacpy(&sa->iso_bdaddr, &iso_pi(sk)->src); sa->iso_bdaddr_type = iso_pi(sk)->src_type; } return sizeof(struct sockaddr_iso); } static int iso_sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct sk_buff *skb, **frag; size_t mtu; int err; BT_DBG("sock %p, sk %p", sock, sk); err = sock_error(sk); if (err) return err; if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; lock_sock(sk); if (sk->sk_state != BT_CONNECTED) { release_sock(sk); return -ENOTCONN; } mtu = iso_pi(sk)->conn->hcon->mtu; release_sock(sk); skb = bt_skb_sendmsg(sk, msg, len, mtu, HCI_ISO_DATA_HDR_SIZE, 0); if (IS_ERR(skb)) return PTR_ERR(skb); len -= skb->len; BT_DBG("skb %p len %d", sk, skb->len); /* Continuation fragments */ frag = &skb_shinfo(skb)->frag_list; while (len) { struct sk_buff *tmp; tmp = bt_skb_sendmsg(sk, msg, len, mtu, 0, 0); if (IS_ERR(tmp)) { kfree_skb(skb); return PTR_ERR(tmp); } *frag = tmp; len -= tmp->len; skb->len += tmp->len; skb->data_len += tmp->len; BT_DBG("frag %p len %d", *frag, tmp->len); frag = &(*frag)->next; } lock_sock(sk); if (sk->sk_state == BT_CONNECTED) err = iso_send_frame(sk, skb); else err = -ENOTCONN; release_sock(sk); if (err < 0) kfree_skb(skb); return err; } static void iso_conn_defer_accept(struct hci_conn *conn) { struct hci_cp_le_accept_cis cp; struct hci_dev *hdev = conn->hdev; BT_DBG("conn %p", conn); conn->state = BT_CONFIG; cp.handle = cpu_to_le16(conn->handle); hci_send_cmd(hdev, HCI_OP_LE_ACCEPT_CIS, sizeof(cp), &cp); } static void iso_conn_big_sync(struct sock *sk) { int err; struct hci_dev *hdev; hdev = hci_get_route(&iso_pi(sk)->dst, &iso_pi(sk)->src, iso_pi(sk)->src_type); if (!hdev) return; /* hci_le_big_create_sync requires hdev lock to be held, since * it enqueues the HCI LE BIG Create Sync command via * hci_cmd_sync_queue_once, which checks hdev flags that might * change. */ hci_dev_lock(hdev); if (!test_and_set_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags)) { err = hci_le_big_create_sync(hdev, iso_pi(sk)->conn->hcon, &iso_pi(sk)->qos, iso_pi(sk)->sync_handle, iso_pi(sk)->bc_num_bis, iso_pi(sk)->bc_bis); if (err) bt_dev_err(hdev, "hci_le_big_create_sync: %d", err); } hci_dev_unlock(hdev); } static int iso_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; struct iso_pinfo *pi = iso_pi(sk); BT_DBG("sk %p", sk); if (test_and_clear_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { lock_sock(sk); switch (sk->sk_state) { case BT_CONNECT2: if (test_bit(BT_SK_PA_SYNC, &pi->flags)) { iso_conn_big_sync(sk); sk->sk_state = BT_LISTEN; } else { iso_conn_defer_accept(pi->conn->hcon); sk->sk_state = BT_CONFIG; } release_sock(sk); return 0; case BT_CONNECTED: if (test_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags)) { iso_conn_big_sync(sk); sk->sk_state = BT_LISTEN; release_sock(sk); return 0; } release_sock(sk); break; case BT_CONNECT: release_sock(sk); return iso_connect_cis(sk); default: release_sock(sk); break; } } return bt_sock_recvmsg(sock, msg, len, flags); } static bool check_io_qos(struct bt_iso_io_qos *qos) { /* If no PHY is enable SDU must be 0 */ if (!qos->phy && qos->sdu) return false; if (qos->interval && (qos->interval < 0xff || qos->interval > 0xfffff)) return false; if (qos->latency && (qos->latency < 0x05 || qos->latency > 0xfa0)) return false; if (qos->phy > BT_ISO_PHY_ANY) return false; return true; } static bool check_ucast_qos(struct bt_iso_qos *qos) { if (qos->ucast.cig > 0xef && qos->ucast.cig != BT_ISO_QOS_CIG_UNSET) return false; if (qos->ucast.cis > 0xef && qos->ucast.cis != BT_ISO_QOS_CIS_UNSET) return false; if (qos->ucast.sca > 0x07) return false; if (qos->ucast.packing > 0x01) return false; if (qos->ucast.framing > 0x01) return false; if (!check_io_qos(&qos->ucast.in)) return false; if (!check_io_qos(&qos->ucast.out)) return false; return true; } static bool check_bcast_qos(struct bt_iso_qos *qos) { if (!qos->bcast.sync_factor) qos->bcast.sync_factor = 0x01; if (qos->bcast.packing > 0x01) return false; if (qos->bcast.framing > 0x01) return false; if (!check_io_qos(&qos->bcast.in)) return false; if (!check_io_qos(&qos->bcast.out)) return false; if (qos->bcast.encryption > 0x01) return false; if (qos->bcast.options > 0x07) return false; if (qos->bcast.skip > 0x01f3) return false; if (!qos->bcast.sync_timeout) qos->bcast.sync_timeout = BT_ISO_SYNC_TIMEOUT; if (qos->bcast.sync_timeout < 0x000a || qos->bcast.sync_timeout > 0x4000) return false; if (qos->bcast.sync_cte_type > 0x1f) return false; if (qos->bcast.mse > 0x1f) return false; if (!qos->bcast.timeout) qos->bcast.sync_timeout = BT_ISO_SYNC_TIMEOUT; if (qos->bcast.timeout < 0x000a || qos->bcast.timeout > 0x4000) return false; return true; } static int iso_sock_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; int err = 0; struct bt_iso_qos qos = default_qos; u32 opt; BT_DBG("sk %p", sk); lock_sock(sk); switch (optname) { case BT_DEFER_SETUP: if (sk->sk_state != BT_BOUND && sk->sk_state != BT_LISTEN) { err = -EINVAL; break; } err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; if (opt) set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); else clear_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); break; case BT_PKT_STATUS: err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; if (opt) set_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags); else clear_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags); break; case BT_ISO_QOS: if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND && sk->sk_state != BT_CONNECT2 && (!test_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags) || sk->sk_state != BT_CONNECTED)) { err = -EINVAL; break; } err = bt_copy_from_sockptr(&qos, sizeof(qos), optval, optlen); if (err) break; iso_pi(sk)->qos = qos; iso_pi(sk)->qos_user_set = true; break; case BT_ISO_BASE: if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND && sk->sk_state != BT_CONNECT2) { err = -EINVAL; break; } if (optlen > sizeof(iso_pi(sk)->base)) { err = -EINVAL; break; } err = bt_copy_from_sockptr(iso_pi(sk)->base, optlen, optval, optlen); if (err) break; iso_pi(sk)->base_len = optlen; break; default: err = -ENOPROTOOPT; break; } release_sock(sk); return err; } static int iso_sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; int len, err = 0; struct bt_iso_qos *qos; u8 base_len; u8 *base; BT_DBG("sk %p", sk); if (get_user(len, optlen)) return -EFAULT; lock_sock(sk); switch (optname) { case BT_DEFER_SETUP: if (sk->sk_state == BT_CONNECTED) { err = -EINVAL; break; } if (put_user(test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags), (u32 __user *)optval)) err = -EFAULT; break; case BT_PKT_STATUS: if (put_user(test_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags), (int __user *)optval)) err = -EFAULT; break; case BT_ISO_QOS: qos = iso_sock_get_qos(sk); len = min_t(unsigned int, len, sizeof(*qos)); if (copy_to_user(optval, qos, len)) err = -EFAULT; break; case BT_ISO_BASE: if (sk->sk_state == BT_CONNECTED && !bacmp(&iso_pi(sk)->dst, BDADDR_ANY)) { base_len = iso_pi(sk)->conn->hcon->le_per_adv_data_len; base = iso_pi(sk)->conn->hcon->le_per_adv_data; } else { base_len = iso_pi(sk)->base_len; base = iso_pi(sk)->base; } len = min_t(unsigned int, len, base_len); if (copy_to_user(optval, base, len)) err = -EFAULT; if (put_user(len, optlen)) err = -EFAULT; break; default: err = -ENOPROTOOPT; break; } release_sock(sk); return err; } static int iso_sock_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; int err = 0; BT_DBG("sock %p, sk %p, how %d", sock, sk, how); if (!sk) return 0; sock_hold(sk); lock_sock(sk); switch (how) { case SHUT_RD: if (sk->sk_shutdown & RCV_SHUTDOWN) goto unlock; sk->sk_shutdown |= RCV_SHUTDOWN; break; case SHUT_WR: if (sk->sk_shutdown & SEND_SHUTDOWN) goto unlock; sk->sk_shutdown |= SEND_SHUTDOWN; break; case SHUT_RDWR: if (sk->sk_shutdown & SHUTDOWN_MASK) goto unlock; sk->sk_shutdown |= SHUTDOWN_MASK; break; } iso_sock_clear_timer(sk); __iso_sock_close(sk); if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && !(current->flags & PF_EXITING)) err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); unlock: release_sock(sk); sock_put(sk); return err; } static int iso_sock_release(struct socket *sock) { struct sock *sk = sock->sk; int err = 0; BT_DBG("sock %p, sk %p", sock, sk); if (!sk) return 0; iso_sock_close(sk); if (sock_flag(sk, SOCK_LINGER) && READ_ONCE(sk->sk_lingertime) && !(current->flags & PF_EXITING)) { lock_sock(sk); err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); release_sock(sk); } sock_orphan(sk); iso_sock_kill(sk); return err; } static void iso_sock_ready(struct sock *sk) { BT_DBG("sk %p", sk); if (!sk) return; lock_sock(sk); iso_sock_clear_timer(sk); sk->sk_state = BT_CONNECTED; sk->sk_state_change(sk); release_sock(sk); } static bool iso_match_big(struct sock *sk, void *data) { struct hci_evt_le_big_sync_estabilished *ev = data; return ev->handle == iso_pi(sk)->qos.bcast.big; } static bool iso_match_big_hcon(struct sock *sk, void *data) { struct hci_conn *hcon = data; return hcon->iso_qos.bcast.big == iso_pi(sk)->qos.bcast.big; } static bool iso_match_pa_sync_flag(struct sock *sk, void *data) { return test_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags); } static void iso_conn_ready(struct iso_conn *conn) { struct sock *parent = NULL; struct sock *sk = conn->sk; struct hci_ev_le_big_sync_estabilished *ev = NULL; struct hci_ev_le_pa_sync_established *ev2 = NULL; struct hci_ev_le_per_adv_report *ev3 = NULL; struct hci_conn *hcon; BT_DBG("conn %p", conn); if (sk) { iso_sock_ready(conn->sk); } else { hcon = conn->hcon; if (!hcon) return; if (test_bit(HCI_CONN_BIG_SYNC, &hcon->flags)) { /* A BIS slave hcon is notified to the ISO layer * after the Command Complete for the LE Setup * ISO Data Path command is received. Get the * parent socket that matches the hcon BIG handle. */ parent = iso_get_sock(&hcon->src, &hcon->dst, BT_LISTEN, iso_match_big_hcon, hcon); } else if (test_bit(HCI_CONN_BIG_SYNC_FAILED, &hcon->flags)) { ev = hci_recv_event_data(hcon->hdev, HCI_EVT_LE_BIG_SYNC_ESTABILISHED); /* Get reference to PA sync parent socket, if it exists */ parent = iso_get_sock(&hcon->src, &hcon->dst, BT_LISTEN, iso_match_pa_sync_flag, NULL); if (!parent && ev) parent = iso_get_sock(&hcon->src, &hcon->dst, BT_LISTEN, iso_match_big, ev); } else if (test_bit(HCI_CONN_PA_SYNC_FAILED, &hcon->flags)) { ev2 = hci_recv_event_data(hcon->hdev, HCI_EV_LE_PA_SYNC_ESTABLISHED); if (ev2) parent = iso_get_sock(&hcon->src, &hcon->dst, BT_LISTEN, iso_match_sid, ev2); } else if (test_bit(HCI_CONN_PA_SYNC, &hcon->flags)) { ev3 = hci_recv_event_data(hcon->hdev, HCI_EV_LE_PER_ADV_REPORT); if (ev3) parent = iso_get_sock(&hcon->src, &hcon->dst, BT_LISTEN, iso_match_sync_handle_pa_report, ev3); } if (!parent) parent = iso_get_sock(&hcon->src, BDADDR_ANY, BT_LISTEN, NULL, NULL); if (!parent) return; lock_sock(parent); sk = iso_sock_alloc(sock_net(parent), NULL, BTPROTO_ISO, GFP_ATOMIC, 0); if (!sk) { release_sock(parent); return; } iso_sock_init(sk, parent); bacpy(&iso_pi(sk)->src, &hcon->src); /* Convert from HCI to three-value type */ if (hcon->src_type == ADDR_LE_DEV_PUBLIC) iso_pi(sk)->src_type = BDADDR_LE_PUBLIC; else iso_pi(sk)->src_type = BDADDR_LE_RANDOM; /* If hcon has no destination address (BDADDR_ANY) it means it * was created by HCI_EV_LE_BIG_SYNC_ESTABILISHED or * HCI_EV_LE_PA_SYNC_ESTABLISHED so we need to initialize using * the parent socket destination address. */ if (!bacmp(&hcon->dst, BDADDR_ANY)) { bacpy(&hcon->dst, &iso_pi(parent)->dst); hcon->dst_type = iso_pi(parent)->dst_type; } if (ev3) { iso_pi(sk)->qos = iso_pi(parent)->qos; hcon->iso_qos = iso_pi(sk)->qos; iso_pi(sk)->bc_num_bis = iso_pi(parent)->bc_num_bis; memcpy(iso_pi(sk)->bc_bis, iso_pi(parent)->bc_bis, ISO_MAX_NUM_BIS); set_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags); } bacpy(&iso_pi(sk)->dst, &hcon->dst); iso_pi(sk)->dst_type = hcon->dst_type; iso_pi(sk)->sync_handle = iso_pi(parent)->sync_handle; memcpy(iso_pi(sk)->base, iso_pi(parent)->base, iso_pi(parent)->base_len); iso_pi(sk)->base_len = iso_pi(parent)->base_len; hci_conn_hold(hcon); iso_chan_add(conn, sk, parent); if ((ev && ((struct hci_evt_le_big_sync_estabilished *)ev)->status) || (ev2 && ev2->status)) { /* Trigger error signal on child socket */ sk->sk_err = ECONNREFUSED; sk->sk_error_report(sk); } if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags)) sk->sk_state = BT_CONNECT2; else sk->sk_state = BT_CONNECTED; /* Wake up parent */ parent->sk_data_ready(parent); release_sock(parent); sock_put(parent); } } static bool iso_match_sid(struct sock *sk, void *data) { struct hci_ev_le_pa_sync_established *ev = data; return ev->sid == iso_pi(sk)->bc_sid; } static bool iso_match_sync_handle(struct sock *sk, void *data) { struct hci_evt_le_big_info_adv_report *ev = data; return le16_to_cpu(ev->sync_handle) == iso_pi(sk)->sync_handle; } static bool iso_match_sync_handle_pa_report(struct sock *sk, void *data) { struct hci_ev_le_per_adv_report *ev = data; return le16_to_cpu(ev->sync_handle) == iso_pi(sk)->sync_handle; } /* ----- ISO interface with lower layer (HCI) ----- */ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) { struct hci_ev_le_pa_sync_established *ev1; struct hci_evt_le_big_info_adv_report *ev2; struct hci_ev_le_per_adv_report *ev3; struct sock *sk; bt_dev_dbg(hdev, "bdaddr %pMR", bdaddr); /* Broadcast receiver requires handling of some events before it can * proceed to establishing a BIG sync: * * 1. HCI_EV_LE_PA_SYNC_ESTABLISHED: The socket may specify a specific * SID to listen to and once sync is estabilished its handle needs to * be stored in iso_pi(sk)->sync_handle so it can be matched once * receiving the BIG Info. * 2. HCI_EVT_LE_BIG_INFO_ADV_REPORT: When connect_ind is triggered by a * a BIG Info it attempts to check if there any listening socket with * the same sync_handle and if it does then attempt to create a sync. * 3. HCI_EV_LE_PER_ADV_REPORT: When a PA report is received, it is stored * in iso_pi(sk)->base so it can be passed up to user, in the case of a * broadcast sink. */ ev1 = hci_recv_event_data(hdev, HCI_EV_LE_PA_SYNC_ESTABLISHED); if (ev1) { sk = iso_get_sock(&hdev->bdaddr, bdaddr, BT_LISTEN, iso_match_sid, ev1); if (sk && !ev1->status) iso_pi(sk)->sync_handle = le16_to_cpu(ev1->handle); goto done; } ev2 = hci_recv_event_data(hdev, HCI_EVT_LE_BIG_INFO_ADV_REPORT); if (ev2) { /* Check if BIGInfo report has already been handled */ sk = iso_get_sock(&hdev->bdaddr, bdaddr, BT_CONNECTED, iso_match_sync_handle, ev2); if (sk) { sock_put(sk); sk = NULL; goto done; } /* Try to get PA sync socket, if it exists */ sk = iso_get_sock(&hdev->bdaddr, bdaddr, BT_CONNECT2, iso_match_sync_handle, ev2); if (!sk) sk = iso_get_sock(&hdev->bdaddr, bdaddr, BT_LISTEN, iso_match_sync_handle, ev2); if (sk) { int err; struct hci_conn *hcon = iso_pi(sk)->conn->hcon; iso_pi(sk)->qos.bcast.encryption = ev2->encryption; if (ev2->num_bis < iso_pi(sk)->bc_num_bis) iso_pi(sk)->bc_num_bis = ev2->num_bis; if (!test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags) && !test_and_set_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags)) { err = hci_le_big_create_sync(hdev, hcon, &iso_pi(sk)->qos, iso_pi(sk)->sync_handle, iso_pi(sk)->bc_num_bis, iso_pi(sk)->bc_bis); if (err) { bt_dev_err(hdev, "hci_le_big_create_sync: %d", err); sock_put(sk); sk = NULL; } } } goto done; } ev3 = hci_recv_event_data(hdev, HCI_EV_LE_PER_ADV_REPORT); if (ev3) { size_t base_len = 0; u8 *base; struct hci_conn *hcon; sk = iso_get_sock(&hdev->bdaddr, bdaddr, BT_LISTEN, iso_match_sync_handle_pa_report, ev3); if (!sk) goto done; hcon = iso_pi(sk)->conn->hcon; if (!hcon) goto done; if (ev3->data_status == LE_PA_DATA_TRUNCATED) { /* The controller was unable to retrieve PA data. */ memset(hcon->le_per_adv_data, 0, HCI_MAX_PER_AD_TOT_LEN); hcon->le_per_adv_data_len = 0; hcon->le_per_adv_data_offset = 0; goto done; } if (hcon->le_per_adv_data_offset + ev3->length > HCI_MAX_PER_AD_TOT_LEN) goto done; memcpy(hcon->le_per_adv_data + hcon->le_per_adv_data_offset, ev3->data, ev3->length); hcon->le_per_adv_data_offset += ev3->length; if (ev3->data_status == LE_PA_DATA_COMPLETE) { /* All PA data has been received. */ hcon->le_per_adv_data_len = hcon->le_per_adv_data_offset; hcon->le_per_adv_data_offset = 0; /* Extract BASE */ base = eir_get_service_data(hcon->le_per_adv_data, hcon->le_per_adv_data_len, EIR_BAA_SERVICE_UUID, &base_len); if (!base || base_len > BASE_MAX_LENGTH) goto done; memcpy(iso_pi(sk)->base, base, base_len); iso_pi(sk)->base_len = base_len; } else { /* This is a PA data fragment. Keep pa_data_len set to 0 * until all data has been reassembled. */ hcon->le_per_adv_data_len = 0; } } else { sk = iso_get_sock(&hdev->bdaddr, BDADDR_ANY, BT_LISTEN, NULL, NULL); } done: if (!sk) return 0; if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) *flags |= HCI_PROTO_DEFER; sock_put(sk); return HCI_LM_ACCEPT; } static void iso_connect_cfm(struct hci_conn *hcon, __u8 status) { if (hcon->type != ISO_LINK) { if (hcon->type != LE_LINK) return; /* Check if LE link has failed */ if (status) { struct hci_link *link, *t; list_for_each_entry_safe(link, t, &hcon->link_list, list) iso_conn_del(link->conn, bt_to_errno(status)); return; } /* Create CIS if pending */ hci_le_create_cis_pending(hcon->hdev); return; } BT_DBG("hcon %p bdaddr %pMR status %d", hcon, &hcon->dst, status); /* Similar to the success case, if HCI_CONN_BIG_SYNC_FAILED or * HCI_CONN_PA_SYNC_FAILED is set, queue the failed connection * into the accept queue of the listening socket and wake up * userspace, to inform the user about the event. */ if (!status || test_bit(HCI_CONN_BIG_SYNC_FAILED, &hcon->flags) || test_bit(HCI_CONN_PA_SYNC_FAILED, &hcon->flags)) { struct iso_conn *conn; conn = iso_conn_add(hcon); if (conn) iso_conn_ready(conn); } else { iso_conn_del(hcon, bt_to_errno(status)); } } static void iso_disconn_cfm(struct hci_conn *hcon, __u8 reason) { if (hcon->type != ISO_LINK) return; BT_DBG("hcon %p reason %d", hcon, reason); iso_conn_del(hcon, bt_to_errno(reason)); } void iso_recv(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) { struct iso_conn *conn = hcon->iso_data; __u16 pb, ts, len; if (!conn) goto drop; pb = hci_iso_flags_pb(flags); ts = hci_iso_flags_ts(flags); BT_DBG("conn %p len %d pb 0x%x ts 0x%x", conn, skb->len, pb, ts); switch (pb) { case ISO_START: case ISO_SINGLE: if (conn->rx_len) { BT_ERR("Unexpected start frame (len %d)", skb->len); kfree_skb(conn->rx_skb); conn->rx_skb = NULL; conn->rx_len = 0; } if (ts) { struct hci_iso_ts_data_hdr *hdr; /* TODO: add timestamp to the packet? */ hdr = skb_pull_data(skb, HCI_ISO_TS_DATA_HDR_SIZE); if (!hdr) { BT_ERR("Frame is too short (len %d)", skb->len); goto drop; } len = __le16_to_cpu(hdr->slen); } else { struct hci_iso_data_hdr *hdr; hdr = skb_pull_data(skb, HCI_ISO_DATA_HDR_SIZE); if (!hdr) { BT_ERR("Frame is too short (len %d)", skb->len); goto drop; } len = __le16_to_cpu(hdr->slen); } flags = hci_iso_data_flags(len); len = hci_iso_data_len(len); BT_DBG("Start: total len %d, frag len %d flags 0x%4.4x", len, skb->len, flags); if (len == skb->len) { /* Complete frame received */ hci_skb_pkt_status(skb) = flags & 0x03; iso_recv_frame(conn, skb); return; } if (pb == ISO_SINGLE) { BT_ERR("Frame malformed (len %d, expected len %d)", skb->len, len); goto drop; } if (skb->len > len) { BT_ERR("Frame is too long (len %d, expected len %d)", skb->len, len); goto drop; } /* Allocate skb for the complete frame (with header) */ conn->rx_skb = bt_skb_alloc(len, GFP_KERNEL); if (!conn->rx_skb) goto drop; hci_skb_pkt_status(conn->rx_skb) = flags & 0x03; skb_copy_from_linear_data(skb, skb_put(conn->rx_skb, skb->len), skb->len); conn->rx_len = len - skb->len; break; case ISO_CONT: BT_DBG("Cont: frag len %d (expecting %d)", skb->len, conn->rx_len); if (!conn->rx_len) { BT_ERR("Unexpected continuation frame (len %d)", skb->len); goto drop; } if (skb->len > conn->rx_len) { BT_ERR("Fragment is too long (len %d, expected %d)", skb->len, conn->rx_len); kfree_skb(conn->rx_skb); conn->rx_skb = NULL; conn->rx_len = 0; goto drop; } skb_copy_from_linear_data(skb, skb_put(conn->rx_skb, skb->len), skb->len); conn->rx_len -= skb->len; return; case ISO_END: skb_copy_from_linear_data(skb, skb_put(conn->rx_skb, skb->len), skb->len); conn->rx_len -= skb->len; if (!conn->rx_len) { struct sk_buff *rx_skb = conn->rx_skb; /* Complete frame received. iso_recv_frame * takes ownership of the skb so set the global * rx_skb pointer to NULL first. */ conn->rx_skb = NULL; iso_recv_frame(conn, rx_skb); } break; } drop: kfree_skb(skb); } static struct hci_cb iso_cb = { .name = "ISO", .connect_cfm = iso_connect_cfm, .disconn_cfm = iso_disconn_cfm, }; static int iso_debugfs_show(struct seq_file *f, void *p) { struct sock *sk; read_lock(&iso_sk_list.lock); sk_for_each(sk, &iso_sk_list.head) { seq_printf(f, "%pMR %pMR %d\n", &iso_pi(sk)->src, &iso_pi(sk)->dst, sk->sk_state); } read_unlock(&iso_sk_list.lock); return 0; } DEFINE_SHOW_ATTRIBUTE(iso_debugfs); static struct dentry *iso_debugfs; static const struct proto_ops iso_sock_ops = { .family = PF_BLUETOOTH, .owner = THIS_MODULE, .release = iso_sock_release, .bind = iso_sock_bind, .connect = iso_sock_connect, .listen = iso_sock_listen, .accept = iso_sock_accept, .getname = iso_sock_getname, .sendmsg = iso_sock_sendmsg, .recvmsg = iso_sock_recvmsg, .poll = bt_sock_poll, .ioctl = bt_sock_ioctl, .mmap = sock_no_mmap, .socketpair = sock_no_socketpair, .shutdown = iso_sock_shutdown, .setsockopt = iso_sock_setsockopt, .getsockopt = iso_sock_getsockopt }; static const struct net_proto_family iso_sock_family_ops = { .family = PF_BLUETOOTH, .owner = THIS_MODULE, .create = iso_sock_create, }; static bool iso_inited; bool iso_enabled(void) { return iso_inited; } int iso_init(void) { int err; BUILD_BUG_ON(sizeof(struct sockaddr_iso) > sizeof(struct sockaddr)); if (iso_inited) return -EALREADY; err = proto_register(&iso_proto, 0); if (err < 0) return err; err = bt_sock_register(BTPROTO_ISO, &iso_sock_family_ops); if (err < 0) { BT_ERR("ISO socket registration failed"); goto error; } err = bt_procfs_init(&init_net, "iso", &iso_sk_list, NULL); if (err < 0) { BT_ERR("Failed to create ISO proc file"); bt_sock_unregister(BTPROTO_ISO); goto error; } BT_INFO("ISO socket layer initialized"); hci_register_cb(&iso_cb); if (!IS_ERR_OR_NULL(bt_debugfs)) iso_debugfs = debugfs_create_file("iso", 0444, bt_debugfs, NULL, &iso_debugfs_fops); iso_inited = true; return 0; error: proto_unregister(&iso_proto); return err; } int iso_exit(void) { if (!iso_inited) return -EALREADY; bt_procfs_cleanup(&init_net, "iso"); debugfs_remove(iso_debugfs); iso_debugfs = NULL; hci_unregister_cb(&iso_cb); bt_sock_unregister(BTPROTO_ISO); proto_unregister(&iso_proto); iso_inited = false; return 0; } |
| 8 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 | // SPDX-License-Identifier: GPL-2.0-only /* ipv6header match - matches IPv6 packets based on whether they contain certain headers */ /* Original idea: Brad Chapman * Rewritten by: Andras Kis-Szabo <kisza@sch.bme.hu> */ /* (C) 2001-2002 Andras Kis-Szabo <kisza@sch.bme.hu> */ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/ipv6.h> #include <linux/types.h> #include <net/checksum.h> #include <net/ipv6.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv6.h> #include <linux/netfilter_ipv6/ip6t_ipv6header.h> MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Xtables: IPv6 header types match"); MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>"); static bool ipv6header_mt6(const struct sk_buff *skb, struct xt_action_param *par) { const struct ip6t_ipv6header_info *info = par->matchinfo; unsigned int temp; int len; u8 nexthdr; unsigned int ptr; /* Make sure this isn't an evil packet */ /* type of the 1st exthdr */ nexthdr = ipv6_hdr(skb)->nexthdr; /* pointer to the 1st exthdr */ ptr = sizeof(struct ipv6hdr); /* available length */ len = skb->len - ptr; temp = 0; while (nf_ip6_ext_hdr(nexthdr)) { const struct ipv6_opt_hdr *hp; struct ipv6_opt_hdr _hdr; int hdrlen; /* No more exthdr -> evaluate */ if (nexthdr == NEXTHDR_NONE) { temp |= MASK_NONE; break; } /* Is there enough space for the next ext header? */ if (len < (int)sizeof(struct ipv6_opt_hdr)) return false; /* ESP -> evaluate */ if (nexthdr == NEXTHDR_ESP) { temp |= MASK_ESP; break; } hp = skb_header_pointer(skb, ptr, sizeof(_hdr), &_hdr); if (!hp) { par->hotdrop = true; return false; } /* Calculate the header length */ if (nexthdr == NEXTHDR_FRAGMENT) hdrlen = 8; else if (nexthdr == NEXTHDR_AUTH) hdrlen = ipv6_authlen(hp); else hdrlen = ipv6_optlen(hp); /* set the flag */ switch (nexthdr) { case NEXTHDR_HOP: temp |= MASK_HOPOPTS; break; case NEXTHDR_ROUTING: temp |= MASK_ROUTING; break; case NEXTHDR_FRAGMENT: temp |= MASK_FRAGMENT; break; case NEXTHDR_AUTH: temp |= MASK_AH; break; case NEXTHDR_DEST: temp |= MASK_DSTOPTS; break; default: return false; } nexthdr = hp->nexthdr; len -= hdrlen; ptr += hdrlen; if (ptr > skb->len) break; } if (nexthdr != NEXTHDR_NONE && nexthdr != NEXTHDR_ESP) temp |= MASK_PROTO; if (info->modeflag) return !((temp ^ info->matchflags ^ info->invflags) & info->matchflags); else { if (info->invflags) return temp != info->matchflags; else return temp == info->matchflags; } } static int ipv6header_mt6_check(const struct xt_mtchk_param *par) { const struct ip6t_ipv6header_info *info = par->matchinfo; /* invflags is 0 or 0xff in hard mode */ if ((!info->modeflag) && info->invflags != 0x00 && info->invflags != 0xFF) return -EINVAL; return 0; } static struct xt_match ipv6header_mt6_reg __read_mostly = { .name = "ipv6header", .family = NFPROTO_IPV6, .match = ipv6header_mt6, .matchsize = sizeof(struct ip6t_ipv6header_info), .checkentry = ipv6header_mt6_check, .destroy = NULL, .me = THIS_MODULE, }; static int __init ipv6header_mt6_init(void) { return xt_register_match(&ipv6header_mt6_reg); } static void __exit ipv6header_mt6_exit(void) { xt_unregister_match(&ipv6header_mt6_reg); } module_init(ipv6header_mt6_init); module_exit(ipv6header_mt6_exit); |
| 6 1 2 3 1 1 1 1 3 13 9 4 13 84 429 1 23 24 24 1 3 11 19 1 1 18 2 1 14 8 1 7 1 2 3 21 22 22 5 1 1 15 14 19 1 9 1 3 11 12 510 516 513 89 424 51 1 1 2 1 1 1 1 1 1 1 1 2 1 2 2 2 1 2 1 1 1 2 1 1 1 2 1 1 1 1 4 1 1 1 1 1 1 1 1 1 326 85 288 1 1 1 5 3 3 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 1 2 1 1 1 3 1 1 1 1 5 3 1 1 1 1 1 15 5 8 20 1 2 3 34 18 1 326 83 555 13 32 311 200 6 3 1 1 1 1 2 2 9 1 8 1 3 3 106 106 7 96 25 4 3 1 9 1 3 1 5 4 1 4 1 4 1 4 1 2 1 1 1 1 1 1 1 1 1 6 1 1 1 1 1 1 1 1 1 1 3 3 2 3 1 1 1 1 1 1 1 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 4 2 1 1 2 1 1 1 1 42 40 123 2 18 84 17 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPv6 BSD socket options interface * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Based on linux/net/ipv4/ip_sockglue.c * * FIXME: Make the setsockopt code POSIX compliant: That is * * o Truncate getsockopt returns * o Return an optlen of the truncated length if need be * * Changes: * David L Stevens <dlstevens@us.ibm.com>: * - added multicast source filtering API for MLDv2 */ #include <linux/module.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/mroute6.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/init.h> #include <linux/sysctl.h> #include <linux/netfilter.h> #include <linux/slab.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/ndisc.h> #include <net/protocol.h> #include <net/transp_v6.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/inet_common.h> #include <net/tcp.h> #include <net/udp.h> #include <net/udplite.h> #include <net/xfrm.h> #include <net/compat.h> #include <net/seg6.h> #include <linux/uaccess.h> struct ip6_ra_chain *ip6_ra_chain; DEFINE_RWLOCK(ip6_ra_lock); DEFINE_STATIC_KEY_FALSE(ip6_min_hopcount); int ip6_ra_control(struct sock *sk, int sel) { struct ip6_ra_chain *ra, *new_ra, **rap; /* RA packet may be delivered ONLY to IPPROTO_RAW socket */ if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_RAW) return -ENOPROTOOPT; new_ra = (sel >= 0) ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL; if (sel >= 0 && !new_ra) return -ENOMEM; write_lock_bh(&ip6_ra_lock); for (rap = &ip6_ra_chain; (ra = *rap) != NULL; rap = &ra->next) { if (ra->sk == sk) { if (sel >= 0) { write_unlock_bh(&ip6_ra_lock); kfree(new_ra); return -EADDRINUSE; } *rap = ra->next; write_unlock_bh(&ip6_ra_lock); sock_put(sk); kfree(ra); return 0; } } if (!new_ra) { write_unlock_bh(&ip6_ra_lock); return -ENOBUFS; } new_ra->sk = sk; new_ra->sel = sel; new_ra->next = ra; *rap = new_ra; sock_hold(sk); write_unlock_bh(&ip6_ra_lock); return 0; } struct ipv6_txoptions *ipv6_update_options(struct sock *sk, struct ipv6_txoptions *opt) { if (inet_test_bit(IS_ICSK, sk)) { if (opt && !((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) && inet_sk(sk)->inet_daddr != LOOPBACK4_IPV6) { struct inet_connection_sock *icsk = inet_csk(sk); icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen; icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie); } } opt = unrcu_pointer(xchg(&inet6_sk(sk)->opt, RCU_INITIALIZER(opt))); sk_dst_reset(sk); return opt; } static bool setsockopt_needs_rtnl(int optname) { switch (optname) { case IPV6_ADDRFORM: case IPV6_ADD_MEMBERSHIP: case IPV6_DROP_MEMBERSHIP: case IPV6_JOIN_ANYCAST: case IPV6_LEAVE_ANYCAST: case MCAST_JOIN_GROUP: case MCAST_LEAVE_GROUP: case MCAST_JOIN_SOURCE_GROUP: case MCAST_LEAVE_SOURCE_GROUP: case MCAST_BLOCK_SOURCE: case MCAST_UNBLOCK_SOURCE: case MCAST_MSFILTER: return true; } return false; } static int copy_group_source_from_sockptr(struct group_source_req *greqs, sockptr_t optval, int optlen) { if (in_compat_syscall()) { struct compat_group_source_req gr32; if (optlen < sizeof(gr32)) return -EINVAL; if (copy_from_sockptr(&gr32, optval, sizeof(gr32))) return -EFAULT; greqs->gsr_interface = gr32.gsr_interface; greqs->gsr_group = gr32.gsr_group; greqs->gsr_source = gr32.gsr_source; } else { if (optlen < sizeof(*greqs)) return -EINVAL; if (copy_from_sockptr(greqs, optval, sizeof(*greqs))) return -EFAULT; } return 0; } static int do_ipv6_mcast_group_source(struct sock *sk, int optname, sockptr_t optval, int optlen) { struct group_source_req greqs; int omode, add; int ret; ret = copy_group_source_from_sockptr(&greqs, optval, optlen); if (ret) return ret; if (greqs.gsr_group.ss_family != AF_INET6 || greqs.gsr_source.ss_family != AF_INET6) return -EADDRNOTAVAIL; if (optname == MCAST_BLOCK_SOURCE) { omode = MCAST_EXCLUDE; add = 1; } else if (optname == MCAST_UNBLOCK_SOURCE) { omode = MCAST_EXCLUDE; add = 0; } else if (optname == MCAST_JOIN_SOURCE_GROUP) { struct sockaddr_in6 *psin6; int retv; psin6 = (struct sockaddr_in6 *)&greqs.gsr_group; retv = ipv6_sock_mc_join_ssm(sk, greqs.gsr_interface, &psin6->sin6_addr, MCAST_INCLUDE); /* prior join w/ different source is ok */ if (retv && retv != -EADDRINUSE) return retv; omode = MCAST_INCLUDE; add = 1; } else /* MCAST_LEAVE_SOURCE_GROUP */ { omode = MCAST_INCLUDE; add = 0; } return ip6_mc_source(add, omode, sk, &greqs); } static int ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen) { struct group_filter *gsf; int ret; if (optlen < GROUP_FILTER_SIZE(0)) return -EINVAL; if (optlen > READ_ONCE(sock_net(sk)->core.sysctl_optmem_max)) return -ENOBUFS; gsf = memdup_sockptr(optval, optlen); if (IS_ERR(gsf)) return PTR_ERR(gsf); /* numsrc >= (4G-140)/128 overflow in 32 bits */ ret = -ENOBUFS; if (gsf->gf_numsrc >= 0x1ffffffU || gsf->gf_numsrc > sysctl_mld_max_msf) goto out_free_gsf; ret = -EINVAL; if (GROUP_FILTER_SIZE(gsf->gf_numsrc) > optlen) goto out_free_gsf; ret = ip6_mc_msfilter(sk, gsf, gsf->gf_slist_flex); out_free_gsf: kfree(gsf); return ret; } static int compat_ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen) { const int size0 = offsetof(struct compat_group_filter, gf_slist_flex); struct compat_group_filter *gf32; void *p; int ret; int n; if (optlen < size0) return -EINVAL; if (optlen > READ_ONCE(sock_net(sk)->core.sysctl_optmem_max) - 4) return -ENOBUFS; p = kmalloc(optlen + 4, GFP_KERNEL); if (!p) return -ENOMEM; gf32 = p + 4; /* we want ->gf_group and ->gf_slist_flex aligned */ ret = -EFAULT; if (copy_from_sockptr(gf32, optval, optlen)) goto out_free_p; /* numsrc >= (4G-140)/128 overflow in 32 bits */ ret = -ENOBUFS; n = gf32->gf_numsrc; if (n >= 0x1ffffffU || n > sysctl_mld_max_msf) goto out_free_p; ret = -EINVAL; if (offsetof(struct compat_group_filter, gf_slist_flex[n]) > optlen) goto out_free_p; ret = ip6_mc_msfilter(sk, &(struct group_filter){ .gf_interface = gf32->gf_interface, .gf_group = gf32->gf_group, .gf_fmode = gf32->gf_fmode, .gf_numsrc = gf32->gf_numsrc}, gf32->gf_slist_flex); out_free_p: kfree(p); return ret; } static int ipv6_mcast_join_leave(struct sock *sk, int optname, sockptr_t optval, int optlen) { struct sockaddr_in6 *psin6; struct group_req greq; if (optlen < sizeof(greq)) return -EINVAL; if (copy_from_sockptr(&greq, optval, sizeof(greq))) return -EFAULT; if (greq.gr_group.ss_family != AF_INET6) return -EADDRNOTAVAIL; psin6 = (struct sockaddr_in6 *)&greq.gr_group; if (optname == MCAST_JOIN_GROUP) return ipv6_sock_mc_join(sk, greq.gr_interface, &psin6->sin6_addr); return ipv6_sock_mc_drop(sk, greq.gr_interface, &psin6->sin6_addr); } static int compat_ipv6_mcast_join_leave(struct sock *sk, int optname, sockptr_t optval, int optlen) { struct compat_group_req gr32; struct sockaddr_in6 *psin6; if (optlen < sizeof(gr32)) return -EINVAL; if (copy_from_sockptr(&gr32, optval, sizeof(gr32))) return -EFAULT; if (gr32.gr_group.ss_family != AF_INET6) return -EADDRNOTAVAIL; psin6 = (struct sockaddr_in6 *)&gr32.gr_group; if (optname == MCAST_JOIN_GROUP) return ipv6_sock_mc_join(sk, gr32.gr_interface, &psin6->sin6_addr); return ipv6_sock_mc_drop(sk, gr32.gr_interface, &psin6->sin6_addr); } static int ipv6_set_opt_hdr(struct sock *sk, int optname, sockptr_t optval, int optlen) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_opt_hdr *new = NULL; struct net *net = sock_net(sk); struct ipv6_txoptions *opt; int err; /* hop-by-hop / destination options are privileged option */ if (optname != IPV6_RTHDR && !sockopt_ns_capable(net->user_ns, CAP_NET_RAW)) return -EPERM; /* remove any sticky options header with a zero option * length, per RFC3542. */ if (optlen > 0) { if (sockptr_is_null(optval)) return -EINVAL; if (optlen < sizeof(struct ipv6_opt_hdr) || optlen & 0x7 || optlen > 8 * 255) return -EINVAL; new = memdup_sockptr(optval, optlen); if (IS_ERR(new)) return PTR_ERR(new); if (unlikely(ipv6_optlen(new) > optlen)) { kfree(new); return -EINVAL; } } opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk)); opt = ipv6_renew_options(sk, opt, optname, new); kfree(new); if (IS_ERR(opt)) return PTR_ERR(opt); /* routing header option needs extra check */ err = -EINVAL; if (optname == IPV6_RTHDR && opt && opt->srcrt) { struct ipv6_rt_hdr *rthdr = opt->srcrt; switch (rthdr->type) { #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPV6_SRCRT_TYPE_2: if (rthdr->hdrlen != 2 || rthdr->segments_left != 1) goto sticky_done; break; #endif case IPV6_SRCRT_TYPE_4: { struct ipv6_sr_hdr *srh = (struct ipv6_sr_hdr *)opt->srcrt; if (!seg6_validate_srh(srh, optlen, false)) goto sticky_done; break; } default: goto sticky_done; } } err = 0; opt = ipv6_update_options(sk, opt); sticky_done: if (opt) { atomic_sub(opt->tot_len, &sk->sk_omem_alloc); txopt_put(opt); } return err; } int do_ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); int val, valbool; int retv = -ENOPROTOOPT; bool needs_rtnl = setsockopt_needs_rtnl(optname); if (sockptr_is_null(optval)) val = 0; else { if (optlen >= sizeof(int)) { if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; } else val = 0; } valbool = (val != 0); if (ip6_mroute_opt(optname)) return ip6_mroute_setsockopt(sk, optname, optval, optlen); /* Handle options that can be set without locking the socket. */ switch (optname) { case IPV6_UNICAST_HOPS: if (optlen < sizeof(int)) return -EINVAL; if (val > 255 || val < -1) return -EINVAL; WRITE_ONCE(np->hop_limit, val); return 0; case IPV6_MULTICAST_LOOP: if (optlen < sizeof(int)) return -EINVAL; if (val != valbool) return -EINVAL; inet6_assign_bit(MC6_LOOP, sk, valbool); return 0; case IPV6_MULTICAST_HOPS: if (sk->sk_type == SOCK_STREAM) return retv; if (optlen < sizeof(int)) return -EINVAL; if (val > 255 || val < -1) return -EINVAL; WRITE_ONCE(np->mcast_hops, val == -1 ? IPV6_DEFAULT_MCASTHOPS : val); return 0; case IPV6_MTU: if (optlen < sizeof(int)) return -EINVAL; if (val && val < IPV6_MIN_MTU) return -EINVAL; WRITE_ONCE(np->frag_size, val); return 0; case IPV6_MINHOPCOUNT: if (optlen < sizeof(int)) return -EINVAL; if (val < 0 || val > 255) return -EINVAL; if (val) static_branch_enable(&ip6_min_hopcount); /* tcp_v6_err() and tcp_v6_rcv() might read min_hopcount * while we are changing it. */ WRITE_ONCE(np->min_hopcount, val); return 0; case IPV6_RECVERR_RFC4884: if (optlen < sizeof(int)) return -EINVAL; if (val < 0 || val > 1) return -EINVAL; inet6_assign_bit(RECVERR6_RFC4884, sk, valbool); return 0; case IPV6_MULTICAST_ALL: if (optlen < sizeof(int)) return -EINVAL; inet6_assign_bit(MC6_ALL, sk, valbool); return 0; case IPV6_AUTOFLOWLABEL: inet6_assign_bit(AUTOFLOWLABEL, sk, valbool); inet6_set_bit(AUTOFLOWLABEL_SET, sk); return 0; case IPV6_DONTFRAG: inet6_assign_bit(DONTFRAG, sk, valbool); return 0; case IPV6_RECVERR: if (optlen < sizeof(int)) return -EINVAL; inet6_assign_bit(RECVERR6, sk, valbool); if (!val) skb_errqueue_purge(&sk->sk_error_queue); return 0; case IPV6_ROUTER_ALERT_ISOLATE: if (optlen < sizeof(int)) return -EINVAL; inet6_assign_bit(RTALERT_ISOLATE, sk, valbool); return 0; case IPV6_MTU_DISCOVER: if (optlen < sizeof(int)) return -EINVAL; if (val < IPV6_PMTUDISC_DONT || val > IPV6_PMTUDISC_OMIT) return -EINVAL; WRITE_ONCE(np->pmtudisc, val); return 0; case IPV6_FLOWINFO_SEND: if (optlen < sizeof(int)) return -EINVAL; inet6_assign_bit(SNDFLOW, sk, valbool); return 0; case IPV6_ADDR_PREFERENCES: if (optlen < sizeof(int)) return -EINVAL; return ip6_sock_set_addr_preferences(sk, val); case IPV6_MULTICAST_IF: if (sk->sk_type == SOCK_STREAM) return -ENOPROTOOPT; if (optlen < sizeof(int)) return -EINVAL; if (val) { struct net_device *dev; int bound_dev_if, midx; rcu_read_lock(); dev = dev_get_by_index_rcu(net, val); if (!dev) { rcu_read_unlock(); return -ENODEV; } midx = l3mdev_master_ifindex_rcu(dev); rcu_read_unlock(); bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); if (bound_dev_if && bound_dev_if != val && (!midx || midx != bound_dev_if)) return -EINVAL; } WRITE_ONCE(np->mcast_oif, val); return 0; case IPV6_UNICAST_IF: { struct net_device *dev; int ifindex; if (optlen != sizeof(int)) return -EINVAL; ifindex = (__force int)ntohl((__force __be32)val); if (!ifindex) { WRITE_ONCE(np->ucast_oif, 0); return 0; } dev = dev_get_by_index(net, ifindex); if (!dev) return -EADDRNOTAVAIL; dev_put(dev); if (READ_ONCE(sk->sk_bound_dev_if)) return -EINVAL; WRITE_ONCE(np->ucast_oif, ifindex); return 0; } } if (needs_rtnl) rtnl_lock(); sockopt_lock_sock(sk); /* Another thread has converted the socket into IPv4 with * IPV6_ADDRFORM concurrently. */ if (unlikely(sk->sk_family != AF_INET6)) goto unlock; switch (optname) { case IPV6_ADDRFORM: if (optlen < sizeof(int)) goto e_inval; if (val == PF_INET) { if (sk->sk_type == SOCK_RAW) break; if (sk->sk_protocol == IPPROTO_UDP || sk->sk_protocol == IPPROTO_UDPLITE) { struct udp_sock *up = udp_sk(sk); if (up->pending == AF_INET6) { retv = -EBUSY; break; } } else if (sk->sk_protocol == IPPROTO_TCP) { if (sk->sk_prot != &tcpv6_prot) { retv = -EBUSY; break; } } else { break; } if (sk->sk_state != TCP_ESTABLISHED) { retv = -ENOTCONN; break; } if (ipv6_only_sock(sk) || !ipv6_addr_v4mapped(&sk->sk_v6_daddr)) { retv = -EADDRNOTAVAIL; break; } __ipv6_sock_mc_close(sk); __ipv6_sock_ac_close(sk); if (sk->sk_protocol == IPPROTO_TCP) { struct inet_connection_sock *icsk = inet_csk(sk); sock_prot_inuse_add(net, sk->sk_prot, -1); sock_prot_inuse_add(net, &tcp_prot, 1); /* Paired with READ_ONCE(sk->sk_prot) in inet6_stream_ops */ WRITE_ONCE(sk->sk_prot, &tcp_prot); /* Paired with READ_ONCE() in tcp_(get|set)sockopt() */ WRITE_ONCE(icsk->icsk_af_ops, &ipv4_specific); WRITE_ONCE(sk->sk_socket->ops, &inet_stream_ops); WRITE_ONCE(sk->sk_family, PF_INET); tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); } else { struct proto *prot = &udp_prot; if (sk->sk_protocol == IPPROTO_UDPLITE) prot = &udplite_prot; sock_prot_inuse_add(net, sk->sk_prot, -1); sock_prot_inuse_add(net, prot, 1); /* Paired with READ_ONCE(sk->sk_prot) in inet6_dgram_ops */ WRITE_ONCE(sk->sk_prot, prot); WRITE_ONCE(sk->sk_socket->ops, &inet_dgram_ops); WRITE_ONCE(sk->sk_family, PF_INET); } /* Disable all options not to allocate memory anymore, * but there is still a race. See the lockless path * in udpv6_sendmsg() and ipv6_local_rxpmtu(). */ np->rxopt.all = 0; inet6_cleanup_sock(sk); module_put(THIS_MODULE); retv = 0; break; } goto e_inval; case IPV6_V6ONLY: if (optlen < sizeof(int) || inet_sk(sk)->inet_num) goto e_inval; sk->sk_ipv6only = valbool; retv = 0; break; case IPV6_RECVPKTINFO: if (optlen < sizeof(int)) goto e_inval; np->rxopt.bits.rxinfo = valbool; retv = 0; break; case IPV6_2292PKTINFO: if (optlen < sizeof(int)) goto e_inval; np->rxopt.bits.rxoinfo = valbool; retv = 0; break; case IPV6_RECVHOPLIMIT: if (optlen < sizeof(int)) goto e_inval; np->rxopt.bits.rxhlim = valbool; retv = 0; break; case IPV6_2292HOPLIMIT: if (optlen < sizeof(int)) goto e_inval; np->rxopt.bits.rxohlim = valbool; retv = 0; break; case IPV6_RECVRTHDR: if (optlen < sizeof(int)) goto e_inval; np->rxopt.bits.srcrt = valbool; retv = 0; break; case IPV6_2292RTHDR: if (optlen < sizeof(int)) goto e_inval; np->rxopt.bits.osrcrt = valbool; retv = 0; break; case IPV6_RECVHOPOPTS: if (optlen < sizeof(int)) goto e_inval; np->rxopt.bits.hopopts = valbool; retv = 0; break; case IPV6_2292HOPOPTS: if (optlen < sizeof(int)) goto e_inval; np->rxopt.bits.ohopopts = valbool; retv = 0; break; case IPV6_RECVDSTOPTS: if (optlen < sizeof(int)) goto e_inval; np->rxopt.bits.dstopts = valbool; retv = 0; break; case IPV6_2292DSTOPTS: if (optlen < sizeof(int)) goto e_inval; np->rxopt.bits.odstopts = valbool; retv = 0; break; case IPV6_TCLASS: if (optlen < sizeof(int)) goto e_inval; if (val < -1 || val > 0xff) goto e_inval; /* RFC 3542, 6.5: default traffic class of 0x0 */ if (val == -1) val = 0; if (sk->sk_type == SOCK_STREAM) { val &= ~INET_ECN_MASK; val |= np->tclass & INET_ECN_MASK; } if (np->tclass != val) { np->tclass = val; sk_dst_reset(sk); } retv = 0; break; case IPV6_RECVTCLASS: if (optlen < sizeof(int)) goto e_inval; np->rxopt.bits.rxtclass = valbool; retv = 0; break; case IPV6_FLOWINFO: if (optlen < sizeof(int)) goto e_inval; np->rxopt.bits.rxflow = valbool; retv = 0; break; case IPV6_RECVPATHMTU: if (optlen < sizeof(int)) goto e_inval; np->rxopt.bits.rxpmtu = valbool; retv = 0; break; case IPV6_TRANSPARENT: if (valbool && !sockopt_ns_capable(net->user_ns, CAP_NET_RAW) && !sockopt_ns_capable(net->user_ns, CAP_NET_ADMIN)) { retv = -EPERM; break; } if (optlen < sizeof(int)) goto e_inval; /* we don't have a separate transparent