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 /* SPDX-License-Identifier: GPL-2.0-only */ /* * Fast and scalable bitmaps. * * Copyright (C) 2016 Facebook * Copyright (C) 2013-2014 Jens Axboe */ #ifndef __LINUX_SCALE_BITMAP_H #define __LINUX_SCALE_BITMAP_H #include <linux/kernel.h> #include <linux/slab.h> struct seq_file; /** * struct sbitmap_word - Word in a &struct sbitmap. */ struct sbitmap_word { /** * @depth: Number of bits being used in @word/@cleared */ unsigned long depth; /** * @word: word holding free bits */ unsigned long word ____cacheline_aligned_in_smp; /** * @cleared: word holding cleared bits */ unsigned long cleared ____cacheline_aligned_in_smp; /** * @swap_lock: Held while swapping word <-> cleared */ spinlock_t swap_lock; } ____cacheline_aligned_in_smp; /** * struct sbitmap - Scalable bitmap. * * A &struct sbitmap is spread over multiple cachelines to avoid ping-pong. This * trades off higher memory usage for better scalability. */ struct sbitmap { /** * @depth: Number of bits used in the whole bitmap. */ unsigned int depth; /** * @shift: log2(number of bits used per word) */ unsigned int shift; /** * @map_nr: Number of words (cachelines) being used for the bitmap. */ unsigned int map_nr; /** * @map: Allocated bitmap. */ struct sbitmap_word *map; }; #define SBQ_WAIT_QUEUES 8 #define SBQ_WAKE_BATCH 8 /** * struct sbq_wait_state - Wait queue in a &struct sbitmap_queue. */ struct sbq_wait_state { /** * @wait_cnt: Number of frees remaining before we wake up. */ atomic_t wait_cnt; /** * @wait: Wait queue. */ wait_queue_head_t wait; } ____cacheline_aligned_in_smp; /** * struct sbitmap_queue - Scalable bitmap with the added ability to wait on free * bits. * * A &struct sbitmap_queue uses multiple wait queues and rolling wakeups to * avoid contention on the wait queue spinlock. This ensures that we don't hit a * scalability wall when we run out of free bits and have to start putting tasks * to sleep. */ struct sbitmap_queue { /** * @sb: Scalable bitmap. */ struct sbitmap sb; /* * @alloc_hint: Cache of last successfully allocated or freed bit. * * This is per-cpu, which allows multiple users to stick to different * cachelines until the map is exhausted. */ unsigned int __percpu *alloc_hint; /** * @wake_batch: Number of bits which must be freed before we wake up any * waiters. */ unsigned int wake_batch; /** * @wake_index: Next wait queue in @ws to wake up. */ atomic_t wake_index; /** * @ws: Wait queues. */ struct sbq_wait_state *ws; /* * @ws_active: count of currently active ws waitqueues */ atomic_t ws_active; /** * @round_robin: Allocate bits in strict round-robin order. */ bool round_robin; /** * @min_shallow_depth: The minimum shallow depth which may be passed to * sbitmap_queue_get_shallow() or __sbitmap_queue_get_shallow(). */ unsigned int min_shallow_depth; }; /** * sbitmap_init_node() - Initialize a &struct sbitmap on a specific memory node. * @sb: Bitmap to initialize. * @depth: Number of bits to allocate. * @shift: Use 2^@shift bits per word in the bitmap; if a negative number if * given, a good default is chosen. * @flags: Allocation flags. * @node: Memory node to allocate on. * * Return: Zero on success or negative errno on failure. */ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift, gfp_t flags, int node); /** * sbitmap_free() - Free memory used by a &struct sbitmap. * @sb: Bitmap to free. */ static inline void sbitmap_free(struct sbitmap *sb) { kfree(sb->map); sb->map = NULL; } /** * sbitmap_resize() - Resize a &struct sbitmap. * @sb: Bitmap to resize. * @depth: New number of bits to resize to. * * Doesn't reallocate anything. It's up to the caller to ensure that the new * depth doesn't exceed the depth that the sb was initialized with. */ void sbitmap_resize(struct sbitmap *sb, unsigned int depth); /** * sbitmap_get() - Try to allocate a free bit from a &struct sbitmap. * @sb: Bitmap to allocate from. * @alloc_hint: Hint for where to start searching for a free bit. * @round_robin: If true, be stricter about allocation order; always allocate * starting from the last allocated bit. This is less efficient * than the default behavior (false). * * This operation provides acquire barrier semantics if it succeeds. * * Return: Non-negative allocated bit number if successful, -1 otherwise. */ int sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint, bool round_robin); /** * sbitmap_get_shallow() - Try to allocate a free bit from a &struct sbitmap, * limiting the depth used from each word. * @sb: Bitmap to allocate from. * @alloc_hint: Hint for where to start searching for a free bit. * @shallow_depth: The maximum number of bits to allocate from a single word. * * This rather specific operation allows for having multiple users with * different allocation limits. E.g., there can be a high-priority class that * uses sbitmap_get() and a low-priority class that uses sbitmap_get_shallow() * with a @shallow_depth of (1 << (@sb->shift - 1)). Then, the low-priority * class can only allocate half of the total bits in the bitmap, preventing it * from starving out the high-priority class. * * Return: Non-negative allocated bit number if successful, -1 otherwise. */ int sbitmap_get_shallow(struct sbitmap *sb, unsigned int alloc_hint, unsigned long shallow_depth); /** * sbitmap_any_bit_set() - Check for a set bit in a &struct sbitmap. * @sb: Bitmap to check. * * Return: true if any bit in the bitmap is set, false otherwise. */ bool sbitmap_any_bit_set(const struct sbitmap *sb); #define SB_NR_TO_INDEX(sb, bitnr) ((bitnr) >> (sb)->shift) #define SB_NR_TO_BIT(sb, bitnr) ((bitnr) & ((1U << (sb)->shift) - 1U)) typedef bool (*sb_for_each_fn)(struct sbitmap *, unsigned int, void *); /** * __sbitmap_for_each_set() - Iterate over each set bit in a &struct sbitmap. * @start: Where to start the iteration. * @sb: Bitmap to iterate over. * @fn: Callback. Should return true to continue or false to break early. * @data: Pointer to pass to callback. * * This is inline even though it's non-trivial so that the function calls to the * callback will hopefully get optimized away. */ static inline void __sbitmap_for_each_set(struct sbitmap *sb, unsigned int start, sb_for_each_fn fn, void *data) { unsigned int index; unsigned int nr; unsigned int scanned = 0; if (start >= sb->depth) start = 0; index = SB_NR_TO_INDEX(sb, start); nr = SB_NR_TO_BIT(sb, start); while (scanned < sb->depth) { unsigned long word; unsigned int depth = min_t(unsigned int, sb->map[index].depth - nr, sb->depth - scanned); scanned += depth; word = sb->map[index].word & ~sb->map[index].cleared; if (!word) goto next; /* * On the first iteration of the outer loop, we need to add the * bit offset back to the size of the word for find_next_bit(). * On all other iterations, nr is zero, so this is a noop. */ depth += nr; while (1) { nr = find_next_bit(&word, depth, nr); if (nr >= depth) break; if (!fn(sb, (index << sb->shift) + nr, data)) return; nr++; } next: nr = 0; if (++index >= sb->map_nr) index = 0; } } /** * sbitmap_for_each_set() - Iterate over each set bit in a &struct sbitmap. * @sb: Bitmap to iterate over. * @fn: Callback. Should return true to continue or false to break early. * @data: Pointer to pass to callback. */ static inline void sbitmap_for_each_set(struct sbitmap *sb, sb_for_each_fn fn, void *data) { __sbitmap_for_each_set(sb, 0, fn, data); } static inline unsigned long *__sbitmap_word(struct sbitmap *sb, unsigned int bitnr) { return &sb->map[SB_NR_TO_INDEX(sb, bitnr)].word; } /* Helpers equivalent to the operations in asm/bitops.h and linux/bitmap.h */ static inline void sbitmap_set_bit(struct sbitmap *sb, unsigned int bitnr) { set_bit(SB_NR_TO_BIT(sb, bitnr), __sbitmap_word(sb, bitnr)); } static inline void sbitmap_clear_bit(struct sbitmap *sb, unsigned int bitnr) { clear_bit(SB_NR_TO_BIT(sb, bitnr), __sbitmap_word(sb, bitnr)); } /* * This one is special, since it doesn't actually clear the bit, rather it * sets the corresponding bit in the ->cleared mask instead. Paired with * the caller doing sbitmap_deferred_clear() if a given index is full, which * will clear the previously freed entries in the corresponding ->word. */ static inline void sbitmap_deferred_clear_bit(struct sbitmap *sb, unsigned int bitnr) { unsigned long *addr = &sb->map[SB_NR_TO_INDEX(sb, bitnr)].cleared; set_bit(SB_NR_TO_BIT(sb, bitnr), addr); } static inline void sbitmap_clear_bit_unlock(struct sbitmap *sb, unsigned int bitnr) { clear_bit_unlock(SB_NR_TO_BIT(sb, bitnr), __sbitmap_word(sb, bitnr)); } static inline int sbitmap_test_bit(struct sbitmap *sb, unsigned int bitnr) { return test_bit(SB_NR_TO_BIT(sb, bitnr), __sbitmap_word(sb, bitnr)); } /** * sbitmap_show() - Dump &struct sbitmap information to a &struct seq_file. * @sb: Bitmap to show. * @m: struct seq_file to write to. * * This is intended for debugging. The format may change at any time. */ void sbitmap_show(struct sbitmap *sb, struct seq_file *m); /** * sbitmap_bitmap_show() - Write a hex dump of a &struct sbitmap to a &struct * seq_file. * @sb: Bitmap to show. * @m: struct seq_file to write to. * * This is intended for debugging. The output isn't guaranteed to be internally * consistent. */ void sbitmap_bitmap_show(struct sbitmap *sb, struct seq_file *m); /** * sbitmap_queue_init_node() - Initialize a &struct sbitmap_queue on a specific * memory node. * @sbq: Bitmap queue to initialize. * @depth: See sbitmap_init_node(). * @shift: See sbitmap_init_node(). * @round_robin: See sbitmap_get(). * @flags: Allocation flags. * @node: Memory node to allocate on. * * Return: Zero on success or negative errno on failure. */ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth, int shift, bool round_robin, gfp_t flags, int node); /** * sbitmap_queue_free() - Free memory used by a &struct sbitmap_queue. * * @sbq: Bitmap queue to free. */ static inline void sbitmap_queue_free(struct sbitmap_queue *sbq) { kfree(sbq->ws); free_percpu(sbq->alloc_hint); sbitmap_free(&sbq->sb); } /** * sbitmap_queue_resize() - Resize a &struct sbitmap_queue. * @sbq: Bitmap queue to resize. * @depth: New number of bits to resize to. * * Like sbitmap_resize(), this doesn't reallocate anything. It has to do * some extra work on the &struct sbitmap_queue, so it's not safe to just * resize the underlying &struct sbitmap. */ void sbitmap_queue_resize(struct sbitmap_queue *sbq, unsigned int depth); /** * __sbitmap_queue_get() - Try to allocate a free bit from a &struct * sbitmap_queue with preemption already disabled. * @sbq: Bitmap queue to allocate from. * * Return: Non-negative allocated bit number if successful, -1 otherwise. */ int __sbitmap_queue_get(struct sbitmap_queue *sbq); /** * __sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct * sbitmap_queue, limiting the depth used from each word, with preemption * already disabled. * @sbq: Bitmap queue to allocate from. * @shallow_depth: The maximum number of bits to allocate from a single word. * See sbitmap_get_shallow(). * * If you call this, make sure to call sbitmap_queue_min_shallow_depth() after * initializing @sbq. * * Return: Non-negative allocated bit number if successful, -1 otherwise. */ int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq, unsigned int shallow_depth); /** * sbitmap_queue_get() - Try to allocate a free bit from a &struct * sbitmap_queue. * @sbq: Bitmap queue to allocate from. * @cpu: Output parameter; will contain the CPU we ran on (e.g., to be passed to * sbitmap_queue_clear()). * * Return: Non-negative allocated bit number if successful, -1 otherwise. */ static inline int sbitmap_queue_get(struct sbitmap_queue *sbq, unsigned int *cpu) { int nr; *cpu = get_cpu(); nr = __sbitmap_queue_get(sbq); put_cpu(); return nr; } /** * sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct * sbitmap_queue, limiting the depth used from each word. * @sbq: Bitmap queue to allocate from. * @cpu: Output parameter; will contain the CPU we ran on (e.g., to be passed to * sbitmap_queue_clear()). * @shallow_depth: The maximum number of bits to allocate from a single word. * See sbitmap_get_shallow(). * * If you call this, make sure to call sbitmap_queue_min_shallow_depth() after * initializing @sbq. * * Return: Non-negative allocated bit number if successful, -1 otherwise. */ static inline int sbitmap_queue_get_shallow(struct sbitmap_queue *sbq, unsigned int *cpu, unsigned int shallow_depth) { int nr; *cpu = get_cpu(); nr = __sbitmap_queue_get_shallow(sbq, shallow_depth); put_cpu(); return nr; } /** * sbitmap_queue_min_shallow_depth() - Inform a &struct sbitmap_queue of the * minimum shallow depth that will be used. * @sbq: Bitmap queue in question. * @min_shallow_depth: The minimum shallow depth that will be passed to * sbitmap_queue_get_shallow() or __sbitmap_queue_get_shallow(). * * sbitmap_queue_clear() batches wakeups as an optimization. The batch size * depends on the depth of the bitmap. Since the shallow allocation functions * effectively operate with a different depth, the shallow depth must be taken * into account when calculating the batch size. This function must be called * with the minimum shallow depth that will be used. Failure to do so can result * in missed wakeups. */ void sbitmap_queue_min_shallow_depth(struct sbitmap_queue *sbq, unsigned int min_shallow_depth); /** * sbitmap_queue_clear() - Free an allocated bit and wake up waiters on a * &struct sbitmap_queue. * @sbq: Bitmap to free from. * @nr: Bit number to free. * @cpu: CPU the bit was allocated on. */ void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr, unsigned int cpu); static inline int sbq_index_inc(int index) { return (index + 1) & (SBQ_WAIT_QUEUES - 1); } static inline void sbq_index_atomic_inc(atomic_t *index) { int old = atomic_read(index); int new = sbq_index_inc(old); atomic_cmpxchg(index, old, new); } /** * sbq_wait_ptr() - Get the next wait queue to use for a &struct * sbitmap_queue. * @sbq: Bitmap queue to wait on. * @wait_index: A counter per "user" of @sbq. */ static inline struct sbq_wait_state *sbq_wait_ptr(struct sbitmap_queue *sbq, atomic_t *wait_index) { struct sbq_wait_state *ws; ws = &sbq->ws[atomic_read(wait_index)]; sbq_index_atomic_inc(wait_index); return ws; } /** * sbitmap_queue_wake_all() - Wake up everything waiting on a &struct * sbitmap_queue. * @sbq: Bitmap queue to wake up. */ void sbitmap_queue_wake_all(struct sbitmap_queue *sbq); /** * sbitmap_queue_wake_up() - Wake up some of waiters in one waitqueue * on a &struct sbitmap_queue. * @sbq: Bitmap queue to wake up. */ void sbitmap_queue_wake_up(struct sbitmap_queue *sbq); /** * sbitmap_queue_show() - Dump &struct sbitmap_queue information to a &struct * seq_file. * @sbq: Bitmap queue to show. * @m: struct seq_file to write to. * * This is intended for debugging. The format may change at any time. */ void sbitmap_queue_show(struct sbitmap_queue *sbq, struct seq_file *m); struct sbq_wait { struct sbitmap_queue *sbq; /* if set, sbq_wait is accounted */ struct wait_queue_entry wait; }; #define DEFINE_SBQ_WAIT(name) \ struct sbq_wait name = { \ .sbq = NULL, \ .wait = { \ .private = current, \ .func = autoremove_wake_function, \ .entry = LIST_HEAD_INIT((name).wait.entry), \ } \ } /* * Wrapper around prepare_to_wait_exclusive(), which maintains some extra * internal state. */ void sbitmap_prepare_to_wait(struct sbitmap_queue *sbq, struct sbq_wait_state *ws, struct sbq_wait *sbq_wait, int state); /* * Must be paired with sbitmap_prepare_to_wait(). */ void sbitmap_finish_wait(struct sbitmap_queue *sbq, struct sbq_wait_state *ws, struct sbq_wait *sbq_wait); /* * Wrapper around add_wait_queue(), which maintains some extra internal state */ void sbitmap_add_wait_queue(struct sbitmap_queue *sbq, struct sbq_wait_state *ws, struct sbq_wait *sbq_wait); /* * Must be paired with sbitmap_add_wait_queue() */ void sbitmap_del_wait_queue(struct sbq_wait *sbq_wait); #endif /* __LINUX_SCALE_BITMAP_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 /* * Performance events: * * Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de> * Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar * Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra * * Data type definitions, declarations, prototypes. * * Started by: Thomas Gleixner and Ingo Molnar * * For licencing details see kernel-base/COPYING */ #ifndef _LINUX_PERF_EVENT_H #define _LINUX_PERF_EVENT_H #include <uapi/linux/perf_event.h> #include <uapi/linux/bpf_perf_event.h> /* * Kernel-internal data types and definitions: */ #ifdef CONFIG_PERF_EVENTS # include <asm/perf_event.h> # include <asm/local64.h> #endif struct perf_guest_info_callbacks { int (*is_in_guest)(void); int (*is_user_mode)(void); unsigned long (*get_guest_ip)(void); void (*handle_intel_pt_intr)(void); }; #ifdef CONFIG_HAVE_HW_BREAKPOINT #include <asm/hw_breakpoint.h> #endif #include <linux/list.h> #include <linux/mutex.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/spinlock.h> #include <linux/hrtimer.h> #include <linux/fs.h> #include <linux/pid_namespace.h> #include <linux/workqueue.h> #include <linux/ftrace.h> #include <linux/cpu.h> #include <linux/irq_work.h> #include <linux/static_key.h> #include <linux/jump_label_ratelimit.h> #include <linux/atomic.h> #include <linux/sysfs.h> #include <linux/perf_regs.h> #include <linux/cgroup.h> #include <linux/refcount.h> #include <linux/security.h> #include <asm/local.h> struct perf_callchain_entry { __u64 nr; __u64 ip[]; /* /proc/sys/kernel/perf_event_max_stack */ }; struct perf_callchain_entry_ctx { struct perf_callchain_entry *entry; u32 max_stack; u32 nr; short contexts; bool contexts_maxed; }; typedef unsigned long (*perf_copy_f)(void *dst, const void *src, unsigned long off, unsigned long len); struct perf_raw_frag { union { struct perf_raw_frag *next; unsigned long pad; }; perf_copy_f copy; void *data; u32 size; } __packed; struct perf_raw_record { struct perf_raw_frag frag; u32 size; }; /* * branch stack layout: * nr: number of taken branches stored in entries[] * hw_idx: The low level index of raw branch records * for the most recent branch. * -1ULL means invalid/unknown. * * Note that nr can vary from sample to sample * branches (to, from) are stored from most recent * to least recent, i.e., entries[0] contains the most * recent branch. * The entries[] is an abstraction of raw branch records, * which may not be stored in age order in HW, e.g. Intel LBR. * The hw_idx is to expose the low level index of raw * branch record for the most recent branch aka entries[0]. * The hw_idx index is between -1 (unknown) and max depth, * which can be retrieved in /sys/devices/cpu/caps/branches. * For the architectures whose raw branch records are * already stored in age order, the hw_idx should be 0. */ struct perf_branch_stack { __u64 nr; __u64 hw_idx; struct perf_branch_entry entries[]; }; struct task_struct; /* * extra PMU register associated with an event */ struct hw_perf_event_extra { u64 config; /* register value */ unsigned int reg; /* register address or index */ int alloc; /* extra register already allocated */ int idx; /* index in shared_regs->regs[] */ }; /** * struct hw_perf_event - performance event hardware details: */ struct hw_perf_event { #ifdef CONFIG_PERF_EVENTS union { struct { /* hardware */ u64 config; u64 last_tag; unsigned long config_base; unsigned long event_base; int event_base_rdpmc; int idx; int last_cpu; int flags; struct hw_perf_event_extra extra_reg; struct hw_perf_event_extra branch_reg; }; struct { /* software */ struct hrtimer hrtimer; }; struct { /* tracepoint */ /* for tp_event->class */ struct list_head tp_list; }; struct { /* amd_power */ u64 pwr_acc; u64 ptsc; }; #ifdef CONFIG_HAVE_HW_BREAKPOINT struct { /* breakpoint */ /* * Crufty hack to avoid the chicken and egg * problem hw_breakpoint has with context * creation and event initalization. */ struct arch_hw_breakpoint info; struct list_head bp_list; }; #endif struct { /* amd_iommu */ u8 iommu_bank; u8 iommu_cntr; u16 padding; u64 conf; u64 conf1; }; }; /* * If the event is a per task event, this will point to the task in * question. See the comment in perf_event_alloc(). */ struct task_struct *target; /* * PMU would store hardware filter configuration * here. */ void *addr_filters; /* Last sync'ed generation of filters */ unsigned long addr_filters_gen; /* * hw_perf_event::state flags; used to track the PERF_EF_* state. */ #define PERF_HES_STOPPED 0x01 /* the counter is stopped */ #define PERF_HES_UPTODATE 0x02 /* event->count up-to-date */ #define PERF_HES_ARCH 0x04 int state; /* * The last observed hardware counter value, updated with a * local64_cmpxchg() such that pmu::read() can be called nested. */ local64_t prev_count; /* * The period to start the next sample with. */ u64 sample_period; union { struct { /* Sampling */ /* * The period we started this sample with. */ u64 last_period; /* * However much is left of the current period; * note that this is a full 64bit value and * allows for generation of periods longer * than hardware might allow. */ local64_t period_left; }; struct { /* Topdown events counting for context switch */ u64 saved_metric; u64 saved_slots; }; }; /* * State for throttling the event, see __perf_event_overflow() and * perf_adjust_freq_unthr_context(). */ u64 interrupts_seq; u64 interrupts; /* * State for freq target events, see __perf_event_overflow() and * perf_adjust_freq_unthr_context(). */ u64 freq_time_stamp; u64 freq_count_stamp; #endif }; struct perf_event; /* * Common implementation detail of pmu::{start,commit,cancel}_txn */ #define PERF_PMU_TXN_ADD 0x1 /* txn to add/schedule event on PMU */ #define PERF_PMU_TXN_READ 0x2 /* txn to read event group from PMU */ /** * pmu::capabilities flags */ #define PERF_PMU_CAP_NO_INTERRUPT 0x01 #define PERF_PMU_CAP_NO_NMI 0x02 #define PERF_PMU_CAP_AUX_NO_SG 0x04 #define PERF_PMU_CAP_EXTENDED_REGS 0x08 #define PERF_PMU_CAP_EXCLUSIVE 0x10 #define PERF_PMU_CAP_ITRACE 0x20 #define PERF_PMU_CAP_HETEROGENEOUS_CPUS 0x40 #define PERF_PMU_CAP_NO_EXCLUDE 0x80 #define PERF_PMU_CAP_AUX_OUTPUT 0x100 struct perf_output_handle; /** * struct pmu - generic performance monitoring unit */ struct pmu { struct list_head entry; struct module *module; struct device *dev; const struct attribute_group **attr_groups; const struct attribute_group **attr_update; const char *name; int type; /* * various common per-pmu feature flags */ int capabilities; int __percpu *pmu_disable_count; struct perf_cpu_context __percpu *pmu_cpu_context; atomic_t exclusive_cnt; /* < 0: cpu; > 0: tsk */ int task_ctx_nr; int hrtimer_interval_ms; /* number of address filters this PMU can do */ unsigned int nr_addr_filters; /* * Fully disable/enable this PMU, can be used to protect from the PMI * as well as for lazy/batch writing of the MSRs. */ void (*pmu_enable) (struct pmu *pmu); /* optional */ void (*pmu_disable) (struct pmu *pmu); /* optional */ /* * Try and initialize the event for this PMU. * * Returns: * -ENOENT -- @event is not for this PMU * * -ENODEV -- @event is for this PMU but PMU not present * -EBUSY -- @event is for this PMU but PMU temporarily unavailable * -EINVAL -- @event is for this PMU but @event is not valid * -EOPNOTSUPP -- @event is for this PMU, @event is valid, but not supported * -EACCES -- @event is for this PMU, @event is valid, but no privileges * * 0 -- @event is for this PMU and valid * * Other error return values are allowed. */ int (*event_init) (struct perf_event *event); /* * Notification that the event was mapped or unmapped. Called * in the context of the mapping task. */ void (*event_mapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ void (*event_unmapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ /* * Flags for ->add()/->del()/ ->start()/->stop(). There are * matching hw_perf_event::state flags. */ #define PERF_EF_START 0x01 /* start the counter when adding */ #define PERF_EF_RELOAD 0x02 /* reload the counter when starting */ #define PERF_EF_UPDATE 0x04 /* update the counter when stopping */ /* * Adds/Removes a counter to/from the PMU, can be done inside a * transaction, see the ->*_txn() methods. * * The add/del callbacks will reserve all hardware resources required * to service the event, this includes any counter constraint * scheduling etc. * * Called with IRQs disabled and the PMU disabled on the CPU the event * is on. * * ->add() called without PERF_EF_START should result in the same state * as ->add() followed by ->stop(). * * ->del() must always PERF_EF_UPDATE stop an event. If it calls * ->stop() that must deal with already being stopped without * PERF_EF_UPDATE. */ int (*add) (struct perf_event *event, int flags); void (*del) (struct perf_event *event, int flags); /* * Starts/Stops a counter present on the PMU. * * The PMI handler should stop the counter when perf_event_overflow() * returns !0. ->start() will be used to continue. * * Also used to change the sample period. * * Called with IRQs disabled and the PMU disabled on the CPU the event * is on -- will be called from NMI context with the PMU generates * NMIs. * * ->stop() with PERF_EF_UPDATE will read the counter and update * period/count values like ->read() would. * * ->start() with PERF_EF_RELOAD will reprogram the counter * value, must be preceded by a ->stop() with PERF_EF_UPDATE. */ void (*start) (struct perf_event *event, int flags); void (*stop) (struct perf_event *event, int flags); /* * Updates the counter value of the event. * * For sampling capable PMUs this will also update the software period * hw_perf_event::period_left field. */ void (*read) (struct perf_event *event); /* * Group events scheduling is treated as a transaction, add * group events as a whole and perform one schedulability test. * If the test fails, roll back the whole group * * Start the transaction, after this ->add() doesn't need to * do schedulability tests. * * Optional. */ void (*start_txn) (struct pmu *pmu, unsigned int txn_flags); /* * If ->start_txn() disabled the ->add() schedulability test * then ->commit_txn() is required to perform one. On success * the transaction is closed. On error the transaction is kept * open until ->cancel_txn() is called. * * Optional. */ int (*commit_txn) (struct pmu *pmu); /* * Will cancel the transaction, assumes ->del() is called * for each successful ->add() during the transaction. * * Optional. */ void (*cancel_txn) (struct pmu *pmu); /* * Will return the value for perf_event_mmap_page::index for this event, * if no implementation is provided it will default to: event->hw.idx + 1. */ int (*event_idx) (struct perf_event *event); /*optional */ /* * context-switches callback */ void (*sched_task) (struct perf_event_context *ctx, bool sched_in); /* * Kmem cache of PMU specific data */ struct kmem_cache *task_ctx_cache; /* * PMU specific parts of task perf event context (i.e. ctx->task_ctx_data) * can be synchronized using this function. See Intel LBR callstack support * implementation and Perf core context switch handling callbacks for usage * examples. */ void (*swap_task_ctx) (struct perf_event_context *prev, struct perf_event_context *next); /* optional */ /* * Set up pmu-private data structures for an AUX area */ void *(*setup_aux) (struct perf_event *event, void **pages, int nr_pages, bool overwrite); /* optional */ /* * Free pmu-private AUX data structures */ void (*free_aux) (void *aux); /* optional */ /* * Take a snapshot of the AUX buffer without touching the event * state, so that preempting ->start()/->stop() callbacks does * not interfere with their logic. Called in PMI context. * * Returns the size of AUX data copied to the output handle. * * Optional. */ long (*snapshot_aux) (struct perf_event *event, struct perf_output_handle *handle, unsigned long size); /* * Validate address range filters: make sure the HW supports the * requested configuration and number of filters; return 0 if the * supplied filters are valid, -errno otherwise. * * Runs in the context of the ioctl()ing process and is not serialized * with the rest of the PMU callbacks. */ int (*addr_filters_validate) (struct list_head *filters); /* optional */ /* * Synchronize address range filter configuration: * translate hw-agnostic filters into hardware configuration in * event::hw::addr_filters. * * Runs as a part of filter sync sequence that is done in ->start() * callback by calling perf_event_addr_filters_sync(). * * May (and should) traverse event::addr_filters::list, for which its * caller provides necessary serialization. */ void (*addr_filters_sync) (struct perf_event *event); /* optional */ /* * Check if event can be used for aux_output purposes for * events of this PMU. * * Runs from perf_event_open(). Should return 0 for "no match" * or non-zero for "match". */ int (*aux_output_match) (struct perf_event *event); /* optional */ /* * Filter events for PMU-specific reasons. */ int (*filter_match) (struct perf_event *event); /* optional */ /* * Check period value for PERF_EVENT_IOC_PERIOD ioctl. */ int (*check_period) (struct perf_event *event, u64 value); /* optional */ }; enum perf_addr_filter_action_t { PERF_ADDR_FILTER_ACTION_STOP = 0, PERF_ADDR_FILTER_ACTION_START, PERF_ADDR_FILTER_ACTION_FILTER, }; /** * struct perf_addr_filter - address range filter definition * @entry: event's filter list linkage * @path: object file's path for file-based filters * @offset: filter range offset * @size: filter range size (size==0 means single address trigger) * @action: filter/start/stop * * This is a hardware-agnostic filter configuration as specified by the user. */ struct perf_addr_filter { struct list_head entry; struct path path; unsigned long offset; unsigned long size; enum perf_addr_filter_action_t action; }; /** * struct perf_addr_filters_head - container for address range filters * @list: list of filters for this event * @lock: spinlock that serializes accesses to the @list and event's * (and its children's) filter generations. * @nr_file_filters: number of file-based filters * * A child event will use parent's @list (and therefore @lock), so they are * bundled together; see perf_event_addr_filters(). */ struct perf_addr_filters_head { struct list_head list; raw_spinlock_t