bit for IPV6 we use the one in the IPv4 socket */ inet_assign_bit(TRANSPARENT, sk, valbool); retv = 0; break; case IPV6_FREEBIND: if (optlen < sizeof(int)) goto e_inval; /* we also don't have a separate freebind bit for IPV6 */ inet_assign_bit(FREEBIND, sk, valbool); retv = 0; break; case IPV6_RECVORIGDSTADDR: if (optlen < sizeof(int)) goto e_inval; np->rxopt.bits.rxorigdstaddr = valbool; retv = 0; break; case IPV6_HOPOPTS: case IPV6_RTHDRDSTOPTS: case IPV6_RTHDR: case IPV6_DSTOPTS: retv = ipv6_set_opt_hdr(sk, optname, optval, optlen); break; case IPV6_PKTINFO: { struct in6_pktinfo pkt; if (optlen == 0) goto e_inval; else if (optlen < sizeof(struct in6_pktinfo) || sockptr_is_null(optval)) goto e_inval; if (copy_from_sockptr(&pkt, optval, sizeof(pkt))) { retv = -EFAULT; break; } if (!sk_dev_equal_l3scope(sk, pkt.ipi6_ifindex)) goto e_inval; np->sticky_pktinfo.ipi6_ifindex = pkt.ipi6_ifindex; np->sticky_pktinfo.ipi6_addr = pkt.ipi6_addr; retv = 0; break; } case IPV6_2292PKTOPTIONS: { struct ipv6_txoptions *opt = NULL; struct msghdr msg; struct flowi6 fl6; struct ipcm6_cookie ipc6; memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; if (optlen == 0) goto update; /* 1K is probably excessive * 1K is surely not enough, 2K per standard header is 16K. */ retv = -EINVAL; if (optlen > 64*1024) break; opt = sock_kmalloc(sk, sizeof(*opt) + optlen, GFP_KERNEL); retv = -ENOBUFS; if (!opt) break; memset(opt, 0, sizeof(*opt)); refcount_set(&opt->refcnt, 1); opt->tot_len = sizeof(*opt) + optlen; retv = -EFAULT; if (copy_from_sockptr(opt + 1, optval, optlen)) goto done; msg.msg_controllen = optlen; msg.msg_control_is_user = false; msg.msg_control = (void *)(opt+1); ipc6.opt = opt; retv = ip6_datagram_send_ctl(net, sk, &msg, &fl6, &ipc6); if (retv) goto done; update: retv = 0; opt = ipv6_update_options(sk, opt); done: if (opt) { atomic_sub(opt->tot_len, &sk->sk_omem_alloc); txopt_put(opt); } break; } case IPV6_ADD_MEMBERSHIP: case IPV6_DROP_MEMBERSHIP: { struct ipv6_mreq mreq; if (optlen < sizeof(struct ipv6_mreq)) goto e_inval; retv = -EPROTO; if (inet_test_bit(IS_ICSK, sk)) break; retv = -EFAULT; if (copy_from_sockptr(&mreq, optval, sizeof(struct ipv6_mreq))) break; if (optname == IPV6_ADD_MEMBERSHIP) retv = ipv6_sock_mc_join(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_multiaddr); else retv = ipv6_sock_mc_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_multiaddr); break; } case IPV6_JOIN_ANYCAST: case IPV6_LEAVE_ANYCAST: { struct ipv6_mreq mreq; if (optlen < sizeof(struct ipv6_mreq)) goto e_inval; retv = -EFAULT; if (copy_from_sockptr(&mreq, optval, sizeof(struct ipv6_mreq))) break; if (optname == IPV6_JOIN_ANYCAST) retv = ipv6_sock_ac_join(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr); else retv = ipv6_sock_ac_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr); break; } case MCAST_JOIN_GROUP: case MCAST_LEAVE_GROUP: if (in_compat_syscall()) retv = compat_ipv6_mcast_join_leave(sk, optname, optval, optlen); else retv = ipv6_mcast_join_leave(sk, optname, optval, optlen); break; case MCAST_JOIN_SOURCE_GROUP: case MCAST_LEAVE_SOURCE_GROUP: case MCAST_BLOCK_SOURCE: case MCAST_UNBLOCK_SOURCE: retv = do_ipv6_mcast_group_source(sk, optname, optval, optlen); break; case MCAST_MSFILTER: if (in_compat_syscall()) retv = compat_ipv6_set_mcast_msfilter(sk, optval, optlen); else retv = ipv6_set_mcast_msfilter(sk, optval, optlen); break; case IPV6_ROUTER_ALERT: if (optlen < sizeof(int)) goto e_inval; retv = ip6_ra_control(sk, val); if (retv == 0) inet6_assign_bit(RTALERT, sk, valbool); break; case IPV6_FLOWLABEL_MGR: retv = ipv6_flowlabel_opt(sk, optval, optlen); break; case IPV6_IPSEC_POLICY: case IPV6_XFRM_POLICY: retv = -EPERM; if (!sockopt_ns_capable(net->user_ns, CAP_NET_ADMIN)) break; retv = xfrm_user_policy(sk, optname, optval, optlen); break; case IPV6_RECVFRAGSIZE: np->rxopt.bits.recvfragsize = valbool; retv = 0; break; } unlock: sockopt_release_sock(sk); if (needs_rtnl) rtnl_unlock(); return retv; e_inval: retv = -EINVAL; goto unlock; } int ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { int err; if (level == SOL_IP && sk->sk_type != SOCK_RAW) return ip_setsockopt(sk, level, optname, optval, optlen); if (level != SOL_IPV6) return -ENOPROTOOPT; err = do_ipv6_setsockopt(sk, level, optname, optval, optlen); #ifdef CONFIG_NETFILTER /* we need to exclude all possible ENOPROTOOPTs except default case */ if (err == -ENOPROTOOPT && optname != IPV6_IPSEC_POLICY && optname != IPV6_XFRM_POLICY) err = nf_setsockopt(sk, PF_INET6, optname, optval, optlen); #endif return err; } EXPORT_SYMBOL(ipv6_setsockopt); static int ipv6_getsockopt_sticky(struct sock *sk, struct ipv6_txoptions *opt, int optname, sockptr_t optval, int len) { struct ipv6_opt_hdr *hdr; if (!opt) return 0; switch (optname) { case IPV6_HOPOPTS: hdr = opt->hopopt; break; case IPV6_RTHDRDSTOPTS: hdr = opt->dst0opt; break; case IPV6_RTHDR: hdr = (struct ipv6_opt_hdr *)opt->srcrt; break; case IPV6_DSTOPTS: hdr = opt->dst1opt; break; default: return -EINVAL; /* should not happen */ } if (!hdr) return 0; len = min_t(unsigned int, len, ipv6_optlen(hdr)); if (copy_to_sockptr(optval, hdr, len)) return -EFAULT; return len; } static int ipv6_get_msfilter(struct sock *sk, sockptr_t optval, sockptr_t optlen, int len) { const int size0 = offsetof(struct group_filter, gf_slist_flex); struct group_filter gsf; int num; int err; if (len < size0) return -EINVAL; if (copy_from_sockptr(&gsf, optval, size0)) return -EFAULT; if (gsf.gf_group.ss_family != AF_INET6) return -EADDRNOTAVAIL; num = gsf.gf_numsrc; sockopt_lock_sock(sk); err = ip6_mc_msfget(sk, &gsf, optval, size0); if (!err) { if (num > gsf.gf_numsrc) num = gsf.gf_numsrc; len = GROUP_FILTER_SIZE(num); if (copy_to_sockptr(optlen, &len, sizeof(int)) || copy_to_sockptr(optval, &gsf, size0)) err = -EFAULT; } sockopt_release_sock(sk); return err; } static int compat_ipv6_get_msfilter(struct sock *sk, sockptr_t optval, sockptr_t optlen, int len) { const int size0 = offsetof(struct compat_group_filter, gf_slist_flex); struct compat_group_filter gf32; struct group_filter gf; int err; int num; if (len < size0) return -EINVAL; if (copy_from_sockptr(&gf32, optval, size0)) return -EFAULT; gf.gf_interface = gf32.gf_interface; gf.gf_fmode = gf32.gf_fmode; num = gf.gf_numsrc = gf32.gf_numsrc; gf.gf_group = gf32.gf_group; if (gf.gf_group.ss_family != AF_INET6) return -EADDRNOTAVAIL; sockopt_lock_sock(sk); err = ip6_mc_msfget(sk, &gf, optval, size0); sockopt_release_sock(sk); if (err) return err; if (num > gf.gf_numsrc) num = gf.gf_numsrc; len = GROUP_FILTER_SIZE(num) - (sizeof(gf)-sizeof(gf32)); if (copy_to_sockptr(optlen, &len, sizeof(int)) || copy_to_sockptr_offset(optval, offsetof(struct compat_group_filter, gf_fmode), &gf.gf_fmode, sizeof(gf32.gf_fmode)) || copy_to_sockptr_offset(optval, offsetof(struct compat_group_filter, gf_numsrc), &gf.gf_numsrc, sizeof(gf32.gf_numsrc))) return -EFAULT; return 0; } int do_ipv6_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen) { struct ipv6_pinfo *np = inet6_sk(sk); int len; int val; if (ip6_mroute_opt(optname)) return ip6_mroute_getsockopt(sk, optname, optval, optlen); if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; switch (optname) { case IPV6_ADDRFORM: if (sk->sk_protocol != IPPROTO_UDP && sk->sk_protocol != IPPROTO_UDPLITE && sk->sk_protocol != IPPROTO_TCP) return -ENOPROTOOPT; if (sk->sk_state != TCP_ESTABLISHED) return -ENOTCONN; val = sk->sk_family; break; case MCAST_MSFILTER: if (in_compat_syscall()) return compat_ipv6_get_msfilter(sk, optval, optlen, len); return ipv6_get_msfilter(sk, optval, optlen, len); case IPV6_2292PKTOPTIONS: { struct msghdr msg; struct sk_buff *skb; if (sk->sk_type != SOCK_STREAM) return -ENOPROTOOPT; if (optval.is_kernel) { msg.msg_control_is_user = false; msg.msg_control = optval.kernel; } else { msg.msg_control_is_user = true; msg.msg_control_user = optval.user; } msg.msg_controllen = len; msg.msg_flags = 0; sockopt_lock_sock(sk); skb = np->pktoptions; if (skb) ip6_datagram_recv_ctl(sk, &msg, skb); sockopt_release_sock(sk); if (!skb) { if (np->rxopt.bits.rxinfo) { int mcast_oif = READ_ONCE(np->mcast_oif); struct in6_pktinfo src_info; src_info.ipi6_ifindex = mcast_oif ? : np->sticky_pktinfo.ipi6_ifindex; src_info.ipi6_addr = mcast_oif ? sk->sk_v6_daddr : np->sticky_pktinfo.ipi6_addr; put_cmsg(&msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info); } if (np->rxopt.bits.rxhlim) { int hlim = READ_ONCE(np->mcast_hops); put_cmsg(&msg, SOL_IPV6, IPV6_HOPLIMIT, sizeof(hlim), &hlim); } if (np->rxopt.bits.rxtclass) { int tclass = (int)ip6_tclass(np->rcv_flowinfo); put_cmsg(&msg, SOL_IPV6, IPV6_TCLASS, sizeof(tclass), &tclass); } if (np->rxopt.bits.rxoinfo) { int mcast_oif = READ_ONCE(np->mcast_oif); struct in6_pktinfo src_info; src_info.ipi6_ifindex = mcast_oif ? : np->sticky_pktinfo.ipi6_ifindex; src_info.ipi6_addr = mcast_oif ? sk->sk_v6_daddr : np->sticky_pktinfo.ipi6_addr; put_cmsg(&msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info); } if (np->rxopt.bits.rxohlim) { int hlim = READ_ONCE(np->mcast_hops); put_cmsg(&msg, SOL_IPV6, IPV6_2292HOPLIMIT, sizeof(hlim), &hlim); } if (np->rxopt.bits.rxflow) { __be32 flowinfo = np->rcv_flowinfo; put_cmsg(&msg, SOL_IPV6, IPV6_FLOWINFO, sizeof(flowinfo), &flowinfo); } } len -= msg.msg_controllen; return copy_to_sockptr(optlen, &len, sizeof(int)); } case IPV6_MTU: { struct dst_entry *dst; val = 0; rcu_read_lock(); dst = __sk_dst_get(sk); if (dst) val = dst_mtu(dst); rcu_read_unlock(); if (!val) return -ENOTCONN; break; } case IPV6_V6ONLY: val = sk->sk_ipv6only; break; case IPV6_RECVPKTINFO: val = np->rxopt.bits.rxinfo; break; case IPV6_2292PKTINFO: val = np->rxopt.bits.rxoinfo; break; case IPV6_RECVHOPLIMIT: val = np->rxopt.bits.rxhlim; break; case IPV6_2292HOPLIMIT: val = np->rxopt.bits.rxohlim; break; case IPV6_RECVRTHDR: val = np->rxopt.bits.srcrt; break; case IPV6_2292RTHDR: val = np->rxopt.bits.osrcrt; break; case IPV6_HOPOPTS: case IPV6_RTHDRDSTOPTS: case IPV6_RTHDR: case IPV6_DSTOPTS: { struct ipv6_txoptions *opt; sockopt_lock_sock(sk); opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk)); len = ipv6_getsockopt_sticky(sk, opt, optname, optval, len); sockopt_release_sock(sk); /* check if ipv6_getsockopt_sticky() returns err code */ if (len < 0) return len; return copy_to_sockptr(optlen, &len, sizeof(int)); } case IPV6_RECVHOPOPTS: val = np->rxopt.bits.hopopts; break; case IPV6_2292HOPOPTS: val = np->rxopt.bits.ohopopts; break; case IPV6_RECVDSTOPTS: val = np->rxopt.bits.dstopts; break; case IPV6_2292DSTOPTS: val = np->rxopt.bits.odstopts; break; case IPV6_TCLASS: val = np->tclass; break; case IPV6_RECVTCLASS: val = np->rxopt.bits.rxtclass; break; case IPV6_FLOWINFO: val = np->rxopt.bits.rxflow; break; case IPV6_RECVPATHMTU: val = np->rxopt.bits.rxpmtu; break; case IPV6_PATHMTU: { struct dst_entry *dst; struct ip6_mtuinfo mtuinfo; if (len < sizeof(mtuinfo)) return -EINVAL; len = sizeof(mtuinfo); memset(&mtuinfo, 0, sizeof(mtuinfo)); rcu_read_lock(); dst = __sk_dst_get(sk); if (dst) mtuinfo.ip6m_mtu = dst_mtu(dst); rcu_read_unlock(); if (!mtuinfo.ip6m_mtu) return -ENOTCONN; if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &mtuinfo, len)) return -EFAULT; return 0; } case IPV6_TRANSPARENT: val = inet_test_bit(TRANSPARENT, sk); break; case IPV6_FREEBIND: val = inet_test_bit(FREEBIND, sk); break; case IPV6_RECVORIGDSTADDR: val = np->rxopt.bits.rxorigdstaddr; break; case IPV6_UNICAST_HOPS: case IPV6_MULTICAST_HOPS: { struct dst_entry *dst; if (optname == IPV6_UNICAST_HOPS) val = READ_ONCE(np->hop_limit); else val = READ_ONCE(np->mcast_hops); if (val < 0) { rcu_read_lock(); dst = __sk_dst_get(sk); if (dst) val = ip6_dst_hoplimit(dst); rcu_read_unlock(); } if (val < 0) val = READ_ONCE(sock_net(sk)->ipv6.devconf_all->hop_limit); break; } case IPV6_MULTICAST_LOOP: val = inet6_test_bit(MC6_LOOP, sk); break; case IPV6_MULTICAST_IF: val = READ_ONCE(np->mcast_oif); break; case IPV6_MULTICAST_ALL: val = inet6_test_bit(MC6_ALL, sk); break; case IPV6_UNICAST_IF: val = (__force int)htonl((__u32) READ_ONCE(np->ucast_oif)); break; case IPV6_MTU_DISCOVER: val = READ_ONCE(np->pmtudisc); break; case IPV6_RECVERR: val = inet6_test_bit(RECVERR6, sk); break; case IPV6_FLOWINFO_SEND: val = inet6_test_bit(SNDFLOW, sk); break; case IPV6_FLOWLABEL_MGR: { struct in6_flowlabel_req freq; int flags; if (len < sizeof(freq)) return -EINVAL; if (copy_from_sockptr(&freq, optval, sizeof(freq))) return -EFAULT; if (freq.flr_action != IPV6_FL_A_GET) return -EINVAL; len = sizeof(freq); flags = freq.flr_flags; memset(&freq, 0, sizeof(freq)); val = ipv6_flowlabel_opt_get(sk, &freq, flags); if (val < 0) return val; if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &freq, len)) return -EFAULT; return 0; } case IPV6_ADDR_PREFERENCES: { u8 srcprefs = READ_ONCE(np->srcprefs); val = 0; if (srcprefs & IPV6_PREFER_SRC_TMP) val |= IPV6_PREFER_SRC_TMP; else if (srcprefs & IPV6_PREFER_SRC_PUBLIC) val |= IPV6_PREFER_SRC_PUBLIC; else { /* XXX: should we return system default? */ val |= IPV6_PREFER_SRC_PUBTMP_DEFAULT; } if (srcprefs & IPV6_PREFER_SRC_COA) val |= IPV6_PREFER_SRC_COA; else val |= IPV6_PREFER_SRC_HOME; break; } case IPV6_MINHOPCOUNT: val = READ_ONCE(np->min_hopcount); break; case IPV6_DONTFRAG: val = inet6_test_bit(DONTFRAG, sk); break; case IPV6_AUTOFLOWLABEL: val = ip6_autoflowlabel(sock_net(sk), sk); break; case IPV6_RECVFRAGSIZE: val = np->rxopt.bits.recvfragsize; break; case IPV6_ROUTER_ALERT: val = inet6_test_bit(RTALERT, sk); break; case IPV6_ROUTER_ALERT_ISOLATE: val = inet6_test_bit(RTALERT_ISOLATE, sk); break; case IPV6_RECVERR_RFC4884: val = inet6_test_bit(RECVERR6_RFC4884, sk); break; default: return -ENOPROTOOPT; } len = min_t(unsigned int, sizeof(int), len); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &val, len)) return -EFAULT; return 0; } int ipv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { int err; if (level == SOL_IP && sk->sk_type != SOCK_RAW) return ip_getsockopt(sk, level, optname, optval, optlen); if (level != SOL_IPV6) return -ENOPROTOOPT; err = do_ipv6_getsockopt(sk, level, optname, USER_SOCKPTR(optval), USER_SOCKPTR(optlen)); #ifdef CONFIG_NETFILTER /* we need to exclude all possible ENOPROTOOPTs except default case */ if (err == -ENOPROTOOPT && optname != IPV6_2292PKTOPTIONS) { int len; if (get_user(len, optlen)) return -EFAULT; err = nf_getsockopt(sk, PF_INET6, optname, optval, &len); if (err >= 0) err = put_user(len, optlen); } #endif return err; } EXPORT_SYMBOL(ipv6_getsockopt); |
| 33 5 1 6 6 2 2 6 9 3 8 119 2 2 1 1 1 1 2 1 8 5 2 1 5 5 5 6 6 5 35 23 8 15 96 98 97 94 4 97 25 25 25 23 1 2 2 24 19 10 32 6 5 5 6 6 1 1 6 6 6 5 2 6 6 6 1 4 5 5 3 3 3 5 5 8 8 7 4 4 14 14 14 12 6 3 3 44 10 4 2 2 2 2 34 2 11 102 99 1 2 1 72 96 82 90 1 1 91 2 95 2 99 30 4 27 1 2 31 2 1 6 6 6 6 6 10 6 6 2 13 1 1 25 8 25 24 1 30 32 31 32 25 8 32 25 8 32 30 2 32 24 8 32 32 20 12 32 32 20 13 13 13 1 12 8 8 3 2 2 1 8 1 5 5 5 4 12 12 11 11 4 7 11 11 3 1 1 1 3 2 3 3 5 5 9 96 94 14 6 7 14 9 12 3 1 8 3 8 1 1 1 8 8 1 1 2 10 9 1 2 4 12 11 6 12 3 1 2 1 2 2 1 1 44 11 44 50 1 2 1 2 44 2 41 2 5 44 13 33 1 9 11 42 1 1 32 1 1 1 1 8 43 12 50 52 50 17 1 1 1 1 14 14 8 8 11 2 9 12 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * fs/eventpoll.c (Efficient event retrieval implementation) * Copyright (C) 2001,...,2009 Davide Libenzi * * Davide Libenzi <davidel@xmailserver.org> */ #include <linux/init.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/signal.h> #include <linux/errno.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/poll.h> #include <linux/string.h> #include <linux/list.h> #include <linux/hash.h> #include <linux/spinlock.h> #include <linux/syscalls.h> #include <linux/rbtree.h> #include <linux/wait.h> #include <linux/eventpoll.h> #include <linux/mount.h> #include <linux/bitops.h> #include <linux/mutex.h> #include <linux/anon_inodes.h> #include <linux/device.h> #include <linux/uaccess.h> #include <asm/io.h> #include <asm/mman.h> #include <linux/atomic.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/compat.h> #include <linux/rculist.h> #include <linux/capability.h> #include <net/busy_poll.h> /* * LOCKING: * There are three level of locking required by epoll : * * 1) epnested_mutex (mutex) * 2) ep->mtx (mutex) * 3) ep->lock (rwlock) * * The acquire order is the one listed above, from 1 to 3. * We need a rwlock (ep->lock) because we manipulate objects * from inside the poll callback, that might be triggered from * a wake_up() that in turn might be called from IRQ context. * So we can't sleep inside the poll callback and hence we need * a spinlock. During the event transfer loop (from kernel to * user space) we could end up sleeping due a copy_to_user(), so * we need a lock that will allow us to sleep. This lock is a * mutex (ep->mtx). It is acquired during the event transfer loop, * during epoll_ctl(EPOLL_CTL_DEL) and during eventpoll_release_file(). * The epnested_mutex is acquired when inserting an epoll fd onto another * epoll fd. We do this so that we walk the epoll tree and ensure that this * insertion does not create a cycle of epoll file descriptors, which * could lead to deadlock. We need a global mutex to prevent two * simultaneous inserts (A into B and B into A) from racing and * constructing a cycle without either insert observing that it is * going to. * It is necessary to acquire multiple "ep->mtx"es at once in the * case when one epoll fd is added to another. In this case, we * always acquire the locks in the order of nesting (i.e. after * epoll_ctl(e1, EPOLL_CTL_ADD, e2), e1->mtx will always be acquired * before e2->mtx). Since we disallow cycles of epoll file * descriptors, this ensures that the mutexes are well-ordered. In * order to communicate this nesting to lockdep, when walking a tree * of epoll file descriptors, we use the current recursion depth as * the lockdep subkey. * It is possible to drop the "ep->mtx" and to use the global * mutex "epnested_mutex" (together with "ep->lock") to have it working, * but having "ep->mtx" will make the interface more scalable. * Events that require holding "epnested_mutex" are very rare, while for * normal operations the epoll private "ep->mtx" will guarantee * a better scalability. */ /* Epoll private bits inside the event mask */ #define EP_PRIVATE_BITS (EPOLLWAKEUP | EPOLLONESHOT | EPOLLET | EPOLLEXCLUSIVE) #define EPOLLINOUT_BITS (EPOLLIN | EPOLLOUT) #define EPOLLEXCLUSIVE_OK_BITS (EPOLLINOUT_BITS | EPOLLERR | EPOLLHUP | \ EPOLLWAKEUP | EPOLLET | EPOLLEXCLUSIVE) /* Maximum number of nesting allowed inside epoll sets */ #define EP_MAX_NESTS 4 #define EP_MAX_EVENTS (INT_MAX / sizeof(struct epoll_event)) #define EP_UNACTIVE_PTR ((void *) -1L) #define EP_ITEM_COST (sizeof(struct epitem) + sizeof(struct eppoll_entry)) struct epoll_filefd { struct file *file; int fd; } __packed; /* Wait structure used by the poll hooks */ struct eppoll_entry { /* List header used to link this structure to the "struct epitem" */ struct eppoll_entry *next; /* The "base" pointer is set to the container "struct epitem" */ struct epitem *base; /* * Wait queue item that will be linked to the target file wait * queue head. */ wait_queue_entry_t wait; /* The wait queue head that linked the "wait" wait queue item */ wait_queue_head_t *whead; }; /* * Each file descriptor added to the eventpoll interface will * have an entry of this type linked to the "rbr" RB tree. * Avoid increasing the size of this struct, there can be many thousands * of these on a server and we do not want this to take another cache line. */ struct epitem { union { /* RB tree node links this structure to the eventpoll RB tree */ struct rb_node rbn; /* Used to free the struct epitem */ struct rcu_head rcu; }; /* List header used to link this structure to the eventpoll ready list */ struct list_head rdllink; /* * Works together "struct eventpoll"->ovflist in keeping the * single linked chain of items. */ struct epitem *next; /* The file descriptor information this item refers to */ struct epoll_filefd ffd; /* * Protected by file->f_lock, true for to-be-released epitem already * removed from the "struct file" items list; together with * eventpoll->refcount orchestrates "struct eventpoll" disposal */ bool dying; /* List containing poll wait queues */ struct eppoll_entry *pwqlist; /* The "container" of this item */ struct eventpoll *ep; /* List header used to link this item to the "struct file" items list */ struct hlist_node fllink; /* wakeup_source used when EPOLLWAKEUP is set */ struct wakeup_source __rcu *ws; /* The structure that describe the interested events and the source fd */ struct epoll_event event; }; /* * This structure is stored inside the "private_data" member of the file * structure and represents the main data structure for the eventpoll * interface. */ struct eventpoll { /* * This mutex is used to ensure that files are not removed * while epoll is using them. This is held during the event * collection loop, the file cleanup path, the epoll file exit * code and the ctl operations. */ struct mutex mtx; /* Wait queue used by sys_epoll_wait() */ wait_queue_head_t wq; /* Wait queue used by file->poll() */ wait_queue_head_t poll_wait; /* List of ready file descriptors */ struct list_head rdllist; /* Lock which protects rdllist and ovflist */ rwlock_t lock; /* RB tree root used to store monitored fd structs */ struct rb_root_cached rbr; /* * This is a single linked list that chains all the "struct epitem" that * happened while transferring ready events to userspace w/out * holding ->lock. */ struct epitem *ovflist; /* wakeup_source used when ep_send_events or __ep_eventpoll_poll is running */ struct wakeup_source *ws; /* The user that created the eventpoll descriptor */ struct user_struct *user; struct file *file; /* used to optimize loop detection check */ u64 gen; struct hlist_head refs; /* * usage count, used together with epitem->dying to * orchestrate the disposal of this struct */ refcount_t refcount; #ifdef CONFIG_NET_RX_BUSY_POLL /* used to track busy poll napi_id */ unsigned int napi_id; /* busy poll timeout */ u32 busy_poll_usecs; /* busy poll packet budget */ u16 busy_poll_budget; bool prefer_busy_poll; #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC /* tracks wakeup nests for lockdep validation */ u8 nests; #endif }; /* Wrapper struct used by poll queueing */ struct ep_pqueue { poll_table pt; struct epitem *epi; }; /* * Configuration options available inside /proc/sys/fs/epoll/ */ /* Maximum number of epoll watched descriptors, per user */ static long max_user_watches __read_mostly; /* Used for cycles detection */ static DEFINE_MUTEX(epnested_mutex); static u64 loop_check_gen = 0; /* Used to check for epoll file descriptor inclusion loops */ static struct eventpoll *inserting_into; /* Slab cache used to allocate "struct epitem" */ static struct kmem_cache *epi_cache __ro_after_init; /* Slab cache used to allocate "struct eppoll_entry" */ static struct kmem_cache *pwq_cache __ro_after_init; /* * List of files with newly added links, where we may need to limit the number * of emanating paths. Protected by the epnested_mutex. */ struct epitems_head { struct hlist_head epitems; struct epitems_head *next; }; static struct epitems_head *tfile_check_list = EP_UNACTIVE_PTR; static struct kmem_cache *ephead_cache __ro_after_init; static inline void free_ephead(struct epitems_head *head) { if (head) kmem_cache_free(ephead_cache, head); } static void list_file(struct file *file) { struct epitems_head *head; head = container_of(file->f_ep, struct epitems_head, epitems); if (!head->next) { head->next = tfile_check_list; tfile_check_list = head; } } static void unlist_file(struct epitems_head *head) { struct epitems_head *to_free = head; struct hlist_node *p = rcu_dereference(hlist_first_rcu(&head->epitems)); if (p) { struct epitem *epi= container_of(p, struct epitem, fllink); spin_lock(&epi->ffd.file->f_lock); if (!hlist_empty(&head->epitems)) to_free = NULL; head->next = NULL; spin_unlock(&epi->ffd.file->f_lock); } free_ephead(to_free); } #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> static long long_zero; static long long_max = LONG_MAX; static struct ctl_table epoll_table[] = { { .procname = "max_user_watches", .data = &max_user_watches, .maxlen = sizeof(max_user_watches), .mode = 0644, .proc_handler = proc_doulongvec_minmax, .extra1 = &long_zero, .extra2 = &long_max, }, }; static void __init epoll_sysctls_init(void) { register_sysctl("fs/epoll", epoll_table); } #else #define epoll_sysctls_init() do { } while (0) #endif /* CONFIG_SYSCTL */ static const struct file_operations eventpoll_fops; static inline int is_file_epoll(struct file *f) { return f->f_op == &eventpoll_fops; } /* Setup the structure that is used as key for the RB tree */ static inline void ep_set_ffd(struct epoll_filefd *ffd, struct file *file, int fd) { ffd->file = file; ffd->fd = fd; } /* Compare RB tree keys */ static inline int ep_cmp_ffd(struct epoll_filefd *p1, struct epoll_filefd *p2) { return (p1->file > p2->file ? +1: (p1->file < p2->file ? -1 : p1->fd - p2->fd)); } /* Tells us if the item is currently linked */ static inline int ep_is_linked(struct epitem *epi) { return !list_empty(&epi->rdllink); } static inline struct eppoll_entry *ep_pwq_from_wait(wait_queue_entry_t *p) { return container_of(p, struct eppoll_entry, wait); } /* Get the "struct epitem" from a wait queue pointer */ static inline struct epitem *ep_item_from_wait(wait_queue_entry_t *p) { return container_of(p, struct eppoll_entry, wait)->base; } /** * ep_events_available - Checks if ready events might be available. * * @ep: Pointer to the eventpoll context. * * Return: a value different than %zero if ready events are available, * or %zero otherwise. */ static inline int ep_events_available(struct eventpoll *ep) { return !list_empty_careful(&ep->rdllist) || READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR; } #ifdef CONFIG_NET_RX_BUSY_POLL /** * busy_loop_ep_timeout - check if busy poll has timed out. The timeout value * from the epoll instance ep is preferred, but if it is not set fallback to * the system-wide global via busy_loop_timeout. * * @start_time: The start time used to compute the remaining time until timeout. * @ep: Pointer to the eventpoll context. * * Return: true if the timeout has expired, false otherwise. */ static bool busy_loop_ep_timeout(unsigned long start_time, struct eventpoll *ep) { unsigned long bp_usec = READ_ONCE(ep->busy_poll_usecs); if (bp_usec) { unsigned long end_time = start_time + bp_usec; unsigned long now = busy_loop_current_time(); return time_after(now, end_time); } else { return busy_loop_timeout(start_time); } } static bool ep_busy_loop_on(struct eventpoll *ep) { return !!READ_ONCE(ep->busy_poll_usecs) || READ_ONCE(ep->prefer_busy_poll) || net_busy_loop_on(); } static bool ep_busy_loop_end(void *p, unsigned long start_time) { struct eventpoll *ep = p; return ep_events_available(ep) || busy_loop_ep_timeout(start_time, ep); } /* * Busy poll if globally on and supporting sockets found && no events, * busy loop will return if need_resched or ep_events_available. * * we must do our busy polling with irqs enabled */ static bool ep_busy_loop(struct eventpoll *ep, int nonblock) { unsigned int napi_id = READ_ONCE(ep->napi_id); u16 budget = READ_ONCE(ep->busy_poll_budget); bool prefer_busy_poll = READ_ONCE(ep->prefer_busy_poll); if (!budget) budget = BUSY_POLL_BUDGET; if (napi_id >= MIN_NAPI_ID && ep_busy_loop_on(ep)) { napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end, ep, prefer_busy_poll, budget); if (ep_events_available(ep)) return true; /* * Busy poll timed out. Drop NAPI ID for now, we can add * it back in when we have moved a socket with a valid NAPI * ID onto the ready list. */ if (prefer_busy_poll) napi_resume_irqs(napi_id); ep->napi_id = 0; return false; } return false; } /* * Set epoll busy poll NAPI ID from sk. */ static inline void ep_set_busy_poll_napi_id(struct epitem *epi) { struct eventpoll *ep = epi->ep; unsigned int napi_id; struct socket *sock; struct sock *sk; if (!ep_busy_loop_on(ep)) return; sock = sock_from_file(epi->ffd.file); if (!sock) return; sk = sock->sk; if (!sk) return; napi_id = READ_ONCE(sk->sk_napi_id); /* Non-NAPI IDs can be rejected * or * Nothing to do if we already have this ID */ if (napi_id < MIN_NAPI_ID || napi_id == ep->napi_id) return; /* record NAPI ID for use in next busy poll */ ep->napi_id = napi_id; } static long ep_eventpoll_bp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct eventpoll *ep = file->private_data; void __user *uarg = (void __user *)arg; struct epoll_params epoll_params; switch (cmd) { case EPIOCSPARAMS: if (copy_from_user(&epoll_params, uarg, sizeof(epoll_params))) return -EFAULT; /* pad byte must be zero */ if (epoll_params.__pad) return -EINVAL; if (epoll_params.busy_poll_usecs > S32_MAX) return -EINVAL; if (epoll_params.prefer_busy_poll > 1) return -EINVAL; if (epoll_params.busy_poll_budget > NAPI_POLL_WEIGHT && !capable(CAP_NET_ADMIN)) return -EPERM; WRITE_ONCE(ep->busy_poll_usecs, epoll_params.busy_poll_usecs); WRITE_ONCE(ep->busy_poll_budget, epoll_params.busy_poll_budget); WRITE_ONCE(ep->prefer_busy_poll, epoll_params.prefer_busy_poll); return 0; case EPIOCGPARAMS: memset(&epoll_params, 0, sizeof(epoll_params)); epoll_params.busy_poll_usecs = READ_ONCE(ep->busy_poll_usecs); epoll_params.busy_poll_budget = READ_ONCE(ep->busy_poll_budget); epoll_params.prefer_busy_poll = READ_ONCE(ep->prefer_busy_poll); if (copy_to_user(uarg, &epoll_params, sizeof(epoll_params))) return -EFAULT; return 0; default: return -ENOIOCTLCMD; } } static void ep_suspend_napi_irqs(struct eventpoll *ep) { unsigned int napi_id = READ_ONCE(ep->napi_id); if (napi_id >= MIN_NAPI_ID && READ_ONCE(ep->prefer_busy_poll)) napi_suspend_irqs(napi_id); } static void ep_resume_napi_irqs(struct eventpoll *ep) { unsigned int napi_id = READ_ONCE(ep->napi_id); if (napi_id >= MIN_NAPI_ID && READ_ONCE(ep->prefer_busy_poll)) napi_resume_irqs(napi_id); } #else static inline bool ep_busy_loop(struct eventpoll *ep, int nonblock) { return false; } static inline void ep_set_busy_poll_napi_id(struct epitem *epi) { } static long ep_eventpoll_bp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return -EOPNOTSUPP; } static void ep_suspend_napi_irqs(struct eventpoll *ep) { } static void ep_resume_napi_irqs(struct eventpoll *ep) { } #endif /* CONFIG_NET_RX_BUSY_POLL */ /* * As described in commit 0ccf831cb lockdep: annotate epoll * the use of wait queues used by epoll is done in a very controlled * manner. Wake ups can nest inside each other, but are never done * with the same locking. For example: * * dfd = socket(...); * efd1 = epoll_create(); * efd2 = epoll_create(); * epoll_ctl(efd1, EPOLL_CTL_ADD, dfd, ...); * epoll_ctl(efd2, EPOLL_CTL_ADD, efd1, ...); * * When a packet arrives to the device underneath "dfd", the net code will * issue a wake_up() on its poll wake list. Epoll (efd1) has installed a * callback wakeup entry on that queue, and the wake_up() performed by the * "dfd" net code will end up in ep_poll_callback(). At this point epoll * (efd1) notices that it may have some event ready, so it needs to wake up * the waiters on its poll wait list (efd2). So it calls ep_poll_safewake() * that ends up in another wake_up(), after having checked about the * recursion constraints. That are, no more than EP_MAX_NESTS, to avoid * stack blasting. * * When CONFIG_DEBUG_LOCK_ALLOC is enabled, make sure lockdep can handle * this special case of epoll. */ #ifdef CONFIG_DEBUG_LOCK_ALLOC static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi, unsigned pollflags) { struct eventpoll *ep_src; unsigned long flags; u8 nests = 0; /* * To set the subclass or nesting level for spin_lock_irqsave_nested() * it might be natural to create a per-cpu nest count. However, since * we can recurse on ep->poll_wait.lock, and a non-raw spinlock can * schedule() in the -rt kernel, the per-cpu variable are no longer * protected. Thus, we are introducing a per eventpoll nest field. * If we are not being call from ep_poll_callback(), epi is NULL and * we are at the first level of nesting, 0. Otherwise, we are being * called from ep_poll_callback() and if a previous wakeup source is * not an epoll file itself, we are at depth 1 since the wakeup source * is depth 0. If the wakeup source is a previous epoll file in the * wakeup chain then we use its nests value and record ours as * nests + 1. The previous epoll file nests value is stable since its * already holding its own poll_wait.lock. */ if (epi) { if ((is_file_epoll(epi->ffd.file))) { ep_src = epi->ffd.file->private_data; nests = ep_src->nests; } else { nests = 1; } } spin_lock_irqsave_nested(&ep->poll_wait.lock, flags, nests); ep->nests = nests + 1; wake_up_locked_poll(&ep->poll_wait, EPOLLIN | pollflags); ep->nests = 0; spin_unlock_irqrestore(&ep->poll_wait.lock, flags); } #else static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi, __poll_t pollflags) { wake_up_poll(&ep->poll_wait, EPOLLIN | pollflags); } #endif static void ep_remove_wait_queue(struct eppoll_entry *pwq) { wait_queue_head_t *whead; rcu_read_lock(); /* * If it is cleared by POLLFREE, it should be rcu-safe. * If we read NULL we need a barrier paired with * smp_store_release() in ep_poll_callback(), otherwise * we rely on whead->lock. */ whead = smp_load_acquire(&pwq->whead); if (whead) remove_wait_queue(whead, &pwq->wait); rcu_read_unlock(); } /* * This function unregisters poll callbacks from the associated file * descriptor. Must be called with "mtx" held. */ static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi) { struct eppoll_entry **p = &epi->pwqlist; struct eppoll_entry *pwq; while ((pwq = *p) != NULL) { *p = pwq->next; ep_remove_wait_queue(pwq); kmem_cache_free(pwq_cache, pwq); } } /* call only when ep->mtx is held */ static inline struct wakeup_source *ep_wakeup_source(struct epitem *epi) { return rcu_dereference_check(epi->ws, lockdep_is_held(&epi->ep->mtx)); } /* call only when ep->mtx is held */ static inline void ep_pm_stay_awake(struct epitem *epi) { struct wakeup_source *ws = ep_wakeup_source(epi); if (ws) __pm_stay_awake(ws); } static inline bool ep_has_wakeup_source(struct epitem *epi) { return rcu_access_pointer(epi->ws) ? true : false; } /* call when ep->mtx cannot be held (ep_poll_callback) */ static inline void ep_pm_stay_awake_rcu(struct epitem *epi) { struct wakeup_source *ws; rcu_read_lock(); ws = rcu_dereference(epi->ws); if (ws) __pm_stay_awake(ws); rcu_read_unlock(); } /* * ep->mutex needs to be held because we could be hit by * eventpoll_release_file() and epoll_ctl(). */ static void ep_start_scan(struct eventpoll *ep, struct list_head *txlist) { /* * Steal the ready list, and re-init the original one to the * empty list. Also, set ep->ovflist to NULL so that events * happening while looping w/out locks, are not lost. We cannot * have the poll callback to queue directly on ep->rdllist, * because we want the "sproc" callback to be able to do it * in a lockless way. */ lockdep_assert_irqs_enabled(); write_lock_irq(&ep->lock); list_splice_init(&ep->rdllist, txlist); WRITE_ONCE(ep->ovflist, NULL); write_unlock_irq(&ep->lock); } static void ep_done_scan(struct eventpoll *ep, struct list_head *txlist) { struct epitem *epi, *nepi; write_lock_irq(&ep->lock); /* * During the time we spent inside the "sproc" callback, some * other events might have been queued by the poll callback. * We re-insert them inside the main ready-list here. */ for (nepi = READ_ONCE(ep->ovflist); (epi = nepi) != NULL; nepi = epi->next, epi->next = EP_UNACTIVE_PTR) { /* * We need to check if the item is already in the list. * During the "sproc" callback execution time, items are * queued into ->ovflist but the "txlist" might already * contain them, and the list_splice() below takes care of them. */ if (!ep_is_linked(epi)) { /* * ->ovflist is LIFO, so we have to reverse it in order * to keep in FIFO. */ list_add(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); } } /* * We need to set back ep->ovflist to EP_UNACTIVE_PTR, so that after * releasing the lock, events will be queued in the normal way inside * ep->rdllist. */ WRITE_ONCE(ep->ovflist, EP_UNACTIVE_PTR); /* * Quickly re-inject items left on "txlist". */ list_splice(txlist, &ep->rdllist); __pm_relax(ep->ws); if (!list_empty(&ep->rdllist)) { if (waitqueue_active(&ep->wq)) wake_up(&ep->wq); } write_unlock_irq(&ep->lock); } static void ep_get(struct eventpoll *ep) { refcount_inc(&ep->refcount); } /* * Returns true if the event poll can be disposed */ static bool ep_refcount_dec_and_test(struct eventpoll *ep) { if (!refcount_dec_and_test(&ep->refcount)) return false; WARN_ON_ONCE(!RB_EMPTY_ROOT(&ep->rbr.rb_root)); return true; } static void ep_free(struct eventpoll *ep) { ep_resume_napi_irqs(ep); mutex_destroy(&ep->mtx); free_uid(ep->user); wakeup_source_unregister(ep->ws); kfree(ep); } /* * Removes a "struct epitem" from the eventpoll RB tree and deallocates * all the associated resources. Must be called with "mtx" held. * If the dying flag is set, do the removal only if force is true. * This prevents ep_clear_and_put() from dropping all the ep references * while running concurrently with eventpoll_release_file(). * Returns true if the eventpoll can be disposed. */ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force) { struct file *file = epi->ffd.file; struct epitems_head *to_free; struct hlist_head *head; lockdep_assert_irqs_enabled(); /* * Removes poll wait queue hooks. */ ep_unregister_pollwait(ep, epi); /* Remove the current item from the list of epoll hooks */ spin_lock(&file->f_lock); if (epi->dying && !force) { spin_unlock(&file->f_lock); return false; } to_free = NULL; head = file->f_ep; if (head->first == &epi->fllink && !epi->fllink.next) { /* See eventpoll_release() for details. */ WRITE_ONCE(file->f_ep, NULL); if (!is_file_epoll(file)) { struct epitems_head *v; v = container_of(head, struct epitems_head, epitems); if (!smp_load_acquire(&v->next)) to_free = v; } } hlist_del_rcu(&epi->fllink); spin_unlock(&file->f_lock); free_ephead(to_free); rb_erase_cached(&epi->rbn, &ep->rbr); write_lock_irq(&ep->lock); if (ep_is_linked(epi)) list_del_init(&epi->rdllink); write_unlock_irq(&ep->lock); wakeup_source_unregister(ep_wakeup_source(epi)); /* * At this point it is safe to free the eventpoll item. Use the union * field epi->rcu, since we are trying to minimize the size of * 'struct epitem'. The 'rbn' field is no longer in use. Protected by * ep->mtx. The rcu read side, reverse_path_check_proc(), does not make * use of the rbn field. */ kfree_rcu(epi, rcu); percpu_counter_dec(&ep->user->epoll_watches); return ep_refcount_dec_and_test(ep); } /* * ep_remove variant for callers owing an additional reference to the ep */ static void ep_remove_safe(struct eventpoll *ep, struct epitem *epi) { WARN_ON_ONCE(__ep_remove(ep, epi, false)); } static void ep_clear_and_put(struct eventpoll *ep) { struct rb_node *rbp, *next; struct epitem *epi; bool dispose; /* We need to release all tasks waiting for these file */ if (waitqueue_active(&ep->poll_wait)) ep_poll_safewake(ep, NULL, 0); mutex_lock(&ep->mtx); /* * Walks through the whole tree by unregistering poll callbacks. */ for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { epi = rb_entry(rbp, struct epitem, rbn); ep_unregister_pollwait(ep, epi); cond_resched(); } /* * Walks through the whole tree and try to free each "struct epitem". * Note that ep_remove_safe() will not remove the epitem in case of a * racing eventpoll_release_file(); the latter will do the removal. * At this point we are sure no poll callbacks will be lingering around. * Since we still own a reference to the eventpoll struct, the loop can't * dispose it. */ for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = next) { next = rb_next(rbp); epi = rb_entry(rbp, struct epitem, rbn); ep_remove_safe(ep, epi); cond_resched(); } dispose = ep_refcount_dec_and_test(ep); mutex_unlock(&ep->mtx); if (dispose) ep_free(ep); } static long ep_eventpoll_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { int ret; if (!is_file_epoll(file)) return -EINVAL; switch (cmd) { case EPIOCSPARAMS: case EPIOCGPARAMS: ret = ep_eventpoll_bp_ioctl(file, cmd, arg); break; default: ret = -EINVAL; break; } return ret; } static int ep_eventpoll_release(struct inode *inode, struct file *file) { struct eventpoll *ep = file->private_data; if (ep) ep_clear_and_put(ep); return 0; } static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt, int depth); static __poll_t __ep_eventpoll_poll(struct file *file, poll_table *wait, int depth) { struct eventpoll *ep = file->private_data; LIST_HEAD(txlist); struct epitem *epi, *tmp; poll_table pt; __poll_t res = 0; init_poll_funcptr(&pt, NULL); /* Insert inside our poll wait queue */ poll_wait(file, &ep->poll_wait, wait); /* * Proceed to find out if wanted events are really available inside * the ready list. */ mutex_lock_nested(&ep->mtx, depth); ep_start_scan(ep, &txlist); list_for_each_entry_safe(epi, tmp, &txlist, rdllink) { if (ep_item_poll(epi, &pt, depth + 1)) { res = EPOLLIN | EPOLLRDNORM; break; } else { /* * Item has been dropped into the ready list by the poll * callback, but it's not actually ready, as far as * caller requested events goes. We can remove it here. */ __pm_relax(ep_wakeup_source(epi)); list_del_init(&epi->rdllink); } } ep_done_scan(ep, &txlist); mutex_unlock(&ep->mtx); return res; } /* * The ffd.file pointer may be in the process of being torn down due to * being closed, but we may not have finished eventpoll_release() yet. * * Normally, even with the atomic_long_inc_not_zero, the file may have * been free'd and then gotten re-allocated to something else (since * files are not RCU-delayed, they are SLAB_TYPESAFE_BY_RCU). * * But for epoll, users hold the ep->mtx mutex, and as such any file in * the process of being free'd will block in eventpoll_release_file() * and thus the underlying file allocation will not be free'd, and the * file re-use cannot happen. * * For the same reason we can avoid a rcu_read_lock() around the * operation - 'ffd.file' cannot go away even if the refcount has * reached zero (but we must still not call out to ->poll() functions * etc). */ static struct file *epi_fget(const struct epitem *epi) { struct file *file; file = epi->ffd.file; if (!file_ref_get(&file->f_ref)) file = NULL; return file; } /* * Differs from ep_eventpoll_poll() in that internal callers already have * the ep->mtx so we need to start from depth=1, such that mutex_lock_nested() * is correctly annotated. */ static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt, int depth) { struct file *file = epi_fget(epi); __poll_t res; /* * We could return EPOLLERR | EPOLLHUP or something, but let's * treat this more as "file doesn't exist, poll didn't happen". */ if (!file) return 0; pt->_key = epi->event.events; if (!is_file_epoll(file)) res = vfs_poll(file, pt); else res = __ep_eventpoll_poll(file, pt, depth); fput(file); return res & epi->event.events; } static __poll_t ep_eventpoll_poll(struct file *file, poll_table *wait) { return __ep_eventpoll_poll(file, wait, 0); } #ifdef CONFIG_PROC_FS static void ep_show_fdinfo(struct seq_file *m, struct file *f) { struct eventpoll *ep = f->private_data; struct rb_node *rbp; mutex_lock(&ep->mtx); for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { struct epitem *epi = rb_entry(rbp, struct epitem, rbn); struct inode *inode = file_inode(epi->ffd.file); seq_printf(m, "tfd: %8d events: %8x data: %16llx " " pos:%lli ino:%lx sdev:%x\n", epi->ffd.fd, epi->event.events, (long long)epi->event.data, (long long)epi->ffd.file->f_pos, inode->i_ino, inode->i_sb->s_dev); if (seq_has_overflowed(m)) break; } mutex_unlock(&ep->mtx); } #endif /* File callbacks that implement the eventpoll file behaviour */ static const struct file_operations eventpoll_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = ep_show_fdinfo, #endif .release = ep_eventpoll_release, .poll = ep_eventpoll_poll, .llseek = noop_llseek, .unlocked_ioctl = ep_eventpoll_ioctl, .compat_ioctl = compat_ptr_ioctl, }; /* * This is called from eventpoll_release() to unlink files from the eventpoll * interface. We need to have this facility to cleanup correctly files that are * closed without being removed from the eventpoll interface. */ void eventpoll_release_file(struct file *file) { struct eventpoll *ep; struct epitem *epi; bool dispose; /* * Use the 'dying' flag to prevent a concurrent ep_clear_and_put() from * touching the epitems list before eventpoll_release_file() can access * the ep->mtx. */ again: spin_lock(&file->f_lock); if (file->f_ep && file->f_ep->first) { epi = hlist_entry(file->f_ep->first, struct epitem, fllink); epi->dying = true; spin_unlock(&file->f_lock); /* * ep access is safe as we still own a reference to the ep * struct */ ep = epi->ep; mutex_lock(&ep->mtx); dispose = __ep_remove(ep, epi, true); mutex_unlock(&ep->mtx); if (dispose) ep_free(ep); goto again; } spin_unlock(&file->f_lock); } static int ep_alloc(struct eventpoll **pep) { struct eventpoll *ep; ep = kzalloc(sizeof(*ep), GFP_KERNEL); if (unlikely(!ep)) return -ENOMEM; mutex_init(&ep->mtx); rwlock_init(&ep->lock); init_waitqueue_head(&ep->wq); init_waitqueue_head(&ep->poll_wait); INIT_LIST_HEAD(&ep->rdllist); ep->rbr = RB_ROOT_CACHED; ep->ovflist = EP_UNACTIVE_PTR; ep->user = get_current_user(); refcount_set(&ep->refcount, 1); *pep = ep; return 0; } /* * Search the file inside the eventpoll tree. The RB tree operations * are protected by the "mtx" mutex, and ep_find() must be called with * "mtx" held. */ static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd) { int kcmp; struct rb_node *rbp; struct epitem *epi, *epir = NULL; struct epoll_filefd ffd; ep_set_ffd(&ffd, file, fd); for (rbp = ep->rbr.rb_root.rb_node; rbp; ) { epi = rb_entry(rbp, struct epitem, rbn); kcmp = ep_cmp_ffd(&ffd, &epi->ffd); if (kcmp > 0) rbp = rbp->rb_right; else if (kcmp < 0) rbp = rbp->rb_left; else { epir = epi; break; } } return epir; } #ifdef CONFIG_KCMP static struct epitem *ep_find_tfd(struct eventpoll *ep, int tfd, unsigned long toff) { struct rb_node *rbp; struct epitem *epi; for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { epi = rb_entry(rbp, struct epitem, rbn); if (epi->ffd.fd == tfd) { if (toff == 0) return epi; else toff--; } cond_resched(); } return NULL; } struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff) { struct file *file_raw; struct eventpoll *ep; struct epitem *epi; if (!is_file_epoll(file)) return ERR_PTR(-EINVAL); ep = file->private_data; mutex_lock(&ep->mtx); epi = ep_find_tfd(ep, tfd, toff); if (epi) file_raw = epi->ffd.file; else file_raw = ERR_PTR(-ENOENT); mutex_unlock(&ep->mtx); return file_raw; } #endif /* CONFIG_KCMP */ /* * Adds a new entry to the tail of the list in a lockless way, i.e. * multiple CPUs are allowed to call this function concurrently. * * Beware: it is necessary to prevent any other modifications of the * existing list until all changes are completed, in other words * concurrent list_add_tail_lockless() calls should be protected * with a read lock, where write lock acts as a barrier which * makes sure all list_add_tail_lockless() calls are fully * completed. * * Also an element can be locklessly added to the list only in one * direction i.e. either to the tail or to the head, otherwise * concurrent access will corrupt the list. * * Return: %false if element has been already added to the list, %true * otherwise. */ static inline bool list_add_tail_lockless(struct list_head *new, struct list_head *head) { struct list_head *prev; /* * This is simple 'new->next = head' operation, but cmpxchg() * is used in order to detect that same element has been just * added to the list from another CPU: the winner observes * new->next == new. */ if (!try_cmpxchg(&new->next, &new, head)) return false; /* * Initially ->next of a new element must be updated with the head * (we are inserting to the tail) and only then pointers are atomically * exchanged. XCHG guarantees memory ordering, thus ->next should be * updated before pointers are actually swapped and pointers are * swapped before prev->next is updated. */ prev = xchg(&head->prev, new); /* * It is safe to modify prev->next and new->prev, because a new element * is added only to the tail and new->next is updated before XCHG. */ prev->next = new; new->prev = prev; return true; } /* * Chains a new epi entry to the tail of the ep->ovflist in a lockless way, * i.e. multiple CPUs are allowed to call this function concurrently. * * Return: %false if epi element has been already chained, %true otherwise. */ static inline bool chain_epi_lockless(struct epitem *epi) { struct eventpoll *ep = epi->ep; /* Fast preliminary check */ if (epi->next != EP_UNACTIVE_PTR) return false; /* Check that the same epi has not been just chained from another CPU */ if (cmpxchg(&epi->next, EP_UNACTIVE_PTR, NULL) != EP_UNACTIVE_PTR) return false; /* Atomically exchange tail */ epi->next = xchg(&ep->ovflist, epi); return true; } /* * This is the callback that is passed to the wait queue wakeup * mechanism. It is called by the stored file descriptors when they * have events to report. * * This callback takes a read lock in order not to contend with concurrent * events from another file descriptor, thus all modifications to ->rdllist * or ->ovflist are lockless. Read lock is paired with the write lock from * ep_start/done_scan(), which stops all list modifications and guarantees * that lists state is seen correctly. * * Another thing worth to mention is that ep_poll_callback() can be called * concurrently for the same @epi from different CPUs if poll table was inited * with several wait queues entries. Plural wakeup from different CPUs of a * single wait queue is serialized by wq.lock, but the case when multiple wait * queues are used should be detected accordingly. This is detected using * cmpxchg() operation. */ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { int pwake = 0; struct epitem *epi = ep_item_from_wait(wait); struct eventpoll *ep = epi->ep; __poll_t pollflags = key_to_poll(key); unsigned long flags; int ewake = 0; read_lock_irqsave(&ep->lock, flags); ep_set_busy_poll_napi_id(epi); /* * If the event mask does not contain any poll(2) event, we consider the * descriptor to be disabled. This condition is likely the effect of the * EPOLLONESHOT bit that disables the descriptor when an event is received, * until the next EPOLL_CTL_MOD will be issued. */ if (!(epi->event.events & ~EP_PRIVATE_BITS)) goto out_unlock; /* * Check the events coming with the callback. At this stage, not * every device reports the events in the "key" parameter of the * callback. We need to be able to handle both cases here, hence the * test for "key" != NULL before the event match test. */ if (pollflags && !(pollflags & epi->event.events)) goto out_unlock; /* * If we are transferring events to userspace, we can hold no locks * (because we're accessing user memory, and because of linux f_op->poll() * semantics). All the events that happen during that period of time are * chained in ep->ovflist and requeued later on. */ if (READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR) { if (chain_epi_lockless(epi)) ep_pm_stay_awake_rcu(epi); } else if (!ep_is_linked(epi)) { /* In the usual case, add event to ready list. */ if (list_add_tail_lockless(&epi->rdllink, &ep->rdllist)) ep_pm_stay_awake_rcu(epi); } /* * Wake up ( if active ) both the eventpoll wait list and the ->poll() * wait list. */ if (waitqueue_active(&ep->wq)) { if ((epi->event.events & EPOLLEXCLUSIVE) && !(pollflags & POLLFREE)) { switch (pollflags & EPOLLINOUT_BITS) { case EPOLLIN: if (epi->event.events & EPOLLIN) ewake = 1; break; case EPOLLOUT: if (epi->event.events & EPOLLOUT) ewake = 1; break; case 0: ewake = 1; break; } } if (sync) wake_up_sync(&ep->wq); else wake_up(&ep->wq); } if (waitqueue_active(&ep->poll_wait)) pwake++; out_unlock: read_unlock_irqrestore(&ep->lock, flags); /* We have to call this outside the lock */ if (pwake) ep_poll_safewake(ep, epi, pollflags & EPOLL_URING_WAKE); if (!(epi->event.events & EPOLLEXCLUSIVE)) ewake = 1; if (pollflags & POLLFREE) { /* * If we race with ep_remove_wait_queue() it can miss * ->whead = NULL and do another remove_wait_queue() after * us, so we can't use __remove_wait_queue(). */ list_del_init(&wait->entry); /* * ->whead != NULL protects us from the race with * ep_clear_and_put() or ep_remove(), ep_remove_wait_queue() * takes whead->lock held by the caller. Once we nullify it, * nothing protects ep/epi or even wait. */ smp_store_release(&ep_pwq_from_wait(wait)->whead, NULL); } return ewake; } /* * This is the callback that is used to add our wait queue to the * target file wakeup lists. */ static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead, poll_table *pt) { struct ep_pqueue *epq = container_of(pt, struct ep_pqueue, pt); struct epitem *epi = epq->epi; struct eppoll_entry *pwq; if (unlikely(!epi)) // an earlier allocation has failed return; pwq = kmem_cache_alloc(pwq_cache, GFP_KERNEL); if (unlikely(!pwq)) { epq->epi = NULL; return; } init_waitqueue_func_entry(&pwq->wait, ep_poll_callback); pwq->whead = whead; pwq->base = epi; if (epi->event.events & EPOLLEXCLUSIVE) add_wait_queue_exclusive(whead, &pwq->wait); else add_wait_queue(whead, &pwq->wait); pwq->next = epi->pwqlist; epi->pwqlist = pwq; } static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi) { int kcmp; struct rb_node **p = &ep->rbr.rb_root.rb_node, *parent = NULL; struct epitem *epic; bool leftmost = true; while (*p) { parent = *p; epic = rb_entry(parent, struct epitem, rbn); kcmp = ep_cmp_ffd(&epi->ffd, &epic->ffd); if (kcmp > 0) { p = &parent->rb_right; leftmost = false; } else p = &parent->rb_left; } rb_link_node(&epi->rbn, parent, p); rb_insert_color_cached(&epi->rbn, &ep->rbr, leftmost); } #define PATH_ARR_SIZE 5 /* * These are the number paths of length 1 to 5, that we are allowing to emanate * from a single file of interest. For example, we allow 1000 paths of length * 1, to emanate from each file of interest. This essentially represents the * potential wakeup paths, which need to be limited in order to avoid massive * uncontrolled wakeup storms. The common use case should be a single ep which * is connected to n file sources. In this case each file source has 1 path * of length 1. Thus, the numbers below should be more than sufficient. These * path limits are enforced during an EPOLL_CTL_ADD operation, since a modify * and delete can't add additional paths. Protected by the epnested_mutex. */ static const int path_limits[PATH_ARR_SIZE] = { 1000, 500, 100, 50, 10 }; static int path_count[PATH_ARR_SIZE]; static int path_count_inc(int nests) { /* Allow an arbitrary number of depth 1 paths */ if (nests == 0) return 0; if (++path_count[nests] > path_limits[nests]) return -1; return 0; } static void path_count_init(void) { int i; for (i = 0; i < PATH_ARR_SIZE; i++) path_count[i] = 0; } static int reverse_path_check_proc(struct hlist_head *refs, int depth) { int error = 0; struct epitem *epi; if (depth > EP_MAX_NESTS) /* too deep nesting */ return -1; /* CTL_DEL can remove links here, but that can't increase our count */ hlist_for_each_entry_rcu(epi, refs, fllink) { struct hlist_head *refs = &epi->ep->refs; if (hlist_empty(refs)) error = path_count_inc(depth); else error = reverse_path_check_proc(refs, depth + 1); if (error != 0) break; } return error; } /** * reverse_path_check - The tfile_check_list is list of epitem_head, which have * links that are proposed to be newly added. We need to * make sure that those added links don't add too many * paths such that we will spend all our time waking up * eventpoll objects. * * Return: %zero if the proposed links don't create too many paths, * %-1 otherwise. */ static int reverse_path_check(void) { struct epitems_head *p; for (p = tfile_check_list; p != EP_UNACTIVE_PTR; p = p->next) { int error; path_count_init(); rcu_read_lock(); error = reverse_path_check_proc(&p->epitems, 0); rcu_read_unlock(); if (error) return error; } return 0; } static int ep_create_wakeup_source(struct epitem *epi) { struct name_snapshot n; struct wakeup_source *ws; if (!epi->ep->ws) { epi->ep->ws = wakeup_source_register(NULL, "eventpoll"); if (!epi->ep->ws) return -ENOMEM; } take_dentry_name_snapshot(&n, epi->ffd.file->f_path.dentry); ws = wakeup_source_register(NULL, n.name.name); release_dentry_name_snapshot(&n); if (!ws) return -ENOMEM; rcu_assign_pointer(epi->ws, ws); return 0; } /* rare code path, only used when EPOLL_CTL_MOD removes a wakeup source */ static noinline void ep_destroy_wakeup_source(struct epitem *epi) { struct wakeup_source *ws = ep_wakeup_source(epi); RCU_INIT_POINTER(epi->ws, NULL); /* * wait for ep_pm_stay_awake_rcu to finish, synchronize_rcu is * used internally by wakeup_source_remove, too (called by * wakeup_source_unregister), so we cannot use call_rcu */ synchronize_rcu(); wakeup_source_unregister(ws); } static int attach_epitem(struct file *file, struct epitem *epi) { struct epitems_head *to_free = NULL; struct hlist_head *head = NULL; struct eventpoll *ep = NULL; if (is_file_epoll(file)) ep = file->private_data; if (ep) { head = &ep->refs; } else if (!READ_ONCE(file->f_ep)) { allocate: to_free = kmem_cache_zalloc(ephead_cache, GFP_KERNEL); if (!to_free) return -ENOMEM; head = &to_free->epitems; } spin_lock(&file->f_lock); if (!file->f_ep) { if (unlikely(!head)) { spin_unlock(&file->f_lock); goto allocate; } /* See eventpoll_release() for details. */ WRITE_ONCE(file->f_ep, head); to_free = NULL; } hlist_add_head_rcu(&epi->fllink, file->f_ep); spin_unlock(&file->f_lock); free_ephead(to_free); return 0; } /* * Must be called with "mtx" held. */ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, struct file *tfile, int fd, int full_check) { int error, pwake = 0; __poll_t revents; struct epitem *epi; struct ep_pqueue epq; struct eventpoll *tep = NULL; if (is_file_epoll(tfile)) tep = tfile->private_data; lockdep_assert_irqs_enabled(); if (unlikely(percpu_counter_compare(&ep->user->epoll_watches, max_user_watches) >= 0)) return -ENOSPC; percpu_counter_inc(&ep->user->epoll_watches); if (!(epi = kmem_cache_zalloc(epi_cache, GFP_KERNEL))) { percpu_counter_dec(&ep->user->epoll_watches); return -ENOMEM; } /* Item initialization follow here ... */ INIT_LIST_HEAD(&epi->rdllink); epi->ep = ep; ep_set_ffd(&epi->ffd, tfile, fd); epi->event = *event; epi->next = EP_UNACTIVE_PTR; if (tep) mutex_lock_nested(&tep->mtx, 1); /* Add the current item to the list of active epoll hook for this file */ if (unlikely(attach_epitem(tfile, epi) < 0)) { if (tep) mutex_unlock(&tep->mtx); kmem_cache_free(epi_cache, epi); percpu_counter_dec(&ep->user->epoll_watches); return -ENOMEM; } if (full_check && !tep) list_file(tfile); /* * Add the current item to the RB tree. All RB tree operations are * protected by "mtx", and ep_insert() is called with "mtx" held. */ ep_rbtree_insert(ep, epi); if (tep) mutex_unlock(&tep->mtx); /* * ep_remove_safe() calls in the later error paths can't lead to * ep_free() as the ep file itself still holds an ep reference. */ ep_get(ep); /* now check if we've created too many backpaths */ if (unlikely(full_check && reverse_path_check())) { ep_remove_safe(ep, epi); return -EINVAL; } if (epi->event.events & EPOLLWAKEUP) { error = ep_create_wakeup_source(epi); if (error) { ep_remove_safe(ep, epi); return error; } } /* Initialize the poll table using the queue callback */ epq.epi = epi; init_poll_funcptr(&epq.pt, ep_ptable_queue_proc); /* * Attach the item to the poll hooks and get current event bits. * We can safely use the file* here because its usage count has * been increased by the caller of this function. Note that after * this operation completes, the poll callback can start hitting * the new item. */ revents = ep_item_poll(epi, &epq.pt, 1); /* * We have to check if something went wrong during the poll wait queue * install process. Namely an allocation for a wait queue failed due * high memory pressure. */ if (unlikely(!epq.epi)) { ep_remove_safe(ep, epi); return -ENOMEM; } /* We have to drop the new item inside our item list to keep track of it */ write_lock_irq(&ep->lock); /* record NAPI ID of new item if present */ ep_set_busy_poll_napi_id(epi); /* If the file is already "ready" we drop it inside the ready list */ if (revents && !ep_is_linked(epi)) { list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); /* Notify waiting tasks that events are available */ if (waitqueue_active(&ep->wq)) wake_up(&ep->wq); if (waitqueue_active(&ep->poll_wait)) pwake++; } write_unlock_irq(&ep->lock); /* We have to call this outside the lock */ if (pwake) ep_poll_safewake(ep, NULL, 0); return 0; } /* * Modify the interest event mask by dropping an event if the new mask * has a match in the current file status. Must be called with "mtx" held. */ static int ep_modify(struct eventpoll *ep, struct epitem *epi, const struct epoll_event *event) { int pwake = 0; poll_table pt; lockdep_assert_irqs_enabled(); init_poll_funcptr(&pt, NULL); /* * Set the new event interest mask before calling f_op->poll(); * otherwise we might miss an event that happens between the * f_op->poll() call and the new event set registering. */ epi->event.events = event->events; /* need barrier below */ epi->event.data = event->data; /* protected by mtx */ if (epi->event.events & EPOLLWAKEUP) { if (!ep_has_wakeup_source(epi)) ep_create_wakeup_source(epi); } else if (ep_has_wakeup_source(epi)) { ep_destroy_wakeup_source(epi); } /* * The following barrier has two effects: * * 1) Flush epi changes above to other CPUs. This ensures * we do not miss events from ep_poll_callback if an * event occurs immediately after we call f_op->poll(). * We need this because we did not take ep->lock while * changing epi above (but ep_poll_callback does take * ep->lock). * * 2) We also need to ensure we do not miss _past_ events * when calling f_op->poll(). This barrier also * pairs with the barrier in wq_has_sleeper (see * comments for wq_has_sleeper). * * This barrier will now guarantee ep_poll_callback or f_op->poll * (or both) will notice the readiness of an item. */ smp_mb(); /* * Get current event bits. We can safely use the file* here because * its usage count has been increased by the caller of this function. * If the item is "hot" and it is not registered inside the ready * list, push it inside. */ if (ep_item_poll(epi, &pt, 1)) { write_lock_irq(&ep->lock); if (!ep_is_linked(epi)) { list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); /* Notify waiting tasks that events are available */ if (waitqueue_active(&ep->wq)) wake_up(&ep->wq); if (waitqueue_active(&ep->poll_wait)) pwake++; } write_unlock_irq(&ep->lock); } /* We have to call this outside the lock */ if (pwake) ep_poll_safewake(ep, NULL, 0); return 0; } static int ep_send_events(struct eventpoll *ep, struct epoll_event __user *events, int maxevents) { struct epitem *epi, *tmp; LIST_HEAD(txlist); poll_table pt; int res = 0; /* * Always short-circuit for fatal signals to allow threads to make a * timely exit without the chance of finding more events available and * fetching repeatedly. */ if (fatal_signal_pending(current)) return -EINTR; init_poll_funcptr(&pt, NULL); mutex_lock(&ep->mtx); ep_start_scan(ep, &txlist); /* * We can loop without lock because we are passed a task private list. * Items cannot vanish during the loop we are holding ep->mtx. */ list_for_each_entry_safe(epi, tmp, &txlist, rdllink) { struct wakeup_source *ws; __poll_t revents; if (res >= maxevents) break; /* * Activate ep->ws before deactivating epi->ws to prevent * triggering auto-suspend here (in case we reactive epi->ws * below). * * This could be rearranged to delay the deactivation of epi->ws * instead, but then epi->ws would temporarily be out of sync * with ep_is_linked(). */ ws = ep_wakeup_source(epi); if (ws) { if (ws->active) __pm_stay_awake(ep->ws); __pm_relax(ws); } list_del_init(&epi->rdllink); /* * If the event mask intersect the caller-requested one, * deliver the event to userspace. Again, we are holding ep->mtx, * so no operations coming from userspace can change the item. */ revents = ep_item_poll(epi, &pt, 1); if (!revents) continue; events = epoll_put_uevent(revents, epi->event.data, events); if (!events) { list_add(&epi->rdllink, &txlist); ep_pm_stay_awake(epi); if (!res) res = -EFAULT; break; } res++; if (epi->event.events & EPOLLONESHOT) epi->event.events &= EP_PRIVATE_BITS; else if (!(epi->event.events & EPOLLET)) { /* * If this file has been added with Level * Trigger mode, we need to insert back inside * the ready list, so that the next call to * epoll_wait() will check again the events * availability. At this point, no one can insert * into ep->rdllist besides us. The epoll_ctl() * callers are locked out by * ep_send_events() holding "mtx" and the * poll callback will queue them in ep->ovflist. */ list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); } } ep_done_scan(ep, &txlist); mutex_unlock(&ep->mtx); return res; } static struct timespec64 *ep_timeout_to_timespec(struct timespec64 *to, long ms) { struct timespec64 now; if (ms < 0) return NULL; if (!ms) { to->tv_sec = 0; to->tv_nsec = 0; return to; } to->tv_sec = ms / MSEC_PER_SEC; to->tv_nsec = NSEC_PER_MSEC * (ms % MSEC_PER_SEC); ktime_get_ts64(&now); *to = timespec64_add_safe(now, *to); return to; } /* * autoremove_wake_function, but remove even on failure to wake up, because we * know that default_wake_function/ttwu will only fail if the thread is already * woken, and in that case the ep_poll loop will remove the entry anyways, not * try to reuse it. */ static int ep_autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned int mode, int sync, void *key) { int ret = default_wake_function(wq_entry, mode, sync, key); /* * Pairs with list_empty_careful in ep_poll, and ensures future loop * iterations see the cause of this wakeup. */ list_del_init_careful(&wq_entry->entry); return ret; } /** * ep_poll - Retrieves ready events, and delivers them to the caller-supplied * event buffer. * * @ep: Pointer to the eventpoll context. * @events: Pointer to the userspace buffer where the ready events should be * stored. * @maxevents: Size (in terms of number of events) of the caller event buffer. * @timeout: Maximum timeout for the ready events fetch operation, in * timespec. If the timeout is zero, the function will not block, * while if the @timeout ptr is NULL, the function will block * until at least one event has been retrieved (or an error * occurred). * * Return: the number of ready events which have been fetched, or an * error code, in case of error. */ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, int maxevents, struct timespec64 *timeout) { int res, eavail, timed_out = 0; u64 slack = 0; wait_queue_entry_t wait; ktime_t expires, *to = NULL; lockdep_assert_irqs_enabled(); if (timeout && (timeout->tv_sec | timeout->tv_nsec)) { slack = select_estimate_accuracy(timeout); to = &expires; *to = timespec64_to_ktime(*timeout); } else if (timeout) { /* * Avoid the unnecessary trip to the wait queue loop, if the * caller specified a non blocking operation. */ timed_out = 1; } /* * This call is racy: We may or may not see events that are being added * to the ready list under the lock (e.g., in IRQ callbacks). For cases * with a non-zero timeout, this thread will check the ready list under * lock and will add to the wait queue. For cases with a zero * timeout, the user by definition should not care and will have to * recheck again. */ eavail = ep_events_available(ep); while (1) { if (eavail) { /* * Try to transfer events to user space. In case we get * 0 events and there's still timeout left over, we go * trying again in search of more luck. */ res = ep_send_events(ep, events, maxevents); if (res) { if (res > 0) ep_suspend_napi_irqs(ep); return res; } } if (timed_out) return 0; eavail = ep_busy_loop(ep, timed_out); if (eavail) continue; if (signal_pending(current)) return -EINTR; /* * Internally init_wait() uses autoremove_wake_function(), * thus wait entry is removed from the wait queue on each * wakeup. Why it is important? In case of several waiters * each new wakeup will hit the next waiter, giving it the * chance to harvest new event. Otherwise wakeup can be * lost. This is also good performance-wise, because on * normal wakeup path no need to call __remove_wait_queue() * explicitly, thus ep->lock is not taken, which halts the * event delivery. * * In fact, we now use an even more aggressive function that * unconditionally removes, because we don't reuse the wait * entry between loop iterations. This lets us also avoid the * performance issue if a process is killed, causing all of its * threads to wake up without being removed normally. */ init_wait(&wait); wait.func = ep_autoremove_wake_function; write_lock_irq(&ep->lock); /* * Barrierless variant, waitqueue_active() is called under * the same lock on wakeup ep_poll_callback() side, so it * is safe to avoid an explicit barrier. */ __set_current_state(TASK_INTERRUPTIBLE); /* * Do the final check under the lock. ep_start/done_scan() * plays with two lists (->rdllist and ->ovflist) and there * is always a race when both lists are empty for short * period of time although events are pending, so lock is * important. */ eavail = ep_events_available(ep); if (!eavail) __add_wait_queue_exclusive(&ep->wq, &wait); write_unlock_irq(&ep->lock); if (!eavail) timed_out = !schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS); __set_current_state(TASK_RUNNING); /* * We were woken up, thus go and try to harvest some events. * If timed out and still on the wait queue, recheck eavail * carefully under lock, below. */ eavail = 1; if (!list_empty_careful(&wait.entry)) { write_lock_irq(&ep->lock); /* * If the thread timed out and is not on the wait queue, * it means that the thread was woken up after its * timeout expired before it could reacquire the lock. * Thus, when wait.entry is empty, it needs to harvest * events. */ if (timed_out) eavail = list_empty(&wait.entry); __remove_wait_queue(&ep->wq, &wait); write_unlock_irq(&ep->lock); } } } /** * ep_loop_check_proc - verify that adding an epoll file inside another * epoll structure does not violate the constraints, in * terms of closed loops, or too deep chains (which can * result in excessive stack usage). * * @ep: the &struct eventpoll to be currently checked. * @depth: Current depth of the path being checked. * * Return: %zero if adding the epoll @file inside current epoll * structure @ep does not violate the constraints, or %-1 otherwise. */ static int ep_loop_check_proc(struct eventpoll *ep, int depth) { int error = 0; struct rb_node *rbp; struct epitem *epi; mutex_lock_nested(&ep->mtx, depth + 1); ep->gen = loop_check_gen; for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { epi = rb_entry(rbp, struct epitem, rbn); if (unlikely(is_file_epoll(epi->ffd.file))) { struct eventpoll *ep_tovisit; ep_tovisit = epi->ffd.file->private_data; if (ep_tovisit->gen == loop_check_gen) continue; if (ep_tovisit == inserting_into || depth > EP_MAX_NESTS) error = -1; else error = ep_loop_check_proc(ep_tovisit, depth + 1); if (error != 0) break; } else { /* * If we've reached a file that is not associated with * an ep, then we need to check if the newly added * links are going to add too many wakeup paths. We do * this by adding it to the tfile_check_list, if it's * not already there, and calling reverse_path_check() * during ep_insert(). */ list_file(epi->ffd.file); } } mutex_unlock(&ep->mtx); return error; } /** * ep_loop_check - Performs a check to verify that adding an epoll file (@to) * into another epoll file (represented by @ep) does not create * closed loops or too deep chains. * * @ep: Pointer to the epoll we are inserting into. * @to: Pointer to the epoll to be inserted. * * Return: %zero if adding the epoll @to inside the epoll @from * does not violate the constraints, or %-1 otherwise. */ static int ep_loop_check(struct eventpoll *ep, struct eventpoll *to) { inserting_into = ep; return ep_loop_check_proc(to, 0); } static void clear_tfile_check_list(void) { rcu_read_lock(); while (tfile_check_list != EP_UNACTIVE_PTR) { struct epitems_head *head = tfile_check_list; tfile_check_list = head->next; unlist_file(head); } rcu_read_unlock(); } /* * Open an eventpoll file descriptor. */ static int do_epoll_create(int flags) { int error, fd; struct eventpoll *ep = NULL; struct file *file; /* Check the EPOLL_* constant for consistency. */ BUILD_BUG_ON(EPOLL_CLOEXEC != O_CLOEXEC); if (flags & ~EPOLL_CLOEXEC) return -EINVAL; /* * Create the internal data structure ("struct eventpoll"). */ error = ep_alloc(&ep); if (error < 0) return error; /* * Creates all the items needed to setup an eventpoll file. That is, * a file structure and a free file descriptor. */ fd = get_unused_fd_flags(O_RDWR | (flags & O_CLOEXEC)); if (fd < 0) { error = fd; goto out_free_ep; } file = anon_inode_getfile("[eventpoll]", &eventpoll_fops, ep, O_RDWR | (flags & O_CLOEXEC)); if (IS_ERR(file)) { error = PTR_ERR(file); goto out_free_fd; } ep->file = file; fd_install(fd, file); return fd; out_free_fd: put_unused_fd(fd); out_free_ep: ep_clear_and_put(ep); return error; } SYSCALL_DEFINE1(epoll_create1, int, flags) { return do_epoll_create(flags); } SYSCALL_DEFINE1(epoll_create, int, size) { if (size <= 0) return -EINVAL; return do_epoll_create(0); } #ifdef CONFIG_PM_SLEEP static inline void ep_take_care_of_epollwakeup(struct epoll_event *epev) { if ((epev->events & EPOLLWAKEUP) && !capable(CAP_BLOCK_SUSPEND)) epev->events &= ~EPOLLWAKEUP; } #else static inline void ep_take_care_of_epollwakeup(struct epoll_event *epev) { epev->events &= ~EPOLLWAKEUP; } #endif static inline int epoll_mutex_lock(struct mutex *mutex, int depth, bool nonblock) { if (!nonblock) { mutex_lock_nested(mutex, depth); return 0; } if (mutex_trylock(mutex)) return 0; return -EAGAIN; } int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, bool nonblock) { int error; int full_check = 0; struct eventpoll *ep; struct epitem *epi; struct eventpoll *tep = NULL; CLASS(fd, f)(epfd); if (fd_empty(f)) return -EBADF; /* Get the "struct file *" for the target file */ CLASS(fd, tf)(fd); if (fd_empty(tf)) return -EBADF; /* The target file descriptor must support poll */ if (!file_can_poll(fd_file(tf))) return -EPERM; /* Check if EPOLLWAKEUP is allowed */ if (ep_op_has_event(op)) ep_take_care_of_epollwakeup(epds); /* * We have to check that the file structure underneath the file descriptor * the user passed to us _is_ an eventpoll file. And also we do not permit * adding an epoll file descriptor inside itself. */ error = -EINVAL; if (fd_file(f) == fd_file(tf) || !is_file_epoll(fd_file(f))) goto error_tgt_fput; /* * epoll adds to the wakeup queue at EPOLL_CTL_ADD time only, * so EPOLLEXCLUSIVE is not allowed for a EPOLL_CTL_MOD operation. * Also, we do not currently supported nested exclusive wakeups. */ if (ep_op_has_event(op) && (epds->events & EPOLLEXCLUSIVE)) { if (op == EPOLL_CTL_MOD) goto error_tgt_fput; if (op == EPOLL_CTL_ADD && (is_file_epoll(fd_file(tf)) || (epds->events & ~EPOLLEXCLUSIVE_OK_BITS))) goto error_tgt_fput; } /* * At this point it is safe to assume that the "private_data" contains * our own data structure. */ ep = fd_file(f)->private_data; /* * When we insert an epoll file descriptor inside another epoll file * descriptor, there is the chance of creating closed loops, which are * better be handled here, than in more critical paths. While we are * checking for loops we also determine the list of files reachable * and hang them on the tfile_check_list, so we can check that we * haven't created too many possible wakeup paths. * * We do not need to take the global 'epumutex' on EPOLL_CTL_ADD when * the epoll file descriptor is attaching directly to a wakeup source, * unless the epoll file descriptor is nested. The purpose of taking the * 'epnested_mutex' on add is to prevent complex toplogies such as loops and * deep wakeup paths from forming in parallel through multiple * EPOLL_CTL_ADD operations. */ error = epoll_mutex_lock(&ep->mtx, 0, nonblock); if (error) goto error_tgt_fput; if (op == EPOLL_CTL_ADD) { if (READ_ONCE(fd_file(f)->f_ep) || ep->gen == loop_check_gen || is_file_epoll(fd_file(tf))) { mutex_unlock(&ep->mtx); error = epoll_mutex_lock(&epnested_mutex, 0, nonblock); if (error) goto error_tgt_fput; loop_check_gen++; full_check = 1; if (is_file_epoll(fd_file(tf))) { tep = fd_file(tf)->private_data; error = -ELOOP; if (ep_loop_check(ep, tep) != 0) goto error_tgt_fput; } error = epoll_mutex_lock(&ep->mtx, 0, nonblock); if (error) goto error_tgt_fput; } } /* * Try to lookup the file inside our RB tree. Since we grabbed "mtx" * above, we can be sure to be able to use the item looked up by * ep_find() till we release the mutex. */ epi = ep_find(ep, fd_file(tf), fd); error = -EINVAL; switch (op) { case EPOLL_CTL_ADD: if (!epi) { epds->events |= EPOLLERR | EPOLLHUP; error = ep_insert(ep, epds, fd_file(tf), fd, full_check); } else error = -EEXIST; break; case EPOLL_CTL_DEL: if (epi) { /* * The eventpoll itself is still alive: the refcount * can't go to zero here. */ ep_remove_safe(ep, epi); error = 0; } else { error = -ENOENT; } break; case EPOLL_CTL_MOD: if (epi) { if (!(epi->event.events & EPOLLEXCLUSIVE)) { epds->events |= EPOLLERR | EPOLLHUP; error = ep_modify(ep, epi, epds); } } else error = -ENOENT; break; } mutex_unlock(&ep->mtx); error_tgt_fput: if (full_check) { clear_tfile_check_list(); loop_check_gen++; mutex_unlock(&epnested_mutex); } return error; } /* * The following function implements the controller interface for * the eventpoll file that enables the insertion/removal/change of * file descriptors inside the interest set. */ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, struct epoll_event __user *, event) { struct epoll_event epds; if (ep_op_has_event(op) && copy_from_user(&epds, event, sizeof(struct epoll_event))) return -EFAULT; return do_epoll_ctl(epfd, op, fd, &epds, false); } /* * Implement the event wait interface for the eventpoll file. It is the kernel * part of the user space epoll_wait(2). */ static int do_epoll_wait(int epfd, struct epoll_event __user *events, int maxevents, struct timespec64 *to) { struct eventpoll *ep; /* The maximum number of event must be greater than zero */ if (maxevents <= 0 || maxevents > EP_MAX_EVENTS) return -EINVAL; /* Verify that the area passed by the user is writeable */ if (!access_ok(events, maxevents * sizeof(struct epoll_event))) return -EFAULT; /* Get the "struct file *" for the eventpoll file */ CLASS(fd, f)(epfd); if (fd_empty(f)) return -EBADF; /* * We have to check that the file structure underneath the fd * the user passed to us _is_ an eventpoll file. */ if (!is_file_epoll(fd_file(f))) return -EINVAL; /* * At this point it is safe to assume that the "private_data" contains * our own data structure. */ ep = fd_file(f)->private_data; /* Time to fish for events ... */ return ep_poll(ep, events, maxevents, to); } SYSCALL_DEFINE4(epoll_wait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout) { struct timespec64 to; return do_epoll_wait(epfd, events, maxevents, ep_timeout_to_timespec(&to, timeout)); } /* * Implement the event wait interface for the eventpoll file. It is the kernel * part of the user space epoll_pwait(2). */ static int do_epoll_pwait(int epfd, struct epoll_event __user *events, int maxevents, struct timespec64 *to, const sigset_t __user *sigmask, size_t sigsetsize) { int error; /* * If the caller wants a certain signal mask to be set during the wait, * we apply it here. */ error = set_user_sigmask(sigmask, sigsetsize); if (error) return error; error = do_epoll_wait(epfd, events, maxevents, to); restore_saved_sigmask_unless(error == -EINTR); return error; } SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout, const sigset_t __user *, sigmask, size_t, sigsetsize) { struct timespec64 to; return do_epoll_pwait(epfd, events, maxevents, ep_timeout_to_timespec(&to, timeout), sigmask, sigsetsize); } SYSCALL_DEFINE6(epoll_pwait2, int, epfd, struct epoll_event __user *, events, int, maxevents, const struct __kernel_timespec __user *, timeout, const sigset_t __user *, sigmask, size_t, sigsetsize) { struct timespec64 ts, *to = NULL; if (timeout) { if (get_timespec64(&ts, timeout)) return -EFAULT; to = &ts; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } return do_epoll_pwait(epfd, events, maxevents, to, sigmask, sigsetsize); } #ifdef CONFIG_COMPAT static int do_compat_epoll_pwait(int epfd, struct epoll_event __user *events, int maxevents, struct timespec64 *timeout, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize) { long err; /* * If the caller wants a certain signal mask to be set during the wait, * we apply it here. */ err = set_compat_user_sigmask(sigmask, sigsetsize); if (err) return err; err = do_epoll_wait(epfd, events, maxevents, timeout); restore_saved_sigmask_unless(err == -EINTR); return err; } COMPAT_SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { struct timespec64 to; return do_compat_epoll_pwait(epfd, events, maxevents, ep_timeout_to_timespec(&to, timeout), sigmask, sigsetsize); } COMPAT_SYSCALL_DEFINE6(epoll_pwait2, int, epfd, struct epoll_event __user *, events, int, maxevents, const struct __kernel_timespec __user *, timeout, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { struct timespec64 ts, *to = NULL; if (timeout) { if (get_timespec64(&ts, timeout)) return -EFAULT; to = &ts; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } return do_compat_epoll_pwait(epfd, events, maxevents, to, sigmask, sigsetsize); } #endif static int __init eventpoll_init(void) { struct sysinfo si; si_meminfo(&si); /* * Allows top 4% of lomem to be allocated for epoll watches (per user). */ max_user_watches = (((si.totalram - si.totalhigh) / 25) << PAGE_SHIFT) / EP_ITEM_COST; BUG_ON(max_user_watches < 0); /* * We can have many thousands of epitems, so prevent this from * using an extra cache line on 64-bit (and smaller) CPUs */ BUILD_BUG_ON(sizeof(void *) <= 8 && sizeof(struct epitem) > 128); /* Allocates slab cache used to allocate "struct epitem" items */ epi_cache = kmem_cache_create("eventpoll_epi", sizeof(struct epitem), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); /* Allocates slab cache used to allocate "struct eppoll_entry" */ pwq_cache = kmem_cache_create("eventpoll_pwq", sizeof(struct eppoll_entry), 0, SLAB_PANIC|SLAB_ACCOUNT, NULL); epoll_sysctls_init(); ephead_cache = kmem_cache_create("ep_head", sizeof(struct epitems_head), 0, SLAB_PANIC|SLAB_ACCOUNT, NULL); return 0; } fs_initcall(eventpoll_init); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 | // SPDX-License-Identifier: GPL-2.0 /* * Zoned block device handling * * Copyright (c) 2015, Hannes Reinecke * Copyright (c) 2015, SUSE Linux GmbH * * Copyright (c) 2016, Damien Le Moal * Copyright (c) 2016, Western Digital * Copyright (c) 2024, Western Digital Corporation or its affiliates. */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/blkdev.h> #include <linux/blk-mq.h> #include <linux/mm.h> #include <linux/vmalloc.h> #include <linux/sched/mm.h> #include <linux/spinlock.h> #include <linux/refcount.h> #include <linux/mempool.h> #include "blk.h" #include "blk-mq-sched.h" #include "blk-mq-debugfs.h" #define ZONE_COND_NAME(name) [BLK_ZONE_COND_##name] = #name static const char *const zone_cond_name[] = { ZONE_COND_NAME(NOT_WP), ZONE_COND_NAME(EMPTY), ZONE_COND_NAME(IMP_OPEN), ZONE_COND_NAME(EXP_OPEN), ZONE_COND_NAME(CLOSED), ZONE_COND_NAME(READONLY), ZONE_COND_NAME(FULL), ZONE_COND_NAME(OFFLINE), }; #undef ZONE_COND_NAME /* * Per-zone write plug. * @node: hlist_node structure for managing the plug using a hash table. * @link: To list the plug in the zone write plug error list of the disk. * @ref: Zone write plug reference counter. A zone write plug reference is * always at least 1 when the plug is hashed in the disk plug hash table. * The reference is incremented whenever a new BIO needing plugging is * submitted and when a function needs to manipulate a plug. The * reference count is decremented whenever a plugged BIO completes and * when a function that referenced the plug returns. The initial * reference is dropped whenever the zone of the zone write plug is reset, * finished and when the zone becomes full (last write BIO to the zone * completes). * @lock: Spinlock to atomically manipulate the plug. * @flags: Flags indicating the plug state. * @zone_no: The number of the zone the plug is managing. * @wp_offset: The zone write pointer location relative to the start of the zone * as a number of 512B sectors. * @bio_list: The list of BIOs that are currently plugged. * @bio_work: Work struct to handle issuing of plugged BIOs * @rcu_head: RCU head to free zone write plugs with an RCU grace period. * @disk: The gendisk the plug belongs to. */ struct blk_zone_wplug { struct hlist_node node; struct list_head link; refcount_t ref; spinlock_t lock; unsigned int flags; unsigned int zone_no; unsigned int wp_offset; struct bio_list bio_list; struct work_struct bio_work; struct rcu_head rcu_head; struct gendisk *disk; }; /* * Zone write plug flags bits: * - BLK_ZONE_WPLUG_PLUGGED: Indicates that the zone write plug is plugged, * that is, that write BIOs are being throttled due to a write BIO already * being executed or the zone write plug bio list is not empty. * - BLK_ZONE_WPLUG_ERROR: Indicates that a write error happened which will be * recovered with a report zone to update the zone write pointer offset. * - BLK_ZONE_WPLUG_UNHASHED: Indicates that the zone write plug was removed * from the disk hash table and that the initial reference to the zone * write plug set when the plug was first added to the hash table has been * dropped. This flag is set when a zone is reset, finished or become full, * to prevent new references to the zone write plug to be taken for * newly incoming BIOs. A zone write plug flagged with this flag will be * freed once all remaining references from BIOs or functions are dropped. */ #define BLK_ZONE_WPLUG_PLUGGED (1U << 0) #define BLK_ZONE_WPLUG_ERROR (1U << 1) #define BLK_ZONE_WPLUG_UNHASHED (1U << 2) #define BLK_ZONE_WPLUG_BUSY (BLK_ZONE_WPLUG_PLUGGED | BLK_ZONE_WPLUG_ERROR) /** * blk_zone_cond_str - Return string XXX in BLK_ZONE_COND_XXX. * @zone_cond: BLK_ZONE_COND_XXX. * * Description: Centralize block layer function to convert BLK_ZONE_COND_XXX * into string format. Useful in the debugging and tracing zone conditions. For * invalid BLK_ZONE_COND_XXX it returns string "UNKNOWN". */ const char *blk_zone_cond_str(enum blk_zone_cond zone_cond) { static const char *zone_cond_str = "UNKNOWN"; if (zone_cond < ARRAY_SIZE(zone_cond_name) && zone_cond_name[zone_cond]) zone_cond_str = zone_cond_name[zone_cond]; return zone_cond_str; } EXPORT_SYMBOL_GPL(blk_zone_cond_str); /** * blkdev_report_zones - Get zones information * @bdev: Target block device * @sector: Sector from which to report zones * @nr_zones: Maximum number of zones to report * @cb: Callback function called for each reported zone * @data: Private data for the callback * * Description: * Get zone information starting from the zone containing @sector for at most * @nr_zones, and call @cb for each zone reported by the device. * To report all zones in a device starting from @sector, the BLK_ALL_ZONES * constant can be passed to @nr_zones. * Returns the number of zones reported by the device, or a negative errno * value in case of failure. * * Note: The caller must use memalloc_noXX_save/restore() calls to control * memory allocations done within this function. */ int blkdev_report_zones(struct block_device *bdev, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data) { struct gendisk *disk = bdev->bd_disk; sector_t capacity = get_capacity(disk); if (!bdev_is_zoned(bdev) || WARN_ON_ONCE(!disk->fops->report_zones)) return -EOPNOTSUPP; if (!nr_zones || sector >= capacity) return 0; return disk->fops->report_zones(disk, sector, nr_zones, cb, data); } EXPORT_SYMBOL_GPL(blkdev_report_zones); static int blkdev_zone_reset_all(struct block_device *bdev) { struct bio bio; bio_init(&bio, bdev, NULL, 0, REQ_OP_ZONE_RESET_ALL | REQ_SYNC); return submit_bio_wait(&bio); } /** * blkdev_zone_mgmt - Execute a zone management operation on a range of zones * @bdev: Target block device * @op: Operation to be performed on the zones * @sector: Start sector of the first zone to operate on * @nr_sectors: Number of sectors, should be at least the length of one zone and * must be zone size aligned. * * Description: * Perform the specified operation on the range of zones specified by * @sector..