lock; unsigned int nr_file_filters; }; struct perf_addr_filter_range { unsigned long start; unsigned long size; }; /** * enum perf_event_state - the states of an event: */ enum perf_event_state { PERF_EVENT_STATE_DEAD = -4, PERF_EVENT_STATE_EXIT = -3, PERF_EVENT_STATE_ERROR = -2, PERF_EVENT_STATE_OFF = -1, PERF_EVENT_STATE_INACTIVE = 0, PERF_EVENT_STATE_ACTIVE = 1, }; struct file; struct perf_sample_data; typedef void (*perf_overflow_handler_t)(struct perf_event *, struct perf_sample_data *, struct pt_regs *regs); /* * Event capabilities. For event_caps and groups caps. * * PERF_EV_CAP_SOFTWARE: Is a software event. * PERF_EV_CAP_READ_ACTIVE_PKG: A CPU event (or cgroup event) that can be read * from any CPU in the package where it is active. * PERF_EV_CAP_SIBLING: An event with this flag must be a group sibling and * cannot be a group leader. If an event with this flag is detached from the * group it is scheduled out and moved into an unrecoverable ERROR state. */ #define PERF_EV_CAP_SOFTWARE BIT(0) #define PERF_EV_CAP_READ_ACTIVE_PKG BIT(1) #define PERF_EV_CAP_SIBLING BIT(2) #define SWEVENT_HLIST_BITS 8 #define SWEVENT_HLIST_SIZE (1 << SWEVENT_HLIST_BITS) struct swevent_hlist { struct hlist_head heads[SWEVENT_HLIST_SIZE]; struct rcu_head rcu_head; }; #define PERF_ATTACH_CONTEXT 0x01 #define PERF_ATTACH_GROUP 0x02 #define PERF_ATTACH_TASK 0x04 #define PERF_ATTACH_TASK_DATA 0x08 #define PERF_ATTACH_ITRACE 0x10 #define PERF_ATTACH_SCHED_CB 0x20 struct perf_cgroup; struct perf_buffer; struct pmu_event_list { raw_spinlock_t lock; struct list_head list; }; #define for_each_sibling_event(sibling, event) \ if ((event)->group_leader == (event)) \ list_for_each_entry((sibling), &(event)->sibling_list, sibling_list) /** * struct perf_event - performance event kernel representation: */ struct perf_event { #ifdef CONFIG_PERF_EVENTS /* * entry onto perf_event_context::event_list; * modifications require ctx->lock * RCU safe iterations. */ struct list_head event_entry; /* * Locked for modification by both ctx->mutex and ctx->lock; holding * either sufficies for read. */ struct list_head sibling_list; struct list_head active_list; /* * Node on the pinned or flexible tree located at the event context; */ struct rb_node group_node; u64 group_index; /* * We need storage to track the entries in perf_pmu_migrate_context; we * cannot use the event_entry because of RCU and we want to keep the * group in tact which avoids us using the other two entries. */ struct list_head migrate_entry; struct hlist_node hlist_entry; struct list_head active_entry; int nr_siblings; /* Not serialized. Only written during event initialization. */ int event_caps; /* The cumulative AND of all event_caps for events in this group. */ int group_caps; struct perf_event *group_leader; struct pmu *pmu; void *pmu_private; enum perf_event_state state; unsigned int attach_state; local64_t count; atomic64_t child_count; /* * These are the total time in nanoseconds that the event * has been enabled (i.e. eligible to run, and the task has * been scheduled in, if this is a per-task event) * and running (scheduled onto the CPU), respectively. */ u64 total_time_enabled; u64 total_time_running; u64 tstamp; /* * timestamp shadows the actual context timing but it can * be safely used in NMI interrupt context. It reflects the * context time as it was when the event was last scheduled in, * or when ctx_sched_in failed to schedule the event because we * run out of PMC. * * ctx_time already accounts for ctx->timestamp. Therefore to * compute ctx_time for a sample, simply add perf_clock(). */ u64 shadow_ctx_time; struct perf_event_attr attr; u16 header_size; u16 id_header_size; u16 read_size; struct hw_perf_event hw; struct perf_event_context *ctx; atomic_long_t refcount; /* * These accumulate total time (in nanoseconds) that children * events have been enabled and running, respectively. */ atomic64_t child_total_time_enabled; atomic64_t child_total_time_running; /* * Protect attach/detach and child_list: */ struct mutex child_mutex; struct list_head child_list; struct perf_event *parent; int oncpu; int cpu; struct list_head owner_entry; struct task_struct *owner; /* mmap bits */ struct mutex mmap_mutex; atomic_t mmap_count; struct perf_buffer *rb; struct list_head rb_entry; unsigned long rcu_batches; int rcu_pending; /* poll related */ wait_queue_head_t waitq; struct fasync_struct *fasync; /* delayed work for NMIs and such */ int pending_wakeup; int pending_kill; int pending_disable; struct irq_work pending; atomic_t event_limit; /* address range filters */ struct perf_addr_filters_head addr_filters; /* vma address array for file-based filders */ struct perf_addr_filter_range *addr_filter_ranges; unsigned long addr_filters_gen; /* for aux_output events */ struct perf_event *aux_event; void (*destroy)(struct perf_event *); struct rcu_head rcu_head; struct pid_namespace *ns; u64 id; u64 (*clock)(void); perf_overflow_handler_t overflow_handler; void *overflow_handler_context; #ifdef CONFIG_BPF_SYSCALL perf_overflow_handler_t orig_overflow_handler; struct bpf_prog *prog; #endif #ifdef CONFIG_EVENT_TRACING struct trace_event_call *tp_event; struct event_filter *filter; #ifdef CONFIG_FUNCTION_TRACER struct ftrace_ops ftrace_ops; #endif #endif #ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; /* cgroup event is attach to */ #endif #ifdef CONFIG_SECURITY void *security; #endif struct list_head sb_list; #endif /* CONFIG_PERF_EVENTS */ }; struct perf_event_groups { struct rb_root tree; u64 index; }; /** * struct perf_event_context - event context structure * * Used as a container for task events and CPU events as well: */ struct perf_event_context { struct pmu *pmu; /* * Protect the states of the events in the list, * nr_active, and the list: */ raw_spinlock_t lock; /* * Protect the list of events. Locking either mutex or lock * is sufficient to ensure the list doesn't change; to change * the list you need to lock both the mutex and the spinlock. */ struct mutex mutex; struct list_head active_ctx_list; struct perf_event_groups pinned_groups; struct perf_event_groups flexible_groups; struct list_head event_list; struct list_head pinned_active; struct list_head flexible_active; int nr_events; int nr_active; int is_active; int nr_stat; int nr_freq; int rotate_disable; /* * Set when nr_events != nr_active, except tolerant to events not * necessary to be active due to scheduling constraints, such as cgroups. */ int rotate_necessary; refcount_t refcount; struct task_struct *task; /* * Context clock, runs when context enabled. */ u64 time; u64 timestamp; /* * These fields let us detect when two contexts have both * been cloned (inherited) from a common ancestor. */ struct perf_event_context *parent_ctx; u64 parent_gen; u64 generation; int pin_count; #ifdef CONFIG_CGROUP_PERF int nr_cgroups; /* cgroup evts */ #endif void *task_ctx_data; /* pmu specific data */ struct rcu_head rcu_head; }; /* * Number of contexts where an event can trigger: * task, softirq, hardirq, nmi. */ #define PERF_NR_CONTEXTS 4 /** * struct perf_event_cpu_context - per cpu event context structure */ struct perf_cpu_context { struct perf_event_context ctx; struct perf_event_context *task_ctx; int active_oncpu; int exclusive; raw_spinlock_t hrtimer_lock; struct hrtimer hrtimer; ktime_t hrtimer_interval; unsigned int hrtimer_active; #ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; struct list_head cgrp_cpuctx_entry; #endif struct list_head sched_cb_entry; int sched_cb_usage; int online; /* * Per-CPU storage for iterators used in visit_groups_merge. The default * storage is of size 2 to hold the CPU and any CPU event iterators. */ int heap_size; struct perf_event **heap; struct perf_event *heap_default[2]; }; struct perf_output_handle { struct perf_event *event; struct perf_buffer *rb; unsigned long wakeup; unsigned long size; u64 aux_flags; union { void *addr; unsigned long head; }; int page; }; struct bpf_perf_event_data_kern { bpf_user_pt_regs_t *regs; struct perf_sample_data *data; struct perf_event *event; }; #ifdef CONFIG_CGROUP_PERF /* * perf_cgroup_info keeps track of time_enabled for a cgroup. * This is a per-cpu dynamically allocated data structure. */ struct perf_cgroup_info { u64 time; u64 timestamp; }; struct perf_cgroup { struct cgroup_subsys_state css; struct perf_cgroup_info __percpu *info; }; /* * Must ensure cgroup is pinned (css_get) before calling * this function. In other words, we cannot call this function * if there is no cgroup event for the current CPU context. */ static inline struct perf_cgroup * perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx) { return container_of(task_css_check(task, perf_event_cgrp_id, ctx ? lockdep_is_held(&ctx->lock) : true), struct perf_cgroup, css); } #endif /* CONFIG_CGROUP_PERF */ #ifdef CONFIG_PERF_EVENTS extern void *perf_aux_output_begin(struct perf_output_handle *handle, struct perf_event *event); extern void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size); extern int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size); extern void *perf_get_aux(struct perf_output_handle *handle); extern void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags); extern void perf_event_itrace_started(struct perf_event *event); extern int perf_pmu_register(struct pmu *pmu, const char *name, int type); extern void perf_pmu_unregister(struct pmu *pmu); extern int perf_num_counters(void); extern const char *perf_pmu_name(void); extern void __perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task); extern void __perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next); extern int perf_event_init_task(struct task_struct *child); extern void perf_event_exit_task(struct task_struct *child); extern void perf_event_free_task(struct task_struct *task); extern void perf_event_delayed_put(struct task_struct *task); extern struct file *perf_event_get(unsigned int fd); extern const struct perf_event *perf_get_event(struct file *file); extern const struct perf_event_attr *perf_event_attrs(struct perf_event *event); extern void perf_event_print_debug(void); extern void perf_pmu_disable(struct pmu *pmu); extern void perf_pmu_enable(struct pmu *pmu); extern void perf_sched_cb_dec(struct pmu *pmu); extern void perf_sched_cb_inc(struct pmu *pmu); extern int perf_event_task_disable(void); extern int perf_event_task_enable(void); extern void perf_pmu_resched(struct pmu *pmu); extern int perf_event_refresh(struct perf_event *event, int refresh); extern void perf_event_update_userpage(struct perf_event *event); extern int perf_event_release_kernel(struct perf_event *event); extern struct perf_event * perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, struct task_struct *task, perf_overflow_handler_t callback, void *context); extern void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu); int perf_event_read_local(struct perf_event *event, u64 *value, u64 *enabled, u64 *running); extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running); struct perf_sample_data { /* * Fields set by perf_sample_data_init(), group so as to * minimize the cachelines touched. */ u64 addr; struct perf_raw_record *raw; struct perf_branch_stack *br_stack; u64 period; u64 weight; u64 txn; union perf_mem_data_src data_src; /* * The other fields, optionally {set,used} by * perf_{prepare,output}_sample(). */ u64 type; u64 ip; struct { u32 pid; u32 tid; } tid_entry; u64 time; u64 id; u64 stream_id; struct { u32 cpu; u32 reserved; } cpu_entry; struct perf_callchain_entry *callchain; u64 aux_size; struct perf_regs regs_user; struct perf_regs regs_intr; u64 stack_user_size; u64 phys_addr; u64 cgroup; } ____cacheline_aligned; /* default value for data source */ #define PERF_MEM_NA (PERF_MEM_S(OP, NA) |\ PERF_MEM_S(LVL, NA) |\ PERF_MEM_S(SNOOP, NA) |\ PERF_MEM_S(LOCK, NA) |\ PERF_MEM_S(TLB, NA)) static inline void perf_sample_data_init(struct perf_sample_data *data, u64 addr, u64 period) { /* remaining struct members initialized in perf_prepare_sample() */ data->addr = addr; data->raw = NULL; data->br_stack = NULL; data->period = period; data->weight = 0; data->data_src.val = PERF_MEM_NA; data->txn = 0; } extern void perf_output_sample(struct perf_output_handle *handle, struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event); extern void perf_prepare_sample(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event, struct pt_regs *regs); extern int perf_event_overflow(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern void perf_event_output_forward(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern void perf_event_output_backward(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern int perf_event_output(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); static inline bool is_default_overflow_handler(struct perf_event *event) { if (likely(event->overflow_handler == perf_event_output_forward)) return true; if (unlikely(event->overflow_handler == perf_event_output_backward)) return true; return false; } extern void perf_event_header__init_id(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event); extern void perf_event__output_id_sample(struct perf_event *event, struct perf_output_handle *handle, struct perf_sample_data *sample); extern void perf_log_lost_samples(struct perf_event *event, u64 lost); static inline bool event_has_any_exclude_flag(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; return attr->exclude_idle || attr->exclude_user || attr->exclude_kernel || attr->exclude_hv || attr->exclude_guest || attr->exclude_host; } static inline bool is_sampling_event(struct perf_event *event) { return event->attr.sample_period != 0; } /* * Return 1 for a software event, 0 for a hardware event */ static inline int is_software_event(struct perf_event *event) { return event->event_caps & PERF_EV_CAP_SOFTWARE; } /* * Return 1 for event in sw context, 0 for event in hw context */ static inline int in_software_context(struct perf_event *event) { return event->ctx->pmu->task_ctx_nr == perf_sw_context; } static inline int is_exclusive_pmu(struct pmu *pmu) { return pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE; } extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX]; extern void ___perf_sw_event(u32, u64, struct pt_regs *, u64); extern void __perf_sw_event(u32, u64, struct pt_regs *, u64); #ifndef perf_arch_fetch_caller_regs static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip) { } #endif /* * When generating a perf sample in-line, instead of from an interrupt / * exception, we lack a pt_regs. This is typically used from software events * like: SW_CONTEXT_SWITCHES, SW_MIGRATIONS and the tie-in with tracepoints. * * We typically don't need a full set, but (for x86) do require: * - ip for PERF_SAMPLE_IP * - cs for user_mode() tests * - sp for PERF_SAMPLE_CALLCHAIN * - eflags for MISC bits and CALLCHAIN (see: perf_hw_regs()) * * NOTE: assumes @regs is otherwise already 0 filled; this is important for * things like PERF_SAMPLE_REGS_INTR. */ static inline void perf_fetch_caller_regs(struct pt_regs *regs) { perf_arch_fetch_caller_regs(regs, CALLER_ADDR0); } static __always_inline void perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { if (static_key_false(&perf_swevent_enabled[event_id])) __perf_sw_event(event_id, nr, regs, addr); } DECLARE_PER_CPU(struct pt_regs, __perf_regs[4]); /* * 'Special' version for the scheduler, it hard assumes no recursion, * which is guaranteed by us not actually scheduling inside other swevents * because those disable preemption. */ static __always_inline void perf_sw_event_sched(u32 event_id, u64 nr, u64 addr) { if (static_key_false(&perf_swevent_enabled[event_id])) { struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]); perf_fetch_caller_regs(regs); ___perf_sw_event(event_id, nr, regs, addr); } } extern struct static_key_false perf_sched_events; static __always_inline bool perf_sw_migrate_enabled(void) { if (static_key_false(&perf_swevent_enabled[PERF_COUNT_SW_CPU_MIGRATIONS])) return true; return false; } static inline void perf_event_task_migrate(struct task_struct *task) { if (perf_sw_migrate_enabled()) task->sched_migrated = 1; } static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_in(prev, task); if (perf_sw_migrate_enabled() && task->sched_migrated) { struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]); perf_fetch_caller_regs(regs); ___perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, regs, 0); task->sched_migrated = 0; } } static inline void perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next) { perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0); if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_out(prev, next); } extern void perf_event_mmap(struct vm_area_struct *vma); extern void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, const char *sym); extern void perf_event_bpf_event(struct bpf_prog *prog, enum perf_bpf_event_type type, u16 flags); extern struct perf_guest_info_callbacks *perf_guest_cbs; extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); extern void perf_event_exec(void); extern void perf_event_comm(struct task_struct *tsk, bool exec); extern void perf_event_namespaces(struct task_struct *tsk); extern void perf_event_fork(struct task_struct *tsk); extern void perf_event_text_poke(const void *addr, const void *old_bytes, size_t old_len, const void *new_bytes, size_t new_len); /* Callchains */ DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry); extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); extern struct perf_callchain_entry * get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, u32 max_stack, bool crosstask, bool add_mark); extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs); extern int get_callchain_buffers(int max_stack); extern void put_callchain_buffers(void); extern struct perf_callchain_entry *get_callchain_entry(int *rctx); extern void put_callchain_entry(int rctx); extern int sysctl_perf_event_max_stack; extern int sysctl_perf_event_max_contexts_per_stack; static inline int perf_callchain_store_context(struct perf_callchain_entry_ctx *ctx, u64 ip) { if (ctx->contexts < sysctl_perf_event_max_contexts_per_stack) { struct perf_callchain_entry *entry = ctx->entry; entry->ip[entry->nr++] = ip; ++ctx->contexts; return 0; } else { ctx->contexts_maxed = true; return -1; /* no more room, stop walking the stack */ } } static inline int perf_callchain_store(struct perf_callchain_entry_ctx *ctx, u64 ip) { if (ctx->nr < ctx->max_stack && !ctx->contexts_maxed) { struct perf_callchain_entry *entry = ctx->entry; entry->ip[entry->nr++] = ip; ++ctx->nr; return 0; } else { return -1; /* no more room, stop walking the stack */ } } extern int sysctl_perf_event_paranoid; extern int sysctl_perf_event_mlock; extern int sysctl_perf_event_sample_rate; extern int sysctl_perf_cpu_time_max_percent; extern void perf_sample_event_took(u64 sample_len_ns); int perf_proc_update_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int perf_event_max_stack_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); /* Access to perf_event_open(2) syscall. */ #define PERF_SECURITY_OPEN 0 /* Finer grained perf_event_open(2) access control. */ #define PERF_SECURITY_CPU 1 #define PERF_SECURITY_KERNEL 2 #define PERF_SECURITY_TRACEPOINT 3 static inline int perf_is_paranoid(void) { return sysctl_perf_event_paranoid > -1; } static inline int perf_allow_kernel(struct perf_event_attr *attr) { if (sysctl_perf_event_paranoid > 1 && !perfmon_capable()) return -EACCES; return security_perf_event_open(attr, PERF_SECURITY_KERNEL); } static inline int perf_allow_cpu(struct perf_event_attr *attr) { if (sysctl_perf_event_paranoid > 0 && !perfmon_capable()) return -EACCES; return security_perf_event_open(attr, PERF_SECURITY_CPU); } static inline int perf_allow_tracepoint(struct perf_event_attr *attr) { if (sysctl_perf_event_paranoid > -1 && !perfmon_capable()) return -EPERM; return security_perf_event_open(attr, PERF_SECURITY_TRACEPOINT); } extern void perf_event_init(void); extern void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, struct pt_regs *regs, struct hlist_head *head, int rctx, struct task_struct *task); extern void perf_bp_event(struct perf_event *event, void *data); #ifndef perf_misc_flags # define perf_misc_flags(regs) \ (user_mode(regs) ? PERF_RECORD_MISC_USER : PERF_RECORD_MISC_KERNEL) # define perf_instruction_pointer(regs) instruction_pointer(regs) #endif #ifndef perf_arch_bpf_user_pt_regs # define perf_arch_bpf_user_pt_regs(regs) regs #endif static inline bool has_branch_stack(struct perf_event *event) { return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK; } static inline bool needs_branch_stack(struct perf_event *event) { return event->attr.branch_sample_type != 0; } static inline bool has_aux(struct perf_event *event) { return event->pmu->setup_aux; } static inline bool is_write_backward(struct perf_event *event) { return !!event->attr.write_backward; } static inline bool has_addr_filter(struct perf_event *event) { return event->pmu->nr_addr_filters; } /* * An inherited event uses parent's filters */ static inline struct perf_addr_filters_head * perf_event_addr_filters(struct perf_event *event) { struct perf_addr_filters_head *ifh = &event->addr_filters; if (event->parent) ifh = &event->parent->addr_filters; return ifh; } extern void perf_event_addr_filters_sync(struct perf_event *event); extern int perf_output_begin(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern int perf_output_begin_forward(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern int perf_output_begin_backward(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern void perf_output_end(struct perf_output_handle *handle); extern unsigned int perf_output_copy(struct perf_output_handle *handle, const void *buf, unsigned int len); extern unsigned int perf_output_skip(struct perf_output_handle *handle, unsigned int len); extern long perf_output_copy_aux(struct perf_output_handle *aux_handle, struct perf_output_handle *handle, unsigned long from, unsigned long to); extern int perf_swevent_get_recursion_context(void); extern void perf_swevent_put_recursion_context(int rctx); extern u64 perf_swevent_set_period(struct perf_event *event); extern void perf_event_enable(struct perf_event *event); extern void perf_event_disable(struct perf_event *event); extern void perf_event_disable_local(struct perf_event *event); extern void perf_event_disable_inatomic(struct perf_event *event); extern void perf_event_task_tick(void); extern int perf_event_account_interrupt(struct perf_event *event); extern int perf_event_period(struct perf_event *event, u64 value); extern u64 perf_event_pause(struct perf_event *event, bool reset); #else /* !CONFIG_PERF_EVENTS: */ static inline void * perf_aux_output_begin(struct perf_output_handle *handle, struct perf_event *event) { return NULL; } static inline void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) { } static inline int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size) { return -EINVAL; } static inline void * perf_get_aux(struct perf_output_handle *handle) { return NULL; } static inline void perf_event_task_migrate(struct task_struct *task) { } static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { } static inline void perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next) { } static inline int perf_event_init_task(struct task_struct *child) { return 0; } static inline void perf_event_exit_task(struct task_struct *child) { } static inline void perf_event_free_task(struct task_struct *task) { } static inline void perf_event_delayed_put(struct task_struct *task) { } static inline struct file *perf_event_get(unsigned int fd) { return ERR_PTR(-EINVAL); } static inline const struct perf_event *perf_get_event(struct file *file) { return ERR_PTR(-EINVAL); } static inline const struct perf_event_attr *perf_event_attrs(struct perf_event *event) { return ERR_PTR(-EINVAL); } static inline int perf_event_read_local(struct perf_event *event, u64 *value, u64 *enabled, u64 *running) { return -EINVAL; } static inline void perf_event_print_debug(void) { } static inline int perf_event_task_disable(void) { return -EINVAL; } static inline int perf_event_task_enable(void) { return -EINVAL; } static inline int perf_event_refresh(struct perf_event *event, int refresh) { return -EINVAL; } static inline void perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { } static inline void perf_sw_event_sched(u32 event_id, u64 nr, u64 addr) { } static inline void perf_bp_event(struct perf_event *event, void *data) { } static inline int perf_register_guest_info_callbacks (struct perf_guest_info_callbacks *callbacks) { return 0; } static inline int perf_unregister_guest_info_callbacks (struct perf_guest_info_callbacks *callbacks) { return 0; } static inline void perf_event_mmap(struct vm_area_struct *vma) { } typedef int (perf_ksymbol_get_name_f)(char *name, int name_len, void *data); static inline void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, const char *sym) { } static inline void perf_event_bpf_event(struct bpf_prog *prog, enum perf_bpf_event_type type, u16 flags) { } static inline void perf_event_exec(void) { } static inline void perf_event_comm(struct task_struct *tsk, bool exec) { } static inline void perf_event_namespaces(struct task_struct *tsk) { } static inline void perf_event_fork(struct task_struct *tsk) { } static inline void perf_event_text_poke(const void *addr, const void *old_bytes, size_t old_len, const void *new_bytes, size_t new_len) { } static inline void perf_event_init(void) { } static inline int perf_swevent_get_recursion_context(void) { return -1; } static inline void perf_swevent_put_recursion_context(int rctx) { } static inline u64 perf_swevent_set_period(struct perf_event *event) { return 0; } static inline void perf_event_enable(struct perf_event *event) { } static inline void perf_event_disable(struct perf_event *event) { } static inline int __perf_event_disable(void *info) { return -1; } static inline void perf_event_task_tick(void) { } static inline int perf_event_release_kernel(struct perf_event *event) { return 0; } static inline int perf_event_period(struct perf_event *event, u64 value) { return -EINVAL; } static inline u64 perf_event_pause(struct perf_event *event, bool reset) { return 0; } #endif #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) extern void perf_restore_debug_store(void); #else static inline void perf_restore_debug_store(void) { } #endif static __always_inline bool perf_raw_frag_last(const struct perf_raw_frag *frag) { return frag->pad < sizeof(u64); } #define perf_output_put(handle, x) perf_output_copy((handle), &(x), sizeof(x)) struct perf_pmu_events_attr { struct device_attribute attr; u64 id; const char *event_str; }; struct perf_pmu_events_ht_attr { struct device_attribute attr; u64 id; const char *event_str_ht; const char *event_str_noht; }; ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr, char *page); #define PMU_EVENT_ATTR(_name, _var, _id, _show) \ static struct perf_pmu_events_attr _var = { \ .attr = __ATTR(_name, 0444, _show, NULL), \ .id = _id, \ }; #define PMU_EVENT_ATTR_STRING(_name, _var, _str) \ static struct perf_pmu_events_attr _var = { \ .attr = __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \ .id = 0, \ .event_str = _str, \ }; #define PMU_FORMAT_ATTR(_name, _format) \ static ssize_t \ _name##_show(struct device *dev, \ struct device_attribute *attr, \ char *page) \ { \ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ return sprintf(page, _format "\n"); \ } \ \ static struct device_attribute format_attr_##_name = __ATTR_RO(_name) /* Performance counter hotplug functions */ #ifdef CONFIG_PERF_EVENTS int perf_event_init_cpu(unsigned int cpu); int perf_event_exit_cpu(unsigned int cpu); #else #define perf_event_init_cpu NULL #define perf_event_exit_cpu NULL #endif extern void __weak arch_perf_update_userpage(struct perf_event *event, struct perf_event_mmap_page *userpg, u64 now); #endif /* _LINUX_PERF_EVENT_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MIN_HEAP_H #define _LINUX_MIN_HEAP_H #include <linux/bug.h> #include <linux/string.h> #include <linux/types.h> /** * struct min_heap - Data structure to hold a min-heap. * @data: Start of array holding the heap elements. * @nr: Number of elements currently in the heap. * @size: Maximum number of elements that can be held in current storage. */ struct min_heap { void *data; int nr; int size; }; /** * struct min_heap_callbacks - Data/functions to customise the min_heap. * @elem_size: The nr of each element in bytes. * @less: Partial order function for this heap. * @swp: Swap elements function. */ struct min_heap_callbacks { int elem_size; bool (*less)(const void *lhs, const void *rhs); void (*swp)(void *lhs, void *rhs); }; /* Sift the element at pos down the heap. */ static __always_inline void min_heapify(struct min_heap *heap, int pos, const struct min_heap_callbacks *func) { void *left, *right, *parent, *smallest; void *data = heap->data; for (;;) { if (pos * 2 + 1 >= heap->nr) break; left = data + ((pos * 2 + 1) * func->elem_size); parent = data + (pos * func->elem_size); smallest = parent; if (func->less(left, smallest)) smallest = left; if (pos * 2 + 2 < heap->nr) { right = data + ((pos * 2 + 2) * func->elem_size); if (func->less(right, smallest)) smallest = right; } if (smallest == parent) break; func->swp(smallest, parent); if (smallest == left) pos = (pos * 2) + 1; else pos = (pos * 2) + 2; } } /* Floyd's approach to heapification that is O(nr). */ static __always_inline void min_heapify_all(struct min_heap *heap, const struct min_heap_callbacks *func) { int i; for (i = heap->nr / 2; i >= 0; i--) min_heapify(heap, i, func); } /* Remove minimum element from the heap, O(log2(nr)). */ static __always_inline void min_heap_pop(struct min_heap *heap, const struct min_heap_callbacks *func) { void *data = heap->data; if (WARN_ONCE(heap->nr <= 0, "Popping an empty heap")) return; /* Place last element at the root (position 0) and then sift down. */ heap->nr--; memcpy(data, data + (heap->nr * func->elem_size), func->elem_size); min_heapify(heap, 0, func); } /* * Remove the minimum element and then push the given element. The * implementation performs 1 sift (O(log2(nr))) and is therefore more * efficient than a pop followed by a push that does 2. */ static __always_inline void min_heap_pop_push(struct min_heap *heap, const void *element, const struct min_heap_callbacks *func) { memcpy(heap->data, element, func->elem_size); min_heapify(heap, 0, func); } /* Push an element on to the heap, O(log2(nr)). */ static __always_inline void min_heap_push(struct min_heap *heap, const void *element, const struct min_heap_callbacks *func) { void *data = heap->data; void *child, *parent; int pos; if (WARN_ONCE(heap->nr >= heap->size, "Pushing on a full heap")) return; /* Place at the end of data. */ pos = heap->nr; memcpy(data + (pos * func->elem_size), element, func->elem_size); heap->nr++; /* Sift child at pos up. */ for (; pos > 0; pos = (pos - 1) / 2) { child = data + (pos * func->elem_size); parent = data + ((pos - 1) / 2) * func->elem_size; if (func->less(parent, child)) break; func->swp(parent, child); } } #endif /* _LINUX_MIN_HEAP_H */