@sector+@nr_sectors. Specifying the entire disk sector range * is valid, but the specified range should not contain conventional zones. * The operation to execute on each zone can be a zone reset, open, close * or finish request. */ int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op, sector_t sector, sector_t nr_sectors) { sector_t zone_sectors = bdev_zone_sectors(bdev); sector_t capacity = bdev_nr_sectors(bdev); sector_t end_sector = sector + nr_sectors; struct bio *bio = NULL; int ret = 0; if (!bdev_is_zoned(bdev)) return -EOPNOTSUPP; if (bdev_read_only(bdev)) return -EPERM; if (!op_is_zone_mgmt(op)) return -EOPNOTSUPP; if (end_sector <= sector || end_sector > capacity) /* Out of range */ return -EINVAL; /* Check alignment (handle eventual smaller last zone) */ if (!bdev_is_zone_start(bdev, sector)) return -EINVAL; if (!bdev_is_zone_start(bdev, nr_sectors) && end_sector != capacity) return -EINVAL; /* * In the case of a zone reset operation over all zones, use * REQ_OP_ZONE_RESET_ALL. */ if (op == REQ_OP_ZONE_RESET && sector == 0 && nr_sectors == capacity) return blkdev_zone_reset_all(bdev); while (sector < end_sector) { bio = blk_next_bio(bio, bdev, 0, op | REQ_SYNC, GFP_KERNEL); bio->bi_iter.bi_sector = sector; sector += zone_sectors; /* This may take a while, so be nice to others */ cond_resched(); } ret = submit_bio_wait(bio); bio_put(bio); return ret; } EXPORT_SYMBOL_GPL(blkdev_zone_mgmt); struct zone_report_args { struct blk_zone __user *zones; }; static int blkdev_copy_zone_to_user(struct blk_zone *zone, unsigned int idx, void *data) { struct zone_report_args *args = data; if (copy_to_user(&args->zones[idx], zone, sizeof(struct blk_zone))) return -EFAULT; return 0; } /* * BLKREPORTZONE ioctl processing. * Called from blkdev_ioctl. */ int blkdev_report_zones_ioctl(struct block_device *bdev, unsigned int cmd, unsigned long arg) { void __user *argp = (void __user *)arg; struct zone_report_args args; struct blk_zone_report rep; int ret; if (!argp) return -EINVAL; if (!bdev_is_zoned(bdev)) return -ENOTTY; if (copy_from_user(&rep, argp, sizeof(struct blk_zone_report))) return -EFAULT; if (!rep.nr_zones) return -EINVAL; args.zones = argp + sizeof(struct blk_zone_report); ret = blkdev_report_zones(bdev, rep.sector, rep.nr_zones, blkdev_copy_zone_to_user, &args); if (ret < 0) return ret; rep.nr_zones = ret; rep.flags = BLK_ZONE_REP_CAPACITY; if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report))) return -EFAULT; return 0; } static int blkdev_truncate_zone_range(struct block_device *bdev, blk_mode_t mode, const struct blk_zone_range *zrange) { loff_t start, end; if (zrange->sector + zrange->nr_sectors <= zrange->sector || zrange->sector + zrange->nr_sectors > get_capacity(bdev->bd_disk)) /* Out of range */ return -EINVAL; start = zrange->sector << SECTOR_SHIFT; end = ((zrange->sector + zrange->nr_sectors) << SECTOR_SHIFT) - 1; return truncate_bdev_range(bdev, mode, start, end); } /* * BLKRESETZONE, BLKOPENZONE, BLKCLOSEZONE and BLKFINISHZONE ioctl processing. * Called from blkdev_ioctl. */ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { void __user *argp = (void __user *)arg; struct blk_zone_range zrange; enum req_op op; int ret; if (!argp) return -EINVAL; if (!bdev_is_zoned(bdev)) return -ENOTTY; if (!(mode & BLK_OPEN_WRITE)) return -EBADF; if (copy_from_user(&zrange, argp, sizeof(struct blk_zone_range))) return -EFAULT; switch (cmd) { case BLKRESETZONE: op = REQ_OP_ZONE_RESET; /* Invalidate the page cache, including dirty pages. */ filemap_invalidate_lock(bdev->bd_mapping); ret = blkdev_truncate_zone_range(bdev, mode, &zrange); if (ret) goto fail; break; case BLKOPENZONE: op = REQ_OP_ZONE_OPEN; break; case BLKCLOSEZONE: op = REQ_OP_ZONE_CLOSE; break; case BLKFINISHZONE: op = REQ_OP_ZONE_FINISH; break; default: return -ENOTTY; } ret = blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors); fail: if (cmd == BLKRESETZONE) filemap_invalidate_unlock(bdev->bd_mapping); return ret; } static bool disk_zone_is_last(struct gendisk *disk, struct blk_zone *zone) { return zone->start + zone->len >= get_capacity(disk); } static bool disk_zone_is_full(struct gendisk *disk, unsigned int zno, unsigned int offset_in_zone) { if (zno < disk->nr_zones - 1) return offset_in_zone >= disk->zone_capacity; return offset_in_zone >= disk->last_zone_capacity; } static bool disk_zone_wplug_is_full(struct gendisk *disk, struct blk_zone_wplug *zwplug) { return disk_zone_is_full(disk, zwplug->zone_no, zwplug->wp_offset); } static bool disk_insert_zone_wplug(struct gendisk *disk, struct blk_zone_wplug *zwplug) { struct blk_zone_wplug *zwplg; unsigned long flags; unsigned int idx = hash_32(zwplug->zone_no, disk->zone_wplugs_hash_bits); /* * Add the new zone write plug to the hash table, but carefully as we * are racing with other submission context, so we may already have a * zone write plug for the same zone. */ spin_lock_irqsave(&disk->zone_wplugs_lock, flags); hlist_for_each_entry_rcu(zwplg, &disk->zone_wplugs_hash[idx], node) { if (zwplg->zone_no == zwplug->zone_no) { spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags); return false; } } hlist_add_head_rcu(&zwplug->node, &disk->zone_wplugs_hash[idx]); spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags); return true; } static struct blk_zone_wplug *disk_get_zone_wplug(struct gendisk *disk, sector_t sector) { unsigned int zno = disk_zone_no(disk, sector); unsigned int idx = hash_32(zno, disk->zone_wplugs_hash_bits); struct blk_zone_wplug *zwplug; rcu_read_lock(); hlist_for_each_entry_rcu(zwplug, &disk->zone_wplugs_hash[idx], node) { if (zwplug->zone_no == zno && refcount_inc_not_zero(&zwplug->ref)) { rcu_read_unlock(); return zwplug; } } rcu_read_unlock(); return NULL; } static void disk_free_zone_wplug_rcu(struct rcu_head *rcu_head) { struct blk_zone_wplug *zwplug = container_of(rcu_head, struct blk_zone_wplug, rcu_head); mempool_free(zwplug, zwplug->disk->zone_wplugs_pool); } static inline void disk_put_zone_wplug(struct blk_zone_wplug *zwplug) { if (refcount_dec_and_test(&zwplug->ref)) { WARN_ON_ONCE(!bio_list_empty(&zwplug->bio_list)); WARN_ON_ONCE(!list_empty(&zwplug->link)); WARN_ON_ONCE(!(zwplug->flags & BLK_ZONE_WPLUG_UNHASHED)); call_rcu(&zwplug->rcu_head, disk_free_zone_wplug_rcu); } } static inline bool disk_should_remove_zone_wplug(struct gendisk *disk, struct blk_zone_wplug *zwplug) { /* If the zone write plug was already removed, we are done. */ if (zwplug->flags & BLK_ZONE_WPLUG_UNHASHED) return false; /* If the zone write plug is still busy, it cannot be removed. */ if (zwplug->flags & BLK_ZONE_WPLUG_BUSY) return false; /* * Completions of BIOs with blk_zone_write_plug_bio_endio() may * happen after handling a request completion with * blk_zone_write_plug_finish_request() (e.g. with split BIOs * that are chained). In such case, disk_zone_wplug_unplug_bio() * should not attempt to remove the zone write plug until all BIO * completions are seen. Check by looking at the zone write plug * reference count, which is 2 when the plug is unused (one reference * taken when the plug was allocated and another reference taken by the * caller context). */ if (refcount_read(&zwplug->ref) > 2) return false; /* We can remove zone write plugs for zones that are empty or full. */ return !zwplug->wp_offset || disk_zone_wplug_is_full(disk, zwplug); } static void disk_remove_zone_wplug(struct gendisk *disk, struct blk_zone_wplug *zwplug) { unsigned long flags; /* If the zone write plug was already removed, we have nothing to do. */ if (zwplug->flags & BLK_ZONE_WPLUG_UNHASHED) return; /* * Mark the zone write plug as unhashed and drop the extra reference we * took when the plug was inserted in the hash table. */ zwplug->flags |= BLK_ZONE_WPLUG_UNHASHED; spin_lock_irqsave(&disk->zone_wplugs_lock, flags); hlist_del_init_rcu(&zwplug->node); spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags); disk_put_zone_wplug(zwplug); } static void blk_zone_wplug_bio_work(struct work_struct *work); /* * Get a reference on the write plug for the zone containing @sector. * If the plug does not exist, it is allocated and hashed. * Return a pointer to the zone write plug with the plug spinlock held. */ static struct blk_zone_wplug *disk_get_and_lock_zone_wplug(struct gendisk *disk, sector_t sector, gfp_t gfp_mask, unsigned long *flags) { unsigned int zno = disk_zone_no(disk, sector); struct blk_zone_wplug *zwplug; again: zwplug = disk_get_zone_wplug(disk, sector); if (zwplug) { /* * Check that a BIO completion or a zone reset or finish * operation has not already removed the zone write plug from * the hash table and dropped its reference count. In such case, * we need to get a new plug so start over from the beginning. */ spin_lock_irqsave(&zwplug->lock, *flags); if (zwplug->flags & BLK_ZONE_WPLUG_UNHASHED) { spin_unlock_irqrestore(&zwplug->lock, *flags); disk_put_zone_wplug(zwplug); goto again; } return zwplug; } /* * Allocate and initialize a zone write plug with an extra reference * so that it is not freed when the zone write plug becomes idle without * the zone being full. */ zwplug = mempool_alloc(disk->zone_wplugs_pool, gfp_mask); if (!zwplug) return NULL; INIT_HLIST_NODE(&zwplug->node); INIT_LIST_HEAD(&zwplug->link); refcount_set(&zwplug->ref, 2); spin_lock_init(&zwplug->lock); zwplug->flags = 0; zwplug->zone_no = zno; zwplug->wp_offset = sector & (disk->queue->limits.chunk_sectors - 1); bio_list_init(&zwplug->bio_list); INIT_WORK(&zwplug->bio_work, blk_zone_wplug_bio_work); zwplug->disk = disk; spin_lock_irqsave(&zwplug->lock, *flags); /* * Insert the new zone write plug in the hash table. This can fail only * if another context already inserted a plug. Retry from the beginning * in such case. */ if (!disk_insert_zone_wplug(disk, zwplug)) { spin_unlock_irqrestore(&zwplug->lock, *flags); mempool_free(zwplug, disk->zone_wplugs_pool); goto again; } return zwplug; } static inline void blk_zone_wplug_bio_io_error(struct blk_zone_wplug *zwplug, struct bio *bio) { struct request_queue *q = zwplug->disk->queue; bio_clear_flag(bio, BIO_ZONE_WRITE_PLUGGING); bio_io_error(bio); disk_put_zone_wplug(zwplug); blk_queue_exit(q); } /* * Abort (fail) all plugged BIOs of a zone write plug. */ static void disk_zone_wplug_abort(struct blk_zone_wplug *zwplug) { struct bio *bio; while ((bio = bio_list_pop(&zwplug->bio_list))) blk_zone_wplug_bio_io_error(zwplug, bio); } /* * Abort (fail) all plugged BIOs of a zone write plug that are not aligned * with the assumed write pointer location of the zone when the BIO will * be unplugged. */ static void disk_zone_wplug_abort_unaligned(struct gendisk *disk, struct blk_zone_wplug *zwplug) { unsigned int wp_offset = zwplug->wp_offset; struct bio_list bl = BIO_EMPTY_LIST; struct bio *bio; while ((bio = bio_list_pop(&zwplug->bio_list))) { if (disk_zone_is_full(disk, zwplug->zone_no, wp_offset) || (bio_op(bio) != REQ_OP_ZONE_APPEND && bio_offset_from_zone_start(bio) != wp_offset)) { blk_zone_wplug_bio_io_error(zwplug, bio); continue; } wp_offset += bio_sectors(bio); bio_list_add(&bl, bio); } bio_list_merge(&zwplug->bio_list, &bl); } static inline void disk_zone_wplug_set_error(struct gendisk *disk, struct blk_zone_wplug *zwplug) { unsigned long flags; if (zwplug->flags & BLK_ZONE_WPLUG_ERROR) return; /* * At this point, we already have a reference on the zone write plug. * However, since we are going to add the plug to the disk zone write * plugs work list, increase its reference count. This reference will * be dropped in disk_zone_wplugs_work() once the error state is * handled, or in disk_zone_wplug_clear_error() if the zone is reset or * finished. */ zwplug->flags |= BLK_ZONE_WPLUG_ERROR; refcount_inc(&zwplug->ref); spin_lock_irqsave(&disk->zone_wplugs_lock, flags); list_add_tail(&zwplug->link, &disk->zone_wplugs_err_list); spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags); } static inline void disk_zone_wplug_clear_error(struct gendisk *disk, struct blk_zone_wplug *zwplug) { unsigned long flags; if (!(zwplug->flags & BLK_ZONE_WPLUG_ERROR)) return; /* * We are racing with the error handling work which drops the reference * on the zone write plug after handling the error state. So remove the * plug from the error list and drop its reference count only if the * error handling has not yet started, that is, if the zone write plug * is still listed. */ spin_lock_irqsave(&disk->zone_wplugs_lock, flags); if (!list_empty(&zwplug->link)) { list_del_init(&zwplug->link); zwplug->flags &= ~BLK_ZONE_WPLUG_ERROR; disk_put_zone_wplug(zwplug); } spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags); } /* * Set a zone write plug write pointer offset to either 0 (zone reset case) * or to the zone size (zone finish case). This aborts all plugged BIOs, which * is fine to do as doing a zone reset or zone finish while writes are in-flight * is a mistake from the user which will most likely cause all plugged BIOs to * fail anyway. */ static void disk_zone_wplug_set_wp_offset(struct gendisk *disk, struct blk_zone_wplug *zwplug, unsigned int wp_offset) { unsigned long flags; spin_lock_irqsave(&zwplug->lock, flags); /* * Make sure that a BIO completion or another zone reset or finish * operation has not already removed the plug from the hash table. */ if (zwplug->flags & BLK_ZONE_WPLUG_UNHASHED) { spin_unlock_irqrestore(&zwplug->lock, flags); return; } /* Update the zone write pointer and abort all plugged BIOs. */ zwplug->wp_offset = wp_offset; disk_zone_wplug_abort(zwplug); /* * Updating the write pointer offset puts back the zone * in a good state. So clear the error flag and decrement the * error count if we were in error state. */ disk_zone_wplug_clear_error(disk, zwplug); /* * The zone write plug now has no BIO plugged: remove it from the * hash table so that it cannot be seen. The plug will be freed * when the last reference is dropped. */ if (disk_should_remove_zone_wplug(disk, zwplug)) disk_remove_zone_wplug(disk, zwplug); spin_unlock_irqrestore(&zwplug->lock, flags); } static bool blk_zone_wplug_handle_reset_or_finish(struct bio *bio, unsigned int wp_offset) { struct gendisk *disk = bio->bi_bdev->bd_disk; sector_t sector = bio->bi_iter.bi_sector; struct blk_zone_wplug *zwplug; /* Conventional zones cannot be reset nor finished. */ if (!bdev_zone_is_seq(bio->bi_bdev, sector)) { bio_io_error(bio); return true; } /* * If we have a zone write plug, set its write pointer offset to 0 * (reset case) or to the zone size (finish case). This will abort all * BIOs plugged for the target zone. It is fine as resetting or * finishing zones while writes are still in-flight will result in the * writes failing anyway. */ zwplug = disk_get_zone_wplug(disk, sector); if (zwplug) { disk_zone_wplug_set_wp_offset(disk, zwplug, wp_offset); disk_put_zone_wplug(zwplug); } return false; } static bool blk_zone_wplug_handle_reset_all(struct bio *bio) { struct gendisk *disk = bio->bi_bdev->bd_disk; struct blk_zone_wplug *zwplug; sector_t sector; /* * Set the write pointer offset of all zone write plugs to 0. This will * abort all plugged BIOs. It is fine as resetting zones while writes * are still in-flight will result in the writes failing anyway. */ for (sector = 0; sector < get_capacity(disk); sector += disk->queue->limits.chunk_sectors) { zwplug = disk_get_zone_wplug(disk, sector); if (zwplug) { disk_zone_wplug_set_wp_offset(disk, zwplug, 0); disk_put_zone_wplug(zwplug); } } return false; } static inline void blk_zone_wplug_add_bio(struct blk_zone_wplug *zwplug, struct bio *bio, unsigned int nr_segs) { /* * Grab an extra reference on the BIO request queue usage counter. * This reference will be reused to submit a request for the BIO for * blk-mq devices and dropped when the BIO is failed and after * it is issued in the case of BIO-based devices. */ percpu_ref_get(&bio->bi_bdev->bd_disk->queue->q_usage_counter); /* * The BIO is being plugged and thus will have to wait for the on-going * write and for all other writes already plugged. So polling makes * no sense. */ bio_clear_polled(bio); /* * Reuse the poll cookie field to store the number of segments when * split to the hardware limits. */ bio->__bi_nr_segments = nr_segs; /* * We always receive BIOs after they are split and ready to be issued. * The block layer passes the parts of a split BIO in order, and the * user must also issue write sequentially. So simply add the new BIO * at the tail of the list to preserve the sequential write order. */ bio_list_add(&zwplug->bio_list, bio); } /* * Called from bio_attempt_back_merge() when a BIO was merged with a request. */ void blk_zone_write_plug_bio_merged(struct bio *bio) { struct blk_zone_wplug *zwplug; unsigned long flags; /* * If the BIO was already plugged, then we were called through * blk_zone_write_plug_init_request() -> blk_attempt_bio_merge(). * For this case, we already hold a reference on the zone write plug for * the BIO and blk_zone_write_plug_init_request() will handle the * zone write pointer offset update. */ if (bio_flagged(bio, BIO_ZONE_WRITE_PLUGGING)) return; bio_set_flag(bio, BIO_ZONE_WRITE_PLUGGING); /* * Get a reference on the zone write plug of the target zone and advance * the zone write pointer offset. Given that this is a merge, we already * have at least one request and one BIO referencing the zone write * plug. So this should not fail. */ zwplug = disk_get_zone_wplug(bio->bi_bdev->bd_disk, bio->bi_iter.bi_sector); if (WARN_ON_ONCE(!zwplug)) return; spin_lock_irqsave(&zwplug->lock, flags); zwplug->wp_offset += bio_sectors(bio); spin_unlock_irqrestore(&zwplug->lock, flags); } /* * Attempt to merge plugged BIOs with a newly prepared request for a BIO that * already went through zone write plugging (either a new BIO or one that was * unplugged). */ void blk_zone_write_plug_init_request(struct request *req) { sector_t req_back_sector = blk_rq_pos(req) + blk_rq_sectors(req); struct request_queue *q = req->q; struct gendisk *disk = q->disk; struct blk_zone_wplug *zwplug = disk_get_zone_wplug(disk, blk_rq_pos(req)); unsigned long flags; struct bio *bio; if (WARN_ON_ONCE(!zwplug)) return; /* * Indicate that completion of this request needs to be handled with * blk_zone_write_plug_finish_request(), which will drop the reference * on the zone write plug we took above on entry to this function. */ req->rq_flags |= RQF_ZONE_WRITE_PLUGGING; if (blk_queue_nomerges(q)) return; /* * Walk through the list of plugged BIOs to check if they can be merged * into the back of the request. */ spin_lock_irqsave(&zwplug->lock, flags); while (!disk_zone_wplug_is_full(disk, zwplug)) { bio = bio_list_peek(&zwplug->bio_list); if (!bio) break; if (bio->bi_iter.bi_sector != req_back_sector || !blk_rq_merge_ok(req, bio)) break; WARN_ON_ONCE(bio_op(bio) != REQ_OP_WRITE_ZEROES && !bio->__bi_nr_segments); bio_list_pop(&zwplug->bio_list); if (bio_attempt_back_merge(req, bio, bio->__bi_nr_segments) != BIO_MERGE_OK) { bio_list_add_head(&zwplug->bio_list, bio); break; } /* * Drop the extra reference on the queue usage we got when * plugging the BIO and advance the write pointer offset. */ blk_queue_exit(q); zwplug->wp_offset += bio_sectors(bio); req_back_sector += bio_sectors(bio); } spin_unlock_irqrestore(&zwplug->lock, flags); } /* * Check and prepare a BIO for submission by incrementing the write pointer * offset of its zone write plug and changing zone append operations into * regular write when zone append emulation is needed. */ static bool blk_zone_wplug_prepare_bio(struct blk_zone_wplug *zwplug, struct bio *bio) { struct gendisk *disk = bio->bi_bdev->bd_disk; /* * Check that the user is not attempting to write to a full zone. * We know such BIO will fail, and that would potentially overflow our * write pointer offset beyond the end of the zone. */ if (disk_zone_wplug_is_full(disk, zwplug)) goto err; if (bio_op(bio) == REQ_OP_ZONE_APPEND) { /* * Use a regular write starting at the current write pointer. * Similarly to native zone append operations, do not allow * merging. */ bio->bi_opf &= ~REQ_OP_MASK; bio->bi_opf |= REQ_OP_WRITE | REQ_NOMERGE; bio->bi_iter.bi_sector += zwplug->wp_offset; /* * Remember that this BIO is in fact a zone append operation * so that we can restore its operation code on completion. */ bio_set_flag(bio, BIO_EMULATES_ZONE_APPEND); } else { /* * Check for non-sequential writes early because we avoid a * whole lot of error handling trouble if we don't send it off * to the driver. */ if (bio_offset_from_zone_start(bio) != zwplug->wp_offset) goto err; } /* Advance the zone write pointer offset. */ zwplug->wp_offset += bio_sectors(bio); return true; err: /* We detected an invalid write BIO: schedule error recovery. */ disk_zone_wplug_set_error(disk, zwplug); kblockd_schedule_work(&disk->zone_wplugs_work); return false; } static bool blk_zone_wplug_handle_write(struct bio *bio, unsigned int nr_segs) { struct gendisk *disk = bio->bi_bdev->bd_disk; sector_t sector = bio->bi_iter.bi_sector; struct blk_zone_wplug *zwplug; gfp_t gfp_mask = GFP_NOIO; unsigned long flags; /* * BIOs must be fully contained within a zone so that we use the correct * zone write plug for the entire BIO. For blk-mq devices, the block * layer should already have done any splitting required to ensure this * and this BIO should thus not be straddling zone boundaries. For * BIO-based devices, it is the responsibility of the driver to split * the bio before submitting it. */ if (WARN_ON_ONCE(bio_straddles_zones(bio))) { bio_io_error(bio); return true; } /* Conventional zones do not need write plugging. */ if (!bdev_zone_is_seq(bio->bi_bdev, sector)) { /* Zone append to conventional zones is not allowed. */ if (bio_op(bio) == REQ_OP_ZONE_APPEND) { bio_io_error(bio); return true; } return false; } if (bio->bi_opf & REQ_NOWAIT) gfp_mask = GFP_NOWAIT; zwplug = disk_get_and_lock_zone_wplug(disk, sector, gfp_mask, &flags); if (!zwplug) { bio_io_error(bio); return true; } /* Indicate that this BIO is being handled using zone write plugging. */ bio_set_flag(bio, BIO_ZONE_WRITE_PLUGGING); /* * If the zone is already plugged or has a pending error, add the BIO * to the plug BIO list. Otherwise, plug and let the BIO execute. */ if (zwplug->flags & BLK_ZONE_WPLUG_BUSY) goto plug; /* * If an error is detected when preparing the BIO, add it to the BIO * list so that error recovery can deal with it. */ if (!blk_zone_wplug_prepare_bio(zwplug, bio)) goto plug; zwplug->flags |= BLK_ZONE_WPLUG_PLUGGED; spin_unlock_irqrestore(&zwplug->lock, flags); return false; plug: zwplug->flags |= BLK_ZONE_WPLUG_PLUGGED; blk_zone_wplug_add_bio(zwplug, bio, nr_segs); spin_unlock_irqrestore(&zwplug->lock, flags); return true; } /** * blk_zone_plug_bio - Handle a zone write BIO with zone write plugging * @bio: The BIO being submitted * @nr_segs: The number of physical segments of @bio * * Handle write, write zeroes and zone append operations requiring emulation * using zone write plugging. * * Return true whenever @bio execution needs to be delayed through the zone * write plug. Otherwise, return false to let the submission path process * @bio normally. */ bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs) { struct block_device *bdev = bio->bi_bdev; if (!bdev->bd_disk->zone_wplugs_hash) return false; /* * If the BIO already has the plugging flag set, then it was already * handled through this path and this is a submission from the zone * plug bio submit work. */ if (bio_flagged(bio, BIO_ZONE_WRITE_PLUGGING)) return false; /* * We do not need to do anything special for empty flush BIOs, e.g * BIOs such as issued by blkdev_issue_flush(). The is because it is * the responsibility of the user to first wait for the completion of * write operations for flush to have any effect on the persistence of * the written data. */ if (op_is_flush(bio->bi_opf) && !bio_sectors(bio)) return false; /* * Regular writes and write zeroes need to be handled through the target * zone write plug. This includes writes with REQ_FUA | REQ_PREFLUSH * which may need to go through the flush machinery depending on the * target device capabilities. Plugging such writes is fine as the flush * machinery operates at the request level, below the plug, and * completion of the flush sequence will go through the regular BIO * completion, which will handle zone write plugging. * Zone append operations for devices that requested emulation must * also be plugged so that these BIOs can be changed into regular * write BIOs. * Zone reset, reset all and finish commands need special treatment * to correctly track the write pointer offset of zones. These commands * are not plugged as we do not need serialization with write * operations. It is the responsibility of the user to not issue reset * and finish commands when write operations are in flight. */ switch (bio_op(bio)) { case REQ_OP_ZONE_APPEND: if (!bdev_emulates_zone_append(bdev)) return false; fallthrough; case REQ_OP_WRITE: case REQ_OP_WRITE_ZEROES: return blk_zone_wplug_handle_write(bio, nr_segs); case REQ_OP_ZONE_RESET: return blk_zone_wplug_handle_reset_or_finish(bio, 0); case REQ_OP_ZONE_FINISH: return blk_zone_wplug_handle_reset_or_finish(bio, bdev_zone_sectors(bdev)); case REQ_OP_ZONE_RESET_ALL: return blk_zone_wplug_handle_reset_all(bio); default: return false; } return false; } EXPORT_SYMBOL_GPL(blk_zone_plug_bio); static void disk_zone_wplug_schedule_bio_work(struct gendisk *disk, struct blk_zone_wplug *zwplug) { /* * Take a reference on the zone write plug and schedule the submission * of the next plugged BIO. blk_zone_wplug_bio_work() will release the * reference we take here. */ WARN_ON_ONCE(!(zwplug->flags & BLK_ZONE_WPLUG_PLUGGED)); refcount_inc(&zwplug->ref); queue_work(disk->zone_wplugs_wq, &zwplug->bio_work); } static void disk_zone_wplug_unplug_bio(struct gendisk *disk, struct blk_zone_wplug *zwplug) { unsigned long flags; spin_lock_irqsave(&zwplug->lock, flags); /* * If we had an error, schedule error recovery. The recovery work * will restart submission of plugged BIOs. */ if (zwplug->flags & BLK_ZONE_WPLUG_ERROR) { spin_unlock_irqrestore(&zwplug->lock, flags); kblockd_schedule_work(&disk->zone_wplugs_work); return; } /* Schedule submission of the next plugged BIO if we have one. */ if (!bio_list_empty(&zwplug->bio_list)) { disk_zone_wplug_schedule_bio_work(disk, zwplug); spin_unlock_irqrestore(&zwplug->lock, flags); return; } zwplug->flags &= ~BLK_ZONE_WPLUG_PLUGGED; /* * If the zone is full (it was fully written or finished, or empty * (it was reset), remove its zone write plug from the hash table. */ if (disk_should_remove_zone_wplug(disk, zwplug)) disk_remove_zone_wplug(disk, zwplug); spin_unlock_irqrestore(&zwplug->lock, flags); } void blk_zone_write_plug_bio_endio(struct bio *bio) { struct gendisk *disk = bio->bi_bdev->bd_disk; struct blk_zone_wplug *zwplug = disk_get_zone_wplug(disk, bio->bi_iter.bi_sector); unsigned long flags; if (WARN_ON_ONCE(!zwplug)) return; /* Make sure we do not see this BIO again by clearing the plug flag. */ bio_clear_flag(bio, BIO_ZONE_WRITE_PLUGGING); /* * If this is a regular write emulating a zone append operation, * restore the original operation code. */ if (bio_flagged(bio, BIO_EMULATES_ZONE_APPEND)) { bio->bi_opf &= ~REQ_OP_MASK; bio->bi_opf |= REQ_OP_ZONE_APPEND; } /* * If the BIO failed, mark the plug as having an error to trigger * recovery. */ if (bio->bi_status != BLK_STS_OK) { spin_lock_irqsave(&zwplug->lock, flags); disk_zone_wplug_set_error(disk, zwplug); spin_unlock_irqrestore(&zwplug->lock, flags); } /* Drop the reference we took when the BIO was issued. */ disk_put_zone_wplug(zwplug); /* * For BIO-based devices, blk_zone_write_plug_finish_request() * is not called. So we need to schedule execution of the next * plugged BIO here. */ if (bdev_test_flag(bio->bi_bdev, BD_HAS_SUBMIT_BIO)) disk_zone_wplug_unplug_bio(disk, zwplug); /* Drop the reference we took when entering this function. */ disk_put_zone_wplug(zwplug); } void blk_zone_write_plug_finish_request(struct request *req) { struct gendisk *disk = req->q->disk; struct blk_zone_wplug *zwplug; zwplug = disk_get_zone_wplug(disk, req->__sector); if (WARN_ON_ONCE(!zwplug)) return; req->rq_flags &= ~RQF_ZONE_WRITE_PLUGGING; /* * Drop the reference we took when the request was initialized in * blk_zone_write_plug_init_request(). */ disk_put_zone_wplug(zwplug); disk_zone_wplug_unplug_bio(disk, zwplug); /* Drop the reference we took when entering this function. */ disk_put_zone_wplug(zwplug); } static void blk_zone_wplug_bio_work(struct work_struct *work) { struct blk_zone_wplug *zwplug = container_of(work, struct blk_zone_wplug, bio_work); struct block_device *bdev; unsigned long flags; struct bio *bio; /* * Submit the next plugged BIO. If we do not have any, clear * the plugged flag. */ spin_lock_irqsave(&zwplug->lock, flags); bio = bio_list_pop(&zwplug->bio_list); if (!bio) { zwplug->flags &= ~BLK_ZONE_WPLUG_PLUGGED; spin_unlock_irqrestore(&zwplug->lock, flags); goto put_zwplug; } if (!blk_zone_wplug_prepare_bio(zwplug, bio)) { /* Error recovery will decide what to do with the BIO. */ bio_list_add_head(&zwplug->bio_list, bio); spin_unlock_irqrestore(&zwplug->lock, flags); goto put_zwplug; } spin_unlock_irqrestore(&zwplug->lock, flags); bdev = bio->bi_bdev; submit_bio_noacct_nocheck(bio); /* * blk-mq devices will reuse the extra reference on the request queue * usage counter we took when the BIO was plugged, but the submission * path for BIO-based devices will not do that. So drop this extra * reference here. */ if (bdev_test_flag(bdev, BD_HAS_SUBMIT_BIO)) blk_queue_exit(bdev->bd_disk->queue); put_zwplug: /* Drop the reference we took in disk_zone_wplug_schedule_bio_work(). */ disk_put_zone_wplug(zwplug); } static unsigned int blk_zone_wp_offset(struct blk_zone *zone) { switch (zone->cond) { case BLK_ZONE_COND_IMP_OPEN: case BLK_ZONE_COND_EXP_OPEN: case BLK_ZONE_COND_CLOSED: return zone->wp - zone->start; case BLK_ZONE_COND_FULL: return zone->len; case BLK_ZONE_COND_EMPTY: return 0; case BLK_ZONE_COND_NOT_WP: case BLK_ZONE_COND_OFFLINE: case BLK_ZONE_COND_READONLY: default: /* * Conventional, offline and read-only zones do not have a valid * write pointer. */ return UINT_MAX; } } static int blk_zone_wplug_report_zone_cb(struct blk_zone *zone, unsigned int idx, void *data) { struct blk_zone *zonep = data; *zonep = *zone; return 0; } static void disk_zone_wplug_handle_error(struct gendisk *disk, struct blk_zone_wplug *zwplug) { sector_t zone_start_sector = bdev_zone_sectors(disk->part0) * zwplug->zone_no; unsigned int noio_flag; struct blk_zone zone; unsigned long flags; int ret; /* Get the current zone information from the device. */ noio_flag = memalloc_noio_save(); ret = disk->fops->report_zones(disk, zone_start_sector, 1, blk_zone_wplug_report_zone_cb, &zone); memalloc_noio_restore(noio_flag); spin_lock_irqsave(&zwplug->lock, flags); /* * A zone reset or finish may have cleared the error already. In such * case, do nothing as the report zones may have seen the "old" write * pointer value before the reset/finish operation completed. */ if (!(zwplug->flags & BLK_ZONE_WPLUG_ERROR)) goto unlock; zwplug->flags &= ~BLK_ZONE_WPLUG_ERROR; if (ret != 1) { /* * We failed to get the zone information, meaning that something * is likely really wrong with the device. Abort all remaining * plugged BIOs as otherwise we could endup waiting forever on * plugged BIOs to complete if there is a queue freeze on-going. */ disk_zone_wplug_abort(zwplug); goto unplug; } /* Update the zone write pointer offset. */ zwplug->wp_offset = blk_zone_wp_offset(&zone); disk_zone_wplug_abort_unaligned(disk, zwplug); /* Restart BIO submission if we still have any BIO left. */ if (!bio_list_empty(&zwplug->bio_list)) { disk_zone_wplug_schedule_bio_work(disk, zwplug); goto unlock; } unplug: zwplug->flags &= ~BLK_ZONE_WPLUG_PLUGGED; if (disk_should_remove_zone_wplug(disk, zwplug)) disk_remove_zone_wplug(disk, zwplug); unlock: spin_unlock_irqrestore(&zwplug->lock, flags); } static void disk_zone_wplugs_work(struct work_struct *work) { struct gendisk *disk = container_of(work, struct gendisk, zone_wplugs_work); struct blk_zone_wplug *zwplug; unsigned long flags; spin_lock_irqsave(&disk->zone_wplugs_lock, flags); while (!list_empty(&disk->zone_wplugs_err_list)) { zwplug = list_first_entry(&disk->zone_wplugs_err_list, struct blk_zone_wplug, link); list_del_init(&zwplug->link); spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags); disk_zone_wplug_handle_error(disk, zwplug); disk_put_zone_wplug(zwplug); spin_lock_irqsave(&disk->zone_wplugs_lock, flags); } spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags); } static inline unsigned int disk_zone_wplugs_hash_size(struct gendisk *disk) { return 1U << disk->zone_wplugs_hash_bits; } void disk_init_zone_resources(struct gendisk *disk) { spin_lock_init(&disk->zone_wplugs_lock); INIT_LIST_HEAD(&disk->zone_wplugs_err_list); INIT_WORK(&disk->zone_wplugs_work, disk_zone_wplugs_work); } /* * For the size of a disk zone write plug hash table, use the size of the * zone write plug mempool, which is the maximum of the disk open zones and * active zones limits. But do not exceed 4KB (512 hlist head entries), that is, * 9 bits. For a disk that has no limits, mempool size defaults to 128. */ #define BLK_ZONE_WPLUG_MAX_HASH_BITS 9 #define BLK_ZONE_WPLUG_DEFAULT_POOL_SIZE 128 static int disk_alloc_zone_resources(struct gendisk *disk, unsigned int pool_size) { unsigned int i; disk->zone_wplugs_hash_bits = min(ilog2(pool_size) + 1, BLK_ZONE_WPLUG_MAX_HASH_BITS); disk->zone_wplugs_hash = kcalloc(disk_zone_wplugs_hash_size(disk), sizeof(struct hlist_head), GFP_KERNEL); if (!disk->zone_wplugs_hash) return -ENOMEM; for (i = 0; i < disk_zone_wplugs_hash_size(disk); i++) INIT_HLIST_HEAD(&disk->zone_wplugs_hash[i]); disk->zone_wplugs_pool = mempool_create_kmalloc_pool(pool_size, sizeof(struct blk_zone_wplug)); if (!disk->zone_wplugs_pool) goto free_hash; disk->zone_wplugs_wq = alloc_workqueue("%s_zwplugs", WQ_MEM_RECLAIM | WQ_HIGHPRI, pool_size, disk->disk_name); if (!disk->zone_wplugs_wq) goto destroy_pool; return 0; destroy_pool: mempool_destroy(disk->zone_wplugs_pool); disk->zone_wplugs_pool = NULL; free_hash: kfree(disk->zone_wplugs_hash); disk->zone_wplugs_hash = NULL; disk->zone_wplugs_hash_bits = 0; return -ENOMEM; } static void disk_destroy_zone_wplugs_hash_table(struct gendisk *disk) { struct blk_zone_wplug *zwplug; unsigned int i; if (!disk->zone_wplugs_hash) return; /* Free all the zone write plugs we have. */ for (i = 0; i < disk_zone_wplugs_hash_size(disk); i++) { while (!hlist_empty(&disk->zone_wplugs_hash[i])) { zwplug = hlist_entry(disk->zone_wplugs_hash[i].first, struct blk_zone_wplug, node); refcount_inc(&zwplug->ref); disk_remove_zone_wplug(disk, zwplug); disk_put_zone_wplug(zwplug); } } kfree(disk->zone_wplugs_hash); disk->zone_wplugs_hash = NULL; disk->zone_wplugs_hash_bits = 0; } static unsigned int disk_set_conv_zones_bitmap(struct gendisk *disk, unsigned long *bitmap) { unsigned int nr_conv_zones = 0; unsigned long flags; spin_lock_irqsave(&disk->zone_wplugs_lock, flags); if (bitmap) nr_conv_zones = bitmap_weight(bitmap, disk->nr_zones); bitmap = rcu_replace_pointer(disk->conv_zones_bitmap, bitmap, lockdep_is_held(&disk->zone_wplugs_lock)); spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags); kfree_rcu_mightsleep(bitmap); return nr_conv_zones; } void disk_free_zone_resources(struct gendisk *disk) { if (!disk->zone_wplugs_pool) return; cancel_work_sync(&disk->zone_wplugs_work); if (disk->zone_wplugs_wq) { destroy_workqueue(disk->zone_wplugs_wq); disk->zone_wplugs_wq = NULL; } disk_destroy_zone_wplugs_hash_table(disk); /* * Wait for the zone write plugs to be RCU-freed before * destorying the mempool. */ rcu_barrier(); mempool_destroy(disk->zone_wplugs_pool); disk->zone_wplugs_pool = NULL; disk_set_conv_zones_bitmap(disk, NULL); disk->zone_capacity = 0; disk->last_zone_capacity = 0; disk->nr_zones = 0; } static inline bool disk_need_zone_resources(struct gendisk *disk) { /* * All mq zoned devices need zone resources so that the block layer * can automatically handle write BIO plugging. BIO-based device drivers * (e.g. DM devices) are normally responsible for handling zone write * ordering and do not need zone resources, unless the driver requires * zone append emulation. */ return queue_is_mq(disk->queue) || queue_emulates_zone_append(disk->queue); } static int disk_revalidate_zone_resources(struct gendisk *disk, unsigned int nr_zones) { struct queue_limits *lim = &disk->queue->limits; unsigned int pool_size; if (!disk_need_zone_resources(disk)) return 0; /* * If the device has no limit on the maximum number of open and active * zones, use BLK_ZONE_WPLUG_DEFAULT_POOL_SIZE. */ pool_size = max(lim->max_open_zones, lim->max_active_zones); if (!pool_size) pool_size = min(BLK_ZONE_WPLUG_DEFAULT_POOL_SIZE, nr_zones); if (!disk->zone_wplugs_hash) return disk_alloc_zone_resources(disk, pool_size); return 0; } struct blk_revalidate_zone_args { struct gendisk *disk; unsigned long *conv_zones_bitmap; unsigned int nr_zones; unsigned int zone_capacity; unsigned int last_zone_capacity; sector_t sector; }; /* * Update the disk zone resources information and device queue limits. * The disk queue is frozen when this is executed. */ static int disk_update_zone_resources(struct gendisk *disk, struct blk_revalidate_zone_args *args) { struct request_queue *q = disk->queue; unsigned int nr_seq_zones, nr_conv_zones; unsigned int pool_size; struct queue_limits lim; int ret; disk->nr_zones = args->nr_zones; disk->zone_capacity = args->zone_capacity; disk->last_zone_capacity = args->last_zone_capacity; nr_conv_zones = disk_set_conv_zones_bitmap(disk, args->conv_zones_bitmap); if (nr_conv_zones >= disk->nr_zones) { pr_warn("%s: Invalid number of conventional zones %u / %u\n", disk->disk_name, nr_conv_zones, disk->nr_zones); return -ENODEV; } lim = queue_limits_start_update(q); /* * Some devices can advertize zone resource limits that are larger than * the number of sequential zones of the zoned block device, e.g. a * small ZNS namespace. For such case, assume that the zoned device has * no zone resource limits. */ nr_seq_zones = disk->nr_zones - nr_conv_zones; if (lim.max_open_zones >= nr_seq_zones) lim.max_open_zones = 0; if (lim.max_active_zones >= nr_seq_zones) lim.max_active_zones = 0; if (!disk->zone_wplugs_pool) goto commit; /* * If the device has no limit on the maximum number of open and active * zones, set its max open zone limit to the mempool size to indicate * to the user that there is a potential performance impact due to * dynamic zone write plug allocation when simultaneously writing to * more zones than the size of the mempool. */ pool_size = max(lim.max_open_zones, lim.max_active_zones); if (!pool_size) pool_size = min(BLK_ZONE_WPLUG_DEFAULT_POOL_SIZE, nr_seq_zones); mempool_resize(disk->zone_wplugs_pool, pool_size); if (!lim.max_open_zones && !lim.max_active_zones) { if (pool_size < nr_seq_zones) lim.max_open_zones = pool_size; else lim.max_open_zones = 0; } commit: blk_mq_freeze_queue(q); ret = queue_limits_commit_update(q, &lim); blk_mq_unfreeze_queue(q); return ret; } static int blk_revalidate_conv_zone(struct blk_zone *zone, unsigned int idx, struct blk_revalidate_zone_args *args) { struct gendisk *disk = args->disk; if (zone->capacity != zone->len) { pr_warn("%s: Invalid conventional zone capacity\n", disk->disk_name); return -ENODEV; } if (disk_zone_is_last(disk, zone)) args->last_zone_capacity = zone->capacity; if (!disk_need_zone_resources(disk)) return 0; if (!args->conv_zones_bitmap) { args->conv_zones_bitmap = bitmap_zalloc(args->nr_zones, GFP_NOIO); if (!args->conv_zones_bitmap) return -ENOMEM; } set_bit(idx, args->conv_zones_bitmap); return 0; } static int blk_revalidate_seq_zone(struct blk_zone *zone, unsigned int idx, struct blk_revalidate_zone_args *args) { struct gendisk *disk = args->disk; struct blk_zone_wplug *zwplug; unsigned int wp_offset; unsigned long flags; /* * Remember the capacity of the first sequential zone and check * if it is constant for all zones, ignoring the last zone as it can be * smaller. */ if (!args->zone_capacity) args->zone_capacity = zone->capacity; if (disk_zone_is_last(disk, zone)) { args->last_zone_capacity = zone->capacity; } else if (zone->capacity != args->zone_capacity) { pr_warn("%s: Invalid variable zone capacity\n", disk->disk_name); return -ENODEV; } /* * We need to track the write pointer of all zones that are not * empty nor full. So make sure we have a zone write plug for * such zone if the device has a zone write plug hash table. */ if (!disk->zone_wplugs_hash) return 0; wp_offset = blk_zone_wp_offset(zone); if (!wp_offset || wp_offset >= zone->capacity) return 0; zwplug = disk_get_and_lock_zone_wplug(disk, zone->wp, GFP_NOIO, &flags); if (!zwplug) return -ENOMEM; spin_unlock_irqrestore(&zwplug->lock, flags); disk_put_zone_wplug(zwplug); return 0; } /* * Helper function to check the validity of zones of a zoned block device. */ static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx, void *data) { struct blk_revalidate_zone_args *args = data; struct gendisk *disk = args->disk; sector_t zone_sectors = disk->queue->limits.chunk_sectors; int ret; /* Check for bad zones and holes in the zone report */ if (zone->start != args->sector) { pr_warn("%s: Zone gap at sectors %llu..%llu\n", disk->disk_name, args->sector, zone->start); return -ENODEV; } if (zone->start >= get_capacity(disk) || !zone->len) { pr_warn("%s: Invalid zone start %llu, length %llu\n", disk->disk_name, zone->start, zone->len); return -ENODEV; } /* * All zones must have the same size, with the exception on an eventual * smaller last zone. */ if (!disk_zone_is_last(disk, zone)) { if (zone->len != zone_sectors) { pr_warn("%s: Invalid zoned device with non constant zone size\n", disk->disk_name); return -ENODEV; } } else if (zone->len > zone_sectors) { pr_warn("%s: Invalid zoned device with larger last zone size\n", disk->disk_name); return -ENODEV; } if (!zone->capacity || zone->capacity > zone->len) { pr_warn("%s: Invalid zone capacity\n", disk->disk_name); return -ENODEV; } /* Check zone type */ switch (zone->type) { case BLK_ZONE_TYPE_CONVENTIONAL: ret = blk_revalidate_conv_zone(zone, idx, args); break; case BLK_ZONE_TYPE_SEQWRITE_REQ: ret = blk_revalidate_seq_zone(zone, idx, args); break; case BLK_ZONE_TYPE_SEQWRITE_PREF: default: pr_warn("%s: Invalid zone type 0x%x at sectors %llu\n", disk->disk_name, (int)zone->type, zone->start); ret = -ENODEV; } if (!ret) args->sector += zone->len; return ret; } /** * blk_revalidate_disk_zones - (re)allocate and initialize zone write plugs * @disk: Target disk * * Helper function for low-level device drivers to check, (re) allocate and * initialize resources used for managing zoned disks. This function should * normally be called by blk-mq based drivers when a zoned gendisk is probed * and when the zone configuration of the gendisk changes (e.g. after a format). * Before calling this function, the device driver must already have set the * device zone size (chunk_sector limit) and the max zone append limit. * BIO based drivers can also use this function as long as the device queue * can be safely frozen. */ int blk_revalidate_disk_zones(struct gendisk *disk) { struct request_queue *q = disk->queue; sector_t zone_sectors = q->limits.chunk_sectors; sector_t capacity = get_capacity(disk); struct blk_revalidate_zone_args args = { }; unsigned int noio_flag; int ret = -ENOMEM; if (WARN_ON_ONCE(!blk_queue_is_zoned(q))) return -EIO; if (!capacity) return -ENODEV; /* * Checks that the device driver indicated a valid zone size and that * the max zone append limit is set. */ if (!zone_sectors || !is_power_of_2(zone_sectors)) { pr_warn("%s: Invalid non power of two zone size (%llu)\n", disk->disk_name, zone_sectors); return -ENODEV; } /* * Ensure that all memory allocations in this context are done as if * GFP_NOIO was specified. */ args.disk = disk; args.nr_zones = (capacity + zone_sectors - 1) >> ilog2(zone_sectors); noio_flag = memalloc_noio_save(); ret = disk_revalidate_zone_resources(disk, args.nr_zones); if (ret) { memalloc_noio_restore(noio_flag); return ret; } ret = disk->fops->report_zones(disk, 0, UINT_MAX, blk_revalidate_zone_cb, &args); if (!ret) { pr_warn("%s: No zones reported\n", disk->disk_name); ret = -ENODEV; } memalloc_noio_restore(noio_flag); /* * If zones where reported, make sure that the entire disk capacity * has been checked. */ if (ret > 0 && args.sector != capacity) { pr_warn("%s: Missing zones from sector %llu\n", disk->disk_name, args.sector); ret = -ENODEV; } /* * Set the new disk zone parameters only once the queue is frozen and * all I/Os are completed. */ if (ret > 0) ret = disk_update_zone_resources(disk, &args); else pr_warn("%s: failed to revalidate zones\n", disk->disk_name); if (ret) { blk_mq_freeze_queue(q); disk_free_zone_resources(disk); blk_mq_unfreeze_queue(q); } return ret; } EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones); #ifdef CONFIG_BLK_DEBUG_FS int queue_zone_wplugs_show(void *data, struct seq_file *m) { struct request_queue *q = data; struct gendisk *disk = q->disk; struct blk_zone_wplug *zwplug; unsigned int zwp_wp_offset, zwp_flags; unsigned int zwp_zone_no, zwp_ref; unsigned int zwp_bio_list_size, i; unsigned long flags; if (!disk->zone_wplugs_hash) return 0; rcu_read_lock(); for (i = 0; i < disk_zone_wplugs_hash_size(disk); i++) { hlist_for_each_entry_rcu(zwplug, &disk->zone_wplugs_hash[i], node) { spin_lock_irqsave(&zwplug->lock, flags); zwp_zone_no = zwplug->zone_no; zwp_flags = zwplug->flags; zwp_ref = refcount_read(&zwplug->ref); zwp_wp_offset = zwplug->wp_offset; zwp_bio_list_size = bio_list_size(&zwplug->bio_list); spin_unlock_irqrestore(&zwplug->lock, flags); seq_printf(m, "%u 0x%x %u %u %u\n", zwp_zone_no, zwp_flags, zwp_ref, zwp_wp_offset, zwp_bio_list_size); } } rcu_read_unlock(); return 0; } #endif |