1 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 // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/file.c * * Copyright (C) 1998-1999, Stephen Tweedie and Bill Hawes * * Manage the dynamic fd arrays in the process files_struct. */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/fs.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/bitops.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/close_range.h> #include <net/sock.h> unsigned int sysctl_nr_open __read_mostly = 1024*1024; unsigned int sysctl_nr_open_min = BITS_PER_LONG; /* our min() is unusable in constant expressions ;-/ */ #define __const_min(x, y) ((x) < (y) ? (x) : (y)) unsigned int sysctl_nr_open_max = __const_min(INT_MAX, ~(size_t)0/sizeof(void *)) & -BITS_PER_LONG; static void __free_fdtable(struct fdtable *fdt) { kvfree(fdt->fd); kvfree(fdt->open_fds); kfree(fdt); } static void free_fdtable_rcu(struct rcu_head *rcu) { __free_fdtable(container_of(rcu, struct fdtable, rcu)); } #define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr)) #define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long)) /* * Copy 'count' fd bits from the old table to the new table and clear the extra * space if any. This does not copy the file pointers. Called with the files * spinlock held for write. */ static void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, unsigned int count) { unsigned int cpy, set; cpy = count / BITS_PER_BYTE; set = (nfdt->max_fds - count) / BITS_PER_BYTE; memcpy(nfdt->open_fds, ofdt->open_fds, cpy); memset((char *)nfdt->open_fds + cpy, 0, set); memcpy(nfdt->close_on_exec, ofdt->close_on_exec, cpy); memset((char *)nfdt->close_on_exec + cpy, 0, set); cpy = BITBIT_SIZE(count); set = BITBIT_SIZE(nfdt->max_fds) - cpy; memcpy(nfdt->full_fds_bits, ofdt->full_fds_bits, cpy); memset((char *)nfdt->full_fds_bits + cpy, 0, set); } /* * Copy all file descriptors from the old table to the new, expanded table and * clear the extra space. Called with the files spinlock held for write. */ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt) { size_t cpy, set; BUG_ON(nfdt->max_fds < ofdt->max_fds); cpy = ofdt->max_fds * sizeof(struct file *); set = (nfdt->max_fds - ofdt->max_fds) * sizeof(struct file *); memcpy(nfdt->fd, ofdt->fd, cpy); memset((char *)nfdt->fd + cpy, 0, set); copy_fd_bitmaps(nfdt, ofdt, ofdt->max_fds); } static struct fdtable * alloc_fdtable(unsigned int nr) { struct fdtable *fdt; void *data; /* * Figure out how many fds we actually want to support in this fdtable. * Allocation steps are keyed to the size of the fdarray, since it * grows far faster than any of the other dynamic data. We try to fit * the fdarray into comfortable page-tuned chunks: starting at 1024B * and growing in powers of two from there on. */ nr /= (1024 / sizeof(struct file *)); nr = roundup_pow_of_two(nr + 1); nr *= (1024 / sizeof(struct file *)); /* * Note that this can drive nr *below* what we had passed if sysctl_nr_open * had been set lower between the check in expand_files() and here. Deal * with that in caller, it's cheaper that way. * * We make sure that nr remains a multiple of BITS_PER_LONG - otherwise * bitmaps handling below becomes unpleasant, to put it mildly... */ if (unlikely(nr > sysctl_nr_open)) nr = ((sysctl_nr_open - 1) | (BITS_PER_LONG - 1)) + 1; fdt = kmalloc(sizeof(struct fdtable), GFP_KERNEL_ACCOUNT); if (!fdt) goto out; fdt->max_fds = nr; data = kvmalloc_array(nr, sizeof(struct file *), GFP_KERNEL_ACCOUNT); if (!data) goto out_fdt; fdt->fd = data; data = kvmalloc(max_t(size_t, 2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES), GFP_KERNEL_ACCOUNT); if (!data) goto out_arr; fdt->open_fds = data; data += nr / BITS_PER_BYTE; fdt->close_on_exec = data; data += nr / BITS_PER_BYTE; fdt->full_fds_bits = data; return fdt; out_arr: kvfree(fdt->fd); out_fdt: kfree(fdt); out: return NULL; } /* * Expand the file descriptor table. * This function will allocate a new fdtable and both fd array and fdset, of * the given size. * Return <0 error code on error; 1 on successful completion. * The files->file_lock should be held on entry, and will be held on exit. */ static int expand_fdtable(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock) { struct fdtable *new_fdt, *cur_fdt; spin_unlock(&files->file_lock); new_fdt = alloc_fdtable(nr); /* make sure all __fd_install() have seen resize_in_progress * or have finished their rcu_read_lock_sched() section. */ if (atomic_read(&files->count) > 1) synchronize_rcu(); spin_lock(&files->file_lock); if (!new_fdt) return -ENOMEM; /* * extremely unlikely race - sysctl_nr_open decreased between the check in * caller and alloc_fdtable(). Cheaper to catch it here... */ if (unlikely(new_fdt->max_fds <= nr)) { __free_fdtable(new_fdt); return -EMFILE; } cur_fdt = files_fdtable(files); BUG_ON(nr < cur_fdt->max_fds); copy_fdtable(new_fdt, cur_fdt); rcu_assign_pointer(files->fdt, new_fdt); if (cur_fdt != &files->fdtab) call_rcu(&cur_fdt->rcu, free_fdtable_rcu); /* coupled with smp_rmb() in __fd_install() */ smp_wmb(); return 1; } /* * Expand files. * This function will expand the file structures, if the requested size exceeds * the current capacity and there is room for expansion. * Return <0 error code on error; 0 when nothing done; 1 when files were * expanded and execution may have blocked. * The files->file_lock should be held on entry, and will be held on exit. */ static int expand_files(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock) { struct fdtable *fdt; int expanded = 0; repeat: fdt = files_fdtable(files); /* Do we need to expand? */ if (nr < fdt->max_fds) return expanded; /* Can we expand? */ if (nr >= sysctl_nr_open) return -EMFILE; if (unlikely(files->resize_in_progress)) { spin_unlock(&files->file_lock); expanded = 1; wait_event(files->resize_wait, !files->resize_in_progress); spin_lock(&files->file_lock); goto repeat; } /* All good, so we try */ files->resize_in_progress = true; expanded = expand_fdtable(files, nr); files->resize_in_progress = false; wake_up_all(&files->resize_wait); return expanded; } static inline void __set_close_on_exec(unsigned int fd, struct fdtable *fdt) { __set_bit(fd, fdt->close_on_exec); } static inline void __clear_close_on_exec(unsigned int fd, struct fdtable *fdt) { if (test_bit(fd, fdt->close_on_exec)) __clear_bit(fd, fdt->close_on_exec); } static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt) { __set_bit(fd, fdt->open_fds); fd /= BITS_PER_LONG; if (!~fdt->open_fds[fd]) __set_bit(fd, fdt->full_fds_bits); } static inline void __clear_open_fd(unsigned int fd, struct fdtable *fdt) { __clear_bit(fd, fdt->open_fds); __clear_bit(fd / BITS_PER_LONG, fdt->full_fds_bits); } static unsigned int count_open_files(struct fdtable *fdt) { unsigned int size = fdt->max_fds; unsigned int i; /* Find the last open fd */ for (i = size / BITS_PER_LONG; i > 0; ) { if (fdt->open_fds[--i]) break; } i = (i + 1) * BITS_PER_LONG; return i; } static unsigned int sane_fdtable_size(struct fdtable *fdt, unsigned int max_fds) { unsigned int count; count = count_open_files(fdt); if (max_fds < NR_OPEN_DEFAULT) max_fds = NR_OPEN_DEFAULT; return min(count, max_fds); } /* * Allocate a new files structure and copy contents from the * passed in files structure. * errorp will be valid only when the returned files_struct is NULL. */ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int *errorp) { struct files_struct *newf; struct file **old_fds, **new_fds; unsigned int open_files, i; struct fdtable *old_fdt, *new_fdt; *errorp = -ENOMEM; newf = kmem_cache_alloc(files_cachep, GFP_KERNEL); if (!newf) goto out; atomic_set(&newf->count, 1); spin_lock_init(&newf->file_lock); newf->resize_in_progress = false; init_waitqueue_head(&newf->resize_wait); newf->next_fd = 0; new_fdt = &newf->fdtab; new_fdt->max_fds = NR_OPEN_DEFAULT; new_fdt->close_on_exec = newf->close_on_exec_init; new_fdt->open_fds = newf->open_fds_init; new_fdt->full_fds_bits = newf->full_fds_bits_init; new_fdt->fd = &newf->fd_array[0]; spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, max_fds); /* * Check whether we need to allocate a larger fd array and fd set. */ while (unlikely(open_files > new_fdt->max_fds)) { spin_unlock(&oldf->file_lock); if (new_fdt != &newf->fdtab) __free_fdtable(new_fdt); new_fdt = alloc_fdtable(open_files - 1); if (!new_fdt) { *errorp = -ENOMEM; goto out_release; } /* beyond sysctl_nr_open; nothing to do */ if (unlikely(new_fdt->max_fds < open_files)) { __free_fdtable(new_fdt); *errorp = -EMFILE; goto out_release; } /* * Reacquire the oldf lock and a pointer to its fd table * who knows it may have a new bigger fd table. We need * the latest pointer. */ spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, max_fds); } copy_fd_bitmaps(new_fdt, old_fdt, open_files); old_fds = old_fdt->fd; new_fds = new_fdt->fd; for (i = open_files; i != 0; i--) { struct file *f = *old_fds++; if (f) { get_file(f); } else { /* * The fd may be claimed in the fd bitmap but not yet * instantiated in the files array if a sibling thread * is partway through open(). So make sure that this * fd is available to the new process. */ __clear_open_fd(open_files - i, new_fdt); } rcu_assign_pointer(*new_fds++, f); } spin_unlock(&oldf->file_lock); /* clear the remainder */ memset(new_fds, 0, (new_fdt->max_fds - open_files) * sizeof(struct file *)); rcu_assign_pointer(newf->fdt, new_fdt); return newf; out_release: kmem_cache_free(files_cachep, newf); out: return NULL; } static struct fdtable *close_files(struct files_struct * files) { /* * It is safe to dereference the fd table without RCU or * ->file_lock because this is the last reference to the * files structure. */ struct fdtable *fdt = rcu_dereference_raw(files->fdt); unsigned int i, j = 0; for (;;) { unsigned long set; i = j * BITS_PER_LONG; if (i >= fdt->max_fds) break; set = fdt->open_fds[j++]; while (set) { if (set & 1) { struct file * file = xchg(&fdt->fd[i], NULL); if (file) { filp_close(file, files); cond_resched(); } } i++; set >>= 1; } } return fdt; } struct files_struct *get_files_struct(struct task_struct *task) { struct files_struct *files; task_lock(task); files = task->files; if (files) atomic_inc(&files->count); task_unlock(task); return files; } void put_files_struct(struct files_struct *files) { if (atomic_dec_and_test(&files->count)) { struct fdtable *fdt = close_files(files); /* free the arrays if they are not embedded */ if (fdt != &files->fdtab) __free_fdtable(fdt); kmem_cache_free(files_cachep, files); } } void reset_files_struct(struct files_struct *files) { struct task_struct *tsk = current; struct files_struct *old; old = tsk->files; task_lock(tsk); tsk->files = files; task_unlock(tsk); put_files_struct(old); } void exit_files(struct task_struct *tsk) { struct files_struct * files = tsk->files; if (files) { task_lock(tsk); tsk->files = NULL; task_unlock(tsk); put_files_struct(files); } } struct files_struct init_files = { .count = ATOMIC_INIT(1), .fdt = &init_files.fdtab, .fdtab = { .max_fds = NR_OPEN_DEFAULT, .fd = &init_files.fd_array[0], .close_on_exec = init_files.close_on_exec_init, .open_fds = init_files.open_fds_init, .full_fds_bits = init_files.full_fds_bits_init, }, .file_lock = __SPIN_LOCK_UNLOCKED(init_files.file_lock), .resize_wait = __WAIT_QUEUE_HEAD_INITIALIZER(init_files.resize_wait), }; static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start) { unsigned int maxfd = fdt->max_fds; unsigned int maxbit = maxfd / BITS_PER_LONG; unsigned int bitbit = start / BITS_PER_LONG; bitbit = find_next_zero_bit(fdt->full_fds_bits, maxbit, bitbit) * BITS_PER_LONG; if (bitbit > maxfd) return maxfd; if (bitbit > start) start = bitbit; return find_next_zero_bit(fdt->open_fds, maxfd, start); } /* * allocate a file descriptor, mark it busy. */ int __alloc_fd(struct files_struct *files, unsigned start, unsigned end, unsigned flags) { unsigned int fd; int error; struct fdtable *fdt; spin_lock(&files->file_lock); repeat: fdt = files_fdtable(files); fd = start; if (fd < files->next_fd) fd = files->next_fd; if (fd < fdt->max_fds) fd = find_next_fd(fdt, fd); /* * N.B. For clone tasks sharing a files structure, this test * will limit the total number of files that can be opened. */ error = -EMFILE; if (fd >= end) goto out; error = expand_files(files, fd); if (error < 0) goto out; /* * If we needed to expand the fs array we * might have blocked - try again. */ if (error) goto repeat; if (start <= files->next_fd) files->next_fd = fd + 1; __set_open_fd(fd, fdt); if (flags & O_CLOEXEC) __set_close_on_exec(fd, fdt); else __clear_close_on_exec(fd, fdt); error = fd; #if 1 /* Sanity check */ if (rcu_access_pointer(fdt->fd[fd]) != NULL) { printk(KERN_WARNING "alloc_fd: slot %d not NULL!\n", fd); rcu_assign_pointer(fdt->fd[fd], NULL); } #endif out: spin_unlock(&files->file_lock); return error; } static int alloc_fd(unsigned start, unsigned flags) { return __alloc_fd(current->files, start, rlimit(RLIMIT_NOFILE), flags); } int __get_unused_fd_flags(unsigned flags, unsigned long nofile) { return __alloc_fd(current->files, 0, nofile, flags); } int get_unused_fd_flags(unsigned flags) { return __get_unused_fd_flags(flags, rlimit(RLIMIT_NOFILE)); } EXPORT_SYMBOL(get_unused_fd_flags); static void __put_unused_fd(struct files_struct *files, unsigned int fd) { struct fdtable *fdt = files_fdtable(files); __clear_open_fd(fd, fdt); if (fd < files->next_fd) files->next_fd = fd; } void put_unused_fd(unsigned int fd) { struct files_struct *files = current->files; spin_lock(&files->file_lock); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); } EXPORT_SYMBOL(put_unused_fd); /* * Install a file pointer in the fd array. * * The VFS is full of places where we drop the files lock between * setting the open_fds bitmap and installing the file in the file * array. At any such point, we are vulnerable to a dup2() race * installing a file in the array before us. We need to detect this and * fput() the struct file we are about to overwrite in this case. * * It should never happen - if we allow dup2() do it, _really_ bad things * will follow. * * NOTE: __fd_install() variant is really, really low-level; don't * use it unless you are forced to by truly lousy API shoved down * your throat. 'files' *MUST* be either current->files or obtained * by get_files_struct(current) done by whoever had given it to you, * or really bad things will happen. Normally you want to use * fd_install() instead. */ void __fd_install(struct files_struct *files, unsigned int fd, struct file *file) { struct fdtable *fdt; rcu_read_lock_sched(); if (unlikely(files->resize_in_progress)) { rcu_read_unlock_sched(); spin_lock(&files->file_lock); fdt = files_fdtable(files); BUG_ON(fdt->fd[fd] != NULL); rcu_assign_pointer(fdt->fd[fd], file); spin_unlock(&files->file_lock); return; } /* coupled with smp_wmb() in expand_fdtable() */ smp_rmb(); fdt = rcu_dereference_sched(files->fdt); BUG_ON(fdt->fd[fd] != NULL); rcu_assign_pointer(fdt->fd[fd], file); rcu_read_unlock_sched(); } /* * This consumes the "file" refcount, so callers should treat it * as if they had called fput(file). */ void fd_install(unsigned int fd, struct file *file) { __fd_install(current->files, fd, file); } EXPORT_SYMBOL(fd_install); static struct file *pick_file(struct files_struct *files, unsigned fd) { struct file *file = NULL; struct fdtable *fdt; spin_lock(&files->file_lock); fdt = files_fdtable(files); if (fd >= fdt->max_fds) goto out_unlock; file = fdt->fd[fd]; if (!file) goto out_unlock; rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); out_unlock: spin_unlock(&files->file_lock); return file; } /* * The same warnings as for __alloc_fd()/__fd_install() apply here... */ int __close_fd(struct files_struct *files, unsigned fd) { struct file *file; file = pick_file(files, fd); if (!file) return -EBADF; return filp_close(file, files); } EXPORT_SYMBOL(__close_fd); /* for ksys_close() */ /** * __close_range() - Close all file descriptors in a given range. * * @fd: starting file descriptor to close * @max_fd: last file descriptor to close * * This closes a range of file descriptors. All file descriptors * from @fd up to and including @max_fd are closed. */ int __close_range(unsigned fd, unsigned max_fd, unsigned int flags) { unsigned int cur_max; struct task_struct *me = current; struct files_struct *cur_fds = me->files, *fds = NULL; if (flags & ~CLOSE_RANGE_UNSHARE) return -EINVAL; if (fd > max_fd) return -EINVAL; rcu_read_lock(); cur_max = files_fdtable(cur_fds)->max_fds; rcu_read_unlock(); /* cap to last valid index into fdtable */ cur_max--; if (flags & CLOSE_RANGE_UNSHARE) { int ret; unsigned int max_unshare_fds = NR_OPEN_MAX; /* * If the requested range is greater than the current maximum, * we're closing everything so only copy all file descriptors * beneath the lowest file descriptor. */ if (max_fd >= cur_max) max_unshare_fds = fd; ret = unshare_fd(CLONE_FILES, max_unshare_fds, &fds); if (ret) return ret; /* * We used to share our file descriptor table, and have now * created a private one, make sure we're using it below. */ if (fds) swap(cur_fds, fds); } max_fd = min(max_fd, cur_max); while (fd <= max_fd) { struct file *file; file = pick_file(cur_fds, fd++); if (!file) continue; filp_close(file, cur_fds); cond_resched(); } if (fds) { /* * We're done closing the files we were supposed to. Time to install * the new file descriptor table and drop the old one. */ task_lock(me); me->files = cur_fds; task_unlock(me); put_files_struct(fds); } return 0; } /* * variant of __close_fd that gets a ref on the file for later fput. * The caller must ensure that filp_close() called on the file, and then * an fput(). */ int __close_fd_get_file(unsigned int fd, struct file **res) { struct files_struct *files = current->files; struct file *file; struct fdtable *fdt; spin_lock(&files->file_lock); fdt = files_fdtable(files); if (fd >= fdt->max_fds) goto out_unlock; file = fdt->fd[fd]; if (!file) goto out_unlock; rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); get_file(file); *res = file; return 0; out_unlock: spin_unlock(&files->file_lock); *res = NULL; return -ENOENT; } void do_close_on_exec(struct files_struct *files) { unsigned i; struct fdtable *fdt; /* exec unshares first */ spin_lock(&files->file_lock); for (i = 0; ; i++) { unsigned long set; unsigned fd = i * BITS_PER_LONG; fdt = files_fdtable(files); if (fd >= fdt->max_fds) break; set = fdt->close_on_exec[i]; if (!set) continue; fdt->close_on_exec[i] = 0; for ( ; set ; fd++, set >>= 1) { struct file *file; if (!(set & 1)) continue; file = fdt->fd[fd]; if (!file) continue; rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); filp_close(file, files); cond_resched(); spin_lock(&files->file_lock); } } spin_unlock(&files->file_lock); } static struct file *__fget_files(struct files_struct *files, unsigned int fd, fmode_t mask, unsigned int refs) { struct file *file; rcu_read_lock(); loop: file = fcheck_files(files, fd); if (file) { /* File object ref couldn't be taken. * dup2() atomicity guarantee is the reason * we loop to catch the new file (or NULL pointer) */ if (file->f_mode & mask) file = NULL; else if (!get_file_rcu_many(file, refs)) goto loop; else if (__fcheck_files(files, fd) != file) { fput_many(file, refs); goto loop; } } rcu_read_unlock(); return file; } static inline struct file *__fget(unsigned int fd, fmode_t mask, unsigned int refs) { return __fget_files(current->files, fd, mask, refs); } struct file *fget_many(unsigned int fd, unsigned int refs) { return __fget(fd, FMODE_PATH, refs); } struct file *fget(unsigned int fd) { return __fget(fd, FMODE_PATH, 1); } EXPORT_SYMBOL(fget); struct file *fget_raw(unsigned int fd) { return __fget(fd, 0, 1); } EXPORT_SYMBOL(fget_raw); struct file *fget_task(struct task_struct *task, unsigned int fd) { struct file *file = NULL; task_lock(task); if (task->files) file = __fget_files(task->files, fd, 0, 1); task_unlock(task); return file; } /* * Lightweight file lookup - no refcnt increment if fd table isn't shared. * * You can use this instead of fget if you satisfy all of the following * conditions: * 1) You must call fput_light before exiting the syscall and returning control * to userspace (i.e. you cannot remember the returned struct file * after * returning to userspace). * 2) You must not call filp_close on the returned struct file * in between * calls to fget_light and fput_light. * 3) You must not clone the current task in between the calls to fget_light * and fput_light. * * The fput_needed flag returned by fget_light should be passed to the * corresponding fput_light. */ static unsigned long __fget_light(unsigned int fd, fmode_t mask) { struct files_struct *files = current->files; struct file *file; if (atomic_read(&files->count) == 1) { file = __fcheck_files(files, fd); if (!file || unlikely(file->f_mode & mask)) return 0; return (unsigned long)file; } else { file = __fget(fd, mask, 1); if (!file) return 0; return FDPUT_FPUT | (unsigned long)file; } } unsigned long __fdget(unsigned int fd) { return __fget_light(fd, FMODE_PATH); } EXPORT_SYMBOL(__fdget); unsigned long __fdget_raw(unsigned int fd) { return __fget_light(fd, 0); } unsigned long __fdget_pos(unsigned int fd) { unsigned long v = __fdget(fd); struct file *file = (struct file *)(v & ~3); if (file && (file->f_mode & FMODE_ATOMIC_POS)) { if (file_count(file) > 1) { v |= FDPUT_POS_UNLOCK; mutex_lock(&file->f_pos_lock); } } return v; } void __f_unlock_pos(struct file *f) { mutex_unlock(&f->f_pos_lock); } /* * We only lock f_pos if we have threads or if the file might be * shared with another process. In both cases we'll have an elevated * file count (done either by fdget() or by fork()). */ void set_close_on_exec(unsigned int fd, int flag) { struct files_struct *files = current->files; struct fdtable *fdt; spin_lock(&files->file_lock); fdt = files_fdtable(files); if (flag) __set_close_on_exec(fd, fdt); else __clear_close_on_exec(fd, fdt); spin_unlock(&files->file_lock); } bool get_close_on_exec(unsigned int fd) { struct files_struct *files = current->files; struct fdtable *fdt; bool res; rcu_read_lock(); fdt = files_fdtable(files); res = close_on_exec(fd, fdt); rcu_read_unlock(); return res; } static int do_dup2(struct files_struct *files, struct file *file, unsigned fd, unsigned flags) __releases(&files->file_lock) { struct file *tofree; struct fdtable *fdt; /* * We need to detect attempts to do dup2() over allocated but still * not finished descriptor. NB: OpenBSD avoids that at the price of * extra work in their equivalent of fget() - they insert struct * file immediately after grabbing descriptor, mark it larval if * more work (e.g. actual opening) is needed and make sure that * fget() treats larval files as absent. Potentially interesting, * but while extra work in fget() is trivial, locking implications * and amount of surgery on open()-related paths in VFS are not. * FreeBSD fails with -EBADF in the same situation, NetBSD "solution" * deadlocks in rather amusing ways, AFAICS. All of that is out of * scope of POSIX or SUS, since neither considers shared descriptor * tables and this condition does not arise without those. */ fdt = files_fdtable(files); tofree = fdt->fd[fd]; if (!tofree && fd_is_open(fd, fdt)) goto Ebusy; get_file(file); rcu_assign_pointer(fdt->fd[fd], file); __set_open_fd(fd, fdt); if (flags & O_CLOEXEC) __set_close_on_exec(fd, fdt); else __clear_close_on_exec(fd, fdt); spin_unlock(&files->file_lock); if (tofree) filp_close(tofree, files); return fd; Ebusy: spin_unlock(&files->file_lock); return -EBUSY; } int replace_fd(unsigned fd, struct file *file, unsigned flags) { int err; struct files_struct *files = current->files; if (!file) return __close_fd(files, fd); if (fd >= rlimit(RLIMIT_NOFILE)) return -EBADF; spin_lock(&files->file_lock); err = expand_files(files, fd); if (unlikely(err < 0)) goto out_unlock; return do_dup2(files, file, fd, flags); out_unlock: spin_unlock(&files->file_lock); return err; } /** * __receive_fd() - Install received file into file descriptor table * * @fd: fd to install into (if negative, a new fd will be allocated) * @file: struct file that was received from another process * @ufd: __user pointer to write new fd number to * @o_flags: the O_* flags to apply to the new fd entry * * Installs a received file into the file descriptor table, with appropriate * checks and count updates. Optionally writes the fd number to userspace, if * @ufd is non-NULL. * * This helper handles its own reference counting of the incoming * struct file. * * Returns newly install fd or -ve on error. */ int __receive_fd(int fd, struct file *file, int __user *ufd, unsigned int o_flags) { int new_fd; int error; error = security_file_receive(file); if (error) return error; if (fd < 0) { new_fd = get_unused_fd_flags(o_flags); if (new_fd < 0) return new_fd; } else { new_fd = fd; } if (ufd) { error = put_user(new_fd, ufd); if (error) { if (fd < 0) put_unused_fd(new_fd); return error; } } if (fd < 0) { fd_install(new_fd, get_file(file)); } else { error = replace_fd(new_fd, file, o_flags); if (error) return error; } /* Bump the sock usage counts, if any. */ __receive_sock(file); return new_fd; } static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags) { int err = -EBADF; struct file *file; struct files_struct *files = current->files; if ((flags & ~O_CLOEXEC) != 0) return -EINVAL; if (unlikely(oldfd == newfd)) return -EINVAL; if (newfd >= rlimit(RLIMIT_NOFILE)) return -EBADF; spin_lock(&files->file_lock); err = expand_files(files, newfd); file = fcheck(oldfd); if (unlikely(!file)) goto Ebadf; if (unlikely(err < 0)) { if (err == -EMFILE) goto Ebadf; goto out_unlock; } return do_dup2(files, file, newfd, flags); Ebadf: err = -EBADF; out_unlock: spin_unlock(&files->file_lock); return err; } SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags) { return ksys_dup3(oldfd, newfd, flags); } SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd) { if (unlikely(newfd == oldfd)) { /* corner case */ struct files_struct *files = current->files; int retval = oldfd; rcu_read_lock(); if (!fcheck_files(files, oldfd)) retval = -EBADF; rcu_read_unlock(); return retval; } return ksys_dup3(oldfd, newfd, 0); } SYSCALL_DEFINE1(dup, unsigned int, fildes) { int ret = -EBADF; struct file *file = fget_raw(fildes); if (file) { ret = get_unused_fd_flags(0); if (ret >= 0) fd_install(ret, file); else fput(file); } return ret; } int f_dupfd(unsigned int from, struct file *file, unsigned flags) { int err; if (from >= rlimit(RLIMIT_NOFILE)) return -EINVAL; err = alloc_fd(from, flags); if (err >= 0) { get_file(file); fd_install(err, file); } return err; } int iterate_fd(struct files_struct *files, unsigned n, int (*f)(const void *, struct file *, unsigned), const void *p) { struct fdtable *fdt; int res = 0; if (!files) return 0; spin_lock(&files->file_lock); for (fdt = files_fdtable(files); n < fdt->max_fds; n++) { struct file *file; file = rcu_dereference_check_fdtable(files, fdt->fd[n]); if (!file) continue; res = f(p, file, n); if (res) break; } spin_unlock(&files->file_lock); return res; } EXPORT_SYMBOL(iterate_fd);