| 22 22 21 22 22 114 111 112 112 112 112 791 790 131 135 132 135 128 135 30 114 113 110 21 22 22 91 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/fs-writeback.c * * Copyright (C) 2002, Linus Torvalds. * * Contains all the functions related to writing back and waiting * upon dirty inodes against superblocks, and writing back dirty * pages against inodes. ie: data writeback. Writeout of the * inode itself is not handled here. * * 10Apr2002 Andrew Morton * Split out of fs/inode.c * Additions for address_space-based writeback */ #include <linux/kernel.h> #include <linux/export.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/kthread.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/tracepoint.h> #include <linux/device.h> #include <linux/memcontrol.h> #include "internal.h" /* * 4MB minimal write chunk size */ #define MIN_WRITEBACK_PAGES (4096UL >> (PAGE_SHIFT - 10)) /* * Passed into wb_writeback(), essentially a subset of writeback_control */ struct wb_writeback_work { long nr_pages; struct super_block *sb; enum writeback_sync_modes sync_mode; unsigned int tagged_writepages:1; unsigned int for_kupdate:1; unsigned int range_cyclic:1; unsigned int for_background:1; unsigned int for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ unsigned int auto_free:1; /* free on completion */ enum wb_reason reason; /* why was writeback initiated? */ struct list_head list; /* pending work list */ struct wb_completion *done; /* set if the caller waits */ }; /* * If an inode is constantly having its pages dirtied, but then the * updates stop dirtytime_expire_interval seconds in the past, it's * possible for the worst case time between when an inode has its * timestamps updated and when they finally get written out to be two * dirtytime_expire_intervals. We set the default to 12 hours (in * seconds), which means most of the time inodes will have their * timestamps written to disk after 12 hours, but in the worst case a * few inodes might not their timestamps updated for 24 hours. */ unsigned int dirtytime_expire_interval = 12 * 60 * 60; static inline struct inode *wb_inode(struct list_head *head) { return list_entry(head, struct inode, i_io_list); } /* * Include the creation of the trace points after defining the * wb_writeback_work structure and inline functions so that the definition * remains local to this file. */ #define CREATE_TRACE_POINTS #include <trace/events/writeback.h> EXPORT_TRACEPOINT_SYMBOL_GPL(wbc_writepage); static bool wb_io_lists_populated(struct bdi_writeback *wb) { if (wb_has_dirty_io(wb)) { return false; } else { set_bit(WB_has_dirty_io, &wb->state); WARN_ON_ONCE(!wb->avg_write_bandwidth); atomic_long_add(wb->avg_write_bandwidth, &wb->bdi->tot_write_bandwidth); return true; } } static void wb_io_lists_depopulated(struct bdi_writeback *wb) { if (wb_has_dirty_io(wb) && list_empty(&wb->b_dirty) && list_empty(&wb->b_io) && list_empty(&wb->b_more_io)) { clear_bit(WB_has_dirty_io, &wb->state); WARN_ON_ONCE(atomic_long_sub_return(wb->avg_write_bandwidth, &wb->bdi->tot_write_bandwidth) < 0); } } /** * inode_io_list_move_locked - move an inode onto a bdi_writeback IO list * @inode: inode to be moved * @wb: target bdi_writeback * @head: one of @wb->b_{dirty|io|more_io|dirty_time} * * Move @inode->i_io_list to @list of @wb and set %WB_has_dirty_io. * Returns %true if @inode is the first occupant of the !dirty_time IO * lists; otherwise, %false. */ static bool inode_io_list_move_locked(struct inode *inode, struct bdi_writeback *wb, struct list_head *head) { assert_spin_locked(&wb->list_lock); assert_spin_locked(&inode->i_lock); WARN_ON_ONCE(inode->i_state & I_FREEING); list_move(&inode->i_io_list, head); /* dirty_time doesn't count as dirty_io until expiration */ if (head != &wb->b_dirty_time) return wb_io_lists_populated(wb); wb_io_lists_depopulated(wb); return false; } static void wb_wakeup(struct bdi_writeback *wb) { spin_lock_irq(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) mod_delayed_work(bdi_wq, &wb->dwork, 0); spin_unlock_irq(&wb->work_lock); } /* * This function is used when the first inode for this wb is marked dirty. It * wakes-up the corresponding bdi thread which should then take care of the * periodic background write-out of dirty inodes. Since the write-out would * starts only 'dirty_writeback_interval' centisecs from now anyway, we just * set up a timer which wakes the bdi thread up later. * * Note, we wouldn't bother setting up the timer, but this function is on the * fast-path (used by '__mark_inode_dirty()'), so we save few context switches * by delaying the wake-up. * * We have to be careful not to postpone flush work if it is scheduled for * earlier. Thus we use queue_delayed_work(). */ static void wb_wakeup_delayed(struct bdi_writeback *wb) { unsigned long timeout; timeout = msecs_to_jiffies(dirty_writeback_interval * 10); spin_lock_irq(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) queue_delayed_work(bdi_wq, &wb->dwork, timeout); spin_unlock_irq(&wb->work_lock); } static void finish_writeback_work(struct wb_writeback_work *work) { struct wb_completion *done = work->done; if (work->auto_free) kfree(work); if (done) { wait_queue_head_t *waitq = done->waitq; /* @done can't be accessed after the following dec */ if (atomic_dec_and_test(&done->cnt)) wake_up_all(waitq); } } static void wb_queue_work(struct bdi_writeback *wb, struct wb_writeback_work *work) { trace_writeback_queue(wb, work); if (work->done) atomic_inc(&work->done->cnt); spin_lock_irq(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) { list_add_tail(&work->list, &wb->work_list); mod_delayed_work(bdi_wq, &wb->dwork, 0); } else finish_writeback_work(work); spin_unlock_irq(&wb->work_lock); } /** * wb_wait_for_completion - wait for completion of bdi_writeback_works * @done: target wb_completion * * Wait for one or more work items issued to @bdi with their ->done field * set to @done, which should have been initialized with * DEFINE_WB_COMPLETION(). This function returns after all such work items * are completed. Work items which are waited upon aren't freed * automatically on completion. */ void wb_wait_for_completion(struct wb_completion *done) { atomic_dec(&done->cnt); /* put down the initial count */ wait_event(*done->waitq, !atomic_read(&done->cnt)); } #ifdef CONFIG_CGROUP_WRITEBACK /* * Parameters for foreign inode detection, see wbc_detach_inode() to see * how they're used. * * These paramters are inherently heuristical as the detection target * itself is fuzzy. All we want to do is detaching an inode from the * current owner if it's being written to by some other cgroups too much. * * The current cgroup writeback is built on the assumption that multiple * cgroups writing to the same inode concurrently is very rare and a mode * of operation which isn't well supported. As such, the goal is not * taking too long when a different cgroup takes over an inode while * avoiding too aggressive flip-flops from occasional foreign writes. * * We record, very roughly, 2s worth of IO time history and if more than * half of that is foreign, trigger the switch. The recording is quantized * to 16 slots. To avoid tiny writes from swinging the decision too much, * writes smaller than 1/8 of avg size are ignored. */ #define WB_FRN_TIME_SHIFT 13 /* 1s = 2^13, upto 8 secs w/ 16bit */ #define WB_FRN_TIME_AVG_SHIFT 3 /* avg = avg * 7/8 + new * 1/8 */ #define WB_FRN_TIME_CUT_DIV 8 /* ignore rounds < avg / 8 */ #define WB_FRN_TIME_PERIOD (2 * (1 << WB_FRN_TIME_SHIFT)) /* 2s */ #define WB_FRN_HIST_SLOTS 16 /* inode->i_wb_frn_history is 16bit */ #define WB_FRN_HIST_UNIT (WB_FRN_TIME_PERIOD / WB_FRN_HIST_SLOTS) /* each slot's duration is 2s / 16 */ #define WB_FRN_HIST_THR_SLOTS (WB_FRN_HIST_SLOTS / 2) /* if foreign slots >= 8, switch */ #define WB_FRN_HIST_MAX_SLOTS (WB_FRN_HIST_THR_SLOTS / 2 + 1) /* one round can affect upto 5 slots */ #define WB_FRN_MAX_IN_FLIGHT 1024 /* don't queue too many concurrently */ /* * Maximum inodes per isw. A specific value has been chosen to make * struct inode_switch_wbs_context fit into 1024 bytes kmalloc. */ #define WB_MAX_INODES_PER_ISW ((1024UL - sizeof(struct inode_switch_wbs_context)) \ / sizeof(struct inode *)) static atomic_t isw_nr_in_flight = ATOMIC_INIT(0); static struct workqueue_struct *isw_wq; void __inode_attach_wb(struct inode *inode, struct folio *folio) { struct backing_dev_info *bdi = inode_to_bdi(inode); struct bdi_writeback *wb = NULL; if (inode_cgwb_enabled(inode)) { struct cgroup_subsys_state *memcg_css; if (folio) { memcg_css = mem_cgroup_css_from_folio(folio); wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); } else { /* must pin memcg_css, see wb_get_create() */ memcg_css = task_get_css(current, memory_cgrp_id); wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); css_put(memcg_css); } } if (!wb) wb = &bdi->wb; /* * There may be multiple instances of this function racing to * update the same inode. Use cmpxchg() to tell the winner. */ if (unlikely(cmpxchg(&inode->i_wb, NULL, wb))) wb_put(wb); } /** * inode_cgwb_move_to_attached - put the inode onto wb->b_attached list * @inode: inode of interest with i_lock held * @wb: target bdi_writeback * * Remove the inode from wb's io lists and if necessarily put onto b_attached * list. Only inodes attached to cgwb's are kept on this list. */ static void inode_cgwb_move_to_attached(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&wb->list_lock); assert_spin_locked(&inode->i_lock); WARN_ON_ONCE(inode->i_state & I_FREEING); inode->i_state &= ~I_SYNC_QUEUED; if (wb != &wb->bdi->wb) list_move(&inode->i_io_list, &wb->b_attached); else list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); } /** * locked_inode_to_wb_and_lock_list - determine a locked inode's wb and lock it * @inode: inode of interest with i_lock held * * Returns @inode's wb with its list_lock held. @inode->i_lock must be * held on entry and is released on return. The returned wb is guaranteed * to stay @inode's associated wb until its list_lock is released. */ static struct bdi_writeback * locked_inode_to_wb_and_lock_list(struct inode *inode) __releases(&inode->i_lock) __acquires(&wb->list_lock) { while (true) { struct bdi_writeback *wb = inode_to_wb(inode); /* * inode_to_wb() association is protected by both * @inode->i_lock and @wb->list_lock but list_lock nests * outside i_lock. Drop i_lock and verify that the * association hasn't changed after acquiring list_lock. */ wb_get(wb); spin_unlock(&inode->i_lock); spin_lock(&wb->list_lock); /* i_wb may have changed inbetween, can't use inode_to_wb() */ if (likely(wb == inode->i_wb)) { wb_put(wb); /* @inode already has ref */ return wb; } spin_unlock(&wb->list_lock); wb_put(wb); cpu_relax(); spin_lock(&inode->i_lock); } } /** * inode_to_wb_and_lock_list - determine an inode's wb and lock it * @inode: inode of interest * * Same as locked_inode_to_wb_and_lock_list() but @inode->i_lock isn't held * on entry. */ static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode) __acquires(&wb->list_lock) { spin_lock(&inode->i_lock); return locked_inode_to_wb_and_lock_list(inode); } struct inode_switch_wbs_context { struct rcu_work work; /* * Multiple inodes can be switched at once. The switching procedure * consists of two parts, separated by a RCU grace period. To make * sure that the second part is executed for each inode gone through * the first part, all inode pointers are placed into a NULL-terminated * array embedded into struct inode_switch_wbs_context. Otherwise * an inode could be left in a non-consistent state. */ struct bdi_writeback *new_wb; struct inode *inodes[]; }; static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { down_write(&bdi->wb_switch_rwsem); } static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { up_write(&bdi->wb_switch_rwsem); } static bool inode_do_switch_wbs(struct inode *inode, struct bdi_writeback *old_wb, struct bdi_writeback *new_wb) { struct address_space *mapping = inode->i_mapping; XA_STATE(xas, &mapping->i_pages, 0); struct folio *folio; bool switched = false; spin_lock(&inode->i_lock); xa_lock_irq(&mapping->i_pages); /* * Once I_FREEING or I_WILL_FREE are visible under i_lock, the eviction * path owns the inode and we shouldn't modify ->i_io_list. */ if (unlikely(inode->i_state & (I_FREEING | I_WILL_FREE))) goto skip_switch; trace_inode_switch_wbs(inode, old_wb, new_wb); /* * Count and transfer stats. Note that PAGECACHE_TAG_DIRTY points * to possibly dirty folios while PAGECACHE_TAG_WRITEBACK points to * folios actually under writeback. */ xas_for_each_marked(&xas, folio, ULONG_MAX, PAGECACHE_TAG_DIRTY) { if (folio_test_dirty(folio)) { long nr = folio_nr_pages(folio); wb_stat_mod(old_wb, WB_RECLAIMABLE, -nr); wb_stat_mod(new_wb, WB_RECLAIMABLE, nr); } } xas_set(&xas, 0); xas_for_each_marked(&xas, folio, ULONG_MAX, PAGECACHE_TAG_WRITEBACK) { long nr = folio_nr_pages(folio); WARN_ON_ONCE(!folio_test_writeback(folio)); wb_stat_mod(old_wb, WB_WRITEBACK, -nr); wb_stat_mod(new_wb, WB_WRITEBACK, nr); } if (mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) { atomic_dec(&old_wb->writeback_inodes); atomic_inc(&new_wb->writeback_inodes); } wb_get(new_wb); /* * Transfer to @new_wb's IO list if necessary. If the @inode is dirty, * the specific list @inode was on is ignored and the @inode is put on * ->b_dirty which is always correct including from ->b_dirty_time. * The transfer preserves @inode->dirtied_when ordering. If the @inode * was clean, it means it was on the b_attached list, so move it onto * the b_attached list of @new_wb. */ if (!list_empty(&inode->i_io_list)) { inode->i_wb = new_wb; if (inode->i_state & I_DIRTY_ALL) { struct inode *pos; list_for_each_entry(pos, &new_wb->b_dirty, i_io_list) if (time_after_eq(inode->dirtied_when, pos->dirtied_when)) break; inode_io_list_move_locked(inode, new_wb, pos->i_io_list.prev); } else { inode_cgwb_move_to_attached(inode, new_wb); } } else { inode->i_wb = new_wb; } /* ->i_wb_frn updates may race wbc_detach_inode() but doesn't matter */ inode->i_wb_frn_winner = 0; inode->i_wb_frn_avg_time = 0; inode->i_wb_frn_history = 0; switched = true; skip_switch: /* * Paired with load_acquire in unlocked_inode_to_wb_begin() and * ensures that the new wb is visible if they see !I_WB_SWITCH. */ smp_store_release(&inode->i_state, inode->i_state & ~I_WB_SWITCH); xa_unlock_irq(&mapping->i_pages); spin_unlock(&inode->i_lock); return switched; } static void inode_switch_wbs_work_fn(struct work_struct *work) { struct inode_switch_wbs_context *isw = container_of(to_rcu_work(work), struct inode_switch_wbs_context, work); struct backing_dev_info *bdi = inode_to_bdi(isw->inodes[0]); struct bdi_writeback *old_wb = isw->inodes[0]->i_wb; struct bdi_writeback *new_wb = isw->new_wb; unsigned long nr_switched = 0; struct inode **inodep; /* * If @inode switches cgwb membership while sync_inodes_sb() is * being issued, sync_inodes_sb() might miss it. Synchronize. */ down_read(&bdi->wb_switch_rwsem); /* * By the time control reaches here, RCU grace period has passed * since I_WB_SWITCH assertion and all wb stat update transactions * between unlocked_inode_to_wb_begin/end() are guaranteed to be * synchronizing against the i_pages lock. * * Grabbing old_wb->list_lock, inode->i_lock and the i_pages lock * gives us exclusion against all wb related operations on @inode * including IO list manipulations and stat updates. */ if (old_wb < new_wb) { spin_lock(&old_wb->list_lock); spin_lock_nested(&new_wb->list_lock, SINGLE_DEPTH_NESTING); } else { spin_lock(&new_wb->list_lock); spin_lock_nested(&old_wb->list_lock, SINGLE_DEPTH_NESTING); } for (inodep = isw->inodes; *inodep; inodep++) { WARN_ON_ONCE((*inodep)->i_wb != old_wb); if (inode_do_switch_wbs(*inodep, old_wb, new_wb)) nr_switched++; } spin_unlock(&new_wb->list_lock); spin_unlock(&old_wb->list_lock); up_read(&bdi->wb_switch_rwsem); if (nr_switched) { wb_wakeup(new_wb); wb_put_many(old_wb, nr_switched); } for (inodep = isw->inodes; *inodep; inodep++) iput(*inodep); wb_put(new_wb); kfree(isw); atomic_dec(&isw_nr_in_flight); } static bool inode_prepare_wbs_switch(struct inode *inode, struct bdi_writeback *new_wb) { /* * Paired with smp_mb() in cgroup_writeback_umount(). * isw_nr_in_flight must be increased before checking SB_ACTIVE and * grabbing an inode, otherwise isw_nr_in_flight can be observed as 0 * in cgroup_writeback_umount() and the isw_wq will be not flushed. */ smp_mb(); if (IS_DAX(inode)) return false; /* while holding I_WB_SWITCH, no one else can update the association */ spin_lock(&inode->i_lock); if (!(inode->i_sb->s_flags & SB_ACTIVE) || inode->i_state & (I_WB_SWITCH | I_FREEING | I_WILL_FREE) || inode_to_wb(inode) == new_wb) { spin_unlock(&inode->i_lock); return false; } inode->i_state |= I_WB_SWITCH; __iget(inode); spin_unlock(&inode->i_lock); return true; } /** * inode_switch_wbs - change the wb association of an inode * @inode: target inode * @new_wb_id: ID of the new wb * * Switch @inode's wb association to the wb identified by @new_wb_id. The * switching is performed asynchronously and may fail silently. */ static void inode_switch_wbs(struct inode *inode, int new_wb_id) { struct backing_dev_info *bdi = inode_to_bdi(inode); struct cgroup_subsys_state *memcg_css; struct inode_switch_wbs_context *isw; /* noop if seems to be already in progress */ if (inode->i_state & I_WB_SWITCH) return; /* avoid queueing a new switch if too many are already in flight */ if (atomic_read(&isw_nr_in_flight) > WB_FRN_MAX_IN_FLIGHT) return; isw = kzalloc(struct_size(isw, inodes, 2), GFP_ATOMIC); if (!isw) return; atomic_inc(&isw_nr_in_flight); /* find and pin the new wb */ rcu_read_lock(); memcg_css = css_from_id(new_wb_id, &memory_cgrp_subsys); if (memcg_css && !css_tryget(memcg_css)) memcg_css = NULL; rcu_read_unlock(); if (!memcg_css) goto out_free; isw->new_wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); css_put(memcg_css); if (!isw->new_wb) goto out_free; if (!inode_prepare_wbs_switch(inode, isw->new_wb)) goto out_free; isw->inodes[0] = inode; /* * In addition to synchronizing among switchers, I_WB_SWITCH tells * the RCU protected stat update paths to grab the i_page * lock so that stat transfer can synchronize against them. * Let's continue after I_WB_SWITCH is guaranteed to be visible. */ INIT_RCU_WORK(&isw->work, inode_switch_wbs_work_fn); queue_rcu_work(isw_wq, &isw->work); return; out_free: atomic_dec(&isw_nr_in_flight); if (isw->new_wb) wb_put(isw->new_wb); kfree(isw); } static bool isw_prepare_wbs_switch(struct inode_switch_wbs_context *isw, struct list_head *list, int *nr) { struct inode *inode; list_for_each_entry(inode, list, i_io_list) { if (!inode_prepare_wbs_switch(inode, isw->new_wb)) continue; isw->inodes[*nr] = inode; (*nr)++; if (*nr >= WB_MAX_INODES_PER_ISW - 1) return true; } return false; } /** * cleanup_offline_cgwb - detach associated inodes * @wb: target wb * * Switch all inodes attached to @wb to a nearest living ancestor's wb in order * to eventually release the dying @wb. Returns %true if not all inodes were * switched and the function has to be restarted. */ bool cleanup_offline_cgwb(struct bdi_writeback *wb) { struct cgroup_subsys_state *memcg_css; struct inode_switch_wbs_context *isw; int nr; bool restart = false; isw = kzalloc(struct_size(isw, inodes, WB_MAX_INODES_PER_ISW), GFP_KERNEL); if (!isw) return restart; atomic_inc(&isw_nr_in_flight); for (memcg_css = wb->memcg_css->parent; memcg_css; memcg_css = memcg_css->parent) { isw->new_wb = wb_get_create(wb->bdi, memcg_css, GFP_KERNEL); if (isw->new_wb) break; } if (unlikely(!isw->new_wb)) isw->new_wb = &wb->bdi->wb; /* wb_get() is noop for bdi's wb */ nr = 0; spin_lock(&wb->list_lock); /* * In addition to the inodes that have completed writeback, also switch * cgwbs for those inodes only with dirty timestamps. Otherwise, those * inodes won't be written back for a long time when lazytime is * enabled, and thus pinning the dying cgwbs. It won't break the * bandwidth restrictions, as writeback of inode metadata is not * accounted for. */ restart = isw_prepare_wbs_switch(isw, &wb->b_attached, &nr); if (!restart) restart = isw_prepare_wbs_switch(isw, &wb->b_dirty_time, &nr); spin_unlock(&wb->list_lock); /* no attached inodes? bail out */ if (nr == 0) { atomic_dec(&isw_nr_in_flight); wb_put(isw->new_wb); kfree(isw); return restart; } /* * In addition to synchronizing among switchers, I_WB_SWITCH tells * the RCU protected stat update paths to grab the i_page * lock so that stat transfer can synchronize against them. * Let's continue after I_WB_SWITCH is guaranteed to be visible. */ INIT_RCU_WORK(&isw->work, inode_switch_wbs_work_fn); queue_rcu_work(isw_wq, &isw->work); return restart; } /** * wbc_attach_and_unlock_inode - associate wbc with target inode and unlock it * @wbc: writeback_control of interest * @inode: target inode * * @inode is locked and about to be written back under the control of @wbc. * Record @inode's writeback context into @wbc and unlock the i_lock. On * writeback completion, wbc_detach_inode() should be called. This is used * to track the cgroup writeback context. */ static void wbc_attach_and_unlock_inode(struct writeback_control *wbc, struct inode *inode) __releases(&inode->i_lock) { if (!inode_cgwb_enabled(inode)) { spin_unlock(&inode->i_lock); return; } wbc->wb = inode_to_wb(inode); wbc->inode = inode; wbc->wb_id = wbc->wb->memcg_css->id; wbc->wb_lcand_id = inode->i_wb_frn_winner; wbc->wb_tcand_id = 0; wbc->wb_bytes = 0; wbc->wb_lcand_bytes = 0; wbc->wb_tcand_bytes = 0; wb_get(wbc->wb); spin_unlock(&inode->i_lock); /* * A dying wb indicates that either the blkcg associated with the * memcg changed or the associated memcg is dying. In the first * case, a replacement wb should already be available and we should * refresh the wb immediately. In the second case, trying to * refresh will keep failing. */ if (unlikely(wb_dying(wbc->wb) && !css_is_dying(wbc->wb->memcg_css))) inode_switch_wbs(inode, wbc->wb_id); } /** * wbc_attach_fdatawrite_inode - associate wbc and inode for fdatawrite * @wbc: writeback_control of interest * @inode: target inode * * This function is to be used by __filemap_fdatawrite_range(), which is an * alternative entry point into writeback code, and first ensures @inode is * associated with a bdi_writeback and attaches it to @wbc. */ void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, struct inode *inode) { spin_lock(&inode->i_lock); inode_attach_wb(inode, NULL); wbc_attach_and_unlock_inode(wbc, inode); } EXPORT_SYMBOL_GPL(wbc_attach_fdatawrite_inode); /** * wbc_detach_inode - disassociate wbc from inode and perform foreign detection * @wbc: writeback_control of the just finished writeback * * To be called after a writeback attempt of an inode finishes and undoes * wbc_attach_and_unlock_inode(). Can be called under any context. * * As concurrent write sharing of an inode is expected to be very rare and * memcg only tracks page ownership on first-use basis severely confining * the usefulness of such sharing, cgroup writeback tracks ownership * per-inode. While the support for concurrent write sharing of an inode * is deemed unnecessary, an inode being written to by different cgroups at * different points in time is a lot more common, and, more importantly, * charging only by first-use can too readily lead to grossly incorrect * behaviors (single foreign page can lead to gigabytes of writeback to be * incorrectly attributed). * * To resolve this issue, cgroup writeback detects the majority dirtier of * an inode and transfers the ownership to it. To avoid unnecessary * oscillation, the detection mechanism keeps track of history and gives * out the switch verdict only if the foreign usage pattern is stable over * a certain amount of time and/or writeback attempts. * * On each writeback attempt, @wbc tries to detect the majority writer * using Boyer-Moore majority vote algorithm. In addition to the byte * count from the majority voting, it also counts the bytes written for the * current wb and the last round's winner wb (max of last round's current * wb, the winner from two rounds ago, and the last round's majority * candidate). Keeping track of the historical winner helps the algorithm * to semi-reliably detect the most active writer even when it's not the * absolute majority. * * Once the winner of the round is determined, whether the winner is * foreign or not and how much IO time the round consumed is recorded in * inode->i_wb_frn_history. If the amount of recorded foreign IO time is * over a certain threshold, the switch verdict is given. */ void wbc_detach_inode(struct writeback_control *wbc) { struct bdi_writeback *wb = wbc->wb; struct inode *inode = wbc->inode; unsigned long avg_time, max_bytes, max_time; u16 history; int max_id; if (!wb) return; history = inode->i_wb_frn_history; avg_time = inode->i_wb_frn_avg_time; /* pick the winner of this round */ if (wbc->wb_bytes >= wbc->wb_lcand_bytes && wbc->wb_bytes >= wbc->wb_tcand_bytes) { max_id = wbc->wb_id; max_bytes = wbc->wb_bytes; } else if (wbc->wb_lcand_bytes >= wbc->wb_tcand_bytes) { max_id = wbc->wb_lcand_id; max_bytes = wbc->wb_lcand_bytes; } else { max_id = wbc->wb_tcand_id; max_bytes = wbc->wb_tcand_bytes; } /* * Calculate the amount of IO time the winner consumed and fold it * into the running average kept per inode. If the consumed IO * time is lower than avag / WB_FRN_TIME_CUT_DIV, ignore it for * deciding whether to switch or not. This is to prevent one-off * small dirtiers from skewing the verdict. */ max_time = DIV_ROUND_UP((max_bytes >> PAGE_SHIFT) << WB_FRN_TIME_SHIFT, wb->avg_write_bandwidth); if (avg_time) avg_time += (max_time >> WB_FRN_TIME_AVG_SHIFT) - (avg_time >> WB_FRN_TIME_AVG_SHIFT); else avg_time = max_time; /* immediate catch up on first run */ if (max_time >= avg_time / WB_FRN_TIME_CUT_DIV) { int slots; /* * The switch verdict is reached if foreign wb's consume * more than a certain proportion of IO time in a * WB_FRN_TIME_PERIOD. This is loosely tracked by 16 slot * history mask where each bit represents one sixteenth of * the period. Determine the number of slots to shift into * history from @max_time. */ slots = min(DIV_ROUND_UP(max_time, WB_FRN_HIST_UNIT), (unsigned long)WB_FRN_HIST_MAX_SLOTS); history <<= slots; if (wbc->wb_id != max_id) history |= (1U << slots) - 1; if (history) trace_inode_foreign_history(inode, wbc, history); /* * Switch if the current wb isn't the consistent winner. * If there are multiple closely competing dirtiers, the * inode may switch across them repeatedly over time, which * is okay. The main goal is avoiding keeping an inode on * the wrong wb for an extended period of time. */ if (hweight16(history) > WB_FRN_HIST_THR_SLOTS) inode_switch_wbs(inode, max_id); } /* * Multiple instances of this function may race to update the * following fields but we don't mind occassional inaccuracies. */ inode->i_wb_frn_winner = max_id; inode->i_wb_frn_avg_time = min(avg_time, (unsigned long)U16_MAX); inode->i_wb_frn_history = history; wb_put(wbc->wb); wbc->wb = NULL; } EXPORT_SYMBOL_GPL(wbc_detach_inode); /** * wbc_account_cgroup_owner - account writeback to update inode cgroup ownership * @wbc: writeback_control of the writeback in progress * @folio: folio being written out * @bytes: number of bytes being written out * * @bytes from @folio are about to written out during the writeback * controlled by @wbc. Keep the book for foreign inode detection. See * wbc_detach_inode(). */ void wbc_account_cgroup_owner(struct writeback_control *wbc, struct folio *folio, size_t bytes) { struct cgroup_subsys_state *css; int id; /* * pageout() path doesn't attach @wbc to the inode being written * out. This is intentional as we don't want the function to block * behind a slow cgroup. Ultimately, we want pageout() to kick off * regular writeback instead of writing things out itself. */ if (!wbc->wb || wbc->no_cgroup_owner) return; css = mem_cgroup_css_from_folio(folio); /* dead cgroups shouldn't contribute to inode ownership arbitration */ if (!(css->flags & CSS_ONLINE)) return; id = css->id; if (id == wbc->wb_id) { wbc->wb_bytes += bytes; return; } if (id == wbc->wb_lcand_id) wbc->wb_lcand_bytes += bytes; /* Boyer-Moore majority vote algorithm */ if (!wbc->wb_tcand_bytes) wbc->wb_tcand_id = id; if (id == wbc->wb_tcand_id) wbc->wb_tcand_bytes += bytes; else wbc->wb_tcand_bytes -= min(bytes, wbc->wb_tcand_bytes); } EXPORT_SYMBOL_GPL(wbc_account_cgroup_owner); /** * wb_split_bdi_pages - split nr_pages to write according to bandwidth * @wb: target bdi_writeback to split @nr_pages to * @nr_pages: number of pages to write for the whole bdi * * Split @wb's portion of @nr_pages according to @wb's write bandwidth in * relation to the total write bandwidth of all wb's w/ dirty inodes on * @wb->bdi. */ static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages) { unsigned long this_bw = wb->avg_write_bandwidth; unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth); if (nr_pages == LONG_MAX) return LONG_MAX; /* * This may be called on clean wb's and proportional distribution * may not make sense, just use the original @nr_pages in those * cases. In general, we wanna err on the side of writing more. */ if (!tot_bw || this_bw >= tot_bw) return nr_pages; else return DIV_ROUND_UP_ULL((u64)nr_pages * this_bw, tot_bw); } /** * bdi_split_work_to_wbs - split a wb_writeback_work to all wb's of a bdi * @bdi: target backing_dev_info * @base_work: wb_writeback_work to issue * @skip_if_busy: skip wb's which already have writeback in progress * * Split and issue @base_work to all wb's (bdi_writeback's) of @bdi which * have dirty inodes. If @base_work->nr_page isn't %LONG_MAX, it's * distributed to the busy wbs according to each wb's proportion in the * total active write bandwidth of @bdi. */ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, struct wb_writeback_work *base_work, bool skip_if_busy) { struct bdi_writeback *last_wb = NULL; struct bdi_writeback *wb = list_entry(&bdi->wb_list, struct bdi_writeback, bdi_node); might_sleep(); restart: rcu_read_lock(); list_for_each_entry_continue_rcu(wb, &bdi->wb_list, bdi_node) { DEFINE_WB_COMPLETION(fallback_work_done, bdi); struct wb_writeback_work fallback_work; struct wb_writeback_work *work; long nr_pages; if (last_wb) { wb_put(last_wb); last_wb = NULL; } /* SYNC_ALL writes out I_DIRTY_TIME too */ if (!wb_has_dirty_io(wb) && (base_work->sync_mode == WB_SYNC_NONE || list_empty(&wb->b_dirty_time))) continue; if (skip_if_busy && writeback_in_progress(wb)) continue; nr_pages = wb_split_bdi_pages(wb, base_work->nr_pages); work = kmalloc(sizeof(*work), GFP_ATOMIC); if (work) { *work = *base_work; work->nr_pages = nr_pages; work->auto_free = 1; wb_queue_work(wb, work); continue; } /* * If wb_tryget fails, the wb has been shutdown, skip it. * * Pin @wb so that it stays on @bdi->wb_list. This allows * continuing iteration from @wb after dropping and * regrabbing rcu read lock. */ if (!wb_tryget(wb)) continue; /* alloc failed, execute synchronously using on-stack fallback */ work = &fallback_work; *work = *base_work; work->nr_pages = nr_pages; work->auto_free = 0; work->done = &fallback_work_done; wb_queue_work(wb, work); last_wb = wb; rcu_read_unlock(); wb_wait_for_completion(&fallback_work_done); goto restart; } rcu_read_unlock(); if (last_wb) wb_put(last_wb); } /** * cgroup_writeback_by_id - initiate cgroup writeback from bdi and memcg IDs * @bdi_id: target bdi id * @memcg_id: target memcg css id * @reason: reason why some writeback work initiated * @done: target wb_completion * * Initiate flush of the bdi_writeback identified by @bdi_id and @memcg_id * with the specified parameters. */ int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, enum wb_reason reason, struct wb_completion *done) { struct backing_dev_info *bdi; struct cgroup_subsys_state *memcg_css; struct bdi_writeback *wb; struct wb_writeback_work *work; unsigned long dirty; int ret; /* lookup bdi and memcg */ bdi = bdi_get_by_id(bdi_id); if (!bdi) return -ENOENT; rcu_read_lock(); memcg_css = css_from_id(memcg_id, &memory_cgrp_subsys); if (memcg_css && !css_tryget(memcg_css)) memcg_css = NULL; rcu_read_unlock(); if (!memcg_css) { ret = -ENOENT; goto out_bdi_put; } /* * And find the associated wb. If the wb isn't there already * there's nothing to flush, don't create one. */ wb = wb_get_lookup(bdi, memcg_css); if (!wb) { ret = -ENOENT; goto out_css_put; } /* * The caller is attempting to write out most of * the currently dirty pages. Let's take the current dirty page * count and inflate it by 25% which should be large enough to * flush out most dirty pages while avoiding getting livelocked by * concurrent dirtiers. * * BTW the memcg stats are flushed periodically and this is best-effort * estimation, so some potential error is ok. */ dirty = memcg_page_state(mem_cgroup_from_css(memcg_css), NR_FILE_DIRTY); dirty = dirty * 10 / 8; /* issue the writeback work */ work = kzalloc(sizeof(*work), GFP_NOWAIT | __GFP_NOWARN); if (work) { work->nr_pages = dirty; work->sync_mode = WB_SYNC_NONE; work->range_cyclic = 1; work->reason = reason; work->done = done; work->auto_free = 1; wb_queue_work(wb, work); ret = 0; } else { ret = -ENOMEM; } wb_put(wb); out_css_put: css_put(memcg_css); out_bdi_put: bdi_put(bdi); return ret; } /** * cgroup_writeback_umount - flush inode wb switches for umount * @sb: target super_block * * This function is called when a super_block is about to be destroyed and * flushes in-flight inode wb switches. An inode wb switch goes through * RCU and then workqueue, so the two need to be flushed in order to ensure * that all previously scheduled switches are finished. As wb switches are * rare occurrences and synchronize_rcu() can take a while, perform * flushing iff wb switches are in flight. */ void cgroup_writeback_umount(struct super_block *sb) { if (!