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 // SPDX-License-Identifier: GPL-2.0 /* * fs/ext4/extents_status.h * * Written by Yongqiang Yang <xiaoqiangnk@gmail.com> * Modified by * Allison Henderson <achender@linux.vnet.ibm.com> * Zheng Liu <wenqing.lz@taobao.com> * */ #ifndef _EXT4_EXTENTS_STATUS_H #define _EXT4_EXTENTS_STATUS_H /* * Turn on ES_DEBUG__ to get lots of info about extent status operations. */ #ifdef ES_DEBUG__ #define es_debug(fmt, ...) printk(fmt, ##__VA_ARGS__) #else #define es_debug(fmt, ...) no_printk(fmt, ##__VA_ARGS__) #endif /* * With ES_AGGRESSIVE_TEST defined, the result of es caching will be * checked with old map_block's result. */ #define ES_AGGRESSIVE_TEST__ /* * These flags live in the high bits of extent_status.es_pblk */ enum { ES_WRITTEN_B, ES_UNWRITTEN_B, ES_DELAYED_B, ES_HOLE_B, ES_REFERENCED_B, ES_FLAGS }; #define ES_SHIFT (sizeof(ext4_fsblk_t)*8 - ES_FLAGS) #define ES_MASK (~((ext4_fsblk_t)0) << ES_SHIFT) #define EXTENT_STATUS_WRITTEN (1 << ES_WRITTEN_B) #define EXTENT_STATUS_UNWRITTEN (1 << ES_UNWRITTEN_B) #define EXTENT_STATUS_DELAYED (1 << ES_DELAYED_B) #define EXTENT_STATUS_HOLE (1 << ES_HOLE_B) #define EXTENT_STATUS_REFERENCED (1 << ES_REFERENCED_B) #define ES_TYPE_MASK ((ext4_fsblk_t)(EXTENT_STATUS_WRITTEN | \ EXTENT_STATUS_UNWRITTEN | \ EXTENT_STATUS_DELAYED | \ EXTENT_STATUS_HOLE) << ES_SHIFT) struct ext4_sb_info; struct ext4_extent; struct extent_status { struct rb_node rb_node; ext4_lblk_t es_lblk; /* first logical block extent covers */ ext4_lblk_t es_len; /* length of extent in block */ ext4_fsblk_t es_pblk; /* first physical block */ }; struct ext4_es_tree { struct rb_root root; struct extent_status *cache_es; /* recently accessed extent */ }; struct ext4_es_stats { unsigned long es_stats_shrunk; struct percpu_counter es_stats_cache_hits; struct percpu_counter es_stats_cache_misses; u64 es_stats_scan_time; u64 es_stats_max_scan_time; struct percpu_counter es_stats_all_cnt; struct percpu_counter es_stats_shk_cnt; }; /* * Pending cluster reservations for bigalloc file systems * * A cluster with a pending reservation is a logical cluster shared by at * least one extent in the extents status tree with delayed and unwritten * status and at least one other written or unwritten extent. The * reservation is said to be pending because a cluster reservation would * have to be taken in the event all blocks in the cluster shared with * written or unwritten extents were deleted while the delayed and * unwritten blocks remained. * * The set of pending cluster reservations is an auxiliary data structure * used with the extents status tree to implement reserved cluster/block * accounting for bigalloc file systems. The set is kept in memory and * records all pending cluster reservations. * * Its primary function is to avoid the need to read extents from the * disk when invalidating pages as a result of a truncate, punch hole, or * collapse range operation. Page invalidation requires a decrease in the * reserved cluster count if it results in the removal of all delayed * and unwritten extents (blocks) from a cluster that is not shared with a * written or unwritten extent, and no decrease otherwise. Determining * whether the cluster is shared can be done by searching for a pending * reservation on it. * * Secondarily, it provides a potentially faster method for determining * whether the reserved cluster count should be increased when a physical * cluster is deallocated as a result of a truncate, punch hole, or * collapse range operation. The necessary information is also present * in the extents status tree, but might be more rapidly accessed in * the pending reservation set in many cases due to smaller size. * * The pending cluster reservation set is implemented as a red-black tree * with the goal of minimizing per page search time overhead. */ struct pending_reservation { struct rb_node rb_node; ext4_lblk_t lclu; }; struct ext4_pending_tree { struct rb_root root; }; extern int __init ext4_init_es(void); extern void ext4_exit_es(void); extern void ext4_es_init_tree(struct ext4_es_tree *tree); extern int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len, ext4_fsblk_t pblk, unsigned int status); extern void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len, ext4_fsblk_t pblk, unsigned int status); extern int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len); extern void ext4_es_find_extent_range(struct inode *inode, int (*match_fn)(struct extent_status *es), ext4_lblk_t lblk, ext4_lblk_t end, struct extent_status *es); extern int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t *next_lblk, struct extent_status *es); extern bool ext4_es_scan_range(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t lblk, ext4_lblk_t end); extern bool ext4_es_scan_clu(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t lblk); static inline unsigned int ext4_es_status(struct extent_status *es) { return es->es_pblk >> ES_SHIFT; } static inline unsigned int ext4_es_type(struct extent_status *es) { return (es->es_pblk & ES_TYPE_MASK) >> ES_SHIFT; } static inline int ext4_es_is_written(struct extent_status *es) { return (ext4_es_type(es) & EXTENT_STATUS_WRITTEN) != 0; } static inline int ext4_es_is_unwritten(struct extent_status *es) { return (ext4_es_type(es) & EXTENT_STATUS_UNWRITTEN) != 0; } static inline int ext4_es_is_delayed(struct extent_status *es) { return (ext4_es_type(es) & EXTENT_STATUS_DELAYED) != 0; } static inline int ext4_es_is_hole(struct extent_status *es) { return (ext4_es_type(es) & EXTENT_STATUS_HOLE) != 0; } static inline int ext4_es_is_mapped(struct extent_status *es) { return (ext4_es_is_written(es) || ext4_es_is_unwritten(es)); } static inline int ext4_es_is_delonly(struct extent_status *es) { return (ext4_es_is_delayed(es) && !ext4_es_is_unwritten(es)); } static inline void ext4_es_set_referenced(struct extent_status *es) { es->es_pblk |= ((ext4_fsblk_t)EXTENT_STATUS_REFERENCED) << ES_SHIFT; } static inline void ext4_es_clear_referenced(struct extent_status *es) { es->es_pblk &= ~(((ext4_fsblk_t)EXTENT_STATUS_REFERENCED) << ES_SHIFT); } static inline int ext4_es_is_referenced(struct extent_status *es) { return (ext4_es_status(es) & EXTENT_STATUS_REFERENCED) != 0; } static inline ext4_fsblk_t ext4_es_pblock(struct extent_status *es) { return es->es_pblk & ~ES_MASK; } static inline ext4_fsblk_t ext4_es_show_pblock(struct extent_status *es) { ext4_fsblk_t pblock = ext4_es_pblock(es); return pblock == ~ES_MASK ? 0 : pblock; } static inline void ext4_es_store_pblock(struct extent_status *es, ext4_fsblk_t pb) { ext4_fsblk_t block; block = (pb & ~ES_MASK) | (es->es_pblk & ES_MASK); es->es_pblk = block; } static inline void ext4_es_store_status(struct extent_status *es, unsigned int status) { es->es_pblk = (((ext4_fsblk_t)status << ES_SHIFT) & ES_MASK) | (es->es_pblk & ~ES_MASK); } static inline void ext4_es_store_pblock_status(struct extent_status *es, ext4_fsblk_t pb, unsigned int status) { es->es_pblk = (((ext4_fsblk_t)status << ES_SHIFT) & ES_MASK) | (pb & ~ES_MASK); } extern int ext4_es_register_shrinker(struct ext4_sb_info *sbi); extern void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi); extern int ext4_seq_es_shrinker_info_show(struct seq_file *seq, void *v); extern int __init ext4_init_pending(void); extern void ext4_exit_pending(void); extern void ext4_init_pending_tree(struct ext4_pending_tree *tree); extern void ext4_remove_pending(struct inode *inode, ext4_lblk_t lblk); extern bool ext4_is_pending(struct inode *inode, ext4_lblk_t lblk); extern int ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk, bool allocated); extern unsigned int ext4_es_delayed_clu(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len); extern void ext4_clear_inode_es(struct inode *inode); #endif /* _EXT4_EXTENTS_STATUS_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __CGROUP_INTERNAL_H #define __CGROUP_INTERNAL_H #include <linux/cgroup.h> #include <linux/kernfs.h> #include <linux/workqueue.h> #include <linux/list.h> #include <linux/refcount.h> #include <linux/fs_parser.h> #define TRACE_CGROUP_PATH_LEN 1024 extern spinlock_t trace_cgroup_path_lock; extern char trace_cgroup_path[TRACE_CGROUP_PATH_LEN]; extern bool cgroup_debug; extern void __init enable_debug_cgroup(void); /* * cgroup_path() takes a spin lock. It is good practice not to take * spin locks within trace point handlers, as they are mostly hidden * from normal view. As cgroup_path() can take the kernfs_rename_lock * spin lock, it is best to not call that function from the trace event * handler. * * Note: trace_cgroup_##type##_enabled() is a static branch that will only * be set when the trace event is enabled. */ #define TRACE_CGROUP_PATH(type, cgrp, ...) \ do { \ if (trace_cgroup_##type##_enabled()) { \ unsigned long flags; \ spin_lock_irqsave(&trace_cgroup_path_lock, \ flags); \ cgroup_path(cgrp, trace_cgroup_path, \ TRACE_CGROUP_PATH_LEN); \ trace_cgroup_##type(cgrp, trace_cgroup_path, \ ##__VA_ARGS__); \ spin_unlock_irqrestore(&trace_cgroup_path_lock, \ flags); \ } \ } while (0) /* * The cgroup filesystem superblock creation/mount context. */ struct cgroup_fs_context { struct kernfs_fs_context kfc; struct cgroup_root *root; struct cgroup_namespace *ns; unsigned int flags; /* CGRP_ROOT_* flags */ /* cgroup1 bits */ bool cpuset_clone_children; bool none; /* User explicitly requested empty subsystem */ bool all_ss; /* Seen 'all' option */ u16 subsys_mask; /* Selected subsystems */ char *name; /* Hierarchy name */ char *release_agent; /* Path for release notifications */ }; static inline struct cgroup_fs_context *cgroup_fc2context(struct fs_context *fc) { struct kernfs_fs_context *kfc = fc->fs_private; return container_of(kfc, struct cgroup_fs_context, kfc); } /* * A cgroup can be associated with multiple css_sets as different tasks may * belong to different cgroups on different hierarchies. In the other * direction, a css_set is naturally associated with multiple cgroups. * This M:N relationship is represented by the following link structure * which exists for each association and allows traversing the associations * from both sides. */ struct cgrp_cset_link { /* the cgroup and css_set this link associates */ struct cgroup *cgrp; struct css_set *cset; /* list of cgrp_cset_links anchored at cgrp->cset_links */ struct list_head cset_link; /* list of cgrp_cset_links anchored at css_set->cgrp_links */ struct list_head cgrp_link; }; /* used to track tasks and csets during migration */ struct cgroup_taskset { /* the src and dst cset list running through cset->mg_node */ struct list_head src_csets; struct list_head dst_csets; /* the number of tasks in the set */ int nr_tasks; /* the subsys currently being processed */ int ssid; /* * Fields for cgroup_taskset_*() iteration. * * Before migration is committed, the target migration tasks are on * ->mg_tasks of the csets on ->src_csets. After, on ->mg_tasks of * the csets on ->dst_csets. ->csets point to either ->src_csets * or ->dst_csets depending on whether migration is committed. * * ->cur_csets and ->cur_task point to the current task position * during iteration. */ struct list_head *csets; struct css_set *cur_cset; struct task_struct *cur_task; }; /* migration context also tracks preloading */ struct cgroup_mgctx { /* * Preloaded source and destination csets. Used to guarantee * atomic success or failure on actual migration. */ struct list_head preloaded_src_csets; struct list_head preloaded_dst_csets; /* tasks and csets to migrate */ struct cgroup_taskset tset; /* subsystems affected by migration */ u16 ss_mask; }; #define CGROUP_TASKSET_INIT(tset) \ { \ .src_csets = LIST_HEAD_INIT(tset.src_csets), \ .dst_csets = LIST_HEAD_INIT(tset.dst_csets), \ .csets = &tset.src_csets, \ } #define CGROUP_MGCTX_INIT(name) \ { \ LIST_HEAD_INIT(name.preloaded_src_csets), \ LIST_HEAD_INIT(name.preloaded_dst_csets), \ CGROUP_TASKSET_INIT(name.tset), \ } #define DEFINE_CGROUP_MGCTX(name) \ struct cgroup_mgctx name = CGROUP_MGCTX_INIT(name) extern struct mutex cgroup_mutex; extern spinlock_t css_set_lock; extern struct cgroup_subsys *cgroup_subsys[]; extern struct list_head cgroup_roots; extern struct file_system_type cgroup_fs_type; /* iterate across the hierarchies */ #define for_each_root(root) \ list_for_each_entry((root), &cgroup_roots, root_list) /** * for_each_subsys - iterate all enabled cgroup subsystems * @ss: the iteration cursor * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end */ #define for_each_subsys(ss, ssid) \ for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT && \ (((ss) = cgroup_subsys[ssid]) || true); (ssid)++) static inline bool cgroup_is_dead(const struct cgroup *cgrp) { return !(cgrp->self.flags & CSS_ONLINE); } static inline bool notify_on_release(const struct cgroup *cgrp) { return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); } void put_css_set_locked(struct css_set *cset); static inline void put_css_set(struct css_set *cset) { unsigned long flags; /* * Ensure that the refcount doesn't hit zero while any readers * can see it. Similar to atomic_dec_and_lock(), but for an * rwlock */ if (refcount_dec_not_one(&cset->refcount)) return; spin_lock_irqsave(&css_set_lock, flags); put_css_set_locked(cset); spin_unlock_irqrestore(&css_set_lock, flags); } /* * refcounted get/put for css_set objects */ static inline void get_css_set(struct css_set *cset) { refcount_inc(&cset->refcount); } bool cgroup_ssid_enabled(int ssid); bool cgroup_on_dfl(const struct cgroup *cgrp); bool cgroup_is_thread_root(struct cgroup *cgrp); bool cgroup_is_threaded(struct cgroup *cgrp); struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root); struct cgroup *task_cgroup_from_root(struct task_struct *task, struct cgroup_root *root); struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn, bool drain_offline); void cgroup_kn_unlock(struct kernfs_node *kn); int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns); void cgroup_free_root(struct cgroup_root *root); void init_cgroup_root(struct cgroup_fs_context *ctx); int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask); int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask); int cgroup_do_get_tree(struct fs_context *fc); int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp); void cgroup_migrate_finish(struct cgroup_mgctx *mgctx); void cgroup_migrate_add_src(struct css_set *src_cset, struct cgroup *dst_cgrp, struct cgroup_mgctx *mgctx); int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx); int cgroup_migrate(struct task_struct *leader, bool threadgroup, struct cgroup_mgctx *mgctx); int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, bool threadgroup); struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup, bool *locked) __acquires(&cgroup_threadgroup_rwsem); void cgroup_procs_write_finish(struct task_struct *task, bool locked) __releases(&cgroup_threadgroup_rwsem); void cgroup_lock_and_drain_offline(struct cgroup *cgrp); int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode); int cgroup_rmdir(struct kernfs_node *kn); int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, struct kernfs_root *kf_root); int __cgroup_task_count(const struct cgroup *cgrp); int cgroup_task_count(const struct cgroup *cgrp); /* * rstat.c */ int cgroup_rstat_init(struct cgroup *cgrp); void cgroup_rstat_exit(struct cgroup *cgrp); void cgroup_rstat_boot(void); void cgroup_base_stat_cputime_show(struct seq_file *seq); /* * namespace.c */ extern const struct proc_ns_operations cgroupns_operations; /* * cgroup-v1.c */ extern struct cftype cgroup1_base_files[]; extern struct kernfs_syscall_ops cgroup1_kf_syscall_ops; extern const struct fs_parameter_spec cgroup1_fs_parameters[]; int proc_cgroupstats_show(struct seq_file *m, void *v); bool cgroup1_ssid_disabled(int ssid); void cgroup1_pidlist_destroy_all(struct cgroup *cgrp); void cgroup1_release_agent(struct work_struct *work); void cgroup1_check_for_release(struct cgroup *cgrp); int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param); int cgroup1_get_tree(struct fs_context *fc); int cgroup1_reconfigure(struct fs_context *ctx); #endif /* __CGROUP_INTERNAL_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _SCSI_DISK_H #define _SCSI_DISK_H /* * More than enough for everybody ;) The huge number of majors * is a leftover from 16bit dev_t days, we don't really need that * much numberspace. */ #define SD_MAJORS 16 /* * Time out in seconds for disks and Magneto-opticals (which are slower). */ #define SD_TIMEOUT (30 * HZ) #define SD_MOD_TIMEOUT (75 * HZ) /* * Flush timeout is a multiplier over the standard device timeout which is * user modifiable via sysfs but initially set to SD_TIMEOUT */ #define SD_FLUSH_TIMEOUT_MULTIPLIER 2 #define SD_WRITE_SAME_TIMEOUT (120 * HZ) /* * Number of allowed retries */ #define SD_MAX_RETRIES 5 #define SD_PASSTHROUGH_RETRIES 1 #define SD_MAX_MEDIUM_TIMEOUTS 2 /* * Size of the initial data buffer for mode and read capacity data */ #define SD_BUF_SIZE 512 /* * Number of sectors at the end of the device to avoid multi-sector * accesses to in the case of last_sector_bug */ #define SD_LAST_BUGGY_SECTORS 8 enum { SD_EXT_CDB_SIZE = 32, /* Extended CDB size */ SD_MEMPOOL_SIZE = 2, /* CDB pool size */ }; enum { SD_DEF_XFER_BLOCKS = 0xffff, SD_MAX_XFER_BLOCKS = 0xffffffff, SD_MAX_WS10_BLOCKS = 0xffff, SD_MAX_WS16_BLOCKS = 0x7fffff, }; enum { SD_LBP_FULL = 0, /* Full logical block provisioning */ SD_LBP_UNMAP, /* Use UNMAP command */ SD_LBP_WS16, /* Use WRITE SAME(16) with UNMAP bit */ SD_LBP_WS10, /* Use WRITE SAME(10) with UNMAP bit */ SD_LBP_ZERO, /* Use WRITE SAME(10) with zero payload */ SD_LBP_DISABLE, /* Discard disabled due to failed cmd */ }; enum { SD_ZERO_WRITE = 0, /* Use WRITE(10/16) command */ SD_ZERO_WS, /* Use WRITE SAME(10/16) command */ SD_ZERO_WS16_UNMAP, /* Use WRITE SAME(16) with UNMAP */ SD_ZERO_WS10_UNMAP, /* Use WRITE SAME(10) with UNMAP */ }; struct scsi_disk { struct scsi_driver *driver; /* always &sd_template */ struct scsi_device *device; struct device dev; struct gendisk *disk; struct opal_dev *opal_dev; #ifdef CONFIG_BLK_DEV_ZONED u32 nr_zones; u32 rev_nr_zones; u32 zone_blocks; u32 rev_zone_blocks; u32 zones_optimal_open; u32 zones_optimal_nonseq; u32 zones_max_open; u32 *zones_wp_offset; spinlock_t zones_wp_offset_lock; u32 *rev_wp_offset; struct mutex rev_mutex; struct work_struct zone_wp_offset_work; char *zone_wp_update_buf; #endif atomic_t openers; sector_t capacity; /* size in logical blocks */ int max_retries; u32 max_xfer_blocks; u32 opt_xfer_blocks; u32 max_ws_blocks; u32 max_unmap_blocks; u32 unmap_granularity; u32 unmap_alignment; u32 index; unsigned int physical_block_size; unsigned int max_medium_access_timeouts; unsigned int medium_access_timed_out; u8 media_present; u8 write_prot; u8 protection_type;/* Data Integrity Field */ u8 provisioning_mode; u8 zeroing_mode; unsigned ATO : 1; /* state of disk ATO bit */ unsigned cache_override : 1; /* temp override of WCE,RCD */ unsigned WCE : 1; /* state of disk WCE bit */ unsigned RCD : 1; /* state of disk RCD bit, unused */ unsigned DPOFUA : 1; /* state of disk DPOFUA bit */ unsigned first_scan : 1; unsigned lbpme : 1; unsigned lbprz : 1; unsigned lbpu : 1; unsigned lbpws : 1; unsigned lbpws10 : 1; unsigned lbpvpd : 1; unsigned ws10 : 1; unsigned ws16 : 1; unsigned rc_basis: 2; unsigned zoned: 2; unsigned urswrz : 1; unsigned security : 1; unsigned ignore_medium_access_errors : 1; }; #define to_scsi_disk(obj) container_of(obj,struct scsi_disk,dev) static inline struct scsi_disk *scsi_disk(struct gendisk *disk) { return container_of(disk->private_data, struct scsi_disk, driver); } #define sd_printk(prefix, sdsk, fmt, a...) \ (sdsk)->disk ? \ sdev_prefix_printk(prefix, (sdsk)->device, \ (sdsk)->disk->disk_name, fmt, ##a) : \ sdev_printk(prefix, (sdsk)->device, fmt, ##a) #define sd_first_printk(prefix, sdsk, fmt, a...) \ do { \ if ((sdsk)->first_scan) \ sd_printk(prefix, sdsk, fmt, ##a); \ } while (0) static inline int scsi_medium_access_command(struct scsi_cmnd *scmd) { switch (scmd->cmnd[0]) { case READ_6: case READ_10: case READ_12: case READ_16: case SYNCHRONIZE_CACHE: case VERIFY: case VERIFY_12: case VERIFY_16: case WRITE_6: case WRITE_10: case WRITE_12: case WRITE_16: case WRITE_SAME: case WRITE_SAME_16: case UNMAP: return 1; case VARIABLE_LENGTH_CMD: switch (scmd->cmnd[9]) { case READ_32: case VERIFY_32: case WRITE_32: case WRITE_SAME_32: return 1; } } return 0; } static inline sector_t logical_to_sectors(struct scsi_device *sdev, sector_t blocks) { return blocks << (ilog2(sdev->sector_size) - 9); } static inline unsigned int logical_to_bytes(struct scsi_device *sdev, sector_t blocks) { return blocks * sdev->sector_size; } static inline sector_t bytes_to_logical(struct scsi_device *sdev, unsigned int bytes) { return bytes >> ilog2(sdev->sector_size); } static inline sector_t sectors_to_logical(struct scsi_device *sdev, sector_t sector) { return sector >> (ilog2(sdev->sector_size) - 9); } #ifdef CONFIG_BLK_DEV_INTEGRITY extern void sd_dif_config_host(struct scsi_disk *); #else /* CONFIG_BLK_DEV_INTEGRITY */ static inline void sd_dif_config_host(struct scsi_disk *disk) { } #endif /* CONFIG_BLK_DEV_INTEGRITY */ static inline int sd_is_zoned(struct scsi_disk *sdkp) { return sdkp->zoned == 1 || sdkp->device->type == TYPE_ZBC; } #ifdef CONFIG_BLK_DEV_ZONED void sd_zbc_release_disk(struct scsi_disk *sdkp); int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buffer); int sd_zbc_revalidate_zones(struct scsi_disk *sdkp); blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd, unsigned char op, bool all); unsigned int sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes, struct scsi_sense_hdr *sshdr); int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd, sector_t *lba, unsigned int nr_blocks); #else /* CONFIG_BLK_DEV_ZONED */ static inline void sd_zbc_release_disk(struct scsi_disk *sdkp) {} static inline int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf) { return 0; } static inline int sd_zbc_revalidate_zones(struct scsi_disk *sdkp) { return 0; } static inline blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd, unsigned char op, bool all) { return BLK_STS_TARGET; } static inline unsigned int sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes, struct scsi_sense_hdr *sshdr) { return good_bytes; } static inline blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd, sector_t *lba, unsigned int nr_blocks) { return BLK_STS_TARGET; } #define sd_zbc_report_zones NULL #endif /* CONFIG_BLK_DEV_ZONED */ void sd_print_sense_hdr(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr); void sd_print_result(const struct scsi_disk *sdkp, const char *msg, int result); #endif /* _SCSI_DISK_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 #ifndef _LINUX_SCHED_ISOLATION_H #define _LINUX_SCHED_ISOLATION_H #include <linux/cpumask.h> #include <linux/init.h> #include <linux/tick.h> enum hk_flags { HK_FLAG_TIMER = 1, HK_FLAG_RCU = (1 << 1), HK_FLAG_MISC = (1 << 2), HK_FLAG_SCHED = (1 << 3), HK_FLAG_TICK = (1 << 4), HK_FLAG_DOMAIN = (1 << 5), HK_FLAG_WQ = (1 << 6), HK_FLAG_MANAGED_IRQ = (1 << 7), HK_FLAG_KTHREAD = (1 << 8), }; #ifdef CONFIG_CPU_ISOLATION DECLARE_STATIC_KEY_FALSE(housekeeping_overridden); extern int housekeeping_any_cpu(enum hk_flags flags); extern const struct cpumask *housekeeping_cpumask(enum hk_flags flags); extern bool housekeeping_enabled(enum hk_flags flags); extern void housekeeping_affine(struct task_struct *t, enum hk_flags flags); extern bool housekeeping_test_cpu(int cpu, enum hk_flags flags); extern void __init housekeeping_init(void); #else static inline int housekeeping_any_cpu(enum hk_flags flags) { return smp_processor_id(); } static inline const struct cpumask *housekeeping_cpumask(enum hk_flags flags) { return cpu_possible_mask; } static inline bool housekeeping_enabled(enum hk_flags flags) { return false; } static inline void housekeeping_affine(struct task_struct *t, enum hk_flags flags) { } static inline void housekeeping_init(void) { } #endif /* CONFIG_CPU_ISOLATION */ static inline bool housekeeping_cpu(int cpu, enum hk_flags flags) { #ifdef CONFIG_CPU_ISOLATION if (static_branch_unlikely(&housekeeping_overridden)) return housekeeping_test_cpu(cpu, flags); #endif return true; } #endif /* _LINUX_SCHED_ISOLATION_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 /* SPDX-License-Identifier: GPL-2.0 */ /* Based on net/mac80211/trace.h */ #undef TRACE_SYSTEM #define TRACE_SYSTEM mac802154 #if !defined(__MAC802154_DRIVER_TRACE) || defined(TRACE_HEADER_MULTI_READ) #define __MAC802154_DRIVER_TRACE #include <linux/tracepoint.h> #include <net/mac802154.h> #include "ieee802154_i.h" #define MAXNAME 32 #define LOCAL_ENTRY __array(char, wpan_phy_name, MAXNAME) #define LOCAL_ASSIGN strlcpy(__entry->wpan_phy_name, \ wpan_phy_name(local->hw.phy), MAXNAME) #define LOCAL_PR_FMT "%s" #define LOCAL_PR_ARG __entry->wpan_phy_name #define CCA_ENTRY __field(enum nl802154_cca_modes, cca_mode) \ __field(enum nl802154_cca_opts, cca_opt) #define CCA_ASSIGN \ do { \ (__entry->cca_mode) = cca->mode; \ (__entry->cca_opt) = cca->opt; \ } while (0) #define CCA_PR_FMT "cca_mode: %d, cca_opt: %d" #define CCA_PR_ARG __entry->cca_mode, __entry->cca_opt #define BOOL_TO_STR(bo) (bo) ? "true" : "false" /* Tracing for driver callbacks */ DECLARE_EVENT_CLASS(local_only_evt4, TP_PROTO(struct ieee802154_local *local), TP_ARGS(local), TP_STRUCT__entry( LOCAL_ENTRY ), TP_fast_assign( LOCAL_ASSIGN; ), TP_printk(LOCAL_PR_FMT, LOCAL_PR_ARG) ); DEFINE_EVENT(local_only_evt4, 802154_drv_return_void, TP_PROTO(struct ieee802154_local *local), TP_ARGS(local) ); TRACE_EVENT(802154_drv_return_int, TP_PROTO(struct ieee802154_local *local, int ret), TP_ARGS(local, ret), TP_STRUCT__entry( LOCAL_ENTRY __field(int, ret) ), TP_fast_assign( LOCAL_ASSIGN; __entry->ret = ret; ), TP_printk(LOCAL_PR_FMT ", returned: %d", LOCAL_PR_ARG, __entry->ret) ); DEFINE_EVENT(local_only_evt4, 802154_drv_start, TP_PROTO(struct ieee802154_local *local), TP_ARGS(local) ); DEFINE_EVENT(local_only_evt4, 802154_drv_stop, TP_PROTO(struct ieee802154_local *local), TP_ARGS(local) ); TRACE_EVENT(802154_drv_set_channel, TP_PROTO(struct ieee802154_local *local, u8 page, u8 channel), TP_ARGS(local, page, channel), TP_STRUCT__entry( LOCAL_ENTRY __field(u8, page) __field(u8, channel) ), TP_fast_assign( LOCAL_ASSIGN; __entry->page = page; __entry->channel = channel; ), TP_printk(LOCAL_PR_FMT ", page: %d, channel: %d", LOCAL_PR_ARG, __entry->page, __entry->channel) ); TRACE_EVENT(802154_drv_set_cca_mode, TP_PROTO(struct ieee802154_local *local, const struct wpan_phy_cca *cca), TP_ARGS(local, cca), TP_STRUCT__entry( LOCAL_ENTRY CCA_ENTRY ), TP_fast_assign( LOCAL_ASSIGN; CCA_ASSIGN; ), TP_printk(LOCAL_PR_FMT ", " CCA_PR_FMT, LOCAL_PR_ARG, CCA_PR_ARG) ); TRACE_EVENT(802154_drv_set_cca_ed_level, TP_PROTO(struct ieee802154_local *local, s32 mbm), TP_ARGS(local, mbm), TP_STRUCT__entry( LOCAL_ENTRY __field(s32, mbm) ), TP_fast_assign( LOCAL_ASSIGN; __entry->mbm = mbm; ), TP_printk(LOCAL_PR_FMT ", ed level: %d", LOCAL_PR_ARG, __entry->mbm) ); TRACE_EVENT(802154_drv_set_tx_power, TP_PROTO(struct ieee802154_local *local, s32 power), TP_ARGS(local, power), TP_STRUCT__entry( LOCAL_ENTRY __field(s32, power) ), TP_fast_assign( LOCAL_ASSIGN; __entry->power = power; ), TP_printk(LOCAL_PR_FMT ", mbm: %d", LOCAL_PR_ARG, __entry->power) ); TRACE_EVENT(802154_drv_set_lbt_mode, TP_PROTO(struct ieee802154_local *local, bool mode), TP_ARGS(local, mode), TP_STRUCT__entry( LOCAL_ENTRY __field(bool, mode) ), TP_fast_assign( LOCAL_ASSIGN; __entry->mode = mode; ), TP_printk(LOCAL_PR_FMT ", lbt mode: %s", LOCAL_PR_ARG, BOOL_TO_STR(__entry->mode)) ); TRACE_EVENT(802154_drv_set_short_addr, TP_PROTO(struct ieee802154_local *local, __le16 short_addr), TP_ARGS(local, short_addr), TP_STRUCT__entry( LOCAL_ENTRY __field(__le16, short_addr) ), TP_fast_assign( LOCAL_ASSIGN; __entry->short_addr = short_addr; ), TP_printk(LOCAL_PR_FMT ", short addr: 0x%04x", LOCAL_PR_ARG, le16_to_cpu(__entry->short_addr)) ); TRACE_EVENT(802154_drv_set_pan_id, TP_PROTO(struct ieee802154_local *local, __le16 pan_id), TP_ARGS(local, pan_id), TP_STRUCT__entry( LOCAL_ENTRY __field(__le16, pan_id) ), TP_fast_assign( LOCAL_ASSIGN; __entry->pan_id = pan_id; ), TP_printk(LOCAL_PR_FMT ", pan id: 0x%04x", LOCAL_PR_ARG, le16_to_cpu(__entry->pan_id)) ); TRACE_EVENT(802154_drv_set_extended_addr, TP_PROTO(struct ieee802154_local *local, __le64 extended_addr), TP_ARGS(local, extended_addr), TP_STRUCT__entry( LOCAL_ENTRY __field(__le64, extended_addr) ), TP_fast_assign( LOCAL_ASSIGN; __entry->extended_addr = extended_addr; ), TP_printk(LOCAL_PR_FMT ", extended addr: 0x%llx", LOCAL_PR_ARG, le64_to_cpu(__entry->extended_addr)) ); TRACE_EVENT(802154_drv_set_pan_coord, TP_PROTO(struct ieee802154_local *local, bool is_coord), TP_ARGS(local, is_coord), TP_STRUCT__entry( LOCAL_ENTRY __field(bool, is_coord) ), TP_fast_assign( LOCAL_ASSIGN; __entry->is_coord = is_coord; ), TP_printk(LOCAL_PR_FMT ", is_coord: %s", LOCAL_PR_ARG, BOOL_TO_STR(__entry->is_coord)) ); TRACE_EVENT(802154_drv_set_csma_params, TP_PROTO(struct ieee802154_local *local, u8 min_be, u8 max_be, u8 max_csma_backoffs), TP_ARGS(local, min_be, max_be, max_csma_backoffs), TP_STRUCT__entry( LOCAL_ENTRY __field(u8, min_be) __field(u8, max_be) __field(u8, max_csma_backoffs) ), TP_fast_assign( LOCAL_ASSIGN, __entry->min_be = min_be; __entry->max_be = max_be; __entry->max_csma_backoffs = max_csma_backoffs; ), TP_printk(LOCAL_PR_FMT ", min be: %d, max be: %d, max csma backoffs: %d", LOCAL_PR_ARG, __entry->min_be, __entry->max_be, __entry->max_csma_backoffs) ); TRACE_EVENT(802154_drv_set_max_frame_retries, TP_PROTO(struct ieee802154_local *local, s8 max_frame_retries), TP_ARGS(local, max_frame_retries), TP_STRUCT__entry( LOCAL_ENTRY __field(s8, max_frame_retries) ), TP_fast_assign( LOCAL_ASSIGN; __entry->max_frame_retries = max_frame_retries; ), TP_printk(LOCAL_PR_FMT ", max frame retries: %d", LOCAL_PR_ARG, __entry->max_frame_retries) ); TRACE_EVENT(802154_drv_set_promiscuous_mode, TP_PROTO(struct ieee802154_local *local, bool on), TP_ARGS(local, on), TP_STRUCT__entry( LOCAL_ENTRY __field(bool, on) ), TP_fast_assign( LOCAL_ASSIGN; __entry->on = on; ), TP_printk(LOCAL_PR_FMT ", promiscuous mode: %s", LOCAL_PR_ARG, BOOL_TO_STR(__entry->on)) ); #endif /* !__MAC802154_DRIVER_TRACE || TRACE_HEADER_MULTI_READ */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE trace #include <trace/define_trace.h>
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM timer #if !defined(_TRACE_TIMER_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_TIMER_H #include <linux/tracepoint.h> #include <linux/hrtimer.h> #include <linux/timer.h> DECLARE_EVENT_CLASS(timer_class, TP_PROTO(struct timer_list *timer), TP_ARGS(timer), TP_STRUCT__entry( __field( void *, timer ) ), TP_fast_assign( __entry->timer = timer; ), TP_printk("timer=%p", __entry->timer) ); /** * timer_init - called when the timer is initialized * @timer: pointer to struct timer_list */ DEFINE_EVENT(timer_class, timer_init, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); #define decode_timer_flags(flags) \ __print_flags(flags, "|", \ { TIMER_MIGRATING, "M" }, \ { TIMER_DEFERRABLE, "D" }, \ { TIMER_PINNED, "P" }, \ { TIMER_IRQSAFE, "I" }) /** * timer_start - called when the timer is started * @timer: pointer to struct timer_list * @expires: the timers expiry time */ TRACE_EVENT(timer_start, TP_PROTO(struct timer_list *timer, unsigned long expires, unsigned int flags), TP_ARGS(timer, expires, flags), TP_STRUCT__entry( __field( void *, timer ) __field( void *, function ) __field( unsigned long, expires ) __field( unsigned long, now ) __field( unsigned int, flags ) ), TP_fast_assign( __entry->timer = timer; __entry->function = timer->function; __entry->expires = expires; __entry->now = jiffies; __entry->flags = flags; ), TP_printk("timer=%p function=%ps expires=%lu [timeout=%ld] cpu=%u idx=%u flags=%s", __entry->timer, __entry->function, __entry->expires, (long)__entry->expires - __entry->now, __entry->flags & TIMER_CPUMASK, __entry->flags >> TIMER_ARRAYSHIFT, decode_timer_flags(__entry->flags & TIMER_TRACE_FLAGMASK)) ); /** * timer_expire_entry - called immediately before the timer callback * @timer: pointer to struct timer_list * * Allows to determine the timer latency. */ TRACE_EVENT(timer_expire_entry, TP_PROTO(struct timer_list *timer, unsigned long baseclk), TP_ARGS(timer, baseclk), TP_STRUCT__entry( __field( void *, timer ) __field( unsigned long, now ) __field( void *, function) __field( unsigned long, baseclk ) ), TP_fast_assign( __entry->timer = timer; __entry->now = jiffies; __entry->function = timer->function; __entry->baseclk = baseclk; ), TP_printk("timer=%p function=%ps now=%lu baseclk=%lu", __entry->timer, __entry->function, __entry->now, __entry->baseclk) ); /** * timer_expire_exit - called immediately after the timer callback returns * @timer: pointer to struct timer_list * * When used in combination with the timer_expire_entry tracepoint we can * determine the runtime of the timer callback function. * * NOTE: Do NOT derefernce timer in TP_fast_assign. The pointer might * be invalid. We solely track the pointer. */ DEFINE_EVENT(timer_class, timer_expire_exit, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); /** * timer_cancel - called when the timer is canceled * @timer: pointer to struct timer_list */ DEFINE_EVENT(timer_class, timer_cancel, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); #define decode_clockid(type) \ __print_symbolic(type, \ { CLOCK_REALTIME, "CLOCK_REALTIME" }, \ { CLOCK_MONOTONIC, "CLOCK_MONOTONIC" }, \ { CLOCK_BOOTTIME, "CLOCK_BOOTTIME" }, \ { CLOCK_TAI, "CLOCK_TAI" }) #define decode_hrtimer_mode(mode) \ __print_symbolic(mode, \ { HRTIMER_MODE_ABS, "ABS" }, \ { HRTIMER_MODE_REL, "REL" }, \ { HRTIMER_MODE_ABS_PINNED, "ABS|PINNED" }, \ { HRTIMER_MODE_REL_PINNED, "REL|PINNED" }, \ { HRTIMER_MODE_ABS_SOFT, "ABS|SOFT" }, \ { HRTIMER_MODE_REL_SOFT, "REL|SOFT" }, \ { HRTIMER_MODE_ABS_PINNED_SOFT, "ABS|PINNED|SOFT" }, \ { HRTIMER_MODE_REL_PINNED_SOFT, "REL|PINNED|SOFT" }) /** * hrtimer_init - called when the hrtimer is initialized * @hrtimer: pointer to struct hrtimer * @clockid: the hrtimers clock * @mode: the hrtimers mode */ TRACE_EVENT(hrtimer_init, TP_PROTO(struct hrtimer *hrtimer, clockid_t clockid, enum hrtimer_mode mode), TP_ARGS(hrtimer, clockid, mode), TP_STRUCT__entry( __field( void *, hrtimer ) __field( clockid_t, clockid ) __field( enum hrtimer_mode, mode ) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->clockid = clockid; __entry->mode = mode; ), TP_printk("hrtimer=%p clockid=%s mode=%s", __entry->hrtimer, decode_clockid(__entry->clockid), decode_hrtimer_mode(__entry->mode)) ); /** * hrtimer_start - called when the hrtimer is started * @hrtimer: pointer to struct hrtimer */ TRACE_EVENT(hrtimer_start, TP_PROTO(struct hrtimer *hrtimer, enum hrtimer_mode mode), TP_ARGS(hrtimer, mode), TP_STRUCT__entry( __field( void *, hrtimer ) __field( void *, function ) __field( s64, expires ) __field( s64, softexpires ) __field( enum hrtimer_mode, mode ) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->function = hrtimer->function; __entry->expires = hrtimer_get_expires(hrtimer); __entry->softexpires = hrtimer_get_softexpires(hrtimer); __entry->mode = mode; ), TP_printk("hrtimer=%p function=%ps expires=%llu softexpires=%llu " "mode=%s", __entry->hrtimer, __entry->function, (unsigned long long) __entry->expires, (unsigned long long) __entry->softexpires, decode_hrtimer_mode(__entry->mode)) ); /** * hrtimer_expire_entry - called immediately before the hrtimer callback * @hrtimer: pointer to struct hrtimer * @now: pointer to variable which contains current time of the * timers base. * * Allows to determine the timer latency. */ TRACE_EVENT(hrtimer_expire_entry, TP_PROTO(struct hrtimer *hrtimer, ktime_t *now), TP_ARGS(hrtimer, now), TP_STRUCT__entry( __field( void *, hrtimer ) __field( s64, now ) __field( void *, function) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->now = *now; __entry->function = hrtimer->function; ), TP_printk("hrtimer=%p function=%ps now=%llu", __entry->hrtimer, __entry->function, (unsigned long long) __entry->now) ); DECLARE_EVENT_CLASS(hrtimer_class, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer), TP_STRUCT__entry( __field( void *, hrtimer ) ), TP_fast_assign( __entry->hrtimer = hrtimer; ), TP_printk("hrtimer=%p", __entry->hrtimer) ); /** * hrtimer_expire_exit - called immediately after the hrtimer callback returns * @hrtimer: pointer to struct hrtimer * * When used in combination with the hrtimer_expire_entry tracepoint we can * determine the runtime of the callback function. */ DEFINE_EVENT(hrtimer_class, hrtimer_expire_exit, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer) ); /** * hrtimer_cancel - called when the hrtimer is canceled * @hrtimer: pointer to struct hrtimer */ DEFINE_EVENT(hrtimer_class, hrtimer_cancel, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer) ); /** * itimer_state - called when itimer is started or canceled * @which: name of the interval timer * @value: the itimers value, itimer is canceled if value->it_value is * zero, otherwise it is started * @expires: the itimers expiry time */ TRACE_EVENT(itimer_state, TP_PROTO(int which, const struct itimerspec64 *const value, unsigned long long expires), TP_ARGS(which, value, expires), TP_STRUCT__entry( __field( int, which ) __field( unsigned long long, expires ) __field( long, value_sec ) __field( long, value_nsec ) __field( long, interval_sec ) __field( long, interval_nsec ) ), TP_fast_assign( __entry->which = which; __entry->expires = expires; __entry->value_sec = value->it_value.tv_sec; __entry->value_nsec = value->it_value.tv_nsec; __entry->interval_sec = value->it_interval.tv_sec; __entry->interval_nsec = value->it_interval.tv_nsec; ), TP_printk("which=%d expires=%llu it_value=%ld.%06ld it_interval=%ld.%06ld", __entry->which, __entry->expires, __entry->value_sec, __entry->value_nsec / NSEC_PER_USEC, __entry->interval_sec, __entry->interval_nsec / NSEC_PER_USEC) ); /** * itimer_expire - called when itimer expires * @which: type of the interval timer * @pid: pid of the process which owns the timer * @now: current time, used to calculate the latency of itimer */ TRACE_EVENT(itimer_expire, TP_PROTO(int which, struct pid *pid, unsigned long long now), TP_ARGS(which, pid, now), TP_STRUCT__entry( __field( int , which ) __field( pid_t, pid ) __field( unsigned long long, now ) ), TP_fast_assign( __entry->which = which; __entry->now = now; __entry->pid = pid_nr(pid); ), TP_printk("which=%d pid=%d now=%llu", __entry->which, (int) __entry->pid, __entry->now) ); #ifdef CONFIG_NO_HZ_COMMON #define TICK_DEP_NAMES \ tick_dep_mask_name(NONE) \ tick_dep_name(POSIX_TIMER) \ tick_dep_name(PERF_EVENTS) \ tick_dep_name(SCHED) \ tick_dep_name(CLOCK_UNSTABLE) \ tick_dep_name_end(RCU) #undef tick_dep_name #undef tick_dep_mask_name #undef tick_dep_name_end /* The MASK will convert to their bits and they need to be processed too */ #define tick_dep_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \ TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); #define tick_dep_name_end(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \ TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); /* NONE only has a mask defined for it */ #define tick_dep_mask_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); TICK_DEP_NAMES #undef tick_dep_name #undef tick_dep_mask_name #undef tick_dep_name_end #define tick_dep_name(sdep) { TICK_DEP_MASK_##sdep, #sdep }, #define tick_dep_mask_name(sdep) { TICK_DEP_MASK_##sdep, #sdep }, #define tick_dep_name_end(sdep) { TICK_DEP_MASK_##sdep, #sdep } #define show_tick_dep_name(val) \ __print_symbolic(val, TICK_DEP_NAMES) TRACE_EVENT(tick_stop, TP_PROTO(int success, int dependency), TP_ARGS(success, dependency), TP_STRUCT__entry( __field( int , success ) __field( int , dependency ) ), TP_fast_assign( __entry->success = success; __entry->dependency = dependency; ), TP_printk("success=%d dependency=%s", __entry->success, \ show_tick_dep_name(__entry->dependency)) ); #endif #endif /* _TRACE_TIMER_H */ /* This part must be outside protection */ #include <trace/define_trace.h>
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * 25-Jul-1998 Major changes to allow for ip chain table * * 3-Jan-2000 Named tables to allow packet selection for different uses. */ /* * Format of an IP firewall descriptor * * src, dst, src_mask, dst_mask are always stored in network byte order. * flags are stored in host byte order (of course). * Port numbers are stored in HOST byte order. */ #ifndef _UAPI_IPTABLES_H #define _UAPI_IPTABLES_H #include <linux/types.h> #include <linux/compiler.h> #include <linux/if.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter/x_tables.h> #ifndef __KERNEL__ #define IPT_FUNCTION_MAXNAMELEN XT_FUNCTION_MAXNAMELEN #define IPT_TABLE_MAXNAMELEN XT_TABLE_MAXNAMELEN #define ipt_match xt_match #define ipt_target xt_target #define ipt_table xt_table #define ipt_get_revision xt_get_revision #define ipt_entry_match xt_entry_match #define ipt_entry_target xt_entry_target #define ipt_standard_target xt_standard_target #define ipt_error_target xt_error_target #define ipt_counters xt_counters #define IPT_CONTINUE XT_CONTINUE #define IPT_RETURN XT_RETURN /* This group is older than old (iptables < v1.4.0-rc1~89) */ #include <linux/netfilter/xt_tcpudp.h> #define ipt_udp xt_udp #define ipt_tcp xt_tcp #define IPT_TCP_INV_SRCPT XT_TCP_INV_SRCPT #define IPT_TCP_INV_DSTPT XT_TCP_INV_DSTPT #define IPT_TCP_INV_FLAGS XT_TCP_INV_FLAGS #define IPT_TCP_INV_OPTION XT_TCP_INV_OPTION #define IPT_TCP_INV_MASK XT_TCP_INV_MASK #define IPT_UDP_INV_SRCPT XT_UDP_INV_SRCPT #define IPT_UDP_INV_DSTPT XT_UDP_INV_DSTPT #define IPT_UDP_INV_MASK XT_UDP_INV_MASK /* The argument to IPT_SO_ADD_COUNTERS. */ #define ipt_counters_info xt_counters_info /* Standard return verdict, or do jump. */ #define IPT_STANDARD_TARGET XT_STANDARD_TARGET /* Error verdict. */ #define IPT_ERROR_TARGET XT_ERROR_TARGET /* fn returns 0 to continue iteration */ #define IPT_MATCH_ITERATE(e, fn, args...) \ XT_MATCH_ITERATE(struct ipt_entry, e, fn, ## args) /* fn returns 0 to continue iteration */ #define IPT_ENTRY_ITERATE(entries, size, fn, args...) \ XT_ENTRY_ITERATE(struct ipt_entry, entries, size, fn, ## args) #endif /* Yes, Virginia, you have to zero the padding. */ struct ipt_ip { /* Source and destination IP addr */ struct in_addr src, dst; /* Mask for src and dest IP addr */ struct in_addr smsk, dmsk; char iniface[IFNAMSIZ], outiface[IFNAMSIZ]; unsigned char iniface_mask[IFNAMSIZ], outiface_mask[IFNAMSIZ]; /* Protocol, 0 = ANY */ __u16 proto; /* Flags word */ __u8 flags; /* Inverse flags */ __u8 invflags; }; /* Values for "flag" field in struct ipt_ip (general ip structure). */ #define IPT_F_FRAG 0x01 /* Set if rule is a fragment rule */ #define IPT_F_GOTO 0x02 /* Set if jump is a goto */ #define IPT_F_MASK 0x03 /* All possible flag bits mask. */ /* Values for "inv" field in struct ipt_ip. */ #define IPT_INV_VIA_IN 0x01 /* Invert the sense of IN IFACE. */ #define IPT_INV_VIA_OUT 0x02 /* Invert the sense of OUT IFACE */ #define IPT_INV_TOS 0x04 /* Invert the sense of TOS. */ #define IPT_INV_SRCIP 0x08 /* Invert the sense of SRC IP. */ #define IPT_INV_DSTIP 0x10 /* Invert the sense of DST OP. */ #define IPT_INV_FRAG 0x20 /* Invert the sense of FRAG. */ #define IPT_INV_PROTO XT_INV_PROTO #define IPT_INV_MASK 0x7F /* All possible flag bits mask. */ /* This structure defines each of the firewall rules. Consists of 3 parts which are 1) general IP header stuff 2) match specific stuff 3) the target to perform if the rule matches */ struct ipt_entry { struct ipt_ip ip; /* Mark with fields that we care about. */ unsigned int nfcache; /* Size of ipt_entry + matches */ __u16 target_offset; /* Size of ipt_entry + matches + target */ __u16 next_offset; /* Back pointer */ unsigned int comefrom; /* Packet and byte counters. */ struct xt_counters counters; /* The matches (if any), then the target. */ unsigned char elems[0]; }; /* * New IP firewall options for [gs]etsockopt at the RAW IP level. * Unlike BSD Linux inherits IP options so you don't have to use a raw * socket for this. Instead we check rights in the calls. * * ATTENTION: check linux/in.h before adding new number here. */ #define IPT_BASE_CTL 64 #define IPT_SO_SET_REPLACE (IPT_BASE_CTL) #define IPT_SO_SET_ADD_COUNTERS (IPT_BASE_CTL + 1) #define IPT_SO_SET_MAX IPT_SO_SET_ADD_COUNTERS #define IPT_SO_GET_INFO (IPT_BASE_CTL) #define IPT_SO_GET_ENTRIES (IPT_BASE_CTL + 1) #define IPT_SO_GET_REVISION_MATCH (IPT_BASE_CTL + 2) #define IPT_SO_GET_REVISION_TARGET (IPT_BASE_CTL + 3) #define IPT_SO_GET_MAX IPT_SO_GET_REVISION_TARGET /* ICMP matching stuff */ struct ipt_icmp { __u8 type; /* type to match */ __u8 code[2]; /* range of code */ __u8 invflags; /* Inverse flags */ }; /* Values for "inv" field for struct ipt_icmp. */ #define IPT_ICMP_INV 0x01 /* Invert the sense of type/code test */ /* The argument to IPT_SO_GET_INFO */ struct ipt_getinfo { /* Which table: caller fills this in. */ char name[XT_TABLE_MAXNAMELEN]; /* Kernel fills these in. */ /* Which hook entry points are valid: bitmask */ unsigned int valid_hooks; /* Hook entry points: one per netfilter hook. */ unsigned int hook_entry[NF_INET_NUMHOOKS]; /* Underflow points. */ unsigned int underflow[NF_INET_NUMHOOKS]; /* Number of entries */ unsigned int num_entries; /* Size of entries. */ unsigned int size; }; /* The argument to IPT_SO_SET_REPLACE. */ struct ipt_replace { /* Which table. */ char name[XT_TABLE_MAXNAMELEN]; /* Which hook entry points are valid: bitmask. You can't change this. */ unsigned int valid_hooks; /* Number of entries */ unsigned int num_entries; /* Total size of new entries */ unsigned int size; /* Hook entry points. */ unsigned int hook_entry[NF_INET_NUMHOOKS]; /* Underflow points. */ unsigned int underflow[NF_INET_NUMHOOKS]; /* Information about old entries: */ /* Number of counters (must be equal to current number of entries). */ unsigned int num_counters; /* The old entries' counters. */ struct xt_counters __user *counters; /* The entries (hang off end: not really an array). */ struct ipt_entry entries[0]; }; /* The argument to IPT_SO_GET_ENTRIES. */ struct ipt_get_entries { /* Which table: user fills this in. */ char name[XT_TABLE_MAXNAMELEN]; /* User fills this in: total entry size. */ unsigned int size; /* The entries. */ struct ipt_entry entrytable[0]; }; /* Helper functions */ static __inline__ struct xt_entry_target * ipt_get_target(struct ipt_entry *e) { return (struct xt_entry_target *)((char *)e + e->target_offset); } /* * Main firewall chains definitions and global var's definitions. */ #endif /* _UAPI_IPTABLES_H */
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 /* netfilter.c: look after the filters for various protocols. * Heavily influenced by the old firewall.c by David Bonn and Alan Cox. * * Thanks to Rob `CmdrTaco' Malda for not influencing this code in any * way. * * This code is GPL. */ #include <linux/kernel.h> #include <linux/netfilter.h> #include <net/protocol.h> #include <linux/init.h> #include <linux/skbuff.h> #include <linux/wait.h> #include <linux/module.h> #include <linux/interrupt.h> #include <linux/if.h> #include <linux/netdevice.h> #include <linux/netfilter_ipv6.h> #include <linux/inetdevice.h> #include <linux/proc_fs.h> #include <linux/mutex.h> #include <linux/mm.h> #include <linux/rcupdate.h> #include <net/net_namespace.h> #include <net/netfilter/nf_queue.h> #include <net/sock.h> #include "nf_internals.h" const struct nf_ipv6_ops __rcu *nf_ipv6_ops __read_mostly; EXPORT_SYMBOL_GPL(nf_ipv6_ops); DEFINE_PER_CPU(bool, nf_skb_duplicated); EXPORT_SYMBOL_GPL(nf_skb_duplicated); #ifdef CONFIG_JUMP_LABEL struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; EXPORT_SYMBOL(nf_hooks_needed); #endif static DEFINE_MUTEX(nf_hook_mutex); /* max hooks per family/hooknum */ #define MAX_HOOK_COUNT 1024 #define nf_entry_dereference(e) \ rcu_dereference_protected(e, lockdep_is_held(&nf_hook_mutex)) static struct nf_hook_entries *allocate_hook_entries_size(u16 num) { struct nf_hook_entries *e; size_t alloc = sizeof(*e) + sizeof(struct nf_hook_entry) * num + sizeof(struct nf_hook_ops *) * num + sizeof(struct nf_hook_entries_rcu_head); if (num == 0) return NULL; e = kvzalloc(alloc, GFP_KERNEL); if (e) e->num_hook_entries = num; return e; } static void __nf_hook_entries_free(struct rcu_head *h) { struct nf_hook_entries_rcu_head *head; head = container_of(h, struct nf_hook_entries_rcu_head, head); kvfree(head->allocation); } static void nf_hook_entries_free(struct nf_hook_entries *e) { struct nf_hook_entries_rcu_head *head; struct nf_hook_ops **ops; unsigned int num; if (!e) return; num = e->num_hook_entries; ops = nf_hook_entries_get_hook_ops(e); head = (void *)&ops[num]; head->allocation = e; call_rcu(&head->head, __nf_hook_entries_free); } static unsigned int accept_all(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return NF_ACCEPT; /* ACCEPT makes nf_hook_slow call next hook */ } static const struct nf_hook_ops dummy_ops = { .hook = accept_all, .priority = INT_MIN, }; static struct nf_hook_entries * nf_hook_entries_grow(const struct nf_hook_entries *old, const struct nf_hook_ops *reg) { unsigned int i, alloc_entries, nhooks, old_entries; struct nf_hook_ops **orig_ops = NULL; struct nf_hook_ops **new_ops; struct nf_hook_entries *new; bool inserted = false; alloc_entries = 1; old_entries = old ? old->num_hook_entries : 0; if (old) { orig_ops = nf_hook_entries_get_hook_ops(old); for (i = 0; i < old_entries; i++) { if (orig_ops[i] != &dummy_ops) alloc_entries++; } } if (alloc_entries > MAX_HOOK_COUNT) return ERR_PTR(-E2BIG); new = allocate_hook_entries_size(alloc_entries); if (!new) return ERR_PTR(-ENOMEM); new_ops = nf_hook_entries_get_hook_ops(new); i = 0; nhooks = 0; while (i < old_entries) { if (orig_ops[i] == &dummy_ops) { ++i; continue; } if (inserted || reg->priority > orig_ops[i]->priority) { new_ops[nhooks] = (void *)orig_ops[i]; new->hooks[nhooks] = old->hooks[i]; i++; } else { new_ops[nhooks] = (void *)reg; new->hooks[nhooks].hook = reg->hook; new->hooks[nhooks].priv = reg->priv; inserted = true; } nhooks++; } if (!inserted) { new_ops[nhooks] = (void *)reg; new->hooks[nhooks].hook = reg->hook; new->hooks[nhooks].priv = reg->priv; } return new; } static void hooks_validate(const struct nf_hook_entries *hooks) { #ifdef CONFIG_DEBUG_MISC struct nf_hook_ops **orig_ops; int prio = INT_MIN; size_t i = 0; orig_ops = nf_hook_entries_get_hook_ops(hooks); for (i = 0; i < hooks->num_hook_entries; i++) { if (orig_ops[i] == &dummy_ops) continue; WARN_ON(orig_ops[i]->priority < prio); if (orig_ops[i]->priority > prio) prio = orig_ops[i]->priority; } #endif } int nf_hook_entries_insert_raw(struct nf_hook_entries __rcu **pp, const struct nf_hook_ops *reg) { struct nf_hook_entries *new_hooks; struct nf_hook_entries *p; p = rcu_dereference_raw(*pp); new_hooks = nf_hook_entries_grow(p, reg); if (IS_ERR(new_hooks)) return PTR_ERR(new_hooks); hooks_validate(new_hooks); rcu_assign_pointer(*pp, new_hooks); BUG_ON(p == new_hooks); nf_hook_entries_free(p); return 0; } EXPORT_SYMBOL_GPL(nf_hook_entries_insert_raw); /* * __nf_hook_entries_try_shrink - try to shrink hook array * * @old -- current hook blob at @pp * @pp -- location of hook blob * * Hook unregistration must always succeed, so to-be-removed hooks * are replaced by a dummy one that will just move to next hook. * * This counts the current dummy hooks, attempts to allocate new blob, * copies the live hooks, then replaces and discards old one. * * return values: * * Returns address to free, or NULL. */ static void *__nf_hook_entries_try_shrink(struct nf_hook_entries *old, struct nf_hook_entries __rcu **pp) { unsigned int i, j, skip = 0, hook_entries; struct nf_hook_entries *new = NULL; struct nf_hook_ops **orig_ops; struct nf_hook_ops **new_ops; if (WARN_ON_ONCE(!old)) return NULL; orig_ops = nf_hook_entries_get_hook_ops(old); for (i = 0; i < old->num_hook_entries; i++) { if (orig_ops[i] == &dummy_ops) skip++; } /* if skip == hook_entries all hooks have been removed */ hook_entries = old->num_hook_entries; if (skip == hook_entries) goto out_assign; if (skip == 0) return NULL; hook_entries -= skip; new = allocate_hook_entries_size(hook_entries); if (!new) return NULL; new_ops = nf_hook_entries_get_hook_ops(new); for (i = 0, j = 0; i < old->num_hook_entries; i++) { if (orig_ops[i] == &dummy_ops) continue; new->hooks[j] = old->hooks[i]; new_ops[j] = (void *)orig_ops[i]; j++; } hooks_validate(new); out_assign: rcu_assign_pointer(*pp, new); return old; } static struct nf_hook_entries __rcu ** nf_hook_entry_head(struct net *net, int pf, unsigned int hooknum, struct net_device *dev) { switch (pf) { case NFPROTO_NETDEV: break; #ifdef CONFIG_NETFILTER_FAMILY_ARP case NFPROTO_ARP: if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_arp) <= hooknum)) return NULL; return net->nf.hooks_arp + hooknum; #endif #ifdef CONFIG_NETFILTER_FAMILY_BRIDGE case NFPROTO_BRIDGE: if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_bridge) <= hooknum)) return NULL; return net->nf.hooks_bridge + hooknum; #endif #ifdef CONFIG_NETFILTER_INGRESS case NFPROTO_INET: if (WARN_ON_ONCE(hooknum != NF_INET_INGRESS)) return NULL; if (!dev || dev_net(dev) != net) { WARN_ON_ONCE(1); return NULL; } return &dev->nf_hooks_ingress; #endif case NFPROTO_IPV4: if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_ipv4) <= hooknum)) return NULL; return net->nf.hooks_ipv4 + hooknum; case NFPROTO_IPV6: if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_ipv6) <= hooknum)) return NULL; return net->nf.hooks_ipv6 + hooknum; #if IS_ENABLED(CONFIG_DECNET) case NFPROTO_DECNET: if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_decnet) <= hooknum)) return NULL; return net->nf.hooks_decnet + hooknum; #endif default: WARN_ON_ONCE(1); return NULL; } #ifdef CONFIG_NETFILTER_INGRESS if (hooknum == NF_NETDEV_INGRESS) { if (dev && dev_net(dev) == net) return &dev->nf_hooks_ingress; } #endif WARN_ON_ONCE(1); return NULL; } static int nf_ingress_check(struct net *net, const struct nf_hook_ops *reg, int hooknum) { #ifndef CONFIG_NETFILTER_INGRESS if (reg->hooknum == hooknum) return -EOPNOTSUPP; #endif if (reg->hooknum != hooknum || !reg->dev || dev_net(reg->dev) != net) return -EINVAL; return 0; } static inline bool nf_ingress_hook(const struct nf_hook_ops *reg, int pf) { if ((pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS) || (pf == NFPROTO_INET && reg->hooknum == NF_INET_INGRESS)) return true; return false; } static void nf_static_key_inc(const struct nf_hook_ops *reg, int pf) { #ifdef CONFIG_JUMP_LABEL int hooknum; if (pf == NFPROTO_INET && reg->hooknum == NF_INET_INGRESS) { pf = NFPROTO_NETDEV; hooknum = NF_NETDEV_INGRESS; } else { hooknum = reg->hooknum; } static_key_slow_inc(&nf_hooks_needed[pf][hooknum]); #endif } static void nf_static_key_dec(const struct nf_hook_ops *reg, int pf) { #ifdef CONFIG_JUMP_LABEL int hooknum; if (pf == NFPROTO_INET && reg->hooknum == NF_INET_INGRESS) { pf = NFPROTO_NETDEV; hooknum = NF_NETDEV_INGRESS; } else { hooknum = reg->hooknum; } static_key_slow_dec(&nf_hooks_needed[pf][hooknum]); #endif } static int __nf_register_net_hook(struct net *net, int pf, const struct nf_hook_ops *reg) { struct nf_hook_entries *p, *new_hooks; struct nf_hook_entries __rcu **pp; int err; switch (pf) { case NFPROTO_NETDEV: err = nf_ingress_check(net, reg, NF_NETDEV_INGRESS); if (err < 0) return err; break; case NFPROTO_INET: if (reg->hooknum != NF_INET_INGRESS) break; err = nf_ingress_check(net, reg, NF_INET_INGRESS); if (err < 0) return err; break; } pp = nf_hook_entry_head(net, pf, reg->hooknum, reg->dev); if (!pp) return -EINVAL; mutex_lock(&nf_hook_mutex); p = nf_entry_dereference(*pp); new_hooks = nf_hook_entries_grow(p, reg); if (!IS_ERR(new_hooks)) rcu_assign_pointer(*pp, new_hooks); mutex_unlock(&nf_hook_mutex); if (IS_ERR(new_hooks)) return PTR_ERR(new_hooks); hooks_validate(new_hooks); #ifdef CONFIG_NETFILTER_INGRESS if (nf_ingress_hook(reg, pf)) net_inc_ingress_queue(); #endif nf_static_key_inc(reg, pf); BUG_ON(p == new_hooks); nf_hook_entries_free(p); return 0; } /* * nf_remove_net_hook - remove a hook from blob * * @oldp: current address of hook blob * @unreg: hook to unregister * * This cannot fail, hook unregistration must always succeed. * Therefore replace the to-be-removed hook with a dummy hook. */ static bool nf_remove_net_hook(struct nf_hook_entries *old, const struct nf_hook_ops *unreg) { struct nf_hook_ops **orig_ops; unsigned int i; orig_ops = nf_hook_entries_get_hook_ops(old); for (i = 0; i < old->num_hook_entries; i++) { if (orig_ops[i] != unreg) continue; WRITE_ONCE(old->hooks[i].hook, accept_all); WRITE_ONCE(orig_ops[i], (void *)&dummy_ops); return true; } return false; } static void __nf_unregister_net_hook(struct net *net, int pf, const struct nf_hook_ops *reg) { struct nf_hook_entries __rcu **pp; struct nf_hook_entries *p; pp = nf_hook_entry_head(net, pf, reg->hooknum, reg->dev); if (!pp) return; mutex_lock(&nf_hook_mutex); p = nf_entry_dereference(*pp); if (WARN_ON_ONCE(!p)) { mutex_unlock(&nf_hook_mutex); return; } if (nf_remove_net_hook(p, reg)) { #ifdef CONFIG_NETFILTER_INGRESS if (nf_ingress_hook(reg, pf)) net_dec_ingress_queue(); #endif nf_static_key_dec(reg, pf); } else { WARN_ONCE(1, "hook not found, pf %d num %d", pf, reg->hooknum); } p = __nf_hook_entries_try_shrink(p, pp); mutex_unlock(&nf_hook_mutex); if (!p) return; nf_queue_nf_hook_drop(net); nf_hook_entries_free(p); } void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg) { if (reg->pf == NFPROTO_INET) { if (reg->hooknum == NF_INET_INGRESS) { __nf_unregister_net_hook(net, NFPROTO_INET, reg); } else { __nf_unregister_net_hook(net, NFPROTO_IPV4, reg); __nf_unregister_net_hook(net, NFPROTO_IPV6, reg); } } else { __nf_unregister_net_hook(net, reg->pf, reg); } } EXPORT_SYMBOL(nf_unregister_net_hook); void nf_hook_entries_delete_raw(struct nf_hook_entries __rcu **pp, const struct nf_hook_ops *reg) { struct nf_hook_entries *p; p = rcu_dereference_raw(*pp); if (nf_remove_net_hook(p, reg)) { p = __nf_hook_entries_try_shrink(p, pp); nf_hook_entries_free(p); } } EXPORT_SYMBOL_GPL(nf_hook_entries_delete_raw); int nf_register_net_hook(struct net *net, const struct nf_hook_ops *reg) { int err; if (reg->pf == NFPROTO_INET) { if (reg->hooknum == NF_INET_INGRESS) { err = __nf_register_net_hook(net, NFPROTO_INET, reg); if (err < 0) return err; } else { err = __nf_register_net_hook(net, NFPROTO_IPV4, reg); if (err < 0) return err; err = __nf_register_net_hook(net, NFPROTO_IPV6, reg); if (err < 0) { __nf_unregister_net_hook(net, NFPROTO_IPV4, reg); return err; } } } else { err = __nf_register_net_hook(net, reg->pf, reg); if (err < 0) return err; } return 0; } EXPORT_SYMBOL(nf_register_net_hook); int nf_register_net_hooks(struct net *net, const struct nf_hook_ops *reg, unsigned int n) { unsigned int i; int err = 0; for (i = 0; i < n; i++) { err = nf_register_net_hook(net, &reg[i]); if (err) goto err; } return err; err: if (i > 0) nf_unregister_net_hooks(net, reg, i); return err; } EXPORT_SYMBOL(nf_register_net_hooks); void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg, unsigned int hookcount) { unsigned int i; for (i = 0; i < hookcount; i++) nf_unregister_net_hook(net, &reg[i]); } EXPORT_SYMBOL(nf_unregister_net_hooks); /* Returns 1 if okfn() needs to be executed by the caller, * -EPERM for NF_DROP, 0 otherwise. Caller must hold rcu_read_lock. */ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state, const struct nf_hook_entries *e, unsigned int s) { unsigned int verdict; int ret; for (; s < e->num_hook_entries; s++) { verdict = nf_hook_entry_hookfn(&e->hooks[s], skb, state); switch (verdict & NF_VERDICT_MASK) { case NF_ACCEPT: break; case NF_DROP: kfree_skb(skb); ret = NF_DROP_GETERR(verdict); if (ret == 0) ret = -EPERM; return ret; case NF_QUEUE: ret = nf_queue(skb, state, s, verdict); if (ret == 1) continue; return ret; default: /* Implicit handling for NF_STOLEN, as well as any other * non conventional verdicts. */ return 0; } } return 1; } EXPORT_SYMBOL(nf_hook_slow); void nf_hook_slow_list(struct list_head *head, struct nf_hook_state *state, const struct nf_hook_entries *e) { struct sk_buff *skb, *next; struct list_head sublist; int ret; INIT_LIST_HEAD(&sublist); list_for_each_entry_safe(skb, next, head, list) { skb_list_del_init(skb); ret = nf_hook_slow(skb, state, e, 0); if (ret == 1) list_add_tail(&skb->list, &sublist); } /* Put passed packets back on main list */ list_splice(&sublist, head); } EXPORT_SYMBOL(nf_hook_slow_list); /* This needs to be compiled in any case to avoid dependencies between the * nfnetlink_queue code and nf_conntrack. */ struct nfnl_ct_hook __rcu *nfnl_ct_hook __read_mostly; EXPORT_SYMBOL_GPL(nfnl_ct_hook); struct nf_ct_hook __rcu *nf_ct_hook __read_mostly; EXPORT_SYMBOL_GPL(nf_ct_hook); #if IS_ENABLED(CONFIG_NF_CONNTRACK) /* This does not belong here, but locally generated errors need it if connection tracking in use: without this, connection may not be in hash table, and hence manufactured ICMP or RST packets will not be associated with it. */ void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *) __rcu __read_mostly; EXPORT_SYMBOL(ip_ct_attach); struct nf_nat_hook __rcu *nf_nat_hook __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_hook); void nf_ct_attach(struct sk_buff *new, const struct sk_buff *skb) { void (*attach)(struct sk_buff *, const struct sk_buff *); if (skb->_nfct) { rcu_read_lock(); attach = rcu_dereference(ip_ct_attach); if (attach) attach(new, skb); rcu_read_unlock(); } } EXPORT_SYMBOL(nf_ct_attach); void nf_conntrack_destroy(struct nf_conntrack *nfct) { struct nf_ct_hook *ct_hook; rcu_read_lock(); ct_hook = rcu_dereference(nf_ct_hook); BUG_ON(ct_hook == NULL); ct_hook->destroy(nfct); rcu_read_unlock(); } EXPORT_SYMBOL(nf_conntrack_destroy); bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, const struct sk_buff *skb) { struct nf_ct_hook *ct_hook; bool ret = false; rcu_read_lock(); ct_hook = rcu_dereference(nf_ct_hook); if (ct_hook) ret = ct_hook->get_tuple_skb(dst_tuple, skb); rcu_read_unlock(); return ret; } EXPORT_SYMBOL(nf_ct_get_tuple_skb); /* Built-in default zone used e.g. by modules. */ const struct nf_conntrack_zone nf_ct_zone_dflt = { .id = NF_CT_DEFAULT_ZONE_ID, .dir = NF_CT_DEFAULT_ZONE_DIR, }; EXPORT_SYMBOL_GPL(nf_ct_zone_dflt); #endif /* CONFIG_NF_CONNTRACK */ static void __net_init __netfilter_net_init(struct nf_hook_entries __rcu **e, int max) { int h; for (h = 0; h < max; h++) RCU_INIT_POINTER(e[h], NULL); } static int __net_init netfilter_net_init(struct net *net) { __netfilter_net_init(net->nf.hooks_ipv4, ARRAY_SIZE(net->nf.hooks_ipv4)); __netfilter_net_init(net->nf.hooks_ipv6, ARRAY_SIZE(net->nf.hooks_ipv6)); #ifdef CONFIG_NETFILTER_FAMILY_ARP __netfilter_net_init(net->nf.hooks_arp, ARRAY_SIZE(net->nf.hooks_arp)); #endif #ifdef CONFIG_NETFILTER_FAMILY_BRIDGE __netfilter_net_init(net->nf.hooks_bridge, ARRAY_SIZE(net->nf.hooks_bridge)); #endif #if IS_ENABLED(CONFIG_DECNET) __netfilter_net_init(net->nf.hooks_decnet, ARRAY_SIZE(net->nf.hooks_decnet)); #endif #ifdef CONFIG_PROC_FS net->nf.proc_netfilter = proc_net_mkdir(net, "netfilter", net->proc_net); if (!net->nf.proc_netfilter) { if (!net_eq(net, &init_net)) pr_err("cannot create netfilter proc entry"); return -ENOMEM; } #endif return 0; } static void __net_exit netfilter_net_exit(struct net *net) { remove_proc_entry("netfilter", net->proc_net); } static struct pernet_operations netfilter_net_ops = { .init = netfilter_net_init, .exit = netfilter_net_exit, }; int __init netfilter_init(void) { int ret; ret = register_pernet_subsys(&netfilter_net_ops); if (ret < 0) goto err; ret = netfilter_log_init(); if (ret < 0) goto err_pernet; return 0; err_pernet: unregister_pernet_subsys(&netfilter_net_ops); err: return ret; }