(sb->s_bdi->capabilities & BDI_CAP_WRITEBACK)) return; /* * SB_ACTIVE should be reliably cleared before checking * isw_nr_in_flight, see generic_shutdown_super(). */ smp_mb(); if (atomic_read(&isw_nr_in_flight)) { /* * Use rcu_barrier() to wait for all pending callbacks to * ensure that all in-flight wb switches are in the workqueue. */ rcu_barrier(); flush_workqueue(isw_wq); } } static int __init cgroup_writeback_init(void) { isw_wq = alloc_workqueue("inode_switch_wbs", 0, 0); if (!isw_wq) return -ENOMEM; return 0; } fs_initcall(cgroup_writeback_init); #else /* CONFIG_CGROUP_WRITEBACK */ static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } static void inode_cgwb_move_to_attached(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&wb->list_lock); assert_spin_locked(&inode->i_lock); WARN_ON_ONCE(inode->i_state & I_FREEING); inode->i_state &= ~I_SYNC_QUEUED; list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); } static struct bdi_writeback * locked_inode_to_wb_and_lock_list(struct inode *inode) __releases(&inode->i_lock) __acquires(&wb->list_lock) { struct bdi_writeback *wb = inode_to_wb(inode); spin_unlock(&inode->i_lock); spin_lock(&wb->list_lock); return wb; } static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode) __acquires(&wb->list_lock) { struct bdi_writeback *wb = inode_to_wb(inode); spin_lock(&wb->list_lock); return wb; } static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages) { return nr_pages; } static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, struct wb_writeback_work *base_work, bool skip_if_busy) { might_sleep(); if (!skip_if_busy || !writeback_in_progress(&bdi->wb)) { base_work->auto_free = 0; wb_queue_work(&bdi->wb, base_work); } } static inline void wbc_attach_and_unlock_inode(struct writeback_control *wbc, struct inode *inode) __releases(&inode->i_lock) { spin_unlock(&inode->i_lock); } #endif /* CONFIG_CGROUP_WRITEBACK */ /* * Add in the number of potentially dirty inodes, because each inode * write can dirty pagecache in the underlying blockdev. */ static unsigned long get_nr_dirty_pages(void) { return global_node_page_state(NR_FILE_DIRTY) + get_nr_dirty_inodes(); } static void wb_start_writeback(struct bdi_writeback *wb, enum wb_reason reason) { if (!wb_has_dirty_io(wb)) return; /* * All callers of this function want to start writeback of all * dirty pages. Places like vmscan can call this at a very * high frequency, causing pointless allocations of tons of * work items and keeping the flusher threads busy retrieving * that work. Ensure that we only allow one of them pending and * inflight at the time. */ if (test_bit(WB_start_all, &wb->state) || test_and_set_bit(WB_start_all, &wb->state)) return; wb->start_all_reason = reason; wb_wakeup(wb); } /** * wb_start_background_writeback - start background writeback * @wb: bdi_writback to write from * * Description: * This makes sure WB_SYNC_NONE background writeback happens. When * this function returns, it is only guaranteed that for given wb * some IO is happening if we are over background dirty threshold. * Caller need not hold sb s_umount semaphore. */ void wb_start_background_writeback(struct bdi_writeback *wb) { /* * We just wake up the flusher thread. It will perform background * writeback as soon as there is no other work to do. */ trace_writeback_wake_background(wb); wb_wakeup(wb); } /* * Remove the inode from the writeback list it is on. */ void inode_io_list_del(struct inode *inode) { struct bdi_writeback *wb; wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); inode->i_state &= ~I_SYNC_QUEUED; list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); spin_unlock(&inode->i_lock); spin_unlock(&wb->list_lock); } EXPORT_SYMBOL(inode_io_list_del); /* * mark an inode as under writeback on the sb */ void sb_mark_inode_writeback(struct inode *inode) { struct super_block *sb = inode->i_sb; unsigned long flags; if (list_empty(&inode->i_wb_list)) { spin_lock_irqsave(&sb->s_inode_wblist_lock, flags); if (list_empty(&inode->i_wb_list)) { list_add_tail(&inode->i_wb_list, &sb->s_inodes_wb); trace_sb_mark_inode_writeback(inode); } spin_unlock_irqrestore(&sb->s_inode_wblist_lock, flags); } } /* * clear an inode as under writeback on the sb */ void sb_clear_inode_writeback(struct inode *inode) { struct super_block *sb = inode->i_sb; unsigned long flags; if (!list_empty(&inode->i_wb_list)) { spin_lock_irqsave(&sb->s_inode_wblist_lock, flags); if (!list_empty(&inode->i_wb_list)) { list_del_init(&inode->i_wb_list); trace_sb_clear_inode_writeback(inode); } spin_unlock_irqrestore(&sb->s_inode_wblist_lock, flags); } } /* * Redirty an inode: set its when-it-was dirtied timestamp and move it to the * furthest end of its superblock's dirty-inode list. * * Before stamping the inode's ->dirtied_when, we check to see whether it is * already the most-recently-dirtied inode on the b_dirty list. If that is * the case then the inode must have been redirtied while it was being written * out and we don't reset its dirtied_when. */ static void redirty_tail_locked(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&inode->i_lock); inode->i_state &= ~I_SYNC_QUEUED; /* * When the inode is being freed just don't bother with dirty list * tracking. Flush worker will ignore this inode anyway and it will * trigger assertions in inode_io_list_move_locked(). */ if (inode->i_state & I_FREEING) { list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); return; } if (!list_empty(&wb->b_dirty)) { struct inode *tail; tail = wb_inode(wb->b_dirty.next); if (time_before(inode->dirtied_when, tail->dirtied_when)) inode->dirtied_when = jiffies; } inode_io_list_move_locked(inode, wb, &wb->b_dirty); } static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) { spin_lock(&inode->i_lock); redirty_tail_locked(inode, wb); spin_unlock(&inode->i_lock); } /* * requeue inode for re-scanning after bdi->b_io list is exhausted. */ static void requeue_io(struct inode *inode, struct bdi_writeback *wb) { inode_io_list_move_locked(inode, wb, &wb->b_more_io); } static void inode_sync_complete(struct inode *inode) { assert_spin_locked(&inode->i_lock); inode->i_state &= ~I_SYNC; /* If inode is clean an unused, put it into LRU now... */ inode_add_lru(inode); /* Called with inode->i_lock which ensures memory ordering. */ inode_wake_up_bit(inode, __I_SYNC); } static bool inode_dirtied_after(struct inode *inode, unsigned long t) { bool ret = time_after(inode->dirtied_when, t); #ifndef CONFIG_64BIT /* * For inodes being constantly redirtied, dirtied_when can get stuck. * It _appears_ to be in the future, but is actually in distant past. * This test is necessary to prevent such wrapped-around relative times * from permanently stopping the whole bdi writeback. */ ret = ret && time_before_eq(inode->dirtied_when, jiffies); #endif return ret; } /* * Move expired (dirtied before dirtied_before) dirty inodes from * @delaying_queue to @dispatch_queue. */ static int move_expired_inodes(struct list_head *delaying_queue, struct list_head *dispatch_queue, unsigned long dirtied_before) { LIST_HEAD(tmp); struct list_head *pos, *node; struct super_block *sb = NULL; struct inode *inode; int do_sb_sort = 0; int moved = 0; while (!list_empty(delaying_queue)) { inode = wb_inode(delaying_queue->prev); if (inode_dirtied_after(inode, dirtied_before)) break; spin_lock(&inode->i_lock); list_move(&inode->i_io_list, &tmp); moved++; inode->i_state |= I_SYNC_QUEUED; spin_unlock(&inode->i_lock); if (sb_is_blkdev_sb(inode->i_sb)) continue; if (sb && sb != inode->i_sb) do_sb_sort = 1; sb = inode->i_sb; } /* just one sb in list, splice to dispatch_queue and we're done */ if (!do_sb_sort) { list_splice(&tmp, dispatch_queue); goto out; } /* * Although inode's i_io_list is moved from 'tmp' to 'dispatch_queue', * we don't take inode->i_lock here because it is just a pointless overhead. * Inode is already marked as I_SYNC_QUEUED so writeback list handling is * fully under our control. */ while (!list_empty(&tmp)) { sb = wb_inode(tmp.prev)->i_sb; list_for_each_prev_safe(pos, node, &tmp) { inode = wb_inode(pos); if (inode->i_sb == sb) list_move(&inode->i_io_list, dispatch_queue); } } out: return moved; } /* * Queue all expired dirty inodes for io, eldest first. * Before * newly dirtied b_dirty b_io b_more_io * =============> gf edc BA * After * newly dirtied b_dirty b_io b_more_io * =============> g fBAedc * | * +--> dequeue for IO */ static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work, unsigned long dirtied_before) { int moved; unsigned long time_expire_jif = dirtied_before; assert_spin_locked(&wb->list_lock); list_splice_init(&wb->b_more_io, &wb->b_io); moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, dirtied_before); if (!work->for_sync) time_expire_jif = jiffies - dirtytime_expire_interval * HZ; moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io, time_expire_jif); if (moved) wb_io_lists_populated(wb); trace_writeback_queue_io(wb, work, dirtied_before, moved); } static int write_inode(struct inode *inode, struct writeback_control *wbc) { int ret; if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode)) { trace_writeback_write_inode_start(inode, wbc); ret = inode->i_sb->s_op->write_inode(inode, wbc); trace_writeback_write_inode(inode, wbc); return ret; } return 0; } /* * Wait for writeback on an inode to complete. Called with i_lock held. * Caller must make sure inode cannot go away when we drop i_lock. */ void inode_wait_for_writeback(struct inode *inode) { struct wait_bit_queue_entry wqe; struct wait_queue_head *wq_head; assert_spin_locked(&inode->i_lock); if (!(inode->i_state & I_SYNC)) return; wq_head = inode_bit_waitqueue(&wqe, inode, __I_SYNC); for (;;) { prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE); /* Checking I_SYNC with inode->i_lock guarantees memory ordering. */ if (!(inode->i_state & I_SYNC)) break; spin_unlock(&inode->i_lock); schedule(); spin_lock(&inode->i_lock); } finish_wait(wq_head, &wqe.wq_entry); } /* * Sleep until I_SYNC is cleared. This function must be called with i_lock * held and drops it. It is aimed for callers not holding any inode reference * so once i_lock is dropped, inode can go away. */ static void inode_sleep_on_writeback(struct inode *inode) __releases(inode->i_lock) { struct wait_bit_queue_entry wqe; struct wait_queue_head *wq_head; bool sleep; assert_spin_locked(&inode->i_lock); wq_head = inode_bit_waitqueue(&wqe, inode, __I_SYNC); prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE); /* Checking I_SYNC with inode->i_lock guarantees memory ordering. */ sleep = !!(inode->i_state & I_SYNC); spin_unlock(&inode->i_lock); if (sleep) schedule(); finish_wait(wq_head, &wqe.wq_entry); } /* * Find proper writeback list for the inode depending on its current state and * possibly also change of its state while we were doing writeback. Here we * handle things such as livelock prevention or fairness of writeback among * inodes. This function can be called only by flusher thread - noone else * processes all inodes in writeback lists and requeueing inodes behind flusher * thread's back can have unexpected consequences. */ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, struct writeback_control *wbc, unsigned long dirtied_before) { if (inode->i_state & I_FREEING) return; /* * Sync livelock prevention. Each inode is tagged and synced in one * shot. If still dirty, it will be redirty_tail()'ed below. Update * the dirty time to prevent enqueue and sync it again. */ if ((inode->i_state & I_DIRTY) && (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)) inode->dirtied_when = jiffies; if (wbc->pages_skipped) { /* * Writeback is not making progress due to locked buffers. * Skip this inode for now. Although having skipped pages * is odd for clean inodes, it can happen for some * filesystems so handle that gracefully. */ if (inode->i_state & I_DIRTY_ALL) redirty_tail_locked(inode, wb); else inode_cgwb_move_to_attached(inode, wb); return; } if (mapping_tagged(inode->i_mapping, PAGECACHE_TAG_DIRTY)) { /* * We didn't write back all the pages. nfs_writepages() * sometimes bales out without doing anything. */ if (wbc->nr_to_write <= 0 && !inode_dirtied_after(inode, dirtied_before)) { /* Slice used up. Queue for next turn. */ requeue_io(inode, wb); } else { /* * Writeback blocked by something other than * congestion. Delay the inode for some time to * avoid spinning on the CPU (100% iowait) * retrying writeback of the dirty page/inode * that cannot be performed immediately. */ redirty_tail_locked(inode, wb); } } else if (inode->i_state & I_DIRTY) { /* * Filesystems can dirty the inode during writeback operations, * such as delayed allocation during submission or metadata * updates after data IO completion. */ redirty_tail_locked(inode, wb); } else if (inode->i_state & I_DIRTY_TIME) { inode->dirtied_when = jiffies; inode_io_list_move_locked(inode, wb, &wb->b_dirty_time); inode->i_state &= ~I_SYNC_QUEUED; } else { /* The inode is clean. Remove from writeback lists. */ inode_cgwb_move_to_attached(inode, wb); } } /* * Write out an inode and its dirty pages (or some of its dirty pages, depending * on @wbc->nr_to_write), and clear the relevant dirty flags from i_state. * * This doesn't remove the inode from the writeback list it is on, except * potentially to move it from b_dirty_time to b_dirty due to timestamp * expiration. The caller is otherwise responsible for writeback list handling. * * The caller is also responsible for setting the I_SYNC flag beforehand and * calling inode_sync_complete() to clear it afterwards. */ static int __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) { struct address_space *mapping = inode->i_mapping; long nr_to_write = wbc->nr_to_write; unsigned dirty; int ret; WARN_ON(!(inode->i_state & I_SYNC)); trace_writeback_single_inode_start(inode, wbc, nr_to_write); ret = do_writepages(mapping, wbc); /* * Make sure to wait on the data before writing out the metadata. * This is important for filesystems that modify metadata on data * I/O completion. We don't do it for sync(2) writeback because it has a * separate, external IO completion path and ->sync_fs for guaranteeing * inode metadata is written back correctly. */ if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync) { int err = filemap_fdatawait(mapping); if (ret == 0) ret = err; } /* * If the inode has dirty timestamps and we need to write them, call * mark_inode_dirty_sync() to notify the filesystem about it and to * change I_DIRTY_TIME into I_DIRTY_SYNC. */ if ((inode->i_state & I_DIRTY_TIME) && (wbc->sync_mode == WB_SYNC_ALL || time_after(jiffies, inode->dirtied_time_when + dirtytime_expire_interval * HZ))) { trace_writeback_lazytime(inode); mark_inode_dirty_sync(inode); } /* * Get and clear the dirty flags from i_state. This needs to be done * after calling writepages because some filesystems may redirty the * inode during writepages due to delalloc. It also needs to be done * after handling timestamp expiration, as that may dirty the inode too. */ spin_lock(&inode->i_lock); dirty = inode->i_state & I_DIRTY; inode->i_state &= ~dirty; /* * Paired with smp_mb() in __mark_inode_dirty(). This allows * __mark_inode_dirty() to test i_state without grabbing i_lock - * either they see the I_DIRTY bits cleared or we see the dirtied * inode. * * I_DIRTY_PAGES is always cleared together above even if @mapping * still has dirty pages. The flag is reinstated after smp_mb() if * necessary. This guarantees that either __mark_inode_dirty() * sees clear I_DIRTY_PAGES or we see PAGECACHE_TAG_DIRTY. */ smp_mb(); if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) inode->i_state |= I_DIRTY_PAGES; else if (unlikely(inode->i_state & I_PINNING_NETFS_WB)) { if (!(inode->i_state & I_DIRTY_PAGES)) { inode->i_state &= ~I_PINNING_NETFS_WB; wbc->unpinned_netfs_wb = true; dirty |= I_PINNING_NETFS_WB; /* Cause write_inode */ } } spin_unlock(&inode->i_lock); /* Don't write the inode if only I_DIRTY_PAGES was set */ if (dirty & ~I_DIRTY_PAGES) { int err = write_inode(inode, wbc); if (ret == 0) ret = err; } wbc->unpinned_netfs_wb = false; trace_writeback_single_inode(inode, wbc, nr_to_write); return ret; } /* * Write out an inode's dirty data and metadata on-demand, i.e. separately from * the regular batched writeback done by the flusher threads in * writeback_sb_inodes(). @wbc controls various aspects of the write, such as * whether it is a data-integrity sync (%WB_SYNC_ALL) or not (%WB_SYNC_NONE). * * To prevent the inode from going away, either the caller must have a reference * to the inode, or the inode must have I_WILL_FREE or I_FREEING set. */ static int writeback_single_inode(struct inode *inode, struct writeback_control *wbc) { struct bdi_writeback *wb; int ret = 0; spin_lock(&inode->i_lock); if (!atomic_read(&inode->i_count)) WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING))); else WARN_ON(inode->i_state & I_WILL_FREE); if (inode->i_state & I_SYNC) { /* * Writeback is already running on the inode. For WB_SYNC_NONE, * that's enough and we can just return. For WB_SYNC_ALL, we * must wait for the existing writeback to complete, then do * writeback again if there's anything left. */ if (wbc->sync_mode != WB_SYNC_ALL) goto out; inode_wait_for_writeback(inode); } WARN_ON(inode->i_state & I_SYNC); /* * If the inode is already fully clean, then there's nothing to do. * * For data-integrity syncs we also need to check whether any pages are * still under writeback, e.g. due to prior WB_SYNC_NONE writeback. If * there are any such pages, we'll need to wait for them. */ if (!(inode->i_state & I_DIRTY_ALL) && (wbc->sync_mode != WB_SYNC_ALL || !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK))) goto out; inode->i_state |= I_SYNC; wbc_attach_and_unlock_inode(wbc, inode); ret = __writeback_single_inode(inode, wbc); wbc_detach_inode(wbc); wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); /* * If the inode is freeing, its i_io_list shoudn't be updated * as it can be finally deleted at this moment. */ if (!(inode->i_state & I_FREEING)) { /* * If the inode is now fully clean, then it can be safely * removed from its writeback list (if any). Otherwise the * flusher threads are responsible for the writeback lists. */ if (!(inode->i_state & I_DIRTY_ALL)) inode_cgwb_move_to_attached(inode, wb); else if (!(inode->i_state & I_SYNC_QUEUED)) { if ((inode->i_state & I_DIRTY)) redirty_tail_locked(inode, wb); else if (inode->i_state & I_DIRTY_TIME) { inode->dirtied_when = jiffies; inode_io_list_move_locked(inode, wb, &wb->b_dirty_time); } } } spin_unlock(&wb->list_lock); inode_sync_complete(inode); out: spin_unlock(&inode->i_lock); return ret; } static long writeback_chunk_size(struct bdi_writeback *wb, struct wb_writeback_work *work) { long pages; /* * WB_SYNC_ALL mode does livelock avoidance by syncing dirty * inodes/pages in one big loop. Setting wbc.nr_to_write=LONG_MAX * here avoids calling into writeback_inodes_wb() more than once. * * The intended call sequence for WB_SYNC_ALL writeback is: * * wb_writeback() * writeback_sb_inodes() <== called only once * write_cache_pages() <== called once for each inode * (quickly) tag currently dirty pages * (maybe slowly) sync all tagged pages */ if (work->sync_mode == WB_SYNC_ALL || work->tagged_writepages) pages = LONG_MAX; else { pages = min(wb->avg_write_bandwidth / 2, global_wb_domain.dirty_limit / DIRTY_SCOPE); pages = min(pages, work->nr_pages); pages = round_down(pages + MIN_WRITEBACK_PAGES, MIN_WRITEBACK_PAGES); } return pages; } /* * Write a portion of b_io inodes which belong to @sb. * * Return the number of pages and/or inodes written. * * NOTE! This is called with wb->list_lock held, and will * unlock and relock that for each inode it ends up doing * IO for. */ static long writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb, struct wb_writeback_work *work) { struct writeback_control wbc = { .sync_mode = work->sync_mode, .tagged_writepages = work->tagged_writepages, .for_kupdate = work->for_kupdate, .for_background = work->for_background, .for_sync = work->for_sync, .range_cyclic = work->range_cyclic, .range_start = 0, .range_end = LLONG_MAX, }; unsigned long start_time = jiffies; long write_chunk; long total_wrote = 0; /* count both pages and inodes */ unsigned long dirtied_before = jiffies; if (work->for_kupdate) dirtied_before = jiffies - msecs_to_jiffies(dirty_expire_interval * 10); while (!list_empty(&wb->b_io)) { struct inode *inode = wb_inode(wb->b_io.prev); struct bdi_writeback *tmp_wb; long wrote; if (inode->i_sb != sb) { if (work->sb) { /* * We only want to write back data for this * superblock, move all inodes not belonging * to it back onto the dirty list. */ redirty_tail(inode, wb); continue; } /* * The inode belongs to a different superblock. * Bounce back to the caller to unpin this and * pin the next superblock. */ break; } /* * Don't bother with new inodes or inodes being freed, first * kind does not need periodic writeout yet, and for the latter * kind writeout is handled by the freer. */ spin_lock(&inode->i_lock); if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { redirty_tail_locked(inode, wb); spin_unlock(&inode->i_lock); continue; } if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) { /* * If this inode is locked for writeback and we are not * doing writeback-for-data-integrity, move it to * b_more_io so that writeback can proceed with the * other inodes on s_io. * * We'll have another go at writing back this inode * when we completed a full scan of b_io. */ requeue_io(inode, wb); spin_unlock(&inode->i_lock); trace_writeback_sb_inodes_requeue(inode); continue; } spin_unlock(&wb->list_lock); /* * We already requeued the inode if it had I_SYNC set and we * are doing WB_SYNC_NONE writeback. So this catches only the * WB_SYNC_ALL case. */ if (inode->i_state & I_SYNC) { /* Wait for I_SYNC. This function drops i_lock... */ inode_sleep_on_writeback(inode); /* Inode may be gone, start again */ spin_lock(&wb->list_lock); continue; } inode->i_state |= I_SYNC; wbc_attach_and_unlock_inode(&wbc, inode); write_chunk = writeback_chunk_size(wb, work); wbc.nr_to_write = write_chunk; wbc.pages_skipped = 0; /* * We use I_SYNC to pin the inode in memory. While it is set * evict_inode() will wait so the inode cannot be freed. */ __writeback_single_inode(inode, &wbc); wbc_detach_inode(&wbc); work->nr_pages -= write_chunk - wbc.nr_to_write; wrote = write_chunk - wbc.nr_to_write - wbc.pages_skipped; wrote = wrote < 0 ? 0 : wrote; total_wrote += wrote; if (need_resched()) { /* * We're trying to balance between building up a nice * long list of IOs to improve our merge rate, and * getting those IOs out quickly for anyone throttling * in balance_dirty_pages(). cond_resched() doesn't * unplug, so get our IOs out the door before we * give up the CPU. */ blk_flush_plug(current->plug, false); cond_resched(); } /* * Requeue @inode if still dirty. Be careful as @inode may * have been switched to another wb in the meantime. */ tmp_wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); if (!(inode->i_state & I_DIRTY_ALL)) total_wrote++; requeue_inode(inode, tmp_wb, &wbc, dirtied_before); inode_sync_complete(inode); spin_unlock(&inode->i_lock); if (unlikely(tmp_wb != wb)) { spin_unlock(&tmp_wb->list_lock); spin_lock(&wb->list_lock); } /* * bail out to wb_writeback() often enough to check * background threshold and other termination conditions. */ if (total_wrote) { if (time_is_before_jiffies(start_time + HZ / 10UL)) break; if (work->nr_pages <= 0) break; } } return total_wrote; } static long __writeback_inodes_wb(struct bdi_writeback *wb, struct wb_writeback_work *work) { unsigned long start_time = jiffies; long wrote = 0; while (!list_empty(&wb->b_io)) { struct inode *inode = wb_inode(wb->b_io.prev); struct super_block *sb = inode->i_sb; if (!super_trylock_shared(sb)) { /* * super_trylock_shared() may fail consistently due to * s_umount being grabbed by someone else. Don't use * requeue_io() to avoid busy retrying the inode/sb. */ redirty_tail(inode, wb); continue; } wrote += writeback_sb_inodes(sb, wb, work); up_read(&sb->s_umount); /* refer to the same tests at the end of writeback_sb_inodes */ if (wrote) { if (time_is_before_jiffies(start_time + HZ / 10UL)) break; if (work->nr_pages <= 0) break; } } /* Leave any unwritten inodes on b_io */ return wrote; } static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, enum wb_reason reason) { struct wb_writeback_work work = { .nr_pages = nr_pages, .sync_mode = WB_SYNC_NONE, .range_cyclic = 1, .reason = reason, }; struct blk_plug plug; blk_start_plug(&plug); spin_lock(&wb->list_lock); if (list_empty(&wb->b_io)) queue_io(wb, &work, jiffies); __writeback_inodes_wb(wb, &work); spin_unlock(&wb->list_lock); blk_finish_plug(&plug); return nr_pages - work.nr_pages; } /* * Explicit flushing or periodic writeback of "old" data. * * Define "old": the first time one of an inode's pages is dirtied, we mark the * dirtying-time in the inode's address_space. So this periodic writeback code * just walks the superblock inode list, writing back any inodes which are * older than a specific point in time. * * Try to run once per dirty_writeback_interval. But if a writeback event * takes longer than a dirty_writeback_interval interval, then leave a * one-second gap. * * dirtied_before takes precedence over nr_to_write. So we'll only write back * all dirty pages if they are all attached to "old" mappings. */ static long wb_writeback(struct bdi_writeback *wb, struct wb_writeback_work *work) { long nr_pages = work->nr_pages; unsigned long dirtied_before = jiffies; struct inode *inode; long progress; struct blk_plug plug; bool queued = false; blk_start_plug(&plug); for (;;) { /* * Stop writeback when nr_pages has been consumed */ if (work->nr_pages <= 0) break; /* * Background writeout and kupdate-style writeback may * run forever. Stop them if there is other work to do * so that e.g. sync can proceed. They'll be restarted * after the other works are all done. */ if ((work->for_background || work->for_kupdate) && !list_empty(&wb->work_list)) break; /* * For background writeout, stop when we are below the * background dirty threshold */ if (work->for_background && !wb_over_bg_thresh(wb)) break; spin_lock(&wb->list_lock); trace_writeback_start(wb, work); if (list_empty(&wb->b_io)) { /* * Kupdate and background works are special and we want * to include all inodes that need writing. Livelock * avoidance is handled by these works yielding to any * other work so we are safe. */ if (work->for_kupdate) { dirtied_before = jiffies - msecs_to_jiffies(dirty_expire_interval * 10); } else if (work->for_background) dirtied_before = jiffies; queue_io(wb, work, dirtied_before); queued = true; } if (work->sb) progress = writeback_sb_inodes(work->sb, wb, work); else progress = __writeback_inodes_wb(wb, work); trace_writeback_written(wb, work); /* * Did we write something? Try for more * * Dirty inodes are moved to b_io for writeback in batches. * The completion of the current batch does not necessarily * mean the overall work is done. So we keep looping as long * as made some progress on cleaning pages or inodes. */ if (progress || !queued) { spin_unlock(&wb->list_lock); continue; } /* * No more inodes for IO, bail */ if (list_empty(&wb->b_more_io)) { spin_unlock(&wb->list_lock); break; } /* * Nothing written. Wait for some inode to * become available for writeback. Otherwise * we'll just busyloop. */ trace_writeback_wait(wb, work); inode = wb_inode(wb->b_more_io.prev); spin_lock(&inode->i_lock); spin_unlock(&wb->list_lock); /* This function drops i_lock... */ inode_sleep_on_writeback(inode); } blk_finish_plug(&plug); return nr_pages - work->nr_pages; } /* * Return the next wb_writeback_work struct that hasn't been processed yet. */ static struct wb_writeback_work *get_next_work_item(struct bdi_writeback *wb) { struct wb_writeback_work *work = NULL; spin_lock_irq(&wb->work_lock); if (!list_empty(&wb->work_list)) { work = list_entry(wb->work_list.next, struct wb_writeback_work, list); list_del_init(&work->list); } spin_unlock_irq(&wb->work_lock); return work; } static long wb_check_background_flush(struct bdi_writeback *wb) { if (wb_over_bg_thresh(wb)) { struct wb_writeback_work work = { .nr_pages = LONG_MAX, .sync_mode = WB_SYNC_NONE, .for_background = 1, .range_cyclic = 1, .reason = WB_REASON_BACKGROUND, }; return wb_writeback(wb, &work); } return 0; } static long wb_check_old_data_flush(struct bdi_writeback *wb) { unsigned long expired; long nr_pages; /* * When set to zero, disable periodic writeback */ if (!dirty_writeback_interval) return 0; expired = wb->last_old_flush + msecs_to_jiffies(dirty_writeback_interval * 10); if (time_before(jiffies, expired)) return 0; wb->last_old_flush = jiffies; nr_pages = get_nr_dirty_pages(); if (nr_pages) { struct wb_writeback_work work = { .nr_pages = nr_pages, .sync_mode = WB_SYNC_NONE, .for_kupdate = 1, .range_cyclic = 1, .reason = WB_REASON_PERIODIC, }; return wb_writeback(wb, &work); } return 0; } static long wb_check_start_all(struct bdi_writeback *wb) { long nr_pages; if (!test_bit(WB_start_all, &wb->state)) return 0; nr_pages = get_nr_dirty_pages(); if (nr_pages) { struct wb_writeback_work work = { .nr_pages = wb_split_bdi_pages(wb, nr_pages), .sync_mode = WB_SYNC_NONE, .range_cyclic = 1, .reason = wb->start_all_reason, }; nr_pages = wb_writeback(wb, &work); } clear_bit(WB_start_all, &wb->state); return nr_pages; } /* * Retrieve work items and do the writeback they describe */ static long wb_do_writeback(struct bdi_writeback *wb) { struct wb_writeback_work *work; long wrote = 0; set_bit(WB_writeback_running, &wb->state); while ((work = get_next_work_item(wb)) != NULL) { trace_writeback_exec(wb, work); wrote += wb_writeback(wb, work); finish_writeback_work(work); } /* * Check for a flush-everything request */ wrote += wb_check_start_all(wb); /* * Check for periodic writeback, kupdated() style */ wrote += wb_check_old_data_flush(wb); wrote += wb_check_background_flush(wb); clear_bit(WB_writeback_running, &wb->state); return wrote; } /* * Handle writeback of dirty data for the device backed by this bdi. Also * reschedules periodically and does kupdated style flushing. */ void wb_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(to_delayed_work(work), struct bdi_writeback, dwork); long pages_written; set_worker_desc("flush-%s", bdi_dev_name(wb->bdi)); if (likely(!current_is_workqueue_rescuer() || !test_bit(WB_registered, &wb->state))) { /* * The normal path. Keep writing back @wb until its * work_list is empty. Note that this path is also taken * if @wb is shutting down even when we're running off the * rescuer as work_list needs to be drained. */ do { pages_written = wb_do_writeback(wb); trace_writeback_pages_written(pages_written); } while (!list_empty(&wb->work_list)); } else { /* * bdi_wq can't get enough workers and we're running off * the emergency worker. Don't hog it. Hopefully, 1024 is * enough for efficient IO. */ pages_written = writeback_inodes_wb(wb, 1024, WB_REASON_FORKER_THREAD); trace_writeback_pages_written(pages_written); } if (!list_empty(&wb->work_list)) wb_wakeup(wb); else if (wb_has_dirty_io(wb) && dirty_writeback_interval) wb_wakeup_delayed(wb); } /* * Start writeback of all dirty pages on this bdi. */ static void __wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, enum wb_reason reason) { struct bdi_writeback *wb; if (!bdi_has_dirty_io(bdi)) return; list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) wb_start_writeback(wb, reason); } void wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, enum wb_reason reason) { rcu_read_lock(); __wakeup_flusher_threads_bdi(bdi, reason); rcu_read_unlock(); } /* * Wakeup the flusher threads to start writeback of all currently dirty pages */ void wakeup_flusher_threads(enum wb_reason reason) { struct backing_dev_info *bdi; /* * If we are expecting writeback progress we must submit plugged IO. */ blk_flush_plug(current->plug, true); rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) __wakeup_flusher_threads_bdi(bdi, reason); rcu_read_unlock(); } /* * Wake up bdi's periodically to make sure dirtytime inodes gets * written back periodically. We deliberately do *not* check the * b_dirtytime list in wb_has_dirty_io(), since this would cause the * kernel to be constantly waking up once there are any dirtytime * inodes on the system. So instead we define a separate delayed work * function which gets called much more rarely. (By default, only * once every 12 hours.) * * If there is any other write activity going on in the file system, * this function won't be necessary. But if the only thing that has * happened on the file system is a dirtytime inode caused by an atime * update, we need this infrastructure below to make sure that inode * eventually gets pushed out to disk. */ static void wakeup_dirtytime_writeback(struct work_struct *w); static DECLARE_DELAYED_WORK(dirtytime_work, wakeup_dirtytime_writeback); static void wakeup_dirtytime_writeback(struct work_struct *w) { struct backing_dev_info *bdi; rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { struct bdi_writeback *wb; list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) if (!list_empty(&wb->b_dirty_time)) wb_wakeup(wb); } rcu_read_unlock(); schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); } static int __init start_dirtytime_writeback(void) { schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); return 0; } __initcall(start_dirtytime_writeback); int dirtytime_interval_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) mod_delayed_work(system_wq, &dirtytime_work, 0); return ret; } /** * __mark_inode_dirty - internal function to mark an inode dirty * * @inode: inode to mark * @flags: what kind of dirty, e.g. I_DIRTY_SYNC. This can be a combination of * multiple I_DIRTY_* flags, except that I_DIRTY_TIME can't be combined * with I_DIRTY_PAGES. * * Mark an inode as dirty. We notify the filesystem, then update the inode's * dirty flags. Then, if needed we add the inode to the appropriate dirty list. * * Most callers should use mark_inode_dirty() or mark_inode_dirty_sync() * instead of calling this directly. * * CAREFUL! We only add the inode to the dirty list if it is hashed or if it * refers to a blockdev. Unhashed inodes will never be added to the dirty list * even if they are later hashed, as they will have been marked dirty already. * * In short, ensure you hash any inodes _before_ you start marking them dirty. * * Note that for blockdevs, inode->dirtied_when represents the dirtying time of * the block-special inode (/dev/hda1) itself. And the ->dirtied_when field of * the kernel-internal blockdev inode represents the dirtying time of the * blockdev's pages. This is why for I_DIRTY_PAGES we always use * page->mapping->host, so the page-dirtying time is recorded in the internal * blockdev inode. */ void __mark_inode_dirty(struct inode *inode, int flags) { struct super_block *sb = inode->i_sb; int dirtytime = 0; struct bdi_writeback *wb = NULL; trace_writeback_mark_inode_dirty(inode, flags); if (flags & I_DIRTY_INODE) { /* * Inode timestamp update will piggback on this dirtying. * We tell ->dirty_inode callback that timestamps need to * be updated by setting I_DIRTY_TIME in flags. */ if (inode->i_state & I_DIRTY_TIME) { spin_lock(&inode->i_lock); if (inode->i_state & I_DIRTY_TIME) { inode->i_state &= ~I_DIRTY_TIME; flags |= I_DIRTY_TIME; } spin_unlock(&inode->i_lock); } /* * Notify the filesystem about the inode being dirtied, so that * (if needed) it can update on-disk fields and journal the * inode. This is only needed when the inode itself is being * dirtied now. I.e. it's only needed for I_DIRTY_INODE, not * for just I_DIRTY_PAGES or I_DIRTY_TIME. */ trace_writeback_dirty_inode_start(inode, flags); if (sb->s_op->dirty_inode) sb->s_op->dirty_inode(inode, flags & (I_DIRTY_INODE | I_DIRTY_TIME)); trace_writeback_dirty_inode(inode, flags); /* I_DIRTY_INODE supersedes I_DIRTY_TIME. */ flags &= ~I_DIRTY_TIME; } else { /* * Else it's either I_DIRTY_PAGES, I_DIRTY_TIME, or nothing. * (We don't support setting both I_DIRTY_PAGES and I_DIRTY_TIME * in one call to __mark_inode_dirty().) */ dirtytime = flags & I_DIRTY_TIME; WARN_ON_ONCE(dirtytime && flags != I_DIRTY_TIME); } /* * Paired with smp_mb() in __writeback_single_inode() for the * following lockless i_state test. See there for details. */ smp_mb(); if ((inode->i_state & flags) == flags) return; spin_lock(&inode->i_lock); if ((inode->i_state & flags) != flags) { const int was_dirty = inode->i_state & I_DIRTY; inode_attach_wb(inode, NULL); inode->i_state |= flags; /* * Grab inode's wb early because it requires dropping i_lock and we * need to make sure following checks happen atomically with dirty * list handling so that we don't move inodes under flush worker's * hands. */ if (!was_dirty) { wb = locked_inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); } /* * If the inode is queued for writeback by flush worker, just * update its dirty state. Once the flush worker is done with * the inode it will place it on the appropriate superblock * list, based upon its state. */ if (inode->i_state & I_SYNC_QUEUED) goto out_unlock; /* * Only add valid (hashed) inodes to the superblock's * dirty list. Add blockdev inodes as well. */ if (!S_ISBLK(inode->i_mode)) { if (inode_unhashed(inode)) goto out_unlock; } if (inode->i_state & I_FREEING) goto out_unlock; /* * If the inode was already on b_dirty/b_io/b_more_io, don't * reposition it (that would break b_dirty time-ordering). */ if (!was_dirty) { struct list_head *dirty_list; bool wakeup_bdi = false; inode->dirtied_when = jiffies; if (dirtytime) inode->dirtied_time_when = jiffies; if (inode->i_state & I_DIRTY) dirty_list = &wb->b_dirty; else dirty_list = &wb->b_dirty_time; wakeup_bdi = inode_io_list_move_locked(inode, wb, dirty_list); spin_unlock(&wb->list_lock); spin_unlock(&inode->i_lock); trace_writeback_dirty_inode_enqueue(inode); /* * If this is the first dirty inode for this bdi, * we have to wake-up the corresponding bdi thread * to make sure background write-back happens * later. */ if (wakeup_bdi && (wb->bdi->capabilities & BDI_CAP_WRITEBACK)) wb_wakeup_delayed(wb); return; } } out_unlock: if (wb) spin_unlock(&wb->list_lock); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(__mark_inode_dirty); /* * The @s_sync_lock is used to serialise concurrent sync operations * to avoid lock contention problems with concurrent wait_sb_inodes() calls. * Concurrent callers will block on the s_sync_lock rather than doing contending * walks. The queueing maintains sync(2) required behaviour as all the IO that * has been issued up to the time this function is enter is guaranteed to be * completed by the time we have gained the lock and waited for all IO that is * in progress regardless of the order callers are granted the lock. */ static void wait_sb_inodes(struct super_block *sb) { LIST_HEAD(sync_list); /* * We need to be protected against the filesystem going from * r/o to r/w or vice versa. */ WARN_ON(!rwsem_is_locked(&sb->s_umount)); mutex_lock(&sb->s_sync_lock); /* * Splice the writeback list onto a temporary list to avoid waiting on * inodes that have started writeback after this point. * * Use rcu_read_lock() to keep the inodes around until we have a * reference. s_inode_wblist_lock protects sb->s_inodes_wb as well as * the local list because inodes can be dropped from either by writeback * completion. */ rcu_read_lock(); spin_lock_irq(&sb->s_inode_wblist_lock); list_splice_init(&sb->s_inodes_wb, &sync_list); /* * Data integrity sync. Must wait for all pages under writeback, because * there may have been pages dirtied before our sync call, but which had * writeout started before we write it out. In which case, the inode * may not be on the dirty list, but we still have to wait for that * writeout. */ while (!list_empty(&sync_list)) { struct inode *inode = list_first_entry(&sync_list, struct inode, i_wb_list); struct address_space *mapping = inode->i_mapping; /* * Move each inode back to the wb list before we drop the lock * to preserve consistency between i_wb_list and the mapping * writeback tag. Writeback completion is responsible to remove * the inode from either list once the writeback tag is cleared. */ list_move_tail(&inode->i_wb_list, &sb->s_inodes_wb); /* * The mapping can appear untagged while still on-list since we * do not have the mapping lock. Skip it here, wb completion * will remove it. */ if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) continue; spin_unlock_irq(&sb->s_inode_wblist_lock); spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) { spin_unlock(&inode->i_lock); spin_lock_irq(&sb->s_inode_wblist_lock); continue; } __iget(inode); spin_unlock(&inode->i_lock); rcu_read_unlock(); /* * We keep the error status of individual mapping so that * applications can catch the writeback error using fsync(2). * See filemap_fdatawait_keep_errors() for details. */ filemap_fdatawait_keep_errors(mapping); cond_resched(); iput(inode); rcu_read_lock(); spin_lock_irq(&sb->s_inode_wblist_lock); } spin_unlock_irq(&sb->s_inode_wblist_lock); rcu_read_unlock(); mutex_unlock(&sb->s_sync_lock); } static void __writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr, enum wb_reason reason, bool skip_if_busy) { struct backing_dev_info *bdi = sb->s_bdi; DEFINE_WB_COMPLETION(done, bdi); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_NONE, .tagged_writepages = 1, .done = &done, .nr_pages = nr, .reason = reason, }; if (!bdi_has_dirty_io(bdi) || bdi == &noop_backing_dev_info) return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); bdi_split_work_to_wbs(sb->s_bdi, &work, skip_if_busy); wb_wait_for_completion(&done); } /** * writeback_inodes_sb_nr - writeback dirty inodes from given super_block * @sb: the superblock * @nr: the number of pages to write * @reason: reason why some writeback work initiated * * Start writeback on some inodes on this super_block. No guarantees are made * on how many (if any) will be written, and this function does not wait * for IO completion of submitted IO. */ void writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr, enum wb_reason reason) { __writeback_inodes_sb_nr(sb, nr, reason, false); } EXPORT_SYMBOL(writeback_inodes_sb_nr); /** * writeback_inodes_sb - writeback dirty inodes from given super_block * @sb: the superblock * @reason: reason why some writeback work was initiated * * Start writeback on some inodes on this super_block. No guarantees are made * on how many (if any) will be written, and this function does not wait * for IO completion of submitted IO. */ void writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) { writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason); } EXPORT_SYMBOL(writeback_inodes_sb); /** * try_to_writeback_inodes_sb - try to start writeback if none underway * @sb: the superblock * @reason: reason why some writeback work was initiated * * Invoke __writeback_inodes_sb_nr if no writeback is currently underway. */ void try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) { if (!down_read_trylock(&sb->s_umount)) return; __writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason, true); up_read(&sb->s_umount); } EXPORT_SYMBOL(try_to_writeback_inodes_sb); /** * sync_inodes_sb - sync sb inode pages * @sb: the superblock * * This function writes and waits on any dirty inode belonging to this * super_block. */ void sync_inodes_sb(struct super_block *sb) { struct backing_dev_info *bdi = sb->s_bdi; DEFINE_WB_COMPLETION(done, bdi); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_ALL, .nr_pages = LONG_MAX, .range_cyclic = 0, .done = &done, .reason = WB_REASON_SYNC, .for_sync = 1, }; /* * Can't skip on !bdi_has_dirty() because we should wait for !dirty * inodes under writeback and I_DIRTY_TIME inodes ignored by * bdi_has_dirty() need to be written out too. */ if (bdi == &noop_backing_dev_info) return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); /* protect against inode wb switch, see inode_switch_wbs_work_fn() */ bdi_down_write_wb_switch_rwsem(bdi); bdi_split_work_to_wbs(bdi, &work, false); wb_wait_for_completion(&done); bdi_up_write_wb_switch_rwsem(bdi); wait_sb_inodes(sb); } EXPORT_SYMBOL(sync_inodes_sb); /** * write_inode_now - write an inode to disk * @inode: inode to write to disk * @sync: whether the write should be synchronous or not * * This function commits an inode to disk immediately if it is dirty. This is * primarily needed by knfsd. * * The caller must either have a ref on the inode or must have set I_WILL_FREE. */ int write_inode_now(struct inode *inode, int sync) { struct writeback_control wbc = { .nr_to_write = LONG_MAX, .sync_mode = sync ? WB_SYNC_ALL : WB_SYNC_NONE, .range_start = 0, .range_end = LLONG_MAX, }; if (!mapping_can_writeback(inode->i_mapping)) wbc.nr_to_write = 0; might_sleep(); return writeback_single_inode(inode, &wbc); } EXPORT_SYMBOL(write_inode_now); /** * sync_inode_metadata - write an inode to disk * @inode: the inode to sync * @wait: wait for I/O to complete. * * Write an inode to disk and adjust its dirty state after completion. * * Note: only writes the actual inode, no associated data or other metadata. */ int sync_inode_metadata(struct inode *inode, int wait) { struct writeback_control wbc = { .sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_NONE, .nr_to_write = 0, /* metadata-only */ }; return writeback_single_inode(inode, &wbc); } EXPORT_SYMBOL(sync_inode_metadata); |