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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _X86_IRQFLAGS_H_ #define _X86_IRQFLAGS_H_ #include <asm/processor-flags.h> #ifndef __ASSEMBLY__ #include <asm/nospec-branch.h> /* Provide __cpuidle; we can't safely include <linux/cpu.h> */ #define __cpuidle __section(".cpuidle.text") /* * Interrupt control: */ /* Declaration required for gcc < 4.9 to prevent -Werror=missing-prototypes */ extern inline unsigned long native_save_fl(void); extern __always_inline unsigned long native_save_fl(void) { unsigned long flags; /* * "=rm" is safe here, because "pop" adjusts the stack before * it evaluates its effective address -- this is part of the * documented behavior of the "pop" instruction. */ asm volatile("# __raw_save_flags\n\t" "pushf ; pop %0" : "=rm" (flags) : /* no input */ : "memory"); return flags; } extern inline void native_restore_fl(unsigned long flags); extern inline void native_restore_fl(unsigned long flags) { asm volatile("push %0 ; popf" : /* no output */ :"g" (flags) :"memory", "cc"); } static __always_inline void native_irq_disable(void) { asm volatile("cli": : :"memory"); } static __always_inline void native_irq_enable(void) { asm volatile("sti": : :"memory"); } static inline __cpuidle void native_safe_halt(void) { mds_idle_clear_cpu_buffers(); asm volatile("sti; hlt": : :"memory"); } static inline __cpuidle void native_halt(void) { mds_idle_clear_cpu_buffers(); asm volatile("hlt": : :"memory"); } #endif #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else #ifndef __ASSEMBLY__ #include <linux/types.h> static __always_inline unsigned long arch_local_save_flags(void) { return native_save_fl(); } static __always_inline void arch_local_irq_restore(unsigned long flags) { native_restore_fl(flags); } static __always_inline void arch_local_irq_disable(void) { native_irq_disable(); } static __always_inline void arch_local_irq_enable(void) { native_irq_enable(); } /* * Used in the idle loop; sti takes one instruction cycle * to complete: */ static inline __cpuidle void arch_safe_halt(void) { native_safe_halt(); } /* * Used when interrupts are already enabled or to * shutdown the processor: */ static inline __cpuidle void halt(void) { native_halt(); } /* * For spinlocks, etc: */ static __always_inline unsigned long arch_local_irq_save(void) { unsigned long flags = arch_local_save_flags(); arch_local_irq_disable(); return flags; } #else #define ENABLE_INTERRUPTS(x) sti #define DISABLE_INTERRUPTS(x) cli #ifdef CONFIG_X86_64 #ifdef CONFIG_DEBUG_ENTRY #define SAVE_FLAGS(x) pushfq; popq %rax #endif #define INTERRUPT_RETURN jmp native_iret #define USERGS_SYSRET64 \ swapgs; \ sysretq; #define USERGS_SYSRET32 \ swapgs; \ sysretl #else #define INTERRUPT_RETURN iret #endif #endif /* __ASSEMBLY__ */ #endif /* CONFIG_PARAVIRT_XXL */ #ifndef __ASSEMBLY__ static __always_inline int arch_irqs_disabled_flags(unsigned long flags) { return !(flags & X86_EFLAGS_IF); } static __always_inline int arch_irqs_disabled(void) { unsigned long flags = arch_local_save_flags(); return arch_irqs_disabled_flags(flags); } #else #ifdef CONFIG_X86_64 #ifdef CONFIG_XEN_PV #define SWAPGS ALTERNATIVE "swapgs", "", X86_FEATURE_XENPV #else #define SWAPGS swapgs #endif #endif #endif /* !__ASSEMBLY__ */ #endif
1 1 1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 // SPDX-License-Identifier: GPL-2.0-only /* * Network interface table. * * Network interfaces (devices) do not have a security field, so we * maintain a table associating each interface with a SID. * * Author: James Morris <jmorris@redhat.com> * * Copyright (C) 2003 Red Hat, Inc., James Morris <jmorris@redhat.com> * Copyright (C) 2007 Hewlett-Packard Development Company, L.P. * Paul Moore <paul@paul-moore.com> */ #include <linux/init.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/stddef.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/notifier.h> #include <linux/netdevice.h> #include <linux/rcupdate.h> #include <net/net_namespace.h> #include "security.h" #include "objsec.h" #include "netif.h" #define SEL_NETIF_HASH_SIZE 64 #define SEL_NETIF_HASH_MAX 1024 struct sel_netif { struct list_head list; struct netif_security_struct nsec; struct rcu_head rcu_head; }; static u32 sel_netif_total; static LIST_HEAD(sel_netif_list); static DEFINE_SPINLOCK(sel_netif_lock); static struct list_head sel_netif_hash[SEL_NETIF_HASH_SIZE]; /** * sel_netif_hashfn - Hashing function for the interface table * @ns: the network namespace * @ifindex: the network interface * * Description: * This is the hashing function for the network interface table, it returns the * bucket number for the given interface. * */ static inline u32 sel_netif_hashfn(const struct net *ns, int ifindex) { return (((uintptr_t)ns + ifindex) & (SEL_NETIF_HASH_SIZE - 1)); } /** * sel_netif_find - Search for an interface record * @ns: the network namespace * @ifindex: the network interface * * Description: * Search the network interface table and return the record matching @ifindex. * If an entry can not be found in the table return NULL. * */ static inline struct sel_netif *sel_netif_find(const struct net *ns, int ifindex) { int idx = sel_netif_hashfn(ns, ifindex); struct sel_netif *netif; list_for_each_entry_rcu(netif, &sel_netif_hash[idx], list) if (net_eq(netif->nsec.ns, ns) && netif->nsec.ifindex == ifindex) return netif; return NULL; } /** * sel_netif_insert - Insert a new interface into the table * @netif: the new interface record * * Description: * Add a new interface record to the network interface hash table. Returns * zero on success, negative values on failure. * */ static int sel_netif_insert(struct sel_netif *netif) { int idx; if (sel_netif_total >= SEL_NETIF_HASH_MAX) return -ENOSPC; idx = sel_netif_hashfn(netif->nsec.ns, netif->nsec.ifindex); list_add_rcu(&netif->list, &sel_netif_hash[idx]); sel_netif_total++; return 0; } /** * sel_netif_destroy - Remove an interface record from the table * @netif: the existing interface record * * Description: * Remove an existing interface record from the network interface table. * */ static void sel_netif_destroy(struct sel_netif *netif) { list_del_rcu(&netif->list); sel_netif_total--; kfree_rcu(netif, rcu_head); } /** * sel_netif_sid_slow - Lookup the SID of a network interface using the policy * @ns: the network namespace * @ifindex: the network interface * @sid: interface SID * * Description: * This function determines the SID of a network interface by querying the * security policy. The result is added to the network interface table to * speedup future queries. Returns zero on success, negative values on * failure. * */ static int sel_netif_sid_slow(struct net *ns, int ifindex, u32 *sid) { int ret = 0; struct sel_netif *netif; struct sel_netif *new; struct net_device *dev; /* NOTE: we always use init's network namespace since we don't * currently support containers */ dev = dev_get_by_index(ns, ifindex); if (unlikely(dev == NULL)) { pr_warn("SELinux: failure in %s(), invalid network interface (%d)\n", __func__, ifindex); return -ENOENT; } spin_lock_bh(&sel_netif_lock); netif = sel_netif_find(ns, ifindex); if (netif != NULL) { *sid = netif->nsec.sid; goto out; } ret = security_netif_sid(&selinux_state, dev->name, sid); if (ret != 0) goto out; new = kzalloc(sizeof(*new), GFP_ATOMIC); if (new) { new->nsec.ns = ns; new->nsec.ifindex = ifindex; new->nsec.sid = *sid; if (sel_netif_insert(new)) kfree(new); } out: spin_unlock_bh(&sel_netif_lock); dev_put(dev); if (unlikely(ret)) pr_warn("SELinux: failure in %s(), unable to determine network interface label (%d)\n", __func__, ifindex); return ret; } /** * sel_netif_sid - Lookup the SID of a network interface * @ns: the network namespace * @ifindex: the network interface * @sid: interface SID * * Description: * This function determines the SID of a network interface using the fastest * method possible. First the interface table is queried, but if an entry * can't be found then the policy is queried and the result is added to the * table to speedup future queries. Returns zero on success, negative values * on failure. * */ int sel_netif_sid(struct net *ns, int ifindex, u32 *sid) { struct sel_netif *netif; rcu_read_lock(); netif = sel_netif_find(ns, ifindex); if (likely(netif != NULL)) { *sid = netif->nsec.sid; rcu_read_unlock(); return 0; } rcu_read_unlock(); return sel_netif_sid_slow(ns, ifindex, sid); } /** * sel_netif_kill - Remove an entry from the network interface table * @ns: the network namespace * @ifindex: the network interface * * Description: * This function removes the entry matching @ifindex from the network interface * table if it exists. * */ static void sel_netif_kill(const struct net *ns, int ifindex) { struct sel_netif *netif; rcu_read_lock(); spin_lock_bh(&sel_netif_lock); netif = sel_netif_find(ns, ifindex); if (netif) sel_netif_destroy(netif); spin_unlock_bh(&sel_netif_lock); rcu_read_unlock(); } /** * sel_netif_flush - Flush the entire network interface table * * Description: * Remove all entries from the network interface table. * */ void sel_netif_flush(void) { int idx; struct sel_netif *netif; spin_lock_bh(&sel_netif_lock); for (idx = 0; idx < SEL_NETIF_HASH_SIZE; idx++) list_for_each_entry(netif, &sel_netif_hash[idx], list) sel_netif_destroy(netif); spin_unlock_bh(&sel_netif_lock); } static int sel_netif_netdev_notifier_handler(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (event == NETDEV_DOWN) sel_netif_kill(dev_net(dev), dev->ifindex); return NOTIFY_DONE; } static struct notifier_block sel_netif_netdev_notifier = { .notifier_call = sel_netif_netdev_notifier_handler, }; static __init int sel_netif_init(void) { int i; if (!selinux_enabled_boot) return 0; for (i = 0; i < SEL_NETIF_HASH_SIZE; i++) INIT_LIST_HEAD(&sel_netif_hash[i]); register_netdevice_notifier(&sel_netif_netdev_notifier); return 0; } __initcall(sel_netif_init);
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 /* SPDX-License-Identifier: GPL-2.0 */ /* * linux/include/linux/nmi.h */ #ifndef LINUX_NMI_H #define LINUX_NMI_H #include <linux/sched.h> #include <asm/irq.h> #if defined(CONFIG_HAVE_NMI_WATCHDOG) #include <asm/nmi.h> #endif #ifdef CONFIG_LOCKUP_DETECTOR void lockup_detector_init(void); void lockup_detector_soft_poweroff(void); void lockup_detector_cleanup(void); bool is_hardlockup(void); extern int watchdog_user_enabled; extern int nmi_watchdog_user_enabled; extern int soft_watchdog_user_enabled; extern int watchdog_thresh; extern unsigned long watchdog_enabled; extern struct cpumask watchdog_cpumask; extern unsigned long *watchdog_cpumask_bits; #ifdef CONFIG_SMP extern int sysctl_softlockup_all_cpu_backtrace; extern int sysctl_hardlockup_all_cpu_backtrace; #else #define sysctl_softlockup_all_cpu_backtrace 0 #define sysctl_hardlockup_all_cpu_backtrace 0 #endif /* !CONFIG_SMP */ #else /* CONFIG_LOCKUP_DETECTOR */ static inline void lockup_detector_init(void) { } static inline void lockup_detector_soft_poweroff(void) { } static inline void lockup_detector_cleanup(void) { } #endif /* !CONFIG_LOCKUP_DETECTOR */ #ifdef CONFIG_SOFTLOCKUP_DETECTOR extern void touch_softlockup_watchdog_sched(void); extern void touch_softlockup_watchdog(void); extern void touch_softlockup_watchdog_sync(void); extern void touch_all_softlockup_watchdogs(void); extern unsigned int softlockup_panic; extern int lockup_detector_online_cpu(unsigned int cpu); extern int lockup_detector_offline_cpu(unsigned int cpu); #else /* CONFIG_SOFTLOCKUP_DETECTOR */ static inline void touch_softlockup_watchdog_sched(void) { } static inline void touch_softlockup_watchdog(void) { } static inline void touch_softlockup_watchdog_sync(void) { } static inline void touch_all_softlockup_watchdogs(void) { } #define lockup_detector_online_cpu NULL #define lockup_detector_offline_cpu NULL #endif /* CONFIG_SOFTLOCKUP_DETECTOR */ #ifdef CONFIG_DETECT_HUNG_TASK void reset_hung_task_detector(void); #else static inline void reset_hung_task_detector(void) { } #endif /* * The run state of the lockup detectors is controlled by the content of the * 'watchdog_enabled' variable. Each lockup detector has its dedicated bit - * bit 0 for the hard lockup detector and bit 1 for the soft lockup detector. * * 'watchdog_user_enabled', 'nmi_watchdog_user_enabled' and * 'soft_watchdog_user_enabled' are variables that are only used as an * 'interface' between the parameters in /proc/sys/kernel and the internal * state bits in 'watchdog_enabled'. The 'watchdog_thresh' variable is * handled differently because its value is not boolean, and the lockup * detectors are 'suspended' while 'watchdog_thresh' is equal zero. */ #define NMI_WATCHDOG_ENABLED_BIT 0 #define SOFT_WATCHDOG_ENABLED_BIT 1 #define NMI_WATCHDOG_ENABLED (1 << NMI_WATCHDOG_ENABLED_BIT) #define SOFT_WATCHDOG_ENABLED (1 << SOFT_WATCHDOG_ENABLED_BIT) #if defined(CONFIG_HARDLOCKUP_DETECTOR) extern void hardlockup_detector_disable(void); extern unsigned int hardlockup_panic; #else static inline void hardlockup_detector_disable(void) {} #endif #if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR) # define NMI_WATCHDOG_SYSCTL_PERM 0644 #else # define NMI_WATCHDOG_SYSCTL_PERM 0444 #endif #if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF) extern void arch_touch_nmi_watchdog(void); extern void hardlockup_detector_perf_stop(void); extern void hardlockup_detector_perf_restart(void); extern void hardlockup_detector_perf_disable(void); extern void hardlockup_detector_perf_enable(void); extern void hardlockup_detector_perf_cleanup(void); extern int hardlockup_detector_perf_init(void); #else static inline void hardlockup_detector_perf_stop(void) { } static inline void hardlockup_detector_perf_restart(void) { } static inline void hardlockup_detector_perf_disable(void) { } static inline void hardlockup_detector_perf_enable(void) { } static inline void hardlockup_detector_perf_cleanup(void) { } # if !defined(CONFIG_HAVE_NMI_WATCHDOG) static inline int hardlockup_detector_perf_init(void) { return -ENODEV; } static inline void arch_touch_nmi_watchdog(void) {} # else static inline int hardlockup_detector_perf_init(void) { return 0; } # endif #endif void watchdog_nmi_stop(void); void watchdog_nmi_start(void); int watchdog_nmi_probe(void); int watchdog_nmi_enable(unsigned int cpu); void watchdog_nmi_disable(unsigned int cpu); /** * touch_nmi_watchdog - restart NMI watchdog timeout. * * If the architecture supports the NMI watchdog, touch_nmi_watchdog() * may be used to reset the timeout - for code which intentionally * disables interrupts for a long time. This call is stateless. */ static inline void touch_nmi_watchdog(void) { arch_touch_nmi_watchdog(); touch_softlockup_watchdog(); } /* * Create trigger_all_cpu_backtrace() out of the arch-provided * base function. Return whether such support was available, * to allow calling code to fall back to some other mechanism: */ #ifdef arch_trigger_cpumask_backtrace static inline bool trigger_all_cpu_backtrace(void) { arch_trigger_cpumask_backtrace(cpu_online_mask, false); return true; } static inline bool trigger_allbutself_cpu_backtrace(void) { arch_trigger_cpumask_backtrace(cpu_online_mask, true); return true; } static inline bool trigger_cpumask_backtrace(struct cpumask *mask) { arch_trigger_cpumask_backtrace(mask, false); return true; } static inline bool trigger_single_cpu_backtrace(int cpu) { arch_trigger_cpumask_backtrace(cpumask_of(cpu), false); return true; } /* generic implementation */ void nmi_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self, void (*raise)(cpumask_t *mask)); bool nmi_cpu_backtrace(struct pt_regs *regs); #else static inline bool trigger_all_cpu_backtrace(void) { return false; } static inline bool trigger_allbutself_cpu_backtrace(void) { return false; } static inline bool trigger_cpumask_backtrace(struct cpumask *mask) { return false; } static inline bool trigger_single_cpu_backtrace(int cpu) { return false; } #endif #ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF u64 hw_nmi_get_sample_period(int watchdog_thresh); #endif #if defined(CONFIG_HARDLOCKUP_CHECK_TIMESTAMP) && \ defined(CONFIG_HARDLOCKUP_DETECTOR) void watchdog_update_hrtimer_threshold(u64 period); #else static inline void watchdog_update_hrtimer_threshold(u64 period) { } #endif struct ctl_table; int proc_watchdog(struct ctl_table *, int, void *, size_t *, loff_t *); int proc_nmi_watchdog(struct ctl_table *, int , void *, size_t *, loff_t *); int proc_soft_watchdog(struct ctl_table *, int , void *, size_t *, loff_t *); int proc_watchdog_thresh(struct ctl_table *, int , void *, size_t *, loff_t *); int proc_watchdog_cpumask(struct ctl_table *, int, void *, size_t *, loff_t *); #ifdef CONFIG_HAVE_ACPI_APEI_NMI #include <asm/nmi.h> #endif #endif
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 /* SPDX-License-Identifier: GPL-2.0 */ /* * A hash table (hashtab) maintains associations between * key values and datum values. The type of the key values * and the type of the datum values is arbitrary. The * functions for hash computation and key comparison are * provided by the creator of the table. * * Author : Stephen Smalley, <sds@tycho.nsa.gov> */ #ifndef _SS_HASHTAB_H_ #define _SS_HASHTAB_H_ #include <linux/types.h> #include <linux/errno.h> #include <linux/sched.h> #define HASHTAB_MAX_NODES U32_MAX struct hashtab_key_params { u32 (*hash)(const void *key); /* hash function */ int (*cmp)(const void *key1, const void *key2); /* key comparison function */ }; struct hashtab_node { void *key; void *datum; struct hashtab_node *next; }; struct hashtab { struct hashtab_node **htable; /* hash table */ u32 size; /* number of slots in hash table */ u32 nel; /* number of elements in hash table */ }; struct hashtab_info { u32 slots_used; u32 max_chain_len; }; /* * Initializes a new hash table with the specified characteristics. * * Returns -ENOMEM if insufficient space is available or 0 otherwise. */ int hashtab_init(struct hashtab *h, u32 nel_hint); int __hashtab_insert(struct hashtab *h, struct hashtab_node **dst, void *key, void *datum); /* * Inserts the specified (key, datum) pair into the specified hash table. * * Returns -ENOMEM on memory allocation error, * -EEXIST if there is already an entry with the same key, * -EINVAL for general errors or 0 otherwise. */ static inline int hashtab_insert(struct hashtab *h, void *key, void *datum, struct hashtab_key_params key_params) { u32 hvalue; struct hashtab_node *prev, *cur; cond_resched(); if (!h->size || h->nel == HASHTAB_MAX_NODES) return -EINVAL; hvalue = key_params.hash(key) & (h->size - 1); prev = NULL; cur = h->htable[hvalue]; while (cur) { int cmp = key_params.cmp(key, cur->key); if (cmp == 0) return -EEXIST; if (cmp < 0) break; prev = cur; cur = cur->next; } return __hashtab_insert(h, prev ? &prev->next : &h->htable[hvalue], key, datum); } /* * Searches for the entry with the specified key in the hash table. * * Returns NULL if no entry has the specified key or * the datum of the entry otherwise. */ static inline void *hashtab_search(struct hashtab *h, const void *key, struct hashtab_key_params key_params) { u32 hvalue; struct hashtab_node *cur; if (!h->size) return NULL; hvalue = key_params.hash(key) & (h->size - 1); cur = h->htable[hvalue]; while (cur) { int cmp = key_params.cmp(key, cur->key); if (cmp == 0) return cur->datum; if (cmp < 0) break; cur = cur->next; } return NULL; } /* * Destroys the specified hash table. */ void hashtab_destroy(struct hashtab *h); /* * Applies the specified apply function to (key,datum,args) * for each entry in the specified hash table. * * The order in which the function is applied to the entries * is dependent upon the internal structure of the hash table. * * If apply returns a non-zero status, then hashtab_map will cease * iterating through the hash table and will propagate the error * return to its caller. */ int hashtab_map(struct hashtab *h, int (*apply)(void *k, void *d, void *args), void *args); int hashtab_duplicate(struct hashtab *new, struct hashtab *orig, int (*copy)(struct hashtab_node *new, struct hashtab_node *orig, void *args), int (*destroy)(void *k, void *d, void *args), void *args); /* Fill info with some hash table statistics */ void hashtab_stat(struct hashtab *h, struct hashtab_info *info); #endif /* _SS_HASHTAB_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_DST_METADATA_H #define __NET_DST_METADATA_H 1 #include <linux/skbuff.h> #include <net/ip_tunnels.h> #include <net/dst.h> enum metadata_type { METADATA_IP_TUNNEL, METADATA_HW_PORT_MUX, }; struct hw_port_info { struct net_device *lower_dev; u32 port_id; }; struct metadata_dst { struct dst_entry dst; enum metadata_type type; union { struct ip_tunnel_info tun_info; struct hw_port_info port_info; } u; }; static inline struct metadata_dst *skb_metadata_dst(const struct sk_buff *skb) { struct metadata_dst *md_dst = (struct metadata_dst *) skb_dst(skb); if (md_dst && md_dst->dst.flags & DST_METADATA) return md_dst; return NULL; } static inline struct ip_tunnel_info * skb_tunnel_info(const struct sk_buff *skb) { struct metadata_dst *md_dst = skb_metadata_dst(skb); struct dst_entry *dst; if (md_dst && md_dst->type == METADATA_IP_TUNNEL) return &md_dst->u.tun_info; dst = skb_dst(skb); if (dst && dst->lwtstate && (dst->lwtstate->type == LWTUNNEL_ENCAP_IP || dst->lwtstate->type == LWTUNNEL_ENCAP_IP6)) return lwt_tun_info(dst->lwtstate); return NULL; } static inline bool skb_valid_dst(const struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); return dst && !(dst->flags & DST_METADATA); } static inline int skb_metadata_dst_cmp(const struct sk_buff *skb_a, const struct sk_buff *skb_b) { const struct metadata_dst *a, *b; if (!(skb_a->_skb_refdst | skb_b->_skb_refdst)) return 0; a = (const struct metadata_dst *) skb_dst(skb_a); b = (const struct metadata_dst *) skb_dst(skb_b); if (!a != !b || a->type != b->type) return 1; switch (a->type) { case METADATA_HW_PORT_MUX: return memcmp(&a->u.port_info, &b->u.port_info, sizeof(a->u.port_info)); case METADATA_IP_TUNNEL: return memcmp(&a->u.tun_info, &b->u.tun_info, sizeof(a->u.tun_info) + a->u.tun_info.options_len); default: return 1; } } void metadata_dst_free(struct metadata_dst *); struct metadata_dst *metadata_dst_alloc(u8 optslen, enum metadata_type type, gfp_t flags); void metadata_dst_free_percpu(struct metadata_dst __percpu *md_dst); struct metadata_dst __percpu * metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags); static inline struct metadata_dst *tun_rx_dst(int md_size) { struct metadata_dst *tun_dst; tun_dst = metadata_dst_alloc(md_size, METADATA_IP_TUNNEL, GFP_ATOMIC); if (!tun_dst) return NULL; tun_dst->u.tun_info.options_len = 0; tun_dst->u.tun_info.mode = 0; return tun_dst; } static inline struct metadata_dst *tun_dst_unclone(struct sk_buff *skb) { struct metadata_dst *md_dst = skb_metadata_dst(skb); int md_size; struct metadata_dst *new_md; if (!md_dst || md_dst->type != METADATA_IP_TUNNEL) return ERR_PTR(-EINVAL); md_size = md_dst->u.tun_info.options_len; new_md = metadata_dst_alloc(md_size, METADATA_IP_TUNNEL, GFP_ATOMIC); if (!new_md) return ERR_PTR(-ENOMEM); memcpy(&new_md->u.tun_info, &md_dst->u.tun_info, sizeof(struct ip_tunnel_info) + md_size); skb_dst_drop(skb); dst_hold(&new_md->dst); skb_dst_set(skb, &new_md->dst); return new_md; } static inline struct ip_tunnel_info *skb_tunnel_info_unclone(struct sk_buff *skb) { struct metadata_dst *dst; dst = tun_dst_unclone(skb); if (IS_ERR(dst)) return NULL; return &dst->u.tun_info; } static inline struct metadata_dst *__ip_tun_set_dst(__be32 saddr, __be32 daddr, __u8 tos, __u8 ttl, __be16 tp_dst, __be16 flags, __be64 tunnel_id, int md_size) { struct metadata_dst *tun_dst; tun_dst = tun_rx_dst(md_size); if (!tun_dst) return NULL; ip_tunnel_key_init(&tun_dst->u.tun_info.key, saddr, daddr, tos, ttl, 0, 0, tp_dst, tunnel_id, flags); return tun_dst; } static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb, __be16 flags, __be64 tunnel_id, int md_size) { const struct iphdr *iph = ip_hdr(skb); return __ip_tun_set_dst(iph->saddr, iph->daddr, iph->tos, iph->ttl, 0, flags, tunnel_id, md_size); } static inline struct metadata_dst *__ipv6_tun_set_dst(const struct in6_addr *saddr, const struct in6_addr *daddr, __u8 tos, __u8 ttl, __be16 tp_dst, __be32 label, __be16 flags, __be64 tunnel_id, int md_size) { struct metadata_dst *tun_dst; struct ip_tunnel_info *info; tun_dst = tun_rx_dst(md_size); if (!tun_dst) return NULL; info = &tun_dst->u.tun_info; info->mode = IP_TUNNEL_INFO_IPV6; info->key.tun_flags = flags; info->key.tun_id = tunnel_id; info->key.tp_src = 0; info->key.tp_dst = tp_dst; info->key.u.ipv6.src = *saddr; info->key.u.ipv6.dst = *daddr; info->key.tos = tos; info->key.ttl = ttl; info->key.label = label; return tun_dst; } static inline struct metadata_dst *ipv6_tun_rx_dst(struct sk_buff *skb, __be16 flags, __be64 tunnel_id, int md_size) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); return __ipv6_tun_set_dst(&ip6h->saddr, &ip6h->daddr, ipv6_get_dsfield(ip6h), ip6h->hop_limit, 0, ip6_flowlabel(ip6h), flags, tunnel_id, md_size); } #endif /* __NET_DST_METADATA_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 /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM fib #if !defined(_TRACE_FIB_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_FIB_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <net/ip_fib.h> #include <linux/tracepoint.h> TRACE_EVENT(fib_table_lookup, TP_PROTO(u32 tb_id, const struct flowi4 *flp, const struct fib_nh_common *nhc, int err), TP_ARGS(tb_id, flp, nhc, err), TP_STRUCT__entry( __field( u32, tb_id ) __field( int, err ) __field( int, oif ) __field( int, iif ) __field( u8, proto ) __field( __u8, tos ) __field( __u8, scope ) __field( __u8, flags ) __array( __u8, src, 4 ) __array( __u8, dst, 4 ) __array( __u8, gw4, 4 ) __array( __u8, gw6, 16 ) __field( u16, sport ) __field( u16, dport ) __dynamic_array(char, name, IFNAMSIZ ) ), TP_fast_assign( struct in6_addr in6_zero = {}; struct net_device *dev; struct in6_addr *in6; __be32 *p32; __entry->tb_id = tb_id; __entry->err = err; __entry->oif = flp->flowi4_oif; __entry->iif = flp->flowi4_iif; __entry->tos = flp->flowi4_tos; __entry->scope = flp->flowi4_scope; __entry->flags = flp->flowi4_flags; p32 = (__be32 *) __entry->src; *p32 = flp->saddr; p32 = (__be32 *) __entry->dst; *p32 = flp->daddr; __entry->proto = flp->flowi4_proto; if (__entry->proto == IPPROTO_TCP || __entry->proto == IPPROTO_UDP) { __entry->sport = ntohs(flp->fl4_sport); __entry->dport = ntohs(flp->fl4_dport); } else { __entry->sport = 0; __entry->dport = 0; } dev = nhc ? nhc->nhc_dev : NULL; __assign_str(name, dev ? dev->name : "-"); if (nhc) { if (nhc->nhc_gw_family == AF_INET) { p32 = (__be32 *) __entry->gw4; *p32 = nhc->nhc_gw.ipv4; in6 = (struct in6_addr *)__entry->gw6; *in6 = in6_zero; } else if (nhc->nhc_gw_family == AF_INET6) { p32 = (__be32 *) __entry->gw4; *p32 = 0; in6 = (struct in6_addr *)__entry->gw6; *in6 = nhc->nhc_gw.ipv6; } } else { p32 = (__be32 *) __entry->gw4; *p32 = 0; in6 = (struct in6_addr *)__entry->gw6; *in6 = in6_zero; } ), TP_printk("table %u oif %d iif %d proto %u %pI4/%u -> %pI4/%u tos %d scope %d flags %x ==> dev %s gw %pI4/%pI6c err %d", __entry->tb_id, __entry->oif, __entry->iif, __entry->proto, __entry->src, __entry->sport, __entry->dst, __entry->dport, __entry->tos, __entry->scope, __entry->flags, __get_str(name), __entry->gw4, __entry->gw6, __entry->err) ); #endif /* _TRACE_FIB_H */ /* This part must be outside protection */ #include <trace/define_trace.h>
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 /* 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. * * Definitions for the TCP module. * * Version: @(#)tcp.h 1.0.5 05/23/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> */ #ifndef _TCP_H #define _TCP_H #define FASTRETRANS_DEBUG 1 #include <linux/list.h> #include <linux/tcp.h> #include <linux/bug.h> #include <linux/slab.h> #include <linux/cache.h> #include <linux/percpu.h> #include <linux/skbuff.h> #include <linux/kref.h> #include <linux/ktime.h> #include <linux/indirect_call_wrapper.h> #include <net/inet_connection_sock.h> #include <net/inet_timewait_sock.h> #include <net/inet_hashtables.h> #include <net/checksum.h> #include <net/request_sock.h> #include <net/sock_reuseport.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ip.h> #include <net/tcp_states.h> #include <net/inet_ecn.h> #include <net/dst.h> #include <net/mptcp.h> #include <linux/seq_file.h> #include <linux/memcontrol.h> #include <linux/bpf-cgroup.h> #include <linux/siphash.h> extern struct inet_hashinfo tcp_hashinfo; DECLARE_PER_CPU(unsigned int, tcp_orphan_count); int tcp_orphan_count_sum(void); void tcp_time_wait(struct sock *sk, int state, int timeo); #define MAX_TCP_HEADER L1_CACHE_ALIGN(128 + MAX_HEADER) #define MAX_TCP_OPTION_SPACE 40 #define TCP_MIN_SND_MSS 48 #define TCP_MIN_GSO_SIZE (TCP_MIN_SND_MSS - MAX_TCP_OPTION_SPACE) /* * Never offer a window over 32767 without using window scaling. Some * poor stacks do signed 16bit maths! */ #define MAX_TCP_WINDOW 32767U /* Minimal accepted MSS. It is (60+60+8) - (20+20). */ #define TCP_MIN_MSS 88U /* The initial MTU to use for probing */ #define TCP_BASE_MSS 1024 /* probing interval, default to 10 minutes as per RFC4821 */ #define TCP_PROBE_INTERVAL 600 /* Specify interval when tcp mtu probing will stop */ #define TCP_PROBE_THRESHOLD 8 /* After receiving this amount of duplicate ACKs fast retransmit starts. */ #define TCP_FASTRETRANS_THRESH 3 /* Maximal number of ACKs sent quickly to accelerate slow-start. */ #define TCP_MAX_QUICKACKS 16U /* Maximal number of window scale according to RFC1323 */ #define TCP_MAX_WSCALE 14U /* urg_data states */ #define TCP_URG_VALID 0x0100 #define TCP_URG_NOTYET 0x0200 #define TCP_URG_READ 0x0400 #define TCP_RETR1 3 /* * This is how many retries it does before it * tries to figure out if the gateway is * down. Minimal RFC value is 3; it corresponds * to ~3sec-8min depending on RTO. */ #define TCP_RETR2 15 /* * This should take at least * 90 minutes to time out. * RFC1122 says that the limit is 100 sec. * 15 is ~13-30min depending on RTO. */ #define TCP_SYN_RETRIES 6 /* This is how many retries are done * when active opening a connection. * RFC1122 says the minimum retry MUST * be at least 180secs. Nevertheless * this value is corresponding to * 63secs of retransmission with the * current initial RTO. */ #define TCP_SYNACK_RETRIES 5 /* This is how may retries are done * when passive opening a connection. * This is corresponding to 31secs of * retransmission with the current * initial RTO. */ #define TCP_TIMEWAIT_LEN (60*HZ) /* how long to wait to destroy TIME-WAIT * state, about 60 seconds */ #define TCP_FIN_TIMEOUT TCP_TIMEWAIT_LEN /* BSD style FIN_WAIT2 deadlock breaker. * It used to be 3min, new value is 60sec, * to combine FIN-WAIT-2 timeout with * TIME-WAIT timer. */ #define TCP_FIN_TIMEOUT_MAX (120 * HZ) /* max TCP_LINGER2 value (two minutes) */ #define TCP_DELACK_MAX ((unsigned)(HZ/5)) /* maximal time to delay before sending an ACK */ #if HZ >= 100 #define TCP_DELACK_MIN ((unsigned)(HZ/25)) /* minimal time to delay before sending an ACK */ #define TCP_ATO_MIN ((unsigned)(HZ/25)) #else #define TCP_DELACK_MIN 4U #define TCP_ATO_MIN 4U #endif #define TCP_RTO_MAX ((unsigned)(120*HZ)) #define TCP_RTO_MIN ((unsigned)(HZ/5)) #define TCP_TIMEOUT_MIN (2U) /* Min timeout for TCP timers in jiffies */ #define TCP_TIMEOUT_INIT ((unsigned)(1*HZ)) /* RFC6298 2.1 initial RTO value */ #define TCP_TIMEOUT_FALLBACK ((unsigned)(3*HZ)) /* RFC 1122 initial RTO value, now * used as a fallback RTO for the * initial data transmission if no * valid RTT sample has been acquired, * most likely due to retrans in 3WHS. */ #define TCP_RESOURCE_PROBE_INTERVAL ((unsigned)(HZ/2U)) /* Maximal interval between probes * for local resources. */ #define TCP_KEEPALIVE_TIME (120*60*HZ) /* two hours */ #define TCP_KEEPALIVE_PROBES 9 /* Max of 9 keepalive probes */ #define TCP_KEEPALIVE_INTVL (75*HZ) #define MAX_TCP_KEEPIDLE 32767 #define MAX_TCP_KEEPINTVL 32767 #define MAX_TCP_KEEPCNT 127 #define MAX_TCP_SYNCNT 127 #define TCP_SYNQ_INTERVAL (HZ/5) /* Period of SYNACK timer */ #define TCP_PAWS_24DAYS (60 * 60 * 24 * 24) #define TCP_PAWS_MSL 60 /* Per-host timestamps are invalidated * after this time. It should be equal * (or greater than) TCP_TIMEWAIT_LEN * to provide reliability equal to one * provided by timewait state. */ #define TCP_PAWS_WINDOW 1 /* Replay window for per-host * timestamps. It must be less than * minimal timewait lifetime. */ /* * TCP option */ #define TCPOPT_NOP 1 /* Padding */ #define TCPOPT_EOL 0 /* End of options */ #define TCPOPT_MSS 2 /* Segment size negotiating */ #define TCPOPT_WINDOW 3 /* Window scaling */ #define TCPOPT_SACK_PERM 4 /* SACK Permitted */ #define TCPOPT_SACK 5 /* SACK Block */ #define TCPOPT_TIMESTAMP 8 /* Better RTT estimations/PAWS */ #define TCPOPT_MD5SIG 19 /* MD5 Signature (RFC2385) */ #define TCPOPT_MPTCP 30 /* Multipath TCP (RFC6824) */ #define TCPOPT_FASTOPEN 34 /* Fast open (RFC7413) */ #define TCPOPT_EXP 254 /* Experimental */ /* Magic number to be after the option value for sharing TCP * experimental options. See draft-ietf-tcpm-experimental-options-00.txt */ #define TCPOPT_FASTOPEN_MAGIC 0xF989 #define TCPOPT_SMC_MAGIC 0xE2D4C3D9 /* * TCP option lengths */ #define TCPOLEN_MSS 4 #define TCPOLEN_WINDOW 3 #define TCPOLEN_SACK_PERM 2 #define TCPOLEN_TIMESTAMP 10 #define TCPOLEN_MD5SIG 18 #define TCPOLEN_FASTOPEN_BASE 2 #define TCPOLEN_EXP_FASTOPEN_BASE 4 #define TCPOLEN_EXP_SMC_BASE 6 /* But this is what stacks really send out. */ #define TCPOLEN_TSTAMP_ALIGNED 12 #define TCPOLEN_WSCALE_ALIGNED 4 #define TCPOLEN_SACKPERM_ALIGNED 4 #define TCPOLEN_SACK_BASE 2 #define TCPOLEN_SACK_BASE_ALIGNED 4 #define TCPOLEN_SACK_PERBLOCK 8 #define TCPOLEN_MD5SIG_ALIGNED 20 #define TCPOLEN_MSS_ALIGNED 4 #define TCPOLEN_EXP_SMC_BASE_ALIGNED 8 /* Flags in tp->nonagle */ #define TCP_NAGLE_OFF 1 /* Nagle's algo is disabled */ #define TCP_NAGLE_CORK 2 /* Socket is corked */ #define TCP_NAGLE_PUSH 4 /* Cork is overridden for already queued data */ /* TCP thin-stream limits */ #define TCP_THIN_LINEAR_RETRIES 6 /* After 6 linear retries, do exp. backoff */ /* TCP initial congestion window as per rfc6928 */ #define TCP_INIT_CWND 10 /* Bit Flags for sysctl_tcp_fastopen */ #define TFO_CLIENT_ENABLE 1 #define TFO_SERVER_ENABLE 2 #define TFO_CLIENT_NO_COOKIE 4 /* Data in SYN w/o cookie option */ /* Accept SYN data w/o any cookie option */ #define TFO_SERVER_COOKIE_NOT_REQD 0x200 /* Force enable TFO on all listeners, i.e., not requiring the * TCP_FASTOPEN socket option. */ #define TFO_SERVER_WO_SOCKOPT1 0x400 /* sysctl variables for tcp */ extern int sysctl_tcp_max_orphans; extern long sysctl_tcp_mem[3]; #define TCP_RACK_LOSS_DETECTION 0x1 /* Use RACK to detect losses */ #define TCP_RACK_STATIC_REO_WND 0x2 /* Use static RACK reo wnd */ #define TCP_RACK_NO_DUPTHRESH 0x4 /* Do not use DUPACK threshold in RACK */ extern atomic_long_t tcp_memory_allocated; extern struct percpu_counter tcp_sockets_allocated; extern unsigned long tcp_memory_pressure; /* optimized version of sk_under_memory_pressure() for TCP sockets */ static inline bool tcp_under_memory_pressure(const struct sock *sk) { if (mem_cgroup_sockets_enabled && sk->sk_memcg && mem_cgroup_under_socket_pressure(sk->sk_memcg)) return true; return READ_ONCE(tcp_memory_pressure); } /* * The next routines deal with comparing 32 bit unsigned ints * and worry about wraparound (automatic with unsigned arithmetic). */ static inline bool before(__u32 seq1, __u32 seq2) { return (__s32)(seq1-seq2) < 0; } #define after(seq2, seq1) before(seq1, seq2) /* is s2<=s1<=s3 ? */ static inline bool between(__u32 seq1, __u32 seq2, __u32 seq3) { return seq3 - seq2 >= seq1 - seq2; } static inline bool tcp_out_of_memory(struct sock *sk) { if (sk->sk_wmem_queued > SOCK_MIN_SNDBUF && sk_memory_allocated(sk) > sk_prot_mem_limits(sk, 2)) return true; return false; } void sk_forced_mem_schedule(struct sock *sk, int size); bool tcp_check_oom(struct sock *sk, int shift); extern struct proto tcp_prot; #define TCP_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.tcp_statistics, field) #define __TCP_INC_STATS(net, field) __SNMP_INC_STATS((net)->mib.tcp_statistics, field) #define TCP_DEC_STATS(net, field) SNMP_DEC_STATS((net)->mib.tcp_statistics, field) #define TCP_ADD_STATS(net, field, val) SNMP_ADD_STATS((net)->mib.tcp_statistics, field, val) void tcp_tasklet_init(void); int tcp_v4_err(struct sk_buff *skb, u32); void tcp_shutdown(struct sock *sk, int how); int tcp_v4_early_demux(struct sk_buff *skb); int tcp_v4_rcv(struct sk_buff *skb); int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw); int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset, size_t size, int flags); ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, size_t size, int flags); int tcp_send_mss(struct sock *sk, int *size_goal, int flags); void tcp_push(struct sock *sk, int flags, int mss_now, int nonagle, int size_goal); void tcp_release_cb(struct sock *sk); void tcp_wfree(struct sk_buff *skb); void tcp_write_timer_handler(struct sock *sk); void tcp_delack_timer_handler(struct sock *sk); int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg); int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb); void tcp_rcv_established(struct sock *sk, struct sk_buff *skb); void tcp_rcv_space_adjust(struct sock *sk); int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp); void tcp_twsk_destructor(struct sock *sk); ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks); static inline void tcp_dec_quickack_mode(struct sock *sk, const unsigned int pkts) { struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ack.quick) { if (pkts >= icsk->icsk_ack.quick) { icsk->icsk_ack.quick = 0; /* Leaving quickack mode we deflate ATO. */ icsk->icsk_ack.ato = TCP_ATO_MIN; } else icsk->icsk_ack.quick -= pkts; } } #define TCP_ECN_OK 1 #define TCP_ECN_QUEUE_CWR 2 #define TCP_ECN_DEMAND_CWR 4 #define TCP_ECN_SEEN 8 enum tcp_tw_status { TCP_TW_SUCCESS = 0, TCP_TW_RST = 1, TCP_TW_ACK = 2, TCP_TW_SYN = 3 }; enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, const struct tcphdr *th); struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, struct request_sock *req, bool fastopen, bool *lost_race); int tcp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb); void tcp_enter_loss(struct sock *sk); void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int flag); void tcp_clear_retrans(struct tcp_sock *tp); void tcp_update_metrics(struct sock *sk); void tcp_init_metrics(struct sock *sk); void tcp_metrics_init(void); bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst); void tcp_close(struct sock *sk, long timeout); void tcp_init_sock(struct sock *sk); void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb); __poll_t tcp_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); void tcp_set_keepalive(struct sock *sk, int val); void tcp_syn_ack_timeout(const struct request_sock *req); int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len); int tcp_set_rcvlowat(struct sock *sk, int val); void tcp_data_ready(struct sock *sk); #ifdef CONFIG_MMU int tcp_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma); #endif void tcp_parse_options(const struct net *net, const struct sk_buff *skb, struct tcp_options_received *opt_rx, int estab, struct tcp_fastopen_cookie *foc); const u8 *tcp_parse_md5sig_option(const struct tcphdr *th); /* * BPF SKB-less helpers */ u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph, struct tcphdr *th, u32 *cookie); u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph, struct tcphdr *th, u32 *cookie); u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct tcphdr *th); /* * TCP v4 functions exported for the inet6 API */ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb); void tcp_v4_mtu_reduced(struct sock *sk); void tcp_req_err(struct sock *sk, u32 seq, bool abort); void tcp_ld_RTO_revert(struct sock *sk, u32 seq); int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb); struct sock *tcp_create_openreq_child(const struct sock *sk, struct request_sock *req, struct sk_buff *skb); void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst); struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst, struct request_sock *req_unhash, bool *own_req); int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb); int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); int tcp_connect(struct sock *sk); enum tcp_synack_type { TCP_SYNACK_NORMAL, TCP_SYNACK_FASTOPEN, TCP_SYNACK_COOKIE, }; struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb); int tcp_disconnect(struct sock *sk, int flags); void tcp_finish_connect(struct sock *sk, struct sk_buff *skb); int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size); void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb); /* From syncookies.c */ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst, u32 tsoff); int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th, u32 cookie); struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb); struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk, struct sk_buff *skb); #ifdef CONFIG_SYN_COOKIES /* Syncookies use a monotonic timer which increments every 60 seconds. * This counter is used both as a hash input and partially encoded into * the cookie value. A cookie is only validated further if the delta * between the current counter value and the encoded one is less than this, * i.e. a sent cookie is valid only at most for 2*60 seconds (or less if * the counter advances immediately after a cookie is generated). */ #define MAX_SYNCOOKIE_AGE 2 #define TCP_SYNCOOKIE_PERIOD (60 * HZ) #define TCP_SYNCOOKIE_VALID (MAX_SYNCOOKIE_AGE * TCP_SYNCOOKIE_PERIOD) /* syncookies: remember time of last synqueue overflow * But do not dirty this field too often (once per second is enough) * It is racy as we do not hold a lock, but race is very minor. */ static inline void tcp_synq_overflow(const struct sock *sk) { unsigned int last_overflow; unsigned int now = jiffies; if (sk->sk_reuseport) { struct sock_reuseport *reuse; reuse = rcu_dereference(sk->sk_reuseport_cb); if (likely(reuse)) { last_overflow = READ_ONCE(reuse->synq_overflow_ts); if (!time_between32(now, last_overflow, last_overflow + HZ)) WRITE_ONCE(reuse->synq_overflow_ts, now); return; } } last_overflow = READ_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp); if (!time_between32(now, last_overflow, last_overflow + HZ)) WRITE_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp, now); } /* syncookies: no recent synqueue overflow on this listening socket? */ static inline bool tcp_synq_no_recent_overflow(const struct sock *sk) { unsigned int last_overflow; unsigned int now = jiffies; if (sk->sk_reuseport) { struct sock_reuseport *reuse; reuse = rcu_dereference(sk->sk_reuseport_cb); if (likely(reuse)) { last_overflow = READ_ONCE(reuse->synq_overflow_ts); return !time_between32(now, last_overflow - HZ, last_overflow + TCP_SYNCOOKIE_VALID); } } last_overflow = READ_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp); /* If last_overflow <= jiffies <= last_overflow + TCP_SYNCOOKIE_VALID, * then we're under synflood. However, we have to use * 'last_overflow - HZ' as lower bound. That's because a concurrent * tcp_synq_overflow() could update .ts_recent_stamp after we read * jiffies but before we store .ts_recent_stamp into last_overflow, * which could lead to rejecting a valid syncookie. */ return !time_between32(now, last_overflow - HZ, last_overflow + TCP_SYNCOOKIE_VALID); } static inline u32 tcp_cookie_time(void) { u64 val = get_jiffies_64(); do_div(val, TCP_SYNCOOKIE_PERIOD); return val; } u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th, u16 *mssp); __u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mss); u64 cookie_init_timestamp(struct request_sock *req, u64 now); bool cookie_timestamp_decode(const struct net *net, struct tcp_options_received *opt); bool cookie_ecn_ok(const struct tcp_options_received *opt, const struct net *net, const struct dst_entry *dst); /* From net/ipv6/syncookies.c */ int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th, u32 cookie); struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb); u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph, const struct tcphdr *th, u16 *mssp); __u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mss); #endif /* tcp_output.c */ void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, int nonagle); int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs); int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs); void tcp_retransmit_timer(struct sock *sk); void tcp_xmit_retransmit_queue(struct sock *); void tcp_simple_retransmit(struct sock *); void tcp_enter_recovery(struct sock *sk, bool ece_ack); int tcp_trim_head(struct sock *, struct sk_buff *, u32); enum tcp_queue { TCP_FRAG_IN_WRITE_QUEUE, TCP_FRAG_IN_RTX_QUEUE, }; int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, struct sk_buff *skb, u32 len, unsigned int mss_now, gfp_t gfp); void tcp_send_probe0(struct sock *); void tcp_send_partial(struct sock *); int tcp_write_wakeup(struct sock *, int mib); void tcp_send_fin(struct sock *sk); void tcp_send_active_reset(struct sock *sk, gfp_t priority); int tcp_send_synack(struct sock *); void tcp_push_one(struct sock *, unsigned int mss_now); void __tcp_send_ack(struct sock *sk, u32 rcv_nxt); void tcp_send_ack(struct sock *sk); void tcp_send_delayed_ack(struct sock *sk); void tcp_send_loss_probe(struct sock *sk); bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto); void tcp_skb_collapse_tstamp(struct sk_buff *skb, const struct sk_buff *next_skb); /* tcp_input.c */ void tcp_rearm_rto(struct sock *sk); void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req); void tcp_reset(struct sock *sk); void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb); void tcp_fin(struct sock *sk); /* tcp_timer.c */ void tcp_init_xmit_timers(struct sock *); static inline void tcp_clear_xmit_timers(struct sock *sk) { if (hrtimer_try_to_cancel(&tcp_sk(sk)->pacing_timer) == 1) __sock_put(sk); if (hrtimer_try_to_cancel(&tcp_sk(sk)->compressed_ack_timer) == 1) __sock_put(sk); inet_csk_clear_xmit_timers(sk); } unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu); unsigned int tcp_current_mss(struct sock *sk); u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when); /* Bound MSS / TSO packet size with the half of the window */ static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize) { int cutoff; /* When peer uses tiny windows, there is no use in packetizing * to sub-MSS pieces for the sake of SWS or making sure there * are enough packets in the pipe for fast recovery. * * On the other hand, for extremely large MSS devices, handling * smaller than MSS windows in this way does make sense. */ if (tp->max_window > TCP_MSS_DEFAULT) cutoff = (tp->max_window >> 1); else cutoff = tp->max_window; if (cutoff && pktsize > cutoff) return max_t(int, cutoff, 68U - tp->tcp_header_len); else return pktsize; } /* tcp.c */ void tcp_get_info(struct sock *, struct tcp_info *); /* Read 'sendfile()'-style from a TCP socket */ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor); void tcp_initialize_rcv_mss(struct sock *sk); int tcp_mtu_to_mss(struct sock *sk, int pmtu); int tcp_mss_to_mtu(struct sock *sk, int mss); void tcp_mtup_init(struct sock *sk); static inline void tcp_bound_rto(const struct sock *sk) { if (inet_csk(sk)->icsk_rto > TCP_RTO_MAX) inet_csk(sk)->icsk_rto = TCP_RTO_MAX; } static inline u32 __tcp_set_rto(const struct tcp_sock *tp) { return usecs_to_jiffies((tp->srtt_us >> 3) + tp->rttvar_us); } static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd) { /* mptcp hooks are only on the slow path */ if (sk_is_mptcp((struct sock *)tp)) return; tp->pred_flags = htonl((tp->tcp_header_len << 26) | ntohl(TCP_FLAG_ACK) | snd_wnd); } static inline void tcp_fast_path_on(struct tcp_sock *tp) { __tcp_fast_path_on(tp, tp->snd_wnd >> tp->rx_opt.snd_wscale); } static inline void tcp_fast_path_check(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); if (RB_EMPTY_ROOT(&tp->out_of_order_queue) && tp->rcv_wnd && atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf && !tp->urg_data) tcp_fast_path_on(tp); } /* Compute the actual rto_min value */ static inline u32 tcp_rto_min(struct sock *sk) { const struct dst_entry *dst = __sk_dst_get(sk); u32 rto_min = inet_csk(sk)->icsk_rto_min; if (dst && dst_metric_locked(dst, RTAX_RTO_MIN)) rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN); return rto_min; } static inline u32 tcp_rto_min_us(struct sock *sk) { return jiffies_to_usecs(tcp_rto_min(sk)); } static inline bool tcp_ca_dst_locked(const struct dst_entry *dst) { return dst_metric_locked(dst, RTAX_CC_ALGO); } /* Minimum RTT in usec. ~0 means not available. */ static inline u32 tcp_min_rtt(const struct tcp_sock *tp) { return minmax_get(&tp->rtt_min); } /* Compute the actual receive window we are currently advertising. * Rcv_nxt can be after the window if our peer push more data * than the offered window. */ static inline u32 tcp_receive_window(const struct tcp_sock *tp) { s32 win = tp->rcv_wup + tp->rcv_wnd - tp->rcv_nxt; if (win < 0) win = 0; return (u32) win; } /* Choose a new window, without checks for shrinking, and without * scaling applied to the result. The caller does these things * if necessary. This is a "raw" window selection. */ u32 __tcp_select_window(struct sock *sk); void tcp_send_window_probe(struct sock *sk); /* TCP uses 32bit jiffies to save some space. * Note that this is different from tcp_time_stamp, which * historically has been the same until linux-4.13. */ #define tcp_jiffies32 ((u32)jiffies) /* * Deliver a 32bit value for TCP timestamp option (RFC 7323) * It is no longer tied to jiffies, but to 1 ms clock. * Note: double check if you want to use tcp_jiffies32 instead of this. */ #define TCP_TS_HZ 1000 static inline u64 tcp_clock_ns(void) { return ktime_get_ns(); } static inline u64 tcp_clock_us(void) { return div_u64(tcp_clock_ns(), NSEC_PER_USEC); } /* This should only be used in contexts where tp->tcp_mstamp is up to date */ static inline u32 tcp_time_stamp(const struct tcp_sock *tp) { return div_u64(tp->tcp_mstamp, USEC_PER_SEC / TCP_TS_HZ); } /* Convert a nsec timestamp into TCP TSval timestamp (ms based currently) */ static inline u32 tcp_ns_to_ts(u64 ns) { return div_u64(ns, NSEC_PER_SEC / TCP_TS_HZ); } /* Could use tcp_clock_us() / 1000, but this version uses a single divide */ static inline u32 tcp_time_stamp_raw(void) { return tcp_ns_to_ts(tcp_clock_ns()); } void tcp_mstamp_refresh(struct tcp_sock *tp); static inline u32 tcp_stamp_us_delta(u64 t1, u64 t0) { return max_t(s64, t1 - t0, 0); } static inline u32 tcp_skb_timestamp(const struct sk_buff *skb) { return tcp_ns_to_ts(skb->skb_mstamp_ns); } /* provide the departure time in us unit */ static inline u64 tcp_skb_timestamp_us(const struct sk_buff *skb) { return div_u64(skb->skb_mstamp_ns, NSEC_PER_USEC); } #define tcp_flag_byte(th) (((u_int8_t *)th)[13]) #define TCPHDR_FIN 0x01 #define TCPHDR_SYN 0x02 #define TCPHDR_RST 0x04 #define TCPHDR_PSH 0x08 #define TCPHDR_ACK 0x10 #define TCPHDR_URG 0x20 #define TCPHDR_ECE 0x40 #define TCPHDR_CWR 0x80 #define TCPHDR_SYN_ECN (TCPHDR_SYN | TCPHDR_ECE | TCPHDR_CWR) /* This is what the send packet queuing engine uses to pass * TCP per-packet control information to the transmission code. * We also store the host-order sequence numbers in here too. * This is 44 bytes if IPV6 is enabled. * If this grows please adjust skbuff.h:skbuff->cb[xxx] size appropriately. */ struct tcp_skb_cb { __u32 seq; /* Starting sequence number */ __u32 end_seq; /* SEQ + FIN + SYN + datalen */ union { /* Note : tcp_tw_isn is used in input path only * (isn chosen by tcp_timewait_state_process()) * * tcp_gso_segs/size are used in write queue only, * cf tcp_skb_pcount()/tcp_skb_mss() */ __u32 tcp_tw_isn; struct { u16 tcp_gso_segs; u16 tcp_gso_size; }; }; __u8 tcp_flags; /* TCP header flags. (tcp[13]) */ __u8 sacked; /* State flags for SACK. */ #define TCPCB_SACKED_ACKED 0x01 /* SKB ACK'd by a SACK block */ #define TCPCB_SACKED_RETRANS 0x02 /* SKB retransmitted */ #define TCPCB_LOST 0x04 /* SKB is lost */ #define TCPCB_TAGBITS 0x07 /* All tag bits */ #define TCPCB_REPAIRED 0x10 /* SKB repaired (no skb_mstamp_ns) */ #define TCPCB_EVER_RETRANS 0x80 /* Ever retransmitted frame */ #define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS| \ TCPCB_REPAIRED) __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */ __u8 txstamp_ack:1, /* Record TX timestamp for ack? */ eor:1, /* Is skb MSG_EOR marked? */ has_rxtstamp:1, /* SKB has a RX timestamp */ unused:5; __u32 ack_seq; /* Sequence number ACK'd */ union { struct { /* There is space for up to 24 bytes */ __u32 in_flight:30,/* Bytes in flight at transmit */ is_app_limited:1, /* cwnd not fully used? */ unused:1; /* pkts S/ACKed so far upon tx of skb, incl retrans: */ __u32 delivered; /* start of send pipeline phase */ u64 first_tx_mstamp; /* when we reached the "delivered" count */ u64 delivered_mstamp; } tx; /* only used for outgoing skbs */ union { struct inet_skb_parm h4; #if IS_ENABLED(CONFIG_IPV6) struct inet6_skb_parm h6; #endif } header; /* For incoming skbs */ struct { __u32 flags; struct sock *sk_redir; void *data_end; } bpf; }; }; #define TCP_SKB_CB(__skb) ((struct tcp_skb_cb *)&((__skb)->cb[0])) static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb) { TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb); } static inline bool tcp_skb_bpf_ingress(const struct sk_buff *skb) { return TCP_SKB_CB(skb)->bpf.flags & BPF_F_INGRESS; } static inline struct sock *tcp_skb_bpf_redirect_fetch(struct sk_buff *skb) { return TCP_SKB_CB(skb)->bpf.sk_redir; } static inline void tcp_skb_bpf_redirect_clear(struct sk_buff *skb) { TCP_SKB_CB(skb)->bpf.sk_redir = NULL; } extern const struct inet_connection_sock_af_ops ipv4_specific; #if IS_ENABLED(CONFIG_IPV6) /* This is the variant of inet6_iif() that must be used by TCP, * as TCP moves IP6CB into a different location in skb->cb[] */ static inline int tcp_v6_iif(const struct sk_buff *skb) { return TCP_SKB_CB(skb)->header.h6.iif; } static inline int tcp_v6_iif_l3_slave(const struct sk_buff *skb) { bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags); return l3_slave ? skb->skb_iif : TCP_SKB_CB(skb)->header.h6.iif; } /* TCP_SKB_CB reference means this can not be used from early demux */ static inline int tcp_v6_sdif(const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) if (skb && ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags)) return TCP_SKB_CB(skb)->header.h6.iif; #endif return 0; } extern const struct inet_connection_sock_af_ops ipv6_specific; INDIRECT_CALLABLE_DECLARE(void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb)); INDIRECT_CALLABLE_DECLARE(int tcp_v6_rcv(struct sk_buff *skb)); INDIRECT_CALLABLE_DECLARE(void tcp_v6_early_demux(struct sk_buff *skb)); #endif /* TCP_SKB_CB reference means this can not be used from early demux */ static inline int tcp_v4_sdif(struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) if (skb && ipv4_l3mdev_skb(TCP_SKB_CB(skb)->header.h4.flags)) return TCP_SKB_CB(skb)->header.h4.iif; #endif return 0; } /* Due to TSO, an SKB can be composed of multiple actual * packets. To keep these tracked properly, we use this. */ static inline int tcp_skb_pcount(const struct sk_buff *skb) { return TCP_SKB_CB(skb)->tcp_gso_segs; } static inline void tcp_skb_pcount_set(struct sk_buff *skb, int segs) { TCP_SKB_CB(skb)->tcp_gso_segs = segs; } static inline void tcp_skb_pcount_add(struct sk_buff *skb, int segs) { TCP_SKB_CB(skb)->tcp_gso_segs += segs; } /* This is valid iff skb is in write queue and tcp_skb_pcount() > 1. */ static inline int tcp_skb_mss(const struct sk_buff *skb) { return TCP_SKB_CB(skb)->tcp_gso_size; } static inline bool tcp_skb_can_collapse_to(const struct sk_buff *skb) { return likely(!TCP_SKB_CB(skb)->eor); } static inline bool tcp_skb_can_collapse(const struct sk_buff *to, const struct sk_buff *from) { return likely(tcp_skb_can_collapse_to(to) && mptcp_skb_can_collapse(to, from)); } /* Events passed to congestion control interface */ enum tcp_ca_event { CA_EVENT_TX_START, /* first transmit when no packets in flight */ CA_EVENT_CWND_RESTART, /* congestion window restart */ CA_EVENT_COMPLETE_CWR, /* end of congestion recovery */ CA_EVENT_LOSS, /* loss timeout */ CA_EVENT_ECN_NO_CE, /* ECT set, but not CE marked */ CA_EVENT_ECN_IS_CE, /* received CE marked IP packet */ }; /* Information about inbound ACK, passed to cong_ops->in_ack_event() */ enum tcp_ca_ack_event_flags { CA_ACK_SLOWPATH = (1 << 0), /* In slow path processing */ CA_ACK_WIN_UPDATE = (1 << 1), /* ACK updated window */ CA_ACK_ECE = (1 << 2), /* ECE bit is set on ack */ }; /* * Interface for adding new TCP congestion control handlers */ #define TCP_CA_NAME_MAX 16 #define TCP_CA_MAX 128 #define TCP_CA_BUF_MAX (TCP_CA_NAME_MAX*TCP_CA_MAX) #define TCP_CA_UNSPEC 0 /* Algorithm can be set on socket without CAP_NET_ADMIN privileges */ #define TCP_CONG_NON_RESTRICTED 0x1 /* Requires ECN/ECT set on all packets */ #define TCP_CONG_NEEDS_ECN 0x2 #define TCP_CONG_MASK (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN) union tcp_cc_info; struct ack_sample { u32 pkts_acked; s32 rtt_us; u32 in_flight; }; /* A rate sample measures the number of (original/retransmitted) data * packets delivered "delivered" over an interval of time "interval_us". * The tcp_rate.c code fills in the rate sample, and congestion * control modules that define a cong_control function to run at the end * of ACK processing can optionally chose to consult this sample when * setting cwnd and pacing rate. * A sample is invalid if "delivered" or "interval_us" is negative. */ struct rate_sample { u64 prior_mstamp; /* starting timestamp for interval */ u32 prior_delivered; /* tp->delivered at "prior_mstamp" */ s32 delivered; /* number of packets delivered over interval */ long interval_us; /* time for tp->delivered to incr "delivered" */ u32 snd_interval_us; /* snd interval for delivered packets */ u32 rcv_interval_us; /* rcv interval for delivered packets */ long rtt_us; /* RTT of last (S)ACKed packet (or -1) */ int losses; /* number of packets marked lost upon ACK */ u32 