| 3904 2090 5953 4 41 5936 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Written by Mark Hemment, 1996 (markhe@nextd.demon.co.uk). * * (C) SGI 2006, Christoph Lameter * Cleaned up and restructured to ease the addition of alternative * implementations of SLAB allocators. * (C) Linux Foundation 2008-2013 * Unified interface for all slab allocators */ #ifndef _LINUX_SLAB_H #define _LINUX_SLAB_H #include <linux/cache.h> #include <linux/gfp.h> #include <linux/overflow.h> #include <linux/types.h> #include <linux/workqueue.h> #include <linux/percpu-refcount.h> #include <linux/cleanup.h> #include <linux/hash.h> enum _slab_flag_bits { _SLAB_CONSISTENCY_CHECKS, _SLAB_RED_ZONE, _SLAB_POISON, _SLAB_KMALLOC, _SLAB_HWCACHE_ALIGN, _SLAB_CACHE_DMA, _SLAB_CACHE_DMA32, _SLAB_STORE_USER, _SLAB_PANIC, _SLAB_TYPESAFE_BY_RCU, _SLAB_TRACE, #ifdef CONFIG_DEBUG_OBJECTS _SLAB_DEBUG_OBJECTS, #endif _SLAB_NOLEAKTRACE, _SLAB_NO_MERGE, #ifdef CONFIG_FAILSLAB _SLAB_FAILSLAB, #endif #ifdef CONFIG_MEMCG _SLAB_ACCOUNT, #endif #ifdef CONFIG_KASAN_GENERIC _SLAB_KASAN, #endif _SLAB_NO_USER_FLAGS, #ifdef CONFIG_KFENCE _SLAB_SKIP_KFENCE, #endif #ifndef CONFIG_SLUB_TINY _SLAB_RECLAIM_ACCOUNT, #endif _SLAB_OBJECT_POISON, _SLAB_CMPXCHG_DOUBLE, #ifdef CONFIG_SLAB_OBJ_EXT _SLAB_NO_OBJ_EXT, #endif _SLAB_FLAGS_LAST_BIT }; #define __SLAB_FLAG_BIT(nr) ((slab_flags_t __force)(1U << (nr))) #define __SLAB_FLAG_UNUSED ((slab_flags_t __force)(0U)) /* * Flags to pass to kmem_cache_create(). * The ones marked DEBUG need CONFIG_SLUB_DEBUG enabled, otherwise are no-op */ /* DEBUG: Perform (expensive) checks on alloc/free */ #define SLAB_CONSISTENCY_CHECKS __SLAB_FLAG_BIT(_SLAB_CONSISTENCY_CHECKS) /* DEBUG: Red zone objs in a cache */ #define SLAB_RED_ZONE __SLAB_FLAG_BIT(_SLAB_RED_ZONE) /* DEBUG: Poison objects */ #define SLAB_POISON __SLAB_FLAG_BIT(_SLAB_POISON) /* Indicate a kmalloc slab */ #define SLAB_KMALLOC __SLAB_FLAG_BIT(_SLAB_KMALLOC) /** * define SLAB_HWCACHE_ALIGN - Align objects on cache line boundaries. * * Sufficiently large objects are aligned on cache line boundary. For object * size smaller than a half of cache line size, the alignment is on the half of * cache line size. In general, if object size is smaller than 1/2^n of cache * line size, the alignment is adjusted to 1/2^n. * * If explicit alignment is also requested by the respective * &struct kmem_cache_args field, the greater of both is alignments is applied. */ #define SLAB_HWCACHE_ALIGN __SLAB_FLAG_BIT(_SLAB_HWCACHE_ALIGN) /* Use GFP_DMA memory */ #define SLAB_CACHE_DMA __SLAB_FLAG_BIT(_SLAB_CACHE_DMA) /* Use GFP_DMA32 memory */ #define SLAB_CACHE_DMA32 __SLAB_FLAG_BIT(_SLAB_CACHE_DMA32) /* DEBUG: Store the last owner for bug hunting */ #define SLAB_STORE_USER __SLAB_FLAG_BIT(_SLAB_STORE_USER) /* Panic if kmem_cache_create() fails */ #define SLAB_PANIC __SLAB_FLAG_BIT(_SLAB_PANIC) /** * define SLAB_TYPESAFE_BY_RCU - **WARNING** READ THIS! * * This delays freeing the SLAB page by a grace period, it does _NOT_ * delay object freeing. This means that if you do kmem_cache_free() * that memory location is free to be reused at any time. Thus it may * be possible to see another object there in the same RCU grace period. * * This feature only ensures the memory location backing the object * stays valid, the trick to using this is relying on an independent * object validation pass. Something like: * * :: * * begin: * rcu_read_lock(); * obj = lockless_lookup(key); * if (obj) { * if (!try_get_ref(obj)) // might fail for free objects * rcu_read_unlock(); * goto begin; * * if (obj->key != key) { // not the object we expected * put_ref(obj); * rcu_read_unlock(); * goto begin; * } * } * rcu_read_unlock(); * * This is useful if we need to approach a kernel structure obliquely, * from its address obtained without the usual locking. We can lock * the structure to stabilize it and check it's still at the given address, * only if we can be sure that the memory has not been meanwhile reused * for some other kind of object (which our subsystem's lock might corrupt). * * rcu_read_lock before reading the address, then rcu_read_unlock after * taking the spinlock within the structure expected at that address. * * Note that it is not possible to acquire a lock within a structure * allocated with SLAB_TYPESAFE_BY_RCU without first acquiring a reference * as described above. The reason is that SLAB_TYPESAFE_BY_RCU pages * are not zeroed before being given to the slab, which means that any * locks must be initialized after each and every kmem_struct_alloc(). * Alternatively, make the ctor passed to kmem_cache_create() initialize * the locks at page-allocation time, as is done in __i915_request_ctor(), * sighand_ctor(), and anon_vma_ctor(). Such a ctor permits readers * to safely acquire those ctor-initialized locks under rcu_read_lock() * protection. * * Note that SLAB_TYPESAFE_BY_RCU was originally named SLAB_DESTROY_BY_RCU. */ #define SLAB_TYPESAFE_BY_RCU __SLAB_FLAG_BIT(_SLAB_TYPESAFE_BY_RCU) /* Trace allocations and frees */ #define SLAB_TRACE __SLAB_FLAG_BIT(_SLAB_TRACE) /* Flag to prevent checks on free */ #ifdef CONFIG_DEBUG_OBJECTS # define SLAB_DEBUG_OBJECTS __SLAB_FLAG_BIT(_SLAB_DEBUG_OBJECTS) #else # define SLAB_DEBUG_OBJECTS __SLAB_FLAG_UNUSED #endif /* Avoid kmemleak tracing */ #define SLAB_NOLEAKTRACE __SLAB_FLAG_BIT(_SLAB_NOLEAKTRACE) /* * Prevent merging with compatible kmem caches. This flag should be used * cautiously. Valid use cases: * * - caches created for self-tests (e.g. kunit) * - general caches created and used by a subsystem, only when a * (subsystem-specific) debug option is enabled * - performance critical caches, should be very rare and consulted with slab * maintainers, and not used together with CONFIG_SLUB_TINY */ #define SLAB_NO_MERGE __SLAB_FLAG_BIT(_SLAB_NO_MERGE) /* Fault injection mark */ #ifdef CONFIG_FAILSLAB # define SLAB_FAILSLAB __SLAB_FLAG_BIT(_SLAB_FAILSLAB) #else # define SLAB_FAILSLAB __SLAB_FLAG_UNUSED #endif /** * define SLAB_ACCOUNT - Account allocations to memcg. * * All object allocations from this cache will be memcg accounted, regardless of * __GFP_ACCOUNT being or not being passed to individual allocations. */ #ifdef CONFIG_MEMCG # define SLAB_ACCOUNT __SLAB_FLAG_BIT(_SLAB_ACCOUNT) #else # define SLAB_ACCOUNT __SLAB_FLAG_UNUSED #endif #ifdef CONFIG_KASAN_GENERIC #define SLAB_KASAN __SLAB_FLAG_BIT(_SLAB_KASAN) #else #define SLAB_KASAN __SLAB_FLAG_UNUSED #endif /* * Ignore user specified debugging flags. * Intended for caches created for self-tests so they have only flags * specified in the code and other flags are ignored. */ #define SLAB_NO_USER_FLAGS __SLAB_FLAG_BIT(_SLAB_NO_USER_FLAGS) #ifdef CONFIG_KFENCE #define SLAB_SKIP_KFENCE __SLAB_FLAG_BIT(_SLAB_SKIP_KFENCE) #else #define SLAB_SKIP_KFENCE __SLAB_FLAG_UNUSED #endif /* The following flags affect the page allocator grouping pages by mobility */ /** * define SLAB_RECLAIM_ACCOUNT - Objects are reclaimable. * * Use this flag for caches that have an associated shrinker. As a result, slab * pages are allocated with __GFP_RECLAIMABLE, which affects grouping pages by * mobility, and are accounted in SReclaimable counter in /proc/meminfo */ #ifndef CONFIG_SLUB_TINY #define SLAB_RECLAIM_ACCOUNT __SLAB_FLAG_BIT(_SLAB_RECLAIM_ACCOUNT) #else #define SLAB_RECLAIM_ACCOUNT __SLAB_FLAG_UNUSED #endif #define SLAB_TEMPORARY SLAB_RECLAIM_ACCOUNT /* Objects are short-lived */ /* Slab created using create_boot_cache */ #ifdef CONFIG_SLAB_OBJ_EXT #define SLAB_NO_OBJ_EXT __SLAB_FLAG_BIT(_SLAB_NO_OBJ_EXT) #else #define SLAB_NO_OBJ_EXT __SLAB_FLAG_UNUSED #endif /* * freeptr_t represents a SLUB freelist pointer, which might be encoded * and not dereferenceable if CONFIG_SLAB_FREELIST_HARDENED is enabled. */ typedef struct { unsigned long v; } freeptr_t; /* * ZERO_SIZE_PTR will be returned for zero sized kmalloc requests. * * Dereferencing ZERO_SIZE_PTR will lead to a distinct access fault. * * ZERO_SIZE_PTR can be passed to kfree though in the same way that NULL can. * Both make kfree a no-op. */ #define ZERO_SIZE_PTR ((void *)16) #define ZERO_OR_NULL_PTR(x) ((unsigned long)(x) <= \ (unsigned long)ZERO_SIZE_PTR) #include <linux/kasan.h> struct list_lru; struct mem_cgroup; /* * struct kmem_cache related prototypes */ bool slab_is_available(void); /** * struct kmem_cache_args - Less common arguments for kmem_cache_create() * * Any uninitialized fields of the structure are interpreted as unused. The * exception is @freeptr_offset where %0 is a valid value, so * @use_freeptr_offset must be also set to %true in order to interpret the field * as used. For @useroffset %0 is also valid, but only with non-%0 * @usersize. * * When %NULL args is passed to kmem_cache_create(), it is equivalent to all * fields unused. */ struct kmem_cache_args { /** * @align: The required alignment for the objects. * * %0 means no specific alignment is requested. */ unsigned int align; /** * @useroffset: Usercopy region offset. * * %0 is a valid offset, when @usersize is non-%0 */ unsigned int useroffset; /** * @usersize: Usercopy region size. * * %0 means no usercopy region is specified. */ unsigned int usersize; /** * @freeptr_offset: Custom offset for the free pointer * in &SLAB_TYPESAFE_BY_RCU caches * * By default &SLAB_TYPESAFE_BY_RCU caches place the free pointer * outside of the object. This might cause the object to grow in size. * Cache creators that have a reason to avoid this can specify a custom * free pointer offset in their struct where the free pointer will be * placed. * * Note that placing the free pointer inside the object requires the * caller to ensure that no fields are invalidated that are required to * guard against object recycling (See &SLAB_TYPESAFE_BY_RCU for * details). * * Using %0 as a value for @freeptr_offset is valid. If @freeptr_offset * is specified, %use_freeptr_offset must be set %true. * * Note that @ctor currently isn't supported with custom free pointers * as a @ctor requires an external free pointer. */ unsigned int freeptr_offset; /** * @use_freeptr_offset: Whether a @freeptr_offset is used. */ bool use_freeptr_offset; /** * @ctor: A constructor for the objects. * * The constructor is invoked for each object in a newly allocated slab * page. It is the cache user's responsibility to free object in the * same state as after calling the constructor, or deal appropriately * with any differences between a freshly constructed and a reallocated * object. * * %NULL means no constructor. */ void (*ctor)(void *); }; struct kmem_cache *__kmem_cache_create_args(const char *name, unsigned int object_size, struct kmem_cache_args *args, slab_flags_t flags); static inline struct kmem_cache * __kmem_cache_create(const char *name, unsigned int size, unsigned int align, slab_flags_t flags, void (*ctor)(void *)) { struct kmem_cache_args kmem_args = { .align = align, .ctor = ctor, }; return __kmem_cache_create_args(name, size, &kmem_args, flags); } /** * kmem_cache_create_usercopy - Create a kmem cache with a region suitable * for copying to userspace. * @name: A string which is used in /proc/slabinfo to identify this cache. * @size: The size of objects to be created in this cache. * @align: The required alignment for the objects. * @flags: SLAB flags * @useroffset: Usercopy region offset * @usersize: Usercopy region size * @ctor: A constructor for the objects, or %NULL. * * This is a legacy wrapper, new code should use either KMEM_CACHE_USERCOPY() * if whitelisting a single field is sufficient, or kmem_cache_create() with * the necessary parameters passed via the args parameter (see * &struct kmem_cache_args) * * Return: a pointer to the cache on success, NULL on failure. */ static inline struct kmem_cache * kmem_cache_create_usercopy(const char *name, unsigned int size, unsigned int align, slab_flags_t flags, unsigned int useroffset, unsigned int usersize, void (*ctor)(void *)) { struct kmem_cache_args kmem_args = { .align = align, .ctor = ctor, .useroffset = useroffset, .usersize = usersize, }; return __kmem_cache_create_args(name, size, &kmem_args, flags); } /* If NULL is passed for @args, use this variant with default arguments. */ static inline struct kmem_cache * __kmem_cache_default_args(const char *name, unsigned int size, struct kmem_cache_args *args, slab_flags_t flags) { struct kmem_cache_args kmem_default_args = {}; /* Make sure we don't get passed garbage. */ if (WARN_ON_ONCE(args)) return ERR_PTR(-EINVAL); return __kmem_cache_create_args(name, size, &kmem_default_args, flags); } /** * kmem_cache_create - Create a kmem cache. * @__name: A string which is used in /proc/slabinfo to identify this cache. * @__object_size: The size of objects to be created in this cache. * @__args: Optional arguments, see &struct kmem_cache_args. Passing %NULL * means defaults will be used for all the arguments. * * This is currently implemented as a macro using ``_Generic()`` to call * either the new variant of the function, or a legacy one. * * The new variant has 4 parameters: * ``kmem_cache_create(name, object_size, args, flags)`` * * See __kmem_cache_create_args() which implements this. * * The legacy variant has 5 parameters: * ``kmem_cache_create(name, object_size, align, flags, ctor)`` * * The align and ctor parameters map to the respective fields of * &struct kmem_cache_args * * Context: Cannot be called within a interrupt, but can be interrupted. * * Return: a pointer to the cache on success, NULL on failure. */ #define kmem_cache_create(__name, __object_size, __args, ...) \ _Generic((__args), \ struct kmem_cache_args *: __kmem_cache_create_args, \ void *: __kmem_cache_default_args, \ default: __kmem_cache_create)(__name, __object_size, __args, __VA_ARGS__) void kmem_cache_destroy(struct kmem_cache *s); int kmem_cache_shrink(struct kmem_cache *s); /* * Please use this macro to create slab caches. Simply specify the * name of the structure and maybe some flags that are listed above. * * The alignment of the struct determines object alignment. If you * f.e. add ____cacheline_aligned_in_smp to the struct declaration * then the objects will be properly aligned in SMP configurations. */ #define KMEM_CACHE(__struct, __flags) \ __kmem_cache_create_args(#__struct, sizeof(struct __struct), \ &(struct kmem_cache_args) { \ .align = __alignof__(struct __struct), \ }, (__flags)) /* * To whitelist a single field for copying to/from usercopy, use this * macro instead for KMEM_CACHE() above. */ #define KMEM_CACHE_USERCOPY(__struct, __flags, __field) \ __kmem_cache_create_args(#__struct, sizeof(struct __struct), \ &(struct kmem_cache_args) { \ .align = __alignof__(struct __struct), \ .useroffset = offsetof(struct __struct, __field), \ .usersize = sizeof_field(struct __struct, __field), \ }, (__flags)) /* * Common kmalloc functions provided by all allocators */ void * __must_check krealloc_noprof(const void *objp, size_t new_size, gfp_t flags) __realloc_size(2); #define krealloc(...) alloc_hooks(krealloc_noprof(__VA_ARGS__)) void kfree(const void *objp); void kfree_sensitive(const void *objp); size_t __ksize(const void *objp); DEFINE_FREE(kfree, void *, if (!IS_ERR_OR_NULL(_T)) kfree(_T)) DEFINE_FREE(kfree_sensitive, void *, if (_T) kfree_sensitive(_T)) /** * ksize - Report actual allocation size of associated object * * @objp: Pointer returned from a prior kmalloc()-family allocation. * * This should not be used for writing beyond the originally requested * allocation size. Either use krealloc() or round up the allocation size * with kmalloc_size_roundup() prior to allocation. If this is used to * access beyond the originally requested allocation size, UBSAN_BOUNDS * and/or FORTIFY_SOURCE may trip, since they only know about the * originally allocated size via the __alloc_size attribute. */ size_t ksize(const void *objp); #ifdef CONFIG_PRINTK bool kmem_dump_obj(void *object); #else static inline bool kmem_dump_obj(void *object) { return false; } #endif /* * Some archs want to perform DMA into kmalloc caches and need a guaranteed * alignment larger than the alignment of a 64-bit integer. * Setting ARCH_DMA_MINALIGN in arch headers allows that. */ #ifdef ARCH_HAS_DMA_MINALIGN #if ARCH_DMA_MINALIGN > 8 && !defined(ARCH_KMALLOC_MINALIGN) #define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN #endif #endif #ifndef ARCH_KMALLOC_MINALIGN #define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) #elif ARCH_KMALLOC_MINALIGN > 8 #define KMALLOC_MIN_SIZE ARCH_KMALLOC_MINALIGN #define KMALLOC_SHIFT_LOW ilog2(KMALLOC_MIN_SIZE) #endif /* * Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment. * Intended for arches that get misalignment faults even for 64 bit integer * aligned buffers. */ #ifndef ARCH_SLAB_MINALIGN #define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) #endif /* * Arches can define this function if they want to decide the minimum slab * alignment at runtime. The value returned by the function must be a power * of two and >= ARCH_SLAB_MINALIGN. */ #ifndef arch_slab_minalign static inline unsigned int arch_slab_minalign(void) { return ARCH_SLAB_MINALIGN; } #endif /* * kmem_cache_alloc and friends return pointers aligned to ARCH_SLAB_MINALIGN. * kmalloc and friends return pointers aligned to both ARCH_KMALLOC_MINALIGN * and ARCH_SLAB_MINALIGN, but here we only assume the former alignment. */ #define __assume_kmalloc_alignment __assume_aligned(ARCH_KMALLOC_MINALIGN) #define __assume_slab_alignment __assume_aligned(ARCH_SLAB_MINALIGN) #define __assume_page_alignment __assume_aligned(PAGE_SIZE) /* * Kmalloc array related definitions */ /* * SLUB directly allocates requests fitting in to an order-1 page * (PAGE_SIZE*2). Larger requests are passed to the page allocator. */ #define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) #define KMALLOC_SHIFT_MAX (MAX_PAGE_ORDER + PAGE_SHIFT) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif /* Maximum allocatable size */ #define KMALLOC_MAX_SIZE (1UL << KMALLOC_SHIFT_MAX) /* Maximum size for which we actually use a slab cache */ #define KMALLOC_MAX_CACHE_SIZE (1UL << KMALLOC_SHIFT_HIGH) /* Maximum order allocatable via the slab allocator */ #define KMALLOC_MAX_ORDER (KMALLOC_SHIFT_MAX - PAGE_SHIFT) /* * Kmalloc subsystem. */ #ifndef KMALLOC_MIN_SIZE #define KMALLOC_MIN_SIZE (1 << KMALLOC_SHIFT_LOW) #endif /* * This restriction comes from byte sized index implementation. * Page size is normally 2^12 bytes and, in this case, if we want to use * byte sized index which can represent 2^8 entries, the size of the object * should be equal or greater to 2^12 / 2^8 = 2^4 = 16. * If minimum size of kmalloc is less than 16, we use it as minimum object * size and give up to use byte sized index. */ #define SLAB_OBJ_MIN_SIZE (KMALLOC_MIN_SIZE < 16 ? \ (KMALLOC_MIN_SIZE) : 16) #ifdef CONFIG_RANDOM_KMALLOC_CACHES #define RANDOM_KMALLOC_CACHES_NR 15 // # of cache copies #else #define RANDOM_KMALLOC_CACHES_NR 0 #endif /* * Whenever changing this, take care of that kmalloc_type() and * create_kmalloc_caches() still work as intended. * * KMALLOC_NORMAL can contain only unaccounted objects whereas KMALLOC_CGROUP * is for accounted but unreclaimable and non-dma objects. All the other * kmem caches can have both accounted and unaccounted objects. */ enum kmalloc_cache_type { KMALLOC_NORMAL = 0, #ifndef CONFIG_ZONE_DMA KMALLOC_DMA = KMALLOC_NORMAL, #endif #ifndef CONFIG_MEMCG KMALLOC_CGROUP = KMALLOC_NORMAL, #endif KMALLOC_RANDOM_START = KMALLOC_NORMAL, KMALLOC_RANDOM_END = KMALLOC_RANDOM_START + RANDOM_KMALLOC_CACHES_NR, #ifdef CONFIG_SLUB_TINY KMALLOC_RECLAIM = KMALLOC_NORMAL, #else KMALLOC_RECLAIM, #endif #ifdef CONFIG_ZONE_DMA KMALLOC_DMA, #endif #ifdef CONFIG_MEMCG KMALLOC_CGROUP, #endif NR_KMALLOC_TYPES }; typedef struct kmem_cache * kmem_buckets[KMALLOC_SHIFT_HIGH + 1]; extern kmem_buckets kmalloc_caches[NR_KMALLOC_TYPES]; /* * Define gfp bits that should not be set for KMALLOC_NORMAL. */ #define KMALLOC_NOT_NORMAL_BITS \ (__GFP_RECLAIMABLE | \ (IS_ENABLED(CONFIG_ZONE_DMA) ? __GFP_DMA : 0) | \ (IS_ENABLED(CONFIG_MEMCG) ? __GFP_ACCOUNT : 0)) extern unsigned long random_kmalloc_seed; static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags, unsigned long caller) { /* * The most common case is KMALLOC_NORMAL, so test for it * with a single branch for all the relevant flags. */ if (likely((flags & KMALLOC_NOT_NORMAL_BITS) == 0)) #ifdef CONFIG_RANDOM_KMALLOC_CACHES /* RANDOM_KMALLOC_CACHES_NR (=15) copies + the KMALLOC_NORMAL */ return KMALLOC_RANDOM_START + hash_64(caller ^ random_kmalloc_seed, ilog2(RANDOM_KMALLOC_CACHES_NR + 1)); #else return KMALLOC_NORMAL; #endif /* * At least one of the flags has to be set. Their priorities in * decreasing order are: * 1) __GFP_DMA * 2) __GFP_RECLAIMABLE * 3) __GFP_ACCOUNT */ if (IS_ENABLED(CONFIG_ZONE_DMA) && (flags & __GFP_DMA)) return KMALLOC_DMA; if (!IS_ENABLED(CONFIG_MEMCG) || (flags & __GFP_RECLAIMABLE)) return KMALLOC_RECLAIM; else return KMALLOC_CGROUP; } /* * Figure out which kmalloc slab an allocation of a certain size * belongs to. * 0 = zero alloc * 1 = 65 .. 96 bytes * 2 = 129 .. 192 bytes * n = 2^(n-1)+1 .. 2^n * * Note: __kmalloc_index() is compile-time optimized, and not runtime optimized; * typical usage is via kmalloc_index() and therefore evaluated at compile-time. * Callers where !size_is_constant should only be test modules, where runtime * overheads of __kmalloc_index() can be tolerated. Also see kmalloc_slab(). */ static __always_inline unsigned int __kmalloc_index(size_t size, bool size_is_constant) { if (!size) return 0; if (size <= KMALLOC_MIN_SIZE) return KMALLOC_SHIFT_LOW; if (KMALLOC_MIN_SIZE <= 32 && size > 64 && size <= 96) return 1; if (KMALLOC_MIN_SIZE <= 64 && size > 128 && size <= 192) return 2; if (size <= 8) return 3; if (size <= 16) return 4; if (size <= 32) return 5; if (size <= 64) return 6; if (size <= 128) return 7; if (size <= 256) return 8; if (size <= 512) return 9; if (size <= 1024) return 10; if (size <= 2 * 1024) return 11; if (size <= 4 * 1024) return 12; if (size <= 8 * 1024) return 13; if (size <= 16 * 1024) return 14; if (size <= 32 * 1024) return 15; if (size <= 64 * 1024) return 16; if (size <= 128 * 1024) return 17; if (size <= 256 * 1024) return 18; if (size <= 512 * 1024) return 19; if (size <= 1024 * 1024) return 20; if (size <= 2 * 1024 * 1024) return 21; if (!IS_ENABLED(CONFIG_PROFILE_ALL_BRANCHES) && size_is_constant) BUILD_BUG_ON_MSG(1, "unexpected size in kmalloc_index()"); else BUG(); /* Will never be reached. Needed because the compiler may complain */ return -1; } static_assert(PAGE_SHIFT <= 20); #define kmalloc_index(s) __kmalloc_index(s, true) #include <linux/alloc_tag.h> /** * kmem_cache_alloc - Allocate an object * @cachep: The cache to allocate from. * @flags: See kmalloc(). * * Allocate an object from this cache. * See kmem_cache_zalloc() for a shortcut of adding __GFP_ZERO to flags. * * Return: pointer to the new object or %NULL in case of error */ void *kmem_cache_alloc_noprof(struct kmem_cache *cachep, gfp_t flags) __assume_slab_alignment __malloc; #define kmem_cache_alloc(...) alloc_hooks(kmem_cache_alloc_noprof(__VA_ARGS__)) void *kmem_cache_alloc_lru_noprof(struct kmem_cache *s, struct list_lru *lru, gfp_t gfpflags) __assume_slab_alignment __malloc; #define kmem_cache_alloc_lru(...) alloc_hooks(kmem_cache_alloc_lru_noprof(__VA_ARGS__)) /** * kmem_cache_charge - memcg charge an already allocated slab memory * @objp: address of the slab object to memcg charge * @gfpflags: describe the allocation context * * kmem_cache_charge allows charging a slab object to the current memcg, * primarily in cases where charging at allocation time might not be possible * because the target memcg is not known (i.e. softirq context) * * The objp should be pointer returned by the slab allocator functions like * kmalloc (with __GFP_ACCOUNT in flags) or kmem_cache_alloc. The memcg charge * behavior can be controlled through gfpflags parameter, which affects how the * necessary internal metadata can be allocated. Including __GFP_NOFAIL denotes * that overcharging is requested instead of failure, but is not applied for the * internal metadata allocation. * * There are several cases where it will return true even if the charging was * not done: * More specifically: * * 1. For !CONFIG_MEMCG or cgroup_disable=memory systems. * 2. Already charged slab objects. * 3. For slab objects from KMALLOC_NORMAL caches - allocated by kmalloc() * without __GFP_ACCOUNT * 4. Allocating internal metadata has failed * * Return: true if charge was successful otherwise false. */ bool kmem_cache_charge(void *objp, gfp_t gfpflags); void kmem_cache_free(struct kmem_cache *s, void *objp); kmem_buckets *kmem_buckets_create(const char *name, slab_flags_t flags, unsigned int useroffset, unsigned int usersize, void (*ctor)(void *)); /* * Bulk allocation and freeing operations. These are accelerated in an * allocator specific way to avoid taking locks repeatedly or building * metadata structures unnecessarily. * * Note that interrupts must be enabled when calling these functions. */ void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p); int kmem_cache_alloc_bulk_noprof(struct kmem_cache *s, gfp_t flags, size_t size, void **p); #define kmem_cache_alloc_bulk(...) alloc_hooks(kmem_cache_alloc_bulk_noprof(__VA_ARGS__)) static __always_inline void kfree_bulk(size_t size, void **p) { kmem_cache_free_bulk(NULL, size, p); } void *kmem_cache_alloc_node_noprof(struct kmem_cache *s, gfp_t flags, int node) __assume_slab_alignment __malloc; #define kmem_cache_alloc_node(...) alloc_hooks(kmem_cache_alloc_node_noprof(__VA_ARGS__)) /* * These macros allow declaring a kmem_buckets * parameter alongside size, which * can be compiled out with CONFIG_SLAB_BUCKETS=n so that a large number of call * sites don't have to pass NULL. */ #ifdef CONFIG_SLAB_BUCKETS #define DECL_BUCKET_PARAMS(_size, _b) size_t (_size), kmem_buckets *(_b) #define PASS_BUCKET_PARAMS(_size, _b) (_size), (_b) #define PASS_BUCKET_PARAM(_b) (_b) #else #define DECL_BUCKET_PARAMS(_size, _b) size_t (_size) #define PASS_BUCKET_PARAMS(_size, _b) (_size) #define PASS_BUCKET_PARAM(_b) NULL #endif /* * The following functions are not to be used directly and are intended only * for internal use from kmalloc() and kmalloc_node() * with the exception of kunit tests */ void *__kmalloc_noprof(size_t size, gfp_t flags) __assume_kmalloc_alignment __alloc_size(1); void *__kmalloc_node_noprof(DECL_BUCKET_PARAMS(size, b), gfp_t flags, int node) __assume_kmalloc_alignment __alloc_size(1); void *__kmalloc_cache_noprof(struct kmem_cache *s, gfp_t flags, size_t size) __assume_kmalloc_alignment __alloc_size(3); void *__kmalloc_cache_node_noprof(struct kmem_cache *s, gfp_t gfpflags, int node, size_t size) __assume_kmalloc_alignment __alloc_size(4); void *__kmalloc_large_noprof(size_t size, gfp_t flags) __assume_page_alignment __alloc_size(1); void *__kmalloc_large_node_noprof(size_t size, gfp_t flags, int node) __assume_page_alignment __alloc_size(1); /** * kmalloc - allocate kernel memory * @size: how many bytes of memory are required. * @flags: describe the allocation context * * kmalloc is the normal method of allocating memory * for objects smaller than page size in the kernel. * * The allocated object address is aligned to at least ARCH_KMALLOC_MINALIGN * bytes. For @size of power of two bytes, the alignment is also guaranteed * to be at least to the size. For other sizes, the alignment is guaranteed to * be at least the largest power-of-two divisor of @size. * * The @flags argument may be one of the GFP flags defined at * include/linux/gfp_types.h and described at * :ref:`Documentation/core-api/mm-api.rst <mm-api-gfp-flags>` * * The recommended usage of the @flags is described at * :ref:`Documentation/core-api/memory-allocation.rst <memory_allocation>` * * Below is a brief outline of the most useful GFP flags * * %GFP_KERNEL * Allocate normal kernel ram. May sleep. * * %GFP_NOWAIT * Allocation will not sleep. * * %GFP_ATOMIC * Allocation will not sleep. May use emergency pools. * * Also it is possible to set different flags by OR'ing * in one or more of the following additional @flags: * * %__GFP_ZERO * Zero the allocated memory before returning. Also see kzalloc(). * * %__GFP_HIGH * This allocation has high priority and may use emergency pools. * * %__GFP_NOFAIL * Indicate that this allocation is in no way allowed to fail * (think twice before using). * * %__GFP_NORETRY * If memory is not immediately available, * then give up at once. * * %__GFP_NOWARN * If allocation fails, don't issue any warnings. * * %__GFP_RETRY_MAYFAIL * Try really hard to succeed the allocation but fail * eventually. */ static __always_inline __alloc_size(1) void *kmalloc_noprof(size_t size, gfp_t flags) { if (__builtin_constant_p(size) && size) { unsigned int index; if (size > KMALLOC_MAX_CACHE_SIZE) return __kmalloc_large_noprof(size, flags); index = kmalloc_index(size); return __kmalloc_cache_noprof( kmalloc_caches[kmalloc_type(flags, _RET_IP_)][index], flags, size); } return __kmalloc_noprof(size, flags); } #define kmalloc(...) alloc_hooks(kmalloc_noprof(__VA_ARGS__)) #define kmem_buckets_alloc(_b, _size, _flags) \ alloc_hooks(__kmalloc_node_noprof(PASS_BUCKET_PARAMS(_size, _b), _flags, NUMA_NO_NODE)) #define kmem_buckets_alloc_track_caller(_b, _size, _flags) \ alloc_hooks(__kmalloc_node_track_caller_noprof(PASS_BUCKET_PARAMS(_size, _b), _flags, NUMA_NO_NODE, _RET_IP_)) static __always_inline __alloc_size(1) void *kmalloc_node_noprof(size_t size, gfp_t flags, int node) { if (__builtin_constant_p(size) && size) { unsigned int index; if (size > KMALLOC_MAX_CACHE_SIZE) return __kmalloc_large_node_noprof(size, flags, node); index = kmalloc_index(size); return __kmalloc_cache_node_noprof( kmalloc_caches[kmalloc_type(flags, _RET_IP_)][index], flags, node, size); } return __kmalloc_node_noprof(PASS_BUCKET_PARAMS(size, NULL), flags, node); } #define kmalloc_node(...) alloc_hooks(kmalloc_node_noprof(__VA_ARGS__)) /** * kmalloc_array - allocate memory for an array. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ static inline __alloc_size(1, 2) void *kmalloc_array_noprof(size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; if (__builtin_constant_p(n) && __builtin_constant_p(size)) return kmalloc_noprof(bytes, flags); return kmalloc_noprof(bytes, flags); } #define kmalloc_array(...) alloc_hooks(kmalloc_array_noprof(__VA_ARGS__)) /** * krealloc_array - reallocate memory for an array. * @p: pointer to the memory chunk to reallocate * @new_n: new number of elements to alloc * @new_size: new size of a single member of the array * @flags: the type of memory to allocate (see kmalloc) * * If __GFP_ZERO logic is requested, callers must ensure that, starting with the * initial memory allocation, every subsequent call to this API for the same * memory allocation is flagged with __GFP_ZERO. Otherwise, it is possible that * __GFP_ZERO is not fully honored by this API. * * See krealloc_noprof() for further details. * * In any case, the contents of the object pointed to are preserved up to the * lesser of the new and old sizes. */ static inline __realloc_size(2, 3) void * __must_check krealloc_array_noprof(void *p, size_t new_n, size_t new_size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(new_n, new_size, &bytes))) return NULL; return krealloc_noprof(p, bytes, flags); } #define krealloc_array(...) alloc_hooks(krealloc_array_noprof(__VA_ARGS__)) /** * kcalloc - allocate memory for an array. The memory is set to zero. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ #define kcalloc(n, size, flags) kmalloc_array(n, size, (flags) | __GFP_ZERO) void *__kmalloc_node_track_caller_noprof(DECL_BUCKET_PARAMS(size, b), gfp_t flags, int node, unsigned long caller) __alloc_size(1); #define kmalloc_node_track_caller_noprof(size, flags, node, caller) \ __kmalloc_node_track_caller_noprof(PASS_BUCKET_PARAMS(size, NULL), flags, node, caller) #define kmalloc_node_track_caller(...) \ alloc_hooks(kmalloc_node_track_caller_noprof(__VA_ARGS__, _RET_IP_)) /* * kmalloc_track_caller is a special version of kmalloc that records the * calling function of the routine calling it for slab leak tracking instead * of just the calling function (confusing, eh?). * It's useful when the call to kmalloc comes from a widely-used standard * allocator where we care about the real place the memory allocation * request comes from. */ #define kmalloc_track_caller(...) kmalloc_node_track_caller(__VA_ARGS__, NUMA_NO_NODE) #define kmalloc_track_caller_noprof(...) \ kmalloc_node_track_caller_noprof(__VA_ARGS__, NUMA_NO_NODE, _RET_IP_) static inline __alloc_size(1, 2) void *kmalloc_array_node_noprof(size_t n, size_t size, gfp_t flags, int node) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; if (__builtin_constant_p(n) && __builtin_constant_p(size)) return kmalloc_node_noprof(bytes, flags, node); return __kmalloc_node_noprof(PASS_BUCKET_PARAMS(bytes, NULL), flags, node); } #define kmalloc_array_node(...) alloc_hooks(kmalloc_array_node_noprof(__VA_ARGS__)) #define kcalloc_node(_n, _size, _flags, _node) \ kmalloc_array_node(_n, _size, (_flags) | __GFP_ZERO, _node) /* * Shortcuts */ #define kmem_cache_zalloc(_k, _flags) kmem_cache_alloc(_k, (_flags)|__GFP_ZERO) /** * kzalloc - allocate memory. The memory is set to zero. * @size: how many bytes of memory are required. * @flags: the type of memory to allocate (see kmalloc). */ static inline __alloc_size(1) void *kzalloc_noprof(size_t size, gfp_t flags) { return kmalloc_noprof(size, flags | __GFP_ZERO); } #define kzalloc(...) alloc_hooks(kzalloc_noprof(__VA_ARGS__)) #define kzalloc_node(_size, _flags, _node) kmalloc_node(_size, (_flags)|__GFP_ZERO, _node) void *__kvmalloc_node_noprof(DECL_BUCKET_PARAMS(size, b), gfp_t flags, int node) __alloc_size(1); #define kvmalloc_node_noprof(size, flags, node) \ __kvmalloc_node_noprof(PASS_BUCKET_PARAMS(size, NULL), flags, node) #define kvmalloc_node(...) alloc_hooks(kvmalloc_node_noprof(__VA_ARGS__)) #define kvmalloc(_size, _flags) kvmalloc_node(_size, _flags, NUMA_NO_NODE) #define kvmalloc_noprof(_size, _flags) kvmalloc_node_noprof(_size, _flags, NUMA_NO_NODE) #define kvzalloc(_size, _flags) kvmalloc(_size, (_flags)|__GFP_ZERO) #define kvzalloc_node(_size, _flags, _node) kvmalloc_node(_size, (_flags)|__GFP_ZERO, _node) #define kmem_buckets_valloc(_b, _size, _flags) \ alloc_hooks(__kvmalloc_node_noprof(PASS_BUCKET_PARAMS(_size, _b), _flags, NUMA_NO_NODE)) static inline __alloc_size(1, 2) void * kvmalloc_array_node_noprof(size_t n, size_t size, gfp_t flags, int node) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; return kvmalloc_node_noprof(bytes, flags, node); } #define kvmalloc_array_noprof(...) kvmalloc_array_node_noprof(__VA_ARGS__, NUMA_NO_NODE) #define kvcalloc_node_noprof(_n,_s,_f,_node) kvmalloc_array_node_noprof(_n,_s,(_f)|__GFP_ZERO,_node) #define kvcalloc_noprof(...) kvcalloc_node_noprof(__VA_ARGS__, NUMA_NO_NODE) #define kvmalloc_array(...) alloc_hooks(kvmalloc_array_noprof(__VA_ARGS__)) #define kvcalloc_node(...) alloc_hooks(kvcalloc_node_noprof(__VA_ARGS__)) #define kvcalloc(...) alloc_hooks(kvcalloc_noprof(__VA_ARGS__)) void *kvrealloc_noprof(const void *p, size_t size, gfp_t flags) __realloc_size(2); #define kvrealloc(...) alloc_hooks(kvrealloc_noprof(__VA_ARGS__)) extern void kvfree(const void *addr); DEFINE_FREE(kvfree, void *, if (!IS_ERR_OR_NULL(_T)) kvfree(_T)) extern void kvfree_sensitive(const void *addr, size_t len); unsigned int kmem_cache_size(struct kmem_cache *s); /** * kmalloc_size_roundup - Report allocation bucket size for the given size * * @size: Number of bytes to round up from. * * This returns the number of bytes that would be available in a kmalloc() * allocation of @size bytes. For example, a 126 byte request would be * rounded up to the next sized kmalloc bucket, 128 bytes. (This is strictly * for the general-purpose kmalloc()-based allocations, and is not for the * pre-sized kmem_cache_alloc()-based allocations.) * * Use this to kmalloc() the full bucket size ahead of time instead of using * ksize() to query the size after an allocation. */ size_t kmalloc_size_roundup(size_t size); void __init kmem_cache_init_late(void); #endif /* _LINUX_SLAB_H */ |
| 6 1 5 5 4 4 4 4 8 8 5 8 8 3700 3709 1452 3406 3783 3796 2884 3479 786 788 2 401 396 8 8 1 5 4 4 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 | // SPDX-License-Identifier: GPL-2.0-only /* * lib/bitmap.c * Helper functions for bitmap.h. */ #include <linux/bitmap.h> #include <linux/bitops.h> #include <linux/ctype.h> #include <linux/device.h> #include <linux/export.h> #include <linux/slab.h> /** * DOC: bitmap introduction * * bitmaps provide an array of bits, implemented using an * array of unsigned longs. The number of valid bits in a * given bitmap does _not_ need to be an exact multiple of * BITS_PER_LONG. * * The possible unused bits in the last, partially used word * of a bitmap are 'don't care'. The implementation makes * no particular effort to keep them zero. It ensures that * their value will not affect the results of any operation. * The bitmap operations that return Boolean (bitmap_empty, * for example) or scalar (bitmap_weight, for example) results * carefully filter out these unused bits from impacting their * results. * * The byte ordering of bitmaps is more natural on little * endian architectures. See the big-endian headers * include/asm-ppc64/bitops.h and include/asm-s390/bitops.h * for the best explanations of this ordering. */ bool __bitmap_equal(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k, lim = bits/BITS_PER_LONG; for (k = 0; k < lim; ++k) if (bitmap1[k] != bitmap2[k]) return false; if (bits % BITS_PER_LONG) if ((bitmap1[k] ^ bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) return false; return true; } EXPORT_SYMBOL(__bitmap_equal); bool __bitmap_or_equal(const unsigned long *bitmap1, const unsigned long *bitmap2, const unsigned long *bitmap3, unsigned int bits) { unsigned int k, lim = bits / BITS_PER_LONG; unsigned long tmp; for (k = 0; k < lim; ++k) { if ((bitmap1[k] | bitmap2[k]) != bitmap3[k]) return false; } if (!