acked_sacked; /* number of packets newly (S)ACKed upon ACK */ u32 prior_in_flight; /* in flight before this ACK */ bool is_app_limited; /* is sample from packet with bubble in pipe? */ bool is_retrans; /* is sample from retransmission? */ bool is_ack_delayed; /* is this (likely) a delayed ACK? */ }; struct tcp_congestion_ops { struct list_head list; u32 key; u32 flags; /* initialize private data (optional) */ void (*init)(struct sock *sk); /* cleanup private data (optional) */ void (*release)(struct sock *sk); /* return slow start threshold (required) */ u32 (*ssthresh)(struct sock *sk); /* do new cwnd calculation (required) */ void (*cong_avoid)(struct sock *sk, u32 ack, u32 acked); /* call before changing ca_state (optional) */ void (*set_state)(struct sock *sk, u8 new_state); /* call when cwnd event occurs (optional) */ void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev); /* call when ack arrives (optional) */ void (*in_ack_event)(struct sock *sk, u32 flags); /* new value of cwnd after loss (required) */ u32 (*undo_cwnd)(struct sock *sk); /* hook for packet ack accounting (optional) */ void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample); /* override sysctl_tcp_min_tso_segs */ u32 (*min_tso_segs)(struct sock *sk); /* returns the multiplier used in tcp_sndbuf_expand (optional) */ u32 (*sndbuf_expand)(struct sock *sk); /* call when packets are delivered to update cwnd and pacing rate, * after all the ca_state processing. (optional) */ void (*cong_control)(struct sock *sk, const struct rate_sample *rs); /* get info for inet_diag (optional) */ size_t (*get_info)(struct sock *sk, u32 ext, int *attr, union tcp_cc_info *info); char name[TCP_CA_NAME_MAX]; struct module *owner; }; int tcp_register_congestion_control(struct tcp_congestion_ops *type); void tcp_unregister_congestion_control(struct tcp_congestion_ops *type); void tcp_assign_congestion_control(struct sock *sk); void tcp_init_congestion_control(struct sock *sk); void tcp_cleanup_congestion_control(struct sock *sk); int tcp_set_default_congestion_control(struct net *net, const char *name); void tcp_get_default_congestion_control(struct net *net, char *name); void tcp_get_available_congestion_control(char *buf, size_t len); void tcp_get_allowed_congestion_control(char *buf, size_t len); int tcp_set_allowed_congestion_control(char *allowed); int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, bool cap_net_admin); u32 tcp_slow_start(struct tcp_sock *tp, u32 acked); void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked); u32 tcp_reno_ssthresh(struct sock *sk); u32 tcp_reno_undo_cwnd(struct sock *sk); void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked); extern struct tcp_congestion_ops tcp_reno; struct tcp_congestion_ops *tcp_ca_find(const char *name); struct tcp_congestion_ops *tcp_ca_find_key(u32 key); u32 tcp_ca_get_key_by_name(struct net *net, const char *name, bool *ecn_ca); #ifdef CONFIG_INET char *tcp_ca_get_name_by_key(u32 key, char *buffer); #else static inline char *tcp_ca_get_name_by_key(u32 key, char *buffer) { return NULL; } #endif static inline bool tcp_ca_needs_ecn(const struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ECN; } static inline void tcp_set_ca_state(struct sock *sk, const u8 ca_state) { struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ca_ops->set_state) icsk->icsk_ca_ops->set_state(sk, ca_state); icsk->icsk_ca_state = ca_state; } static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event) { const struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ca_ops->cwnd_event) icsk->icsk_ca_ops->cwnd_event(sk, event); } /* From tcp_rate.c */ void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb); void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, struct rate_sample *rs); void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, bool is_sack_reneg, struct rate_sample *rs); void tcp_rate_check_app_limited(struct sock *sk); /* These functions determine how the current flow behaves in respect of SACK * handling. SACK is negotiated with the peer, and therefore it can vary * between different flows. * * tcp_is_sack - SACK enabled * tcp_is_reno - No SACK */ static inline int tcp_is_sack(const struct tcp_sock *tp) { return likely(tp->rx_opt.sack_ok); } static inline bool tcp_is_reno(const struct tcp_sock *tp) { return !tcp_is_sack(tp); } static inline unsigned int tcp_left_out(const struct tcp_sock *tp) { return tp->sacked_out + tp->lost_out; } /* This determines how many packets are "in the network" to the best * of our knowledge. In many cases it is conservative, but where * detailed information is available from the receiver (via SACK * blocks etc.) we can make more aggressive calculations. * * Use this for decisions involving congestion control, use just * tp->packets_out to determine if the send queue is empty or not. * * Read this equation as: * * "Packets sent once on transmission queue" MINUS * "Packets left network, but not honestly ACKed yet" PLUS * "Packets fast retransmitted" */ static inline unsigned int tcp_packets_in_flight(const struct tcp_sock *tp) { return tp->packets_out - tcp_left_out(tp) + tp->retrans_out; } #define TCP_INFINITE_SSTHRESH 0x7fffffff static inline bool tcp_in_slow_start(const struct tcp_sock *tp) { return tp->snd_cwnd < tp->snd_ssthresh; } static inline bool tcp_in_initial_slowstart(const struct tcp_sock *tp) { return tp->snd_ssthresh >= TCP_INFINITE_SSTHRESH; } static inline bool tcp_in_cwnd_reduction(const struct sock *sk) { return (TCPF_CA_CWR | TCPF_CA_Recovery) & (1 << inet_csk(sk)->icsk_ca_state); } /* If cwnd > ssthresh, we may raise ssthresh to be half-way to cwnd. * The exception is cwnd reduction phase, when cwnd is decreasing towards * ssthresh. */ static inline __u32 tcp_current_ssthresh(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); if (tcp_in_cwnd_reduction(sk)) return tp->snd_ssthresh; else return max(tp->snd_ssthresh, ((tp->snd_cwnd >> 1) + (tp->snd_cwnd >> 2))); } /* Use define here intentionally to get WARN_ON location shown at the caller */ #define tcp_verify_left_out(tp) WARN_ON(tcp_left_out(tp) > tp->packets_out) void tcp_enter_cwr(struct sock *sk); __u32 tcp_init_cwnd(const struct tcp_sock *tp, const struct dst_entry *dst); /* The maximum number of MSS of available cwnd for which TSO defers * sending if not using sysctl_tcp_tso_win_divisor. */ static inline __u32 tcp_max_tso_deferred_mss(const struct tcp_sock *tp) { return 3; } /* Returns end sequence number of the receiver's advertised window */ static inline u32 tcp_wnd_end(const struct tcp_sock *tp) { return tp->snd_una + tp->snd_wnd; } /* We follow the spirit of RFC2861 to validate cwnd but implement a more * flexible approach. The RFC suggests cwnd should not be raised unless * it was fully used previously. And that's exactly what we do in * congestion avoidance mode. But in slow start we allow cwnd to grow * as long as the application has used half the cwnd. * Example : * cwnd is 10 (IW10), but application sends 9 frames. * We allow cwnd to reach 18 when all frames are ACKed. * This check is safe because it's as aggressive as slow start which already * risks 100% overshoot. The advantage is that we discourage application to * either send more filler packets or data to artificially blow up the cwnd * usage, and allow application-limited process to probe bw more aggressively. */ static inline bool tcp_is_cwnd_limited(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); /* If in slow start, ensure cwnd grows to twice what was ACKed. */ if (tcp_in_slow_start(tp)) return tp->snd_cwnd < 2 * tp->max_packets_out; return tp->is_cwnd_limited; } /* BBR congestion control needs pacing. * Same remark for SO_MAX_PACING_RATE. * sch_fq packet scheduler is efficiently handling pacing, * but is not always installed/used. * Return true if TCP stack should pace packets itself. */ static inline bool tcp_needs_internal_pacing(const struct sock *sk) { return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED; } /* Estimates in how many jiffies next packet for this flow can be sent. * Scheduling a retransmit timer too early would be silly. */ static inline unsigned long tcp_pacing_delay(const struct sock *sk) { s64 delay = tcp_sk(sk)->tcp_wstamp_ns - tcp_sk(sk)->tcp_clock_cache; return delay > 0 ? nsecs_to_jiffies(delay) : 0; } static inline void tcp_reset_xmit_timer(struct sock *sk, const int what, unsigned long when, const unsigned long max_when) { inet_csk_reset_xmit_timer(sk, what, when + tcp_pacing_delay(sk), max_when); } /* Something is really bad, we could not queue an additional packet, * because qdisc is full or receiver sent a 0 window, or we are paced. * We do not want to add fuel to the fire, or abort too early, * so make sure the timer we arm now is at least 200ms in the future, * regardless of current icsk_rto value (as it could be ~2ms) */ static inline unsigned long tcp_probe0_base(const struct sock *sk) { return max_t(unsigned long, inet_csk(sk)->icsk_rto, TCP_RTO_MIN); } /* Variant of inet_csk_rto_backoff() used for zero window probes */ static inline unsigned long tcp_probe0_when(const struct sock *sk, unsigned long max_when) { u64 when = (u64)tcp_probe0_base(sk) << inet_csk(sk)->icsk_backoff; return (unsigned long)min_t(u64, when, max_when); } static inline void tcp_check_probe_timer(struct sock *sk) { if (!tcp_sk(sk)->packets_out && !inet_csk(sk)->icsk_pending) tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, tcp_probe0_base(sk), TCP_RTO_MAX); } static inline void tcp_init_wl(struct tcp_sock *tp, u32 seq) { tp->snd_wl1 = seq; } static inline void tcp_update_wl(struct tcp_sock *tp, u32 seq) { tp->snd_wl1 = seq; } /* * Calculate(/check) TCP checksum */ static inline __sum16 tcp_v4_check(int len, __be32 saddr, __be32 daddr, __wsum base) { return csum_tcpudp_magic(saddr, daddr, len, IPPROTO_TCP, base); } static inline bool tcp_checksum_complete(struct sk_buff *skb) { return !skb_csum_unnecessary(skb) && __skb_checksum_complete(skb); } bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb); int tcp_filter(struct sock *sk, struct sk_buff *skb); void tcp_set_state(struct sock *sk, int state); void tcp_done(struct sock *sk); int tcp_abort(struct sock *sk, int err); static inline void tcp_sack_reset(struct tcp_options_received *rx_opt) { rx_opt->dsack = 0; rx_opt->num_sacks = 0; } void tcp_cwnd_restart(struct sock *sk, s32 delta); static inline void tcp_slow_start_after_idle_check(struct sock *sk) { const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; struct tcp_sock *tp = tcp_sk(sk); s32 delta; if (!sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle || tp->packets_out || ca_ops->cong_control) return; delta = tcp_jiffies32 - tp->lsndtime; if (delta > inet_csk(sk)->icsk_rto) tcp_cwnd_restart(sk, delta); } /* Determine a window scaling and initial window to offer. */ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, __u32 *rcv_wnd, __u32 *window_clamp, int wscale_ok, __u8 *rcv_wscale, __u32 init_rcv_wnd); static inline int tcp_win_from_space(const struct sock *sk, int space) { int tcp_adv_win_scale = sock_net(sk)->ipv4.sysctl_tcp_adv_win_scale; return tcp_adv_win_scale <= 0 ? (space>>(-tcp_adv_win_scale)) : space - (space>>tcp_adv_win_scale); } /* Note: caller must be prepared to deal with negative returns */ static inline int tcp_space(const struct sock *sk) { return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) - READ_ONCE(sk->sk_backlog.len) - atomic_read(&sk->sk_rmem_alloc)); } static inline int tcp_full_space(const struct sock *sk) { return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf)); } void tcp_cleanup_rbuf(struct sock *sk, int copied); /* We provision sk_rcvbuf around 200% of sk_rcvlowat. * If 87.5 % (7/8) of the space has been consumed, we want to override * SO_RCVLOWAT constraint, since we are receiving skbs with too small * len/truesize ratio. */ static inline bool tcp_rmem_pressure(const struct sock *sk) { int rcvbuf, threshold; if (tcp_under_memory_pressure(sk)) return true; rcvbuf = READ_ONCE(sk->sk_rcvbuf); threshold = rcvbuf - (rcvbuf >> 3); return atomic_read(&sk->sk_rmem_alloc) > threshold; } extern void tcp_openreq_init_rwin(struct request_sock *req, const struct sock *sk_listener, const struct dst_entry *dst); void tcp_enter_memory_pressure(struct sock *sk); void tcp_leave_memory_pressure(struct sock *sk); static inline int keepalive_intvl_when(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); return tp->keepalive_intvl ? : net->ipv4.sysctl_tcp_keepalive_intvl; } static inline int keepalive_time_when(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); return tp->keepalive_time ? : net->ipv4.sysctl_tcp_keepalive_time; } static inline int keepalive_probes(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); return tp->keepalive_probes ? : net->ipv4.sysctl_tcp_keepalive_probes; } static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp) { const struct inet_connection_sock *icsk = &tp->inet_conn; return min_t(u32, tcp_jiffies32 - icsk->icsk_ack.lrcvtime, tcp_jiffies32 - tp->rcv_tstamp); } static inline int tcp_fin_time(const struct sock *sk) { int fin_timeout = tcp_sk(sk)->linger2 ? : sock_net(sk)->ipv4.sysctl_tcp_fin_timeout; const int rto = inet_csk(sk)->icsk_rto; if (fin_timeout < (rto << 2) - (rto >> 1)) fin_timeout = (rto << 2) - (rto >> 1); return fin_timeout; } static inline bool tcp_paws_check(const struct tcp_options_received *rx_opt, int paws_win) { if ((s32)(rx_opt->ts_recent - rx_opt->rcv_tsval) <= paws_win) return true; if (unlikely(!time_before32(ktime_get_seconds(), rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS))) return true; /* * Some OSes send SYN and SYNACK messages with tsval=0 tsecr=0, * then following tcp messages have valid values. Ignore 0 value, * or else 'negative' tsval might forbid us to accept their packets. */ if (!rx_opt->ts_recent) return true; return false; } static inline bool tcp_paws_reject(const struct tcp_options_received *rx_opt, int rst) { if (tcp_paws_check(rx_opt, 0)) return false; /* RST segments are not recommended to carry timestamp, and, if they do, it is recommended to ignore PAWS because "their cleanup function should take precedence over timestamps." Certainly, it is mistake. It is necessary to understand the reasons of this constraint to relax it: if peer reboots, clock may go out-of-sync and half-open connections will not be reset. Actually, the problem would be not existing if all the implementations followed draft about maintaining clock via reboots. Linux-2.2 DOES NOT! However, we can relax time bounds for RST segments to MSL. */ if (rst && !time_before32(ktime_get_seconds(), rx_opt->ts_recent_stamp + TCP_PAWS_MSL)) return false; return true; } bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb, int mib_idx, u32 *last_oow_ack_time); static inline void tcp_mib_init(struct net *net) { /* See RFC 2012 */ TCP_ADD_STATS(net, TCP_MIB_RTOALGORITHM, 1); TCP_ADD_STATS(net, TCP_MIB_RTOMIN, TCP_RTO_MIN*1000/HZ); TCP_ADD_STATS(net, TCP_MIB_RTOMAX, TCP_RTO_MAX*1000/HZ); TCP_ADD_STATS(net, TCP_MIB_MAXCONN, -1); } /* from STCP */ static inline void tcp_clear_retrans_hints_partial(struct tcp_sock *tp) { tp->lost_skb_hint = NULL; } static inline void tcp_clear_all_retrans_hints(struct tcp_sock *tp) { tcp_clear_retrans_hints_partial(tp); tp->retransmit_skb_hint = NULL; } union tcp_md5_addr { struct in_addr a4; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr a6; #endif }; /* - key database */ struct tcp_md5sig_key { struct hlist_node node; u8 keylen; u8 family; /* AF_INET or AF_INET6 */ u8 prefixlen; union tcp_md5_addr addr; int l3index; /* set if key added with L3 scope */ u8 key[TCP_MD5SIG_MAXKEYLEN]; struct rcu_head rcu; }; /* - sock block */ struct tcp_md5sig_info { struct hlist_head head; struct rcu_head rcu; }; /* - pseudo header */ struct tcp4_pseudohdr { __be32 saddr; __be32 daddr; __u8 pad; __u8 protocol; __be16 len; }; struct tcp6_pseudohdr { struct in6_addr saddr; struct in6_addr daddr; __be32 len; __be32 protocol; /* including padding */ }; union tcp_md5sum_block { struct tcp4_pseudohdr ip4; #if IS_ENABLED(CONFIG_IPV6) struct tcp6_pseudohdr ip6; #endif }; /* - pool: digest algorithm, hash description and scratch buffer */ struct tcp_md5sig_pool { struct ahash_request *md5_req; void *scratch; }; /* - functions */ int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, const struct sock *sk, const struct sk_buff *skb); int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, const u8 *newkey, u8 newkeylen, gfp_t gfp); int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index); struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk); #ifdef CONFIG_TCP_MD5SIG #include <linux/jump_label.h> extern struct static_key_false tcp_md5_needed; struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family); static inline struct tcp_md5sig_key * tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family) { if (!static_branch_unlikely(&tcp_md5_needed)) return NULL; return __tcp_md5_do_lookup(sk, l3index, addr, family); } #define tcp_twsk_md5_key(twsk) ((twsk)->tw_md5_key) #else static inline struct tcp_md5sig_key * tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family) { return NULL; } #define tcp_twsk_md5_key(twsk) NULL #endif bool tcp_alloc_md5sig_pool(void); struct tcp_md5sig_pool *tcp_get_md5sig_pool(void); static inline void tcp_put_md5sig_pool(void) { local_bh_enable(); } int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *, const struct sk_buff *, unsigned int header_len); int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *key); /* From tcp_fastopen.c */ void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie); void tcp_fastopen_cache_set(struct sock *sk, u16 mss, struct tcp_fastopen_cookie *cookie, bool syn_lost, u16 try_exp); struct tcp_fastopen_request { /* Fast Open cookie. Size 0 means a cookie request */ struct tcp_fastopen_cookie cookie; struct msghdr *data; /* data in MSG_FASTOPEN */ size_t size; int copied; /* queued in tcp_connect() */ struct ubuf_info *uarg; }; void tcp_free_fastopen_req(struct tcp_sock *tp); void tcp_fastopen_destroy_cipher(struct sock *sk); void tcp_fastopen_ctx_destroy(struct net *net); int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk, void *primary_key, void *backup_key); int tcp_fastopen_get_cipher(struct net *net, struct inet_connection_sock *icsk, u64 *key); void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb); struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct tcp_fastopen_cookie *foc, const struct dst_entry *dst); void tcp_fastopen_init_key_once(struct net *net); bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie); bool tcp_fastopen_defer_connect(struct sock *sk, int *err); #define TCP_FASTOPEN_KEY_LENGTH sizeof(siphash_key_t) #define TCP_FASTOPEN_KEY_MAX 2 #define TCP_FASTOPEN_KEY_BUF_LENGTH \ (TCP_FASTOPEN_KEY_LENGTH * TCP_FASTOPEN_KEY_MAX) /* Fastopen key context */ struct tcp_fastopen_context { siphash_key_t key[TCP_FASTOPEN_KEY_MAX]; int num; struct rcu_head rcu; }; extern unsigned int sysctl_tcp_fastopen_blackhole_timeout; void tcp_fastopen_active_disable(struct sock *sk); bool tcp_fastopen_active_should_disable(struct sock *sk); void tcp_fastopen_active_disable_ofo_check(struct sock *sk); void tcp_fastopen_active_detect_blackhole(struct sock *sk, bool expired); /* Caller needs to wrap with rcu_read_(un)lock() */ static inline struct tcp_fastopen_context *tcp_fastopen_get_ctx(const struct sock *sk) { struct tcp_fastopen_context *ctx; ctx = rcu_dereference(inet_csk(sk)->icsk_accept_queue.fastopenq.ctx); if (!ctx) ctx = rcu_dereference(sock_net(sk)->ipv4.tcp_fastopen_ctx); return ctx; } static inline bool tcp_fastopen_cookie_match(const struct tcp_fastopen_cookie *foc, const struct tcp_fastopen_cookie *orig) { if (orig->len == TCP_FASTOPEN_COOKIE_SIZE && orig->len == foc->len && !memcmp(orig->val, foc->val, foc->len)) return true; return false; } static inline int tcp_fastopen_context_len(const struct tcp_fastopen_context *ctx) { return ctx->num; } /* Latencies incurred by various limits for a sender. They are * chronograph-like stats that are mutually exclusive. */ enum tcp_chrono { TCP_CHRONO_UNSPEC, TCP_CHRONO_BUSY, /* Actively sending data (non-empty write queue) */ TCP_CHRONO_RWND_LIMITED, /* Stalled by insufficient receive window */ TCP_CHRONO_SNDBUF_LIMITED, /* Stalled by insufficient send buffer */ __TCP_CHRONO_MAX, }; void tcp_chrono_start(struct sock *sk, const enum tcp_chrono type); void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type); /* This helper is needed, because skb->tcp_tsorted_anchor uses * the same memory storage than skb->destructor/_skb_refdst */ static inline void tcp_skb_tsorted_anchor_cleanup(struct sk_buff *skb) { skb->destructor = NULL; skb->_skb_refdst = 0UL; } #define tcp_skb_tsorted_save(skb) { \ unsigned long _save = skb->_skb_refdst; \ skb->_skb_refdst = 0UL; #define tcp_skb_tsorted_restore(skb) \ skb->_skb_refdst = _save; \ } void tcp_write_queue_purge(struct sock *sk); static inline struct sk_buff *tcp_rtx_queue_head(const struct sock *sk) { return skb_rb_first(&sk->tcp_rtx_queue); } static inline struct sk_buff *tcp_rtx_queue_tail(const struct sock *sk) { return skb_rb_last(&sk->tcp_rtx_queue); } static inline struct sk_buff *tcp_write_queue_head(const struct sock *sk) { return skb_peek(&sk->sk_write_queue); } static inline struct sk_buff *tcp_write_queue_tail(const struct sock *sk) { return skb_peek_tail(&sk->sk_write_queue); } #define tcp_for_write_queue_from_safe(skb, tmp, sk) \ skb_queue_walk_from_safe(&(sk)->sk_write_queue, skb, tmp) static inline struct sk_buff *tcp_send_head(const struct sock *sk) { return skb_peek(&sk->sk_write_queue); } static inline bool tcp_skb_is_last(const struct sock *sk, const struct sk_buff *skb) { return skb_queue_is_last(&sk->sk_write_queue, skb); } /** * tcp_write_queue_empty - test if any payload (or FIN) is available in write queue * @sk: socket * * Since the write queue can have a temporary empty skb in it, * we must not use "return skb_queue_empty(&sk->sk_write_queue)" */ static inline bool tcp_write_queue_empty(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); return tp->write_seq == tp->snd_nxt; } static inline bool tcp_rtx_queue_empty(const struct sock *sk) { return RB_EMPTY_ROOT(&sk->tcp_rtx_queue); } static inline bool tcp_rtx_and_write_queues_empty(const struct sock *sk) { return tcp_rtx_queue_empty(sk) && tcp_write_queue_empty(sk); } static inline void tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb) { __skb_queue_tail(&sk->sk_write_queue, skb); /* Queue it, remembering where we must start sending. */ if (sk->sk_write_queue.next == skb) tcp_chrono_start(sk, TCP_CHRONO_BUSY); } /* Insert new before skb on the write queue of sk. */ static inline void tcp_insert_write_queue_before(struct sk_buff *new, struct sk_buff *skb, struct sock *sk) { __skb_queue_before(&sk->sk_write_queue, skb, new); } static inline void tcp_unlink_write_queue(struct sk_buff *skb, struct sock *sk) { tcp_skb_tsorted_anchor_cleanup(skb); __skb_unlink(skb, &sk->sk_write_queue); } void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb); static inline void tcp_rtx_queue_unlink(struct sk_buff *skb, struct sock *sk) { tcp_skb_tsorted_anchor_cleanup(skb); rb_erase(&skb->rbnode, &sk->tcp_rtx_queue); } static inline void tcp_rtx_queue_unlink_and_free(struct sk_buff *skb, struct sock *sk) { list_del(&skb->tcp_tsorted_anchor); tcp_rtx_queue_unlink(skb, sk); sk_wmem_free_skb(sk, skb); } static inline void tcp_push_pending_frames(struct sock *sk) { if (tcp_send_head(sk)) { struct tcp_sock *tp = tcp_sk(sk); __tcp_push_pending_frames(sk, tcp_current_mss(sk), tp->nonagle); } } /* Start sequence of the skb just after the highest skb with SACKed * bit, valid only if sacked_out > 0 or when the caller has ensured * validity by itself. */ static inline u32 tcp_highest_sack_seq(struct tcp_sock *tp) { if (!tp->sacked_out) return tp->snd_una; if (tp->highest_sack == NULL) return tp->snd_nxt; return TCP_SKB_CB(tp->highest_sack)->seq; } static inline void tcp_advance_highest_sack(struct sock *sk, struct sk_buff *skb) { tcp_sk(sk)->highest_sack = skb_rb_next(skb); } static inline struct sk_buff *tcp_highest_sack(struct sock *sk) { return tcp_sk(sk)->highest_sack; } static inline void tcp_highest_sack_reset(struct sock *sk) { tcp_sk(sk)->highest_sack = tcp_rtx_queue_head(sk); } /* Called when old skb is about to be deleted and replaced by new skb */ static inline void tcp_highest_sack_replace(struct sock *sk, struct sk_buff *old, struct sk_buff *new) { if (old == tcp_highest_sack(sk)) tcp_sk(sk)->highest_sack = new; } /* This helper checks if socket has IP_TRANSPARENT set */ static inline bool inet_sk_transparent(const struct sock *sk) { switch (sk->sk_state) { case TCP_TIME_WAIT: return inet_twsk(sk)->tw_transparent; case TCP_NEW_SYN_RECV: return inet_rsk(inet_reqsk(sk))->no_srccheck; } return inet_sk(sk)->transparent; } /* Determines whether this is a thin stream (which may suffer from * increased latency). Used to trigger latency-reducing mechanisms. */ static inline bool tcp_stream_is_thin(struct tcp_sock *tp) { return tp->packets_out < 4 && !tcp_in_initial_slowstart(tp); } /* /proc */ enum tcp_seq_states { TCP_SEQ_STATE_LISTENING, TCP_SEQ_STATE_ESTABLISHED, }; void *tcp_seq_start(struct seq_file *seq, loff_t *pos); void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos); void tcp_seq_stop(struct seq_file *seq, void *v); struct tcp_seq_afinfo { sa_family_t family; }; struct tcp_iter_state { struct seq_net_private p; enum tcp_seq_states state; struct sock *syn_wait_sk; struct tcp_seq_afinfo *bpf_seq_afinfo; int bucket, offset, sbucket, num; loff_t last_pos; }; extern struct request_sock_ops tcp_request_sock_ops; extern struct request_sock_ops tcp6_request_sock_ops; void tcp_v4_destroy_sock(struct sock *sk); struct sk_buff *tcp_gso_segment(struct sk_buff *skb, netdev_features_t features); struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb); INDIRECT_CALLABLE_DECLARE(int tcp4_gro_complete(struct sk_buff *skb, int thoff)); INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb)); INDIRECT_CALLABLE_DECLARE(int tcp6_gro_complete(struct sk_buff *skb, int thoff)); INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb)); int tcp_gro_complete(struct sk_buff *skb); void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr); static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); return tp->notsent_lowat ?: net->ipv4.sysctl_tcp_notsent_lowat; } /* @wake is one when sk_stream_write_space() calls us. * This sends EPOLLOUT only if notsent_bytes is half the limit. * This mimics the strategy used in sock_def_write_space(). */ static inline bool tcp_stream_memory_free(const struct sock *sk, int wake) { const struct tcp_sock *tp = tcp_sk(sk); u32 notsent_bytes = READ_ONCE(tp->write_seq) - READ_ONCE(tp->snd_nxt); return (notsent_bytes << wake) < tcp_notsent_lowat(tp); } #ifdef CONFIG_PROC_FS int tcp4_proc_init(void); void tcp4_proc_exit(void); #endif int tcp_rtx_synack(const struct sock *sk, struct request_sock *req); int tcp_conn_request(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb); /* TCP af-specific functions */ struct tcp_sock_af_ops { #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *(*md5_lookup) (const struct sock *sk, const struct sock *addr_sk); int (*calc_md5_hash)(char *location, const struct tcp_md5sig_key *md5, const struct sock *sk, const struct sk_buff *skb); int (*md5_parse)(struct sock *sk, int optname, sockptr_t optval, int optlen); #endif }; struct tcp_request_sock_ops { u16 mss_clamp; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *(*req_md5_lookup)(const struct sock *sk, const struct sock *addr_sk); int (*calc_md5_hash) (char *location, const struct tcp_md5sig_key *md5, const struct sock *sk, const struct sk_buff *skb); #endif void (*init_req)(struct request_sock *req, const struct sock *sk_listener, struct sk_buff *skb); #ifdef CONFIG_SYN_COOKIES __u32 (*cookie_init_seq)(const struct sk_buff *skb, __u16 *mss); #endif struct dst_entry *(*route_req)(const struct sock *sk, struct flowi *fl, const struct request_sock *req); u32 (*init_seq)(const struct sk_buff *skb); u32 (*init_ts_off)(const struct net *net, const struct sk_buff *skb); int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb); }; extern const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops; #if IS_ENABLED(CONFIG_IPV6) extern const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops; #endif #ifdef CONFIG_SYN_COOKIES static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops, const struct sock *sk, struct sk_buff *skb, __u16 *mss) { tcp_synq_overflow(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT); return ops->cookie_init_seq(skb, mss); } #else static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops, const struct sock *sk, struct sk_buff *skb, __u16 *mss) { return 0; } #endif int tcpv4_offload_init(void); void tcp_v4_init(void); void tcp_init(void); /* tcp_recovery.c */ void tcp_mark_skb_lost(struct sock *sk, struct sk_buff *skb); void tcp_newreno_mark_lost(struct sock *sk, bool snd_una_advanced); extern s32 tcp_rack_skb_timeout(struct tcp_sock *tp, struct sk_buff *skb, u32 reo_wnd); extern bool tcp_rack_mark_lost(struct sock *sk); extern void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq, u64 xmit_time); extern void tcp_rack_reo_timeout(struct sock *sk); extern void tcp_rack_update_reo_wnd(struct sock *sk, struct rate_sample *rs); /* At how many usecs into the future should the RTO fire? */ static inline s64 tcp_rto_delta_us(const struct sock *sk) { const struct sk_buff *skb = tcp_rtx_queue_head(sk); u32 rto = inet_csk(sk)->icsk_rto; u64 rto_time_stamp_us = tcp_skb_timestamp_us(skb) + jiffies_to_usecs(rto); return rto_time_stamp_us - tcp_sk(sk)->tcp_mstamp; } /* * Save and compile IPv4 options, return a pointer to it */ static inline struct ip_options_rcu *tcp_v4_save_options(struct net *net, struct sk_buff *skb) { const struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt; struct ip_options_rcu *dopt = NULL; if (opt->optlen) { int opt_size