(bits % BITS_PER_LONG)) return true; tmp = (bitmap1[k] | bitmap2[k]) ^ bitmap3[k]; return (tmp & BITMAP_LAST_WORD_MASK(bits)) == 0; } void __bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int bits) { unsigned int k, lim = BITS_TO_LONGS(bits); for (k = 0; k < lim; ++k) dst[k] = ~src[k]; } EXPORT_SYMBOL(__bitmap_complement); /** * __bitmap_shift_right - logical right shift of the bits in a bitmap * @dst : destination bitmap * @src : source bitmap * @shift : shift by this many bits * @nbits : bitmap size, in bits * * Shifting right (dividing) means moving bits in the MS -> LS bit * direction. Zeros are fed into the vacated MS positions and the * LS bits shifted off the bottom are lost. */ void __bitmap_shift_right(unsigned long *dst, const unsigned long *src, unsigned shift, unsigned nbits) { unsigned k, lim = BITS_TO_LONGS(nbits); unsigned off = shift/BITS_PER_LONG, rem = shift % BITS_PER_LONG; unsigned long mask = BITMAP_LAST_WORD_MASK(nbits); for (k = 0; off + k < lim; ++k) { unsigned long upper, lower; /* * If shift is not word aligned, take lower rem bits of * word above and make them the top rem bits of result. */ if (!rem || off + k + 1 >= lim) upper = 0; else { upper = src[off + k + 1]; if (off + k + 1 == lim - 1) upper &= mask; upper <<= (BITS_PER_LONG - rem); } lower = src[off + k]; if (off + k == lim - 1) lower &= mask; lower >>= rem; dst[k] = lower | upper; } if (off) memset(&dst[lim - off], 0, off*sizeof(unsigned long)); } EXPORT_SYMBOL(__bitmap_shift_right); /** * __bitmap_shift_left - logical left shift of the bits in a bitmap * @dst : destination bitmap * @src : source bitmap * @shift : shift by this many bits * @nbits : bitmap size, in bits * * Shifting left (multiplying) means moving bits in the LS -> MS * direction. Zeros are fed into the vacated LS bit positions * and those MS bits shifted off the top are lost. */ void __bitmap_shift_left(unsigned long *dst, const unsigned long *src, unsigned int shift, unsigned int nbits) { int k; unsigned int lim = BITS_TO_LONGS(nbits); unsigned int off = shift/BITS_PER_LONG, rem = shift % BITS_PER_LONG; for (k = lim - off - 1; k >= 0; --k) { unsigned long upper, lower; /* * If shift is not word aligned, take upper rem bits of * word below and make them the bottom rem bits of result. */ if (rem && k > 0) lower = src[k - 1] >> (BITS_PER_LONG - rem); else lower = 0; upper = src[k] << rem; dst[k + off] = lower | upper; } if (off) memset(dst, 0, off*sizeof(unsigned long)); } EXPORT_SYMBOL(__bitmap_shift_left); /** * bitmap_cut() - remove bit region from bitmap and right shift remaining bits * @dst: destination bitmap, might overlap with src * @src: source bitmap * @first: start bit of region to be removed * @cut: number of bits to remove * @nbits: bitmap size, in bits * * Set the n-th bit of @dst iff the n-th bit of @src is set and * n is less than @first, or the m-th bit of @src is set for any * m such that @first <= n < nbits, and m = n + @cut. * * In pictures, example for a big-endian 32-bit architecture: * * The @src bitmap is:: * * 31 63 * | | * 10000000 11000001 11110010 00010101 10000000 11000001 01110010 00010101 * | | | | * 16 14 0 32 * * if @cut is 3, and @first is 14, bits 14-16 in @src are cut and @dst is:: * * 31 63 * | | * 10110000 00011000 00110010 00010101 00010000 00011000 00101110 01000010 * | | | * 14 (bit 17 0 32 * from @src) * * Note that @dst and @src might overlap partially or entirely. * * This is implemented in the obvious way, with a shift and carry * step for each moved bit. Optimisation is left as an exercise * for the compiler. */ void bitmap_cut(unsigned long *dst, const unsigned long *src, unsigned int first, unsigned int cut, unsigned int nbits) { unsigned int len = BITS_TO_LONGS(nbits); unsigned long keep = 0, carry; int i; if (first % BITS_PER_LONG) { keep = src[first / BITS_PER_LONG] & (~0UL >> (BITS_PER_LONG - first % BITS_PER_LONG)); } memmove(dst, src, len * sizeof(*dst)); while (cut--) { for (i = first / BITS_PER_LONG; i < len; i++) { if (i < len - 1) carry = dst[i + 1] & 1UL; else carry = 0; dst[i] = (dst[i] >> 1) | (carry << (BITS_PER_LONG - 1)); } } dst[first / BITS_PER_LONG] &= ~0UL << (first % BITS_PER_LONG); dst[first / BITS_PER_LONG] |= keep; } EXPORT_SYMBOL(bitmap_cut); bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; unsigned int lim = bits/BITS_PER_LONG; unsigned long result = 0; for (k = 0; k < lim; k++) result |= (dst[k] = bitmap1[k] & bitmap2[k]); if (bits % BITS_PER_LONG) result |= (dst[k] = bitmap1[k] & bitmap2[k] & BITMAP_LAST_WORD_MASK(bits)); return result != 0; } EXPORT_SYMBOL(__bitmap_and); void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; unsigned int nr = BITS_TO_LONGS(bits); for (k = 0; k < nr; k++) dst[k] = bitmap1[k] | bitmap2[k]; } EXPORT_SYMBOL(__bitmap_or); void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; unsigned int nr = BITS_TO_LONGS(bits); for (k = 0; k < nr; k++) dst[k] = bitmap1[k] ^ bitmap2[k]; } EXPORT_SYMBOL(__bitmap_xor); bool __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; unsigned int lim = bits/BITS_PER_LONG; unsigned long result = 0; for (k = 0; k < lim; k++) result |= (dst[k] = bitmap1[k] & ~bitmap2[k]); if (bits % BITS_PER_LONG) result |= (dst[k] = bitmap1[k] & ~bitmap2[k] & BITMAP_LAST_WORD_MASK(bits)); return result != 0; } EXPORT_SYMBOL(__bitmap_andnot); void __bitmap_replace(unsigned long *dst, const unsigned long *old, const unsigned long *new, const unsigned long *mask, unsigned int nbits) { unsigned int k; unsigned int nr = BITS_TO_LONGS(nbits); for (k = 0; k < nr; k++) dst[k] = (old[k] & ~mask[k]) | (new[k] & mask[k]); } EXPORT_SYMBOL(__bitmap_replace); bool __bitmap_intersects(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k, lim = bits/BITS_PER_LONG; for (k = 0; k < lim; ++k) if (bitmap1[k] & bitmap2[k]) return true; if (bits % BITS_PER_LONG) if ((bitmap1[k] & bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) return true; return false; } EXPORT_SYMBOL(__bitmap_intersects); bool __bitmap_subset(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k, lim = bits/BITS_PER_LONG; for (k = 0; k < lim; ++k) if (bitmap1[k] & ~bitmap2[k]) return false; if (bits % BITS_PER_LONG) if ((bitmap1[k] & ~bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) return false; return true; } EXPORT_SYMBOL(__bitmap_subset); #define BITMAP_WEIGHT(FETCH, bits) \ ({ \ unsigned int __bits = (bits), idx, w = 0; \ \ for (idx = 0; idx < __bits / BITS_PER_LONG; idx++) \ w += hweight_long(FETCH); \ \ if (__bits % BITS_PER_LONG) \ w += hweight_long((FETCH) & BITMAP_LAST_WORD_MASK(__bits)); \ \ w; \ }) unsigned int __bitmap_weight(const unsigned long *bitmap, unsigned int bits) { return BITMAP_WEIGHT(bitmap[idx], bits); } EXPORT_SYMBOL(__bitmap_weight); unsigned int __bitmap_weight_and(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { return BITMAP_WEIGHT(bitmap1[idx] & bitmap2[idx], bits); } EXPORT_SYMBOL(__bitmap_weight_and); unsigned int __bitmap_weight_andnot(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { return BITMAP_WEIGHT(bitmap1[idx] & ~bitmap2[idx], bits); } EXPORT_SYMBOL(__bitmap_weight_andnot); void __bitmap_set(unsigned long *map, unsigned int start, int len) { unsigned long *p = map + BIT_WORD(start); const unsigned int size = start + len; int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG); unsigned long mask_to_set = BITMAP_FIRST_WORD_MASK(start); while (len - bits_to_set >= 0) { *p |= mask_to_set; len -= bits_to_set; bits_to_set = BITS_PER_LONG; mask_to_set = ~0UL; p++; } if (len) { mask_to_set &= BITMAP_LAST_WORD_MASK(size); *p |= mask_to_set; } } EXPORT_SYMBOL(__bitmap_set); void __bitmap_clear(unsigned long *map, unsigned int start, int len) { unsigned long *p = map + BIT_WORD(start); const unsigned int size = start + len; int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG); unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start); while (len - bits_to_clear >= 0) { *p &= ~mask_to_clear; len -= bits_to_clear; bits_to_clear = BITS_PER_LONG; mask_to_clear = ~0UL; p++; } if (len) { mask_to_clear &= BITMAP_LAST_WORD_MASK(size); *p &= ~mask_to_clear; } } EXPORT_SYMBOL(__bitmap_clear); /** * bitmap_find_next_zero_area_off - find a contiguous aligned zero area * @map: The address to base the search on * @size: The bitmap size in bits * @start: The bitnumber to start searching at * @nr: The number of zeroed bits we're looking for * @align_mask: Alignment mask for zero area * @align_offset: Alignment offset for zero area. * * The @align_mask should be one less than a power of 2; the effect is that * the bit offset of all zero areas this function finds plus @align_offset * is multiple of that power of 2. */ unsigned long bitmap_find_next_zero_area_off(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, unsigned long align_mask, unsigned long align_offset) { unsigned long index, end, i; again: index = find_next_zero_bit(map, size, start); /* Align allocation */ index = __ALIGN_MASK(index + align_offset, align_mask) - align_offset; end = index + nr; if (end > size) return end; i = find_next_bit(map, end, index); if (i < end) { start = i + 1; goto again; } return index; } EXPORT_SYMBOL(bitmap_find_next_zero_area_off); /** * bitmap_pos_to_ord - find ordinal of set bit at given position in bitmap * @buf: pointer to a bitmap * @pos: a bit position in @buf (0 <= @pos < @nbits) * @nbits: number of valid bit positions in @buf * * Map the bit at position @pos in @buf (of length @nbits) to the * ordinal of which set bit it is. If it is not set or if @pos * is not a valid bit position, map to -1. * * If for example, just bits 4 through 7 are set in @buf, then @pos * values 4 through 7 will get mapped to 0 through 3, respectively, * and other @pos values will get mapped to -1. When @pos value 7 * gets mapped to (returns) @ord value 3 in this example, that means * that bit 7 is the 3rd (starting with 0th) set bit in @buf. * * The bit positions 0 through @bits are valid positions in @buf. */ static int bitmap_pos_to_ord(const unsigned long *buf, unsigned int pos, unsigned int nbits) { if (pos >= nbits || !test_bit(pos, buf)) return -1; return bitmap_weight(buf, pos); } /** * bitmap_remap - Apply map defined by a pair of bitmaps to another bitmap * @dst: remapped result * @src: subset to be remapped * @old: defines domain of map * @new: defines range of map * @nbits: number of bits in each of these bitmaps * * Let @old and @new define a mapping of bit positions, such that * whatever position is held by the n-th set bit in @old is mapped * to the n-th set bit in @new. In the more general case, allowing * for the possibility that the weight 'w' of @new is less than the * weight of @old, map the position of the n-th set bit in @old to * the position of the m-th set bit in @new, where m == n % w. * * If either of the @old and @new bitmaps are empty, or if @src and * @dst point to the same location, then this routine copies @src * to @dst. * * The positions of unset bits in @old are mapped to themselves * (the identity map). * * Apply the above specified mapping to @src, placing the result in * @dst, clearing any bits previously set in @dst. * * For example, lets say that @old has bits 4 through 7 set, and * @new has bits 12 through 15 set. This defines the mapping of bit * position 4 to 12, 5 to 13, 6 to 14 and 7 to 15, and of all other * bit positions unchanged. So if say @src comes into this routine * with bits 1, 5 and 7 set, then @dst should leave with bits 1, * 13 and 15 set. */ void bitmap_remap(unsigned long *dst, const unsigned long *src, const unsigned long *old, const unsigned long *new, unsigned int nbits) { unsigned int oldbit, w; if (dst == src) /* following doesn't handle inplace remaps */ return; bitmap_zero(dst, nbits); w = bitmap_weight(new, nbits); for_each_set_bit(oldbit, src, nbits) { int n = bitmap_pos_to_ord(old, oldbit, nbits); if (n < 0 || w == 0) set_bit(oldbit, dst); /* identity map */ else set_bit(find_nth_bit(new, nbits, n % w), dst); } } EXPORT_SYMBOL(bitmap_remap); /** * bitmap_bitremap - Apply map defined by a pair of bitmaps to a single bit * @oldbit: bit position to be mapped * @old: defines domain of map * @new: defines range of map * @bits: number of bits in each of these bitmaps * * Let @old and @new define a mapping of bit positions, such that * whatever position is held by the n-th set bit in @old is mapped * to the n-th set bit in @new. In the more general case, allowing * for the possibility that the weight 'w' of @new is less than the * weight of @old, map the position of the n-th set bit in @old to * the position of the m-th set bit in @new, where m == n % w. * * The positions of unset bits in @old are mapped to themselves * (the identity map). * * Apply the above specified mapping to bit position @oldbit, returning * the new bit position. * * For example, lets say that @old has bits 4 through 7 set, and * @new has bits 12 through 15 set. This defines the mapping of bit * position 4 to 12, 5 to 13, 6 to 14 and 7 to 15, and of all other * bit positions unchanged. So if say @oldbit is 5, then this routine * returns 13. */ int bitmap_bitremap(int oldbit, const unsigned long *old, const unsigned long *new, int bits) { int w = bitmap_weight(new, bits); int n = bitmap_pos_to_ord(old, oldbit, bits); if (n < 0 || w == 0) return oldbit; else return find_nth_bit(new, bits, n % w); } EXPORT_SYMBOL(bitmap_bitremap); #ifdef CONFIG_NUMA /** * bitmap_onto - translate one bitmap relative to another * @dst: resulting translated bitmap * @orig: original untranslated bitmap * @relmap: bitmap relative to which translated * @bits: number of bits in each of these bitmaps * * Set the n-th bit of @dst iff there exists some m such that the * n-th bit of @relmap is set, the m-th bit of @orig is set, and * the n-th bit of @relmap is also the m-th _set_ bit of @relmap. * (If you understood the previous sentence the first time your * read it, you're overqualified for your current job.) * * In other words, @orig is mapped onto (surjectively) @dst, * using the map { <n, m> | the n-th bit of @relmap is the * m-th set bit of @relmap }. * * Any set bits in @orig above bit number W, where W is the * weight of (number of set bits in) @relmap are mapped nowhere. * In particular, if for all bits m set in @orig, m >= W, then * @dst will end up empty. In situations where the possibility * of such an empty result is not desired, one way to avoid it is * to use the bitmap_fold() operator, below, to first fold the * @orig bitmap over itself so that all its set bits x are in the * range 0 <= x < W. The bitmap_fold() operator does this by * setting the bit (m % W) in @dst, for each bit (m) set in @orig. * * Example [1] for bitmap_onto(): * Let's say @relmap has bits 30-39 set, and @orig has bits * 1, 3, 5, 7, 9 and 11 set. Then on return from this routine, * @dst will have bits 31, 33, 35, 37 and 39 set. * * When bit 0 is set in @orig, it means turn on the bit in * @dst corresponding to whatever is the first bit (if any) * that is turned on in @relmap. Since bit 0 was off in the * above example, we leave off that bit (bit 30) in @dst. * * When bit 1 is set in @orig (as in the above example), it * means turn on the bit in @dst corresponding to whatever * is the second bit that is turned on in @relmap. The second * bit in @relmap that was turned on in the above example was * bit 31, so we turned on bit 31 in @dst. * * Similarly, we turned on bits 33, 35, 37 and 39 in @dst, * because they were the 4th, 6th, 8th and 10th set bits * set in @relmap, and the 4th, 6th, 8th and 10th bits of * @orig (i.e. bits 3, 5, 7 and 9) were also set. * * When bit 11 is set in @orig, it means turn on the bit in * @dst corresponding to whatever is the twelfth bit that is * turned on in @relmap. In the above example, there were * only ten bits turned on in @relmap (30..39), so that bit * 11 was set in @orig had no affect on @dst. * * Example [2] for bitmap_fold() + bitmap_onto(): * Let's say @relmap has these ten bits set:: * * 40 41 42 43 45 48 53 61 74 95 * * (for the curious, that's 40 plus the first ten terms of the * Fibonacci sequence.) * * Further lets say we use the following code, invoking * bitmap_fold() then bitmap_onto, as suggested above to * avoid the possibility of an empty @dst result:: * * unsigned long *tmp; // a temporary bitmap's bits * * bitmap_fold(tmp, orig, bitmap_weight(relmap, bits), bits); * bitmap_onto(dst, tmp, relmap, bits); * * Then this table shows what various values of @dst would be, for * various @orig's. I list the zero-based positions of each set bit. * The tmp column shows the intermediate result, as computed by * using bitmap_fold() to fold the @orig bitmap modulo ten * (the weight of @relmap): * * =============== ============== ================= * @orig tmp @dst * 0 0 40 * 1 1 41 * 9 9 95 * 10 0 40 [#f1]_ * 1 3 5 7 1 3 5 7 41 43 48 61 * 0 1 2 3 4 0 1 2 3 4 40 41 42 43 45 * 0 9 18 27 0 9 8 7 40 61 74 95 * 0 10 20 30 0 40 * 0 11 22 33 0 1 2 3 40 41 42 43 * 0 12 24 36 0 2 4 6 40 42 45 53 * 78 102 211 1 2 8 41 42 74 [#f1]_ * =============== ============== ================= * * .. [#f1] * * For these marked lines, if we hadn't first done bitmap_fold() * into tmp, then the @dst result would have been empty. * * If either of @orig or @relmap is empty (no set bits), then @dst * will be returned empty. * * If (as explained above) the only set bits in @orig are in positions * m where m >= W, (where W is the weight of @relmap) then @dst will * once again be returned empty. * * All bits in @dst not set by the above rule are cleared. */ void bitmap_onto(unsigned long *dst, const unsigned long *orig, const unsigned long *relmap, unsigned int bits) { unsigned int n, m; /* same meaning as in above comment */ if (dst == orig) /* following doesn't handle inplace mappings */ return; bitmap_zero(dst, bits); /* * The following code is a more efficient, but less * obvious, equivalent to the loop: * for (m = 0; m < bitmap_weight(relmap, bits); m++) { * n = find_nth_bit(orig, bits, m); * if (test_bit(m, orig)) * set_bit(n, dst); * } */ m = 0; for_each_set_bit(n, relmap, bits) { /* m == bitmap_pos_to_ord(relmap, n, bits) */ if (test_bit(m, orig)) set_bit(n, dst); m++; } } /** * bitmap_fold - fold larger bitmap into smaller, modulo specified size * @dst: resulting smaller bitmap * @orig: original larger bitmap * @sz: specified size * @nbits: number of bits in each of these bitmaps * * For each bit oldbit in @orig, set bit oldbit mod @sz in @dst. * Clear all other bits in @dst. See further the comment and * Example [2] for bitmap_onto() for why and how to use this. */ void bitmap_fold(unsigned long *dst, const unsigned long *orig, unsigned int sz, unsigned int nbits) { unsigned int oldbit; if (dst == orig) /* following doesn't handle inplace mappings */ return; bitmap_zero(dst, nbits); for_each_set_bit(oldbit, orig, nbits) set_bit(oldbit % sz, dst); } #endif /* CONFIG_NUMA */ unsigned long *bitmap_alloc(unsigned int nbits, gfp_t flags) { return kmalloc_array(BITS_TO_LONGS(nbits), sizeof(unsigned long), flags); } EXPORT_SYMBOL(bitmap_alloc); unsigned long *bitmap_zalloc(unsigned int nbits, gfp_t flags) { return bitmap_alloc(nbits, flags | __GFP_ZERO); } EXPORT_SYMBOL(bitmap_zalloc); unsigned long *bitmap_alloc_node(unsigned int nbits, gfp_t flags, int node) { return kmalloc_array_node(BITS_TO_LONGS(nbits), sizeof(unsigned long), flags, node); } EXPORT_SYMBOL(bitmap_alloc_node); unsigned long *bitmap_zalloc_node(unsigned int nbits, gfp_t flags, int node) { return bitmap_alloc_node(nbits, flags | __GFP_ZERO, node); } EXPORT_SYMBOL(bitmap_zalloc_node); void bitmap_free(const unsigned long *bitmap) { kfree(bitmap); } EXPORT_SYMBOL(bitmap_free); static void devm_bitmap_free(void *data) { unsigned long *bitmap = data; bitmap_free(bitmap); } unsigned long *devm_bitmap_alloc(struct device *dev, unsigned int nbits, gfp_t flags) { unsigned long *bitmap; int ret; bitmap = bitmap_alloc(nbits, flags); if (!bitmap) return NULL; ret = devm_add_action_or_reset(dev, devm_bitmap_free, bitmap); if (ret) return NULL; return bitmap; } EXPORT_SYMBOL_GPL(devm_bitmap_alloc); unsigned long *devm_bitmap_zalloc(struct device *dev, unsigned int nbits, gfp_t flags) { return devm_bitmap_alloc(dev, nbits, flags | __GFP_ZERO); } EXPORT_SYMBOL_GPL(devm_bitmap_zalloc); #if BITS_PER_LONG == 64 /** * bitmap_from_arr32 - copy the contents of u32 array of bits to bitmap * @bitmap: array of unsigned longs, the destination bitmap * @buf: array of u32 (in host byte order), the source bitmap * @nbits: number of bits in @bitmap */ void bitmap_from_arr32(unsigned long *bitmap, const u32 *buf, unsigned int nbits) { unsigned int i, halfwords; halfwords = DIV_ROUND_UP(nbits, 32); for (i = 0; i < halfwords; i++) { bitmap[i/2] = (unsigned long) buf[i]; if (++i < halfwords) bitmap[i/2] |= ((unsigned long) buf[i]) << 32; } /* Clear tail bits in last word beyond nbits. */ if (nbits % BITS_PER_LONG) bitmap[(halfwords - 1) / 2] &= BITMAP_LAST_WORD_MASK(nbits); } EXPORT_SYMBOL(bitmap_from_arr32); /** * bitmap_to_arr32 - copy the contents of bitmap to a u32 array of bits * @buf: array of u32 (in host byte order), the dest bitmap * @bitmap: array of unsigned longs, the source bitmap * @nbits: number of bits in @bitmap */ void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap, unsigned int nbits) { unsigned int i, halfwords; halfwords = DIV_ROUND_UP(nbits, 32); for (i = 0; i < halfwords; i++) { buf[i] = (u32) (bitmap[i/2] & UINT_MAX); if (++i < halfwords) buf[i] = (u32) (bitmap[i/2] >> 32); } /* Clear tail bits in last element of array beyond nbits. */ if (nbits % BITS_PER_LONG) buf[halfwords - 1] &= (u32) (UINT_MAX >> ((-nbits) & 31)); } EXPORT_SYMBOL(bitmap_to_arr32); #endif #if BITS_PER_LONG == 32 /** * bitmap_from_arr64 - copy the contents of u64 array of bits to bitmap * @bitmap: array of unsigned longs, the destination bitmap * @buf: array of u64 (in host byte order), the source bitmap * @nbits: number of bits in @bitmap */ void bitmap_from_arr64(unsigned long *bitmap, const u64 *buf, unsigned int nbits) { int n; for (n = nbits; n > 0; n -= 64) { u64 val = *buf++; *bitmap++ = val; if (n > 32) *bitmap++ = val >> 32; } /* * Clear tail bits in the last word beyond nbits. * * Negative index is OK because here we point to the word next * to the last word of the bitmap, except for nbits == 0, which * is tested implicitly. */ if (nbits % BITS_PER_LONG) bitmap[-1] &= BITMAP_LAST_WORD_MASK(nbits); } EXPORT_SYMBOL(bitmap_from_arr64); /** * bitmap_to_arr64 - copy the contents of bitmap to a u64 array of bits * @buf: array of u64 (in host byte order), the dest bitmap * @bitmap: array of unsigned longs, the source bitmap * @nbits: number of bits in @bitmap */ void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits) { const unsigned long *end = bitmap + BITS_TO_LONGS(nbits); while (bitmap < end) { *buf = *bitmap++; if (bitmap < end) *buf |= (u64)(*bitmap++) << 32; buf++; } /* Clear tail bits in the last element of array beyond nbits. */ if (nbits % 64) buf[-1] &= GENMASK_ULL((nbits - 1) % 64, 0); } EXPORT_SYMBOL(bitmap_to_arr64); #endif |
| 2 1 1 1 1 1 10 12 2 2 9 4 10 10 10 2 2 1 1 1 1 1 1 3 3 1 5 5 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 | // SPDX-License-Identifier: GPL-2.0-or-later /* SCTP kernel implementation * (C) Copyright Red Hat Inc. 2022 * * This file is part of the SCTP kernel implementation * * These functions manipulate sctp stream queue/scheduling. * * Please send any bug reports or fixes you make to the * email addresched(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * Xin Long <lucien.xin@gmail.com> */ #include <linux/list.h> #include <net/sctp/sctp.h> #include <net/sctp/sm.h> #include <net/sctp/stream_sched.h> /* Fair Capacity and Weighted Fair Queueing handling * RFC 8260 section 3.5 and 3.6 */ static void sctp_sched_fc_unsched_all(struct sctp_stream *stream); static int sctp_sched_wfq_set(struct sctp_stream *stream, __u16 sid, __u16 weight, gfp_t gfp) { struct sctp_stream_out_ext *soute = SCTP_SO(stream, sid)->ext; if (!weight) return -EINVAL; soute->fc_weight = weight; return 0; } static int sctp_sched_wfq_get(struct sctp_stream *stream, __u16 sid, __u16 *value) { struct sctp_stream_out_ext *soute = SCTP_SO(stream, sid)->ext; *value = soute->fc_weight; return 0; } static int sctp_sched_fc_set(struct sctp_stream *stream, __u16 sid, __u16 weight, gfp_t gfp) { return 0; } static int sctp_sched_fc_get(struct sctp_stream *stream, __u16 sid, __u16 *value) { return 0; } static int sctp_sched_fc_init(struct sctp_stream *stream) { INIT_LIST_HEAD(&stream->fc_list); return 0; } static int sctp_sched_fc_init_sid(struct sctp_stream *stream, __u16 sid, gfp_t gfp) { struct sctp_stream_out_ext *soute = SCTP_SO(stream, sid)->ext; INIT_LIST_HEAD(&soute->fc_list); soute->fc_length = 0; soute->fc_weight = 1; return 0; } static void sctp_sched_fc_free_sid(struct sctp_stream *stream, __u16 sid) { } static void sctp_sched_fc_sched(struct sctp_stream *stream, struct sctp_stream_out_ext *soute) { struct sctp_stream_out_ext *pos; if (!list_empty(&soute->fc_list)) return; list_for_each_entry(pos, &stream->fc_list, fc_list) if ((__u64)pos->fc_length * soute->fc_weight >= (__u64)soute->fc_length * pos->fc_weight) break; list_add_tail(&soute->fc_list, &pos->fc_list); } static void sctp_sched_fc_enqueue(struct sctp_outq *q, struct sctp_datamsg *msg) { struct sctp_stream *stream; struct sctp_chunk *ch; __u16 sid; ch = list_first_entry(&msg->chunks, struct sctp_chunk, frag_list); sid = sctp_chunk_stream_no(ch); stream = &q->asoc->stream; sctp_sched_fc_sched(stream, SCTP_SO(stream, sid)->ext); } static struct sctp_chunk *sctp_sched_fc_dequeue(struct sctp_outq *q) { struct sctp_stream *stream = &q->asoc->stream; struct sctp_stream_out_ext *soute; struct sctp_chunk *ch; /* Bail out quickly if queue is empty */ if (list_empty(&q->out_chunk_list)) return NULL; /* Find which chunk is next */ if (stream->out_curr) soute = stream->out_curr->ext; else soute = list_entry(stream->fc_list.next, struct sctp_stream_out_ext, fc_list); ch = list_entry(soute->outq.next, struct sctp_chunk, stream_list); sctp_sched_dequeue_common(q, ch); return ch; } static void sctp_sched_fc_dequeue_done(struct sctp_outq *q, struct sctp_chunk *ch) { struct sctp_stream *stream = &q->asoc->stream; struct sctp_stream_out_ext *soute, *pos; __u16 sid, i; sid = sctp_chunk_stream_no(ch); soute = SCTP_SO(stream, sid)->ext; /* reduce all fc_lengths by U32_MAX / 4 if the current fc_length overflows. */ if (soute->fc_length > U32_MAX - ch->skb->len) { for (i = 0; i < stream->outcnt; i++) { pos = SCTP_SO(stream, i)->ext; if (!pos) continue; if (pos->fc_length <= (U32_MAX >> 2)) { pos->fc_length = 0; continue; } pos->fc_length -= (U32_MAX >> 2); } } soute->fc_length += ch->skb->len; if (list_empty(&soute->outq)) { list_del_init(&soute->fc_list); return; } pos = soute; list_for_each_entry_continue(pos, &stream->fc_list, fc_list) if ((__u64)pos->fc_length * soute->fc_weight >= (__u64)soute->fc_length * pos->fc_weight) break; list_move_tail(&soute->fc_list, &pos->fc_list); } static void sctp_sched_fc_sched_all(struct sctp_stream *stream) { struct sctp_association *asoc; struct sctp_chunk *ch; asoc = container_of(stream, struct sctp_association, stream); list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list) { __u16 sid = sctp_chunk_stream_no(ch); if (SCTP_SO(stream, sid)->ext) sctp_sched_fc_sched(stream, SCTP_SO(stream, sid)->ext); } } static void sctp_sched_fc_unsched_all(struct sctp_stream *stream) { struct sctp_stream_out_ext *soute, *tmp; list_for_each_entry_safe(soute, tmp, &stream->fc_list, fc_list) list_del_init(&soute->fc_list); } static struct sctp_sched_ops sctp_sched_fc = { .set = sctp_sched_fc_set, .get = sctp_sched_fc_get, .init = sctp_sched_fc_init, .init_sid = sctp_sched_fc_init_sid, .free_sid = sctp_sched_fc_free_sid, .enqueue = sctp_sched_fc_enqueue, .dequeue = sctp_sched_fc_dequeue, .dequeue_done = sctp_sched_fc_dequeue_done, .sched_all = sctp_sched_fc_sched_all, .unsched_all = sctp_sched_fc_unsched_all, }; void sctp_sched_ops_fc_init(void) { sctp_sched_ops_register(SCTP_SS_FC, &sctp_sched_fc); } static struct sctp_sched_ops sctp_sched_wfq = { .set = sctp_sched_wfq_set, .get = sctp_sched_wfq_get, .init = sctp_sched_fc_init, .init_sid = sctp_sched_fc_init_sid, .free_sid = sctp_sched_fc_free_sid, .enqueue = sctp_sched_fc_enqueue, .dequeue = sctp_sched_fc_dequeue, .dequeue_done = sctp_sched_fc_dequeue_done, .sched_all = sctp_sched_fc_sched_all, .unsched_all = sctp_sched_fc_unsched_all, }; void sctp_sched_ops_wfq_init(void) { sctp_sched_ops_register(SCTP_SS_WFQ, &sctp_sched_wfq); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Stubs for the Network PHY library */ #include <linux/rtnetlink.h> struct kernel_hwtstamp_config; struct netlink_ext_ack; struct phy_device; #if IS_ENABLED(CONFIG_PHYLIB) extern const struct phylib_stubs *phylib_stubs; struct phylib_stubs { int (*hwtstamp_get)(struct phy_device *phydev, struct kernel_hwtstamp_config *config); int (*hwtstamp_set)(struct phy_device *phydev, struct kernel_hwtstamp_config *config, struct netlink_ext_ack *extack); }; static inline int phy_hwtstamp_get(struct phy_device *phydev, struct kernel_hwtstamp_config *config) { /* phylib_register_stubs() and phylib_unregister_stubs() * also run under rtnl_lock(). */ ASSERT_RTNL(); if (!phylib_stubs) return -EOPNOTSUPP; return phylib_stubs->hwtstamp_get(phydev, config); } static inline int phy_hwtstamp_set(struct phy_device *phydev, struct kernel_hwtstamp_config *config, struct netlink_ext_ack *extack) { /* phylib_register_stubs() and phylib_unregister_stubs() * also run under rtnl_lock(). */ ASSERT_RTNL(); if (!phylib_stubs) return -EOPNOTSUPP; return phylib_stubs->hwtstamp_set(phydev, config, extack); } #else static inline int phy_hwtstamp_get(struct phy_device *phydev, struct kernel_hwtstamp_config *config) { return -EOPNOTSUPP; } static inline int phy_hwtstamp_set(struct phy_device *phydev, struct kernel_hwtstamp_config *config, struct netlink_ext_ack *extack) { return -EOPNOTSUPP; } #endif |
| 23 1 22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright 2002-2005, Instant802 Networks, Inc. * Copyright 2005, Devicescape Software, Inc. * Copyright (c) 2006 Jiri Benc <jbenc@suse.cz> * Copyright (C) 2022, 2024 Intel Corporation */ #ifndef IEEE80211_RATE_H #define IEEE80211_RATE_H #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/types.h> #include <net/mac80211.h> #include "ieee80211_i.h" #include "sta_info.h" #include "driver-ops.h" struct rate_control_ref { const struct rate_control_ops *ops; void *priv; }; void rate_control_get_rate(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, struct ieee80211_tx_rate_control *txrc); void rate_control_tx_status(struct ieee80211_local *local, struct ieee80211_tx_status *st); void rate_control_rate_init(struct link_sta_info *link_sta); void rate_control_rate_init_all_links(struct sta_info *sta); void rate_control_rate_update(struct ieee80211_local *local, struct ieee80211_supported_band *sband, struct link_sta_info *link_sta, u32 changed); static inline void *rate_control_alloc_sta(struct rate_control_ref *ref, struct sta_info *sta, gfp_t gfp) { spin_lock_init(&sta->rate_ctrl_lock); return ref->ops->alloc_sta(ref->priv, &sta->sta, gfp); } static inline void rate_control_free_sta(struct sta_info *sta) { struct rate_control_ref *ref = sta->rate_ctrl; struct ieee80211_sta *ista = &sta->sta; void *priv_sta = sta->rate_ctrl_priv; ref->ops->free_sta(ref->priv, ista, priv_sta); } static inline void rate_control_add_sta_debugfs(struct sta_info *sta) { #ifdef CONFIG_MAC80211_DEBUGFS struct rate_control_ref *ref = sta->rate_ctrl; if (ref && sta->debugfs_dir && ref->ops->add_sta_debugfs) ref->ops->add_sta_debugfs(ref->priv, sta->rate_ctrl_priv, sta->debugfs_dir); #endif } extern const struct debugfs_short_fops rcname_ops; static inline void rate_control_add_debugfs(struct ieee80211_local *local) { #ifdef CONFIG_MAC80211_DEBUGFS struct dentry *debugfsdir; if (!local->rate_ctrl) return; if (!local->rate_ctrl->ops->add_debugfs) return; debugfsdir = debugfs_create_dir("rc", local->hw.wiphy->debugfsdir); local->debugfs.rcdir = debugfsdir; debugfs_create_file("name", 0400, debugfsdir, local->rate_ctrl, &rcname_ops); local->rate_ctrl->ops->add_debugfs(&local->hw, local->rate_ctrl->priv, debugfsdir); #endif } void ieee80211_check_rate_mask(struct ieee80211_link_data *link); /* Get a reference to the rate control algorithm. If `name' is NULL, get the * first available algorithm. */ int ieee80211_init_rate_ctrl_alg(struct ieee80211_local *local, const char *name); void rate_control_deinitialize(struct ieee80211_local *local); /* Rate control algorithms */ #ifdef CONFIG_MAC80211_RC_MINSTREL int rc80211_minstrel_init(void); void rc80211_minstrel_exit(void); #else static inline int rc80211_minstrel_init(void) { return 0; } static inline void rc80211_minstrel_exit(void) { } #endif #endif /* IEEE80211_RATE_H */ |
| 237 222 40 1 32 40 375 74 616 14 14 29 8 23 14 123 123 121 1 519 147 85 316 47 91 279 282 313 200 50 201 19 19 13 7 2 5 5 2 4 2 5 5 3 50 51 39 3 13 3 3 1 1 39 268 270 267 44 250 51 1 9 4 6 1 8 6 12 12 5 9 1 6 1 2 5 6 8 2 13 4 10 2 9 3 3 3 3 3 4 3 20 20 1 10 12 1 1 3 1 5 1 125 1 1 1 1 118 4 15 8 1 8 7 7 4 12 1 29 4 9 47 48 7 110 6 1 4 1 47 66 18 3 15 1 1 1 106 10 95 1 23 16 14 1 4 4 1 3 14 1 16 16 2 7 3 7 1 12 2 19 19 14 1 1 1 1 1 10 10 2 10 8 9 17 132 59 84 59 59 2 6 51 8 12 46 1 50 4 46 3 1 1 1 84 1 5 80 3 79 68 16 16 3 1 1 1 16 15 4 82 81 1 71 38 1 3 3 1 3 4 1 1 3 3 307 242 122 97 24 82 10 881 182 884 544 774 182 192 209 24 82 145 5 5 5 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * IPv4 Forwarding Information Base: FIB frontend. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> */ #include <linux/module.h> #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/capability.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/errno.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> #include <linux/if_addr.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <linux/cache.h> #include <linux/init.h> #include <linux/list.h> #include <linux/slab.h> #include <net/inet_dscp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> #include <net/tcp.h> #include <net/sock.h> #include <net/arp.h> #include <net/ip_fib.h> #include <net/nexthop.h> #include <net/rtnetlink.h> #include <net/xfrm.h> #include <net/l3mdev.h> #include <net/lwtunnel.h> #include <trace/events/fib.h> #ifndef CONFIG_IP_MULTIPLE_TABLES static int __net_init fib4_rules_init(struct net *net) { struct fib_table *local_table, *main_table; main_table = fib_trie_table(RT_TABLE_MAIN, NULL); if (!main_table) return -ENOMEM; local_table = fib_trie_table(RT_TABLE_LOCAL, main_table); if (!local_table) goto fail; hlist_add_head_rcu(&local_table->tb_hlist, &net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX]); hlist_add_head_rcu(&main_table->tb_hlist, &net->ipv4.fib_table_hash[TABLE_MAIN_INDEX]); return 0; fail: fib_free_table(main_table); return -ENOMEM; } #else struct fib_table *fib_new_table(struct net *net, u32 id) { struct fib_table *tb, *alias = NULL; unsigned int h; if (id == 0) id = RT_TABLE_MAIN; tb = fib_get_table(net, id); if (tb) return tb; if (id == RT_TABLE_LOCAL && !net->ipv4.fib_has_custom_rules) alias = fib_new_table(net, RT_TABLE_MAIN); tb = fib_trie_table(id, alias); if (!tb) return NULL; switch (id) { case RT_TABLE_MAIN: rcu_assign_pointer(net->ipv4.fib_main, tb); break; case RT_TABLE_DEFAULT: rcu_assign_pointer(net->ipv4.fib_default, tb); break; default: break; } h = id & (FIB_TABLE_HASHSZ - 1); hlist_add_head_rcu(&tb->tb_hlist, &net->ipv4.fib_table_hash[h]); return tb; } EXPORT_SYMBOL_GPL(fib_new_table); /* caller must hold either rtnl or rcu read lock */ struct fib_table *fib_get_table(struct net *net, u32 id) { struct fib_table *tb; struct hlist_head *head; unsigned int h; if (id == 0) id = RT_TABLE_MAIN; h = id & (FIB_TABLE_HASHSZ - 1); head = &net->ipv4.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, head, tb_hlist, lockdep_rtnl_is_held()) { if (tb->tb_id == id) return tb; } return NULL; } #endif /* CONFIG_IP_MULTIPLE_TABLES */ static void fib_replace_table(struct net *net, struct fib_table *old, struct fib_table *new) { #ifdef CONFIG_IP_MULTIPLE_TABLES switch (new->tb_id) { case RT_TABLE_MAIN: rcu_assign_pointer(net->ipv4.fib_main, new); break; case RT_TABLE_DEFAULT: rcu_assign_pointer(net->ipv4.fib_default, new); break; default: break; } #endif /* replace the old table in the hlist */ hlist_replace_rcu(&old->tb_hlist, &new->tb_hlist); } int fib_unmerge(struct net *net) { struct fib_table *old, *new, *main_table; /* attempt to fetch local table if it has been allocated */ old = fib_get_table(net, RT_TABLE_LOCAL); if (!old) return 0; new = fib_trie_unmerge(old); if (!new) return -ENOMEM; /* table is already unmerged */ if (new == old) return 0; /* replace merged table with clean table */ fib_replace_table(net, old, new); fib_free_table(old); /* attempt to fetch main table if it has been allocated */ main_table = fib_get_table(net, RT_TABLE_MAIN); if (!main_table) return 0; /* flush local entries from main table */ fib_table_flush_external(main_table); return 0; } void fib_flush(struct net *net) { int flushed = 0; unsigned int h; for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct hlist_node *tmp; struct fib_table *tb; hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) flushed += fib_table_flush(net, tb, false); } if (flushed) rt_cache_flush(net); } /* * Find address type as if only "dev" was present in the system. If * on_dev is NULL then all interfaces are taken into consideration. */ static inline unsigned int __inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr, u32 tb_id) { struct flowi4 fl4 = { .daddr = addr }; struct fib_result res; unsigned int ret = RTN_BROADCAST; struct fib_table *table; if (ipv4_is_zeronet(addr) || ipv4_is_lbcast(addr)) return RTN_BROADCAST; if (ipv4_is_multicast(addr)) return RTN_MULTICAST; rcu_read_lock(); table = fib_get_table(net, tb_id); if (table) { ret = RTN_UNICAST; if (!fib_table_lookup(table, &fl4, &res, FIB_LOOKUP_NOREF)) { struct fib_nh_common *nhc = fib_info_nhc(res.fi, 0); if (!dev || dev == nhc->nhc_dev) ret = res.type; } } rcu_read_unlock(); return ret; } unsigned int inet_addr_type_table(struct net *net, __be32 addr, u32 tb_id) { return __inet_dev_addr_type(net, NULL, addr, tb_id); } EXPORT_SYMBOL(inet_addr_type_table); unsigned int inet_addr_type(struct net *net, __be32 addr) { return __inet_dev_addr_type(net, NULL, addr, RT_TABLE_LOCAL); } EXPORT_SYMBOL(inet_addr_type); unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr) { u32 rt_table = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL; return __inet_dev_addr_type(net, dev, addr, rt_table); } EXPORT_SYMBOL(inet_dev_addr_type); /* inet_addr_type with dev == NULL but using the table from a dev * if one is associated */ unsigned int inet_addr_type_dev_table(struct net *net, const struct net_device *dev, __be32 addr) { u32 rt_table = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL; return __inet_dev_addr_type(net, NULL, addr, rt_table); } EXPORT_SYMBOL(inet_addr_type_dev_table); __be32 fib_compute_spec_dst(struct sk_buff *skb) { struct net_device *dev = skb->dev; struct in_device *in_dev; struct fib_result res; struct rtable *rt; struct net *net; int scope; rt = skb_rtable(skb); if ((rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST | RTCF_LOCAL)) == RTCF_LOCAL) return ip_hdr(skb)->daddr; in_dev = __in_dev_get_rcu(dev); net = dev_net(dev); scope = RT_SCOPE_UNIVERSE; if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) { bool vmark = in_dev && IN_DEV_SRC_VMARK(in_dev); struct flowi4 fl4 = { .flowi4_iif = LOOPBACK_IFINDEX, .flowi4_l3mdev = l3mdev_master_ifindex_rcu(dev), .daddr = ip_hdr(skb)->saddr, .flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(ip_hdr(skb))), .flowi4_scope = scope, .flowi4_mark = vmark ? skb->mark : 0, }; if (!fib_lookup(net, &fl4, &res, 0)) return fib_result_prefsrc(net, &res); } else { scope = RT_SCOPE_LINK; } return inet_select_addr(dev, ip_hdr(skb)->saddr, scope); } bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev) { bool dev_match = false; #ifdef CONFIG_IP_ROUTE_MULTIPATH if (unlikely(fi->nh)) { dev_match = nexthop_uses_dev(fi->nh, dev); } else { int ret; for (ret = 0; ret < fib_info_num_path(fi); ret++) { const struct fib_nh_common *nhc = fib_info_nhc(fi, ret); if (nhc_l3mdev_matches_dev(nhc, dev)) { dev_match = true; break; } } } #else if (fib_info_nhc(fi, 0)->nhc_dev == dev) dev_match = true; #endif return dev_match; } EXPORT_SYMBOL_GPL(fib_info_nh_uses_dev); /* Given (packet source, input interface) and optional (dst, oif, tos): * - (main) check, that source is valid i.e. not broadcast or our local * address. * - figure out what "logical" interface this packet arrived * and calculate "specific destination" address. * - check, that packet arrived from expected physical interface. * called with rcu_read_lock() */ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, dscp_t dscp, int oif, struct net_device *dev, int rpf, struct in_device *idev, u32 *itag) { struct net *net = dev_net(dev); enum skb_drop_reason reason; struct flow_keys flkeys; int ret, no_addr; struct fib_result res; struct flowi4 fl4; bool dev_match; fl4.flowi4_oif = 0; fl4.flowi4_l3mdev = l3mdev_master_ifindex_rcu(dev); fl4.flowi4_iif = oif ? : LOOPBACK_IFINDEX; fl4.daddr = src; fl4.saddr = dst; fl4.flowi4_tos = inet_dscp_to_dsfield(dscp); fl4.flowi4_scope = RT_SCOPE_UNIVERSE; fl4.flowi4_tun_key.tun_id = 0; fl4.flowi4_flags = 0; fl4.flowi4_uid = sock_net_uid(net, NULL); fl4.flowi4_multipath_hash = 0; no_addr = idev->ifa_list == NULL; fl4.flowi4_mark = IN_DEV_SRC_VMARK(idev) ? skb->mark : 0; if (!fib4_rules_early_flow_dissect(net, skb, &fl4, &flkeys)) { fl4.flowi4_proto = 0; fl4.fl4_sport = 0; fl4.fl4_dport = 0; } else { swap(fl4.fl4_sport, fl4.fl4_dport); } if (fib_lookup(net, &fl4, &res, 0)) goto last_resort; if (res.type != RTN_UNICAST) { if (res.type != RTN_LOCAL) { reason = SKB_DROP_REASON_IP_INVALID_SOURCE; goto e_inval; } else if (!IN_DEV_ACCEPT_LOCAL(idev)) { reason = SKB_DROP_REASON_IP_LOCAL_SOURCE; goto e_inval; } } fib_combine_itag(itag, &res); dev_match = fib_info_nh_uses_dev(res.fi, dev); /* This is not common, loopback packets retain skb_dst so normally they * would not even hit this slow path. */ dev_match = dev_match || (res.type == RTN_LOCAL && dev == net->loopback_dev); if (dev_match) { ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST; return ret; } if (no_addr) goto last_resort; if (rpf == 1) goto e_rpf; fl4.flowi4_oif = dev->ifindex; ret = 0; if (fib_lookup(net, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE) == 0) { if (res.type == RTN_UNICAST) ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST; } return ret; last_resort: if (rpf) goto e_rpf; *itag = 0; return 0; e_inval: return -reason; e_rpf: return -SKB_DROP_REASON_IP_RPFILTER; } /* Ignore rp_filter for packets protected by IPsec. */ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, dscp_t dscp, int oif, struct net_device *dev, struct in_device *idev, u32 *itag) { int r = secpath_exists(skb) ? 0 : IN_DEV_RPFILTER(idev); struct net *net = dev_net(dev); if (!r && !fib_num_tclassid_users(net) && (dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev))) { if (IN_DEV_ACCEPT_LOCAL(idev)) goto ok; /* with custom local routes in place, checking local addresses * only will be too optimistic, with custom rules, checking * local addresses only can be too strict, e.g. due to vrf */ if (net->ipv4.fib_has_custom_local_routes || fib4_has_custom_rules(net)) goto full_check; /* Within the same container, it is regarded as a martian source, * and the same host but different containers are not. */ if (inet_lookup_ifaddr_rcu(net, src)) return -SKB_DROP_REASON_IP_LOCAL_SOURCE; ok: *itag = 0; return 0; } full_check: return __fib_validate_source(skb, src, dst, dscp, oif, dev, r, idev, itag); } static inline __be32 sk_extract_addr(struct sockaddr *addr) { return ((struct sockaddr_in *) addr)->sin_addr.s_addr; } static int put_rtax(struct nlattr *mx, int len, int type, u32 value) { struct nlattr *nla; nla = (struct nlattr *) ((char *) mx + len); nla->nla_type = type; nla->nla_len = nla_attr_size(4); *(u32 *) nla_data(nla) = value; return len + nla_total_size(4); } static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt, struct fib_config *cfg) { __be32 addr; int plen; memset(cfg, 0, sizeof(*cfg)); cfg->fc_nlinfo.nl_net = net; if (rt->rt_dst.sa_family != AF_INET) return -EAFNOSUPPORT; /* * Check mask for validity: * a) it must be contiguous. * b) destination must have all host bits clear. * c) if application forgot to set correct family (AF_INET), * reject request unless it is absolutely clear i.e. * both family and mask are zero. */ plen = 32; addr = sk_extract_addr(&rt->rt_dst); if (!(rt->rt_flags & RTF_HOST)) { __be32 mask = sk_extract_addr(&rt->rt_genmask); if (rt->rt_genmask.sa_family != AF_INET) { if (mask || rt->rt_genmask.sa_family) return -EAFNOSUPPORT; } if (bad_mask(mask, addr)) return -EINVAL; plen = inet_mask_len(mask); } cfg->fc_dst_len = plen; cfg->fc_dst = addr; if (cmd != SIOCDELRT) { cfg->fc_nlflags = NLM_F_CREATE; cfg->fc_protocol = RTPROT_BOOT; } if (rt->rt_metric) cfg->fc_priority = rt->rt_metric - 1; if (rt->rt_flags & RTF_REJECT) { cfg->fc_scope = RT_SCOPE_HOST; cfg->fc_type = RTN_UNREACHABLE; return 0; } cfg->fc_scope = RT_SCOPE_NOWHERE; cfg->fc_type = RTN_UNICAST; if (rt->rt_dev) { char *colon; struct net_device *dev; char devname[IFNAMSIZ]; if (copy_from_user(devname, rt->rt_dev, IFNAMSIZ-1)) return -EFAULT; devname[IFNAMSIZ-1] = 0; colon = strchr(devname, ':'); if (colon) *colon = 0; dev = __dev_get_by_name(net, devname); if (!dev) return -ENODEV; cfg->fc_oif = dev->ifindex; cfg->fc_table = l3mdev_fib_table(dev); if (colon) { const struct in_ifaddr *ifa; struct in_device *in_dev; in_dev = __in_dev_get_rtnl(dev); if (!in_dev) return -ENODEV; *colon = ':'; rcu_read_lock(); in_dev_for_each_ifa_rcu(ifa, in_dev) { if (strcmp(ifa->ifa_label, devname) == 0) break; } rcu_read_unlock(); if (!ifa) return -ENODEV; cfg->fc_prefsrc = ifa->ifa_local; } } addr = sk_extract_addr(&rt->rt_gateway); if (rt->rt_gateway.sa_family == AF_INET && addr) { unsigned int addr_type; cfg->fc_gw4 = addr; cfg->fc_gw_family = AF_INET; addr_type = inet_addr_type_table(net, addr, cfg->fc_table); if (rt->rt_flags & RTF_GATEWAY && addr_type == RTN_UNICAST) cfg->fc_scope = RT_SCOPE_UNIVERSE; } if (!cfg->fc_table) cfg->fc_table = RT_TABLE_MAIN; if (cmd == SIOCDELRT) return 0; if (rt->rt_flags & RTF_GATEWAY && !cfg->fc_gw_family) return -EINVAL; if (cfg->fc_scope == RT_SCOPE_NOWHERE) cfg->fc_scope = RT_SCOPE_LINK; if (rt->rt_flags & (RTF_MTU | RTF_WINDOW | RTF_IRTT)) { struct nlattr *mx; int len = 0; mx = kcalloc(3, nla_total_size(4), GFP_KERNEL); if (!mx) return -ENOMEM; if (rt->rt_flags & RTF_MTU) len = put_rtax(mx, len, RTAX_ADVMSS, rt->rt_mtu - 40); if (rt->rt_flags & RTF_WINDOW) len = put_rtax(mx, len, RTAX_WINDOW, rt->rt_window); if (rt->rt_flags & RTF_IRTT) len = put_rtax(mx, len, RTAX_RTT, rt->rt_irtt << 3); cfg->fc_mx = mx; cfg->fc_mx_len = len; } return 0; } /* * Handle IP routing ioctl calls. * These are used to manipulate the routing tables */ int ip_rt_ioctl(struct net *net, unsigned int cmd, struct rtentry *rt) { struct fib_config cfg; int err; switch (cmd) { case SIOCADDRT: /* Add a route */ case SIOCDELRT: /* Delete a route */ if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; rtnl_lock(); err = rtentry_to_fib_config(net, cmd, rt, &cfg); if (err == 0) { struct fib_table *tb; if (cmd == SIOCDELRT) { tb = fib_get_table(net, cfg.fc_table); if (tb) err = fib_table_delete(net, tb, &cfg, NULL); else err = -ESRCH; } else { tb = fib_new_table(net, cfg.fc_table); if (tb) err = fib_table_insert(net, tb, &cfg, NULL); else err = -ENOBUFS; } /* allocated by rtentry_to_fib_config() */ kfree(cfg.fc_mx); } rtnl_unlock(); return err; } return -EINVAL; } const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = { [RTA_UNSPEC] = { .strict_start_type = RTA_DPORT + 1 }, [RTA_DST] = { .type = NLA_U32 }, [RTA_SRC] = { .type = NLA_U32 }, [RTA_IIF] = { .type = NLA_U32 }, [RTA_OIF] = { .type = NLA_U32 }, [RTA_GATEWAY] = { .type = NLA_U32 }, [RTA_PRIORITY] = { .type = NLA_U32 }, [RTA_PREFSRC] = { .type = NLA_U32 }, [RTA_METRICS] = { .type = NLA_NESTED }, [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, [RTA_FLOW] = { .type = NLA_U32 }, [RTA_ENCAP_TYPE] = { .type = NLA_U16 }, [RTA_ENCAP] = { .type = NLA_NESTED }, [RTA_UID] = { .type = NLA_U32 }, [RTA_MARK] = { .type = NLA_U32 }, [RTA_TABLE] = { .type = NLA_U32 }, [RTA_IP_PROTO] = { .type = NLA_U8 }, [RTA_SPORT] = { .type = NLA_U16 }, [RTA_DPORT] = { .type = NLA_U16 }, [RTA_NH_ID] = { .type = NLA_U32 }, }; int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla, struct netlink_ext_ack *extack) { struct rtvia *via; int alen; if (nla_len(nla) < offsetof(struct rtvia, rtvia_addr)) { NL_SET_ERR_MSG(extack, "Invalid attribute length for RTA_VIA"); return -EINVAL; } via = nla_data(nla); alen = nla_len(nla) - offsetof(struct rtvia, rtvia_addr); switch (via->rtvia_family) { case AF_INET: if (alen != sizeof(__be32)) { NL_SET_ERR_MSG(extack, "Invalid IPv4 address in RTA_VIA"); return -EINVAL; } cfg->fc_gw_family = AF_INET; cfg->fc_gw4 = *((__be32 *)via->rtvia_addr); break; case AF_INET6: #if IS_ENABLED(CONFIG_IPV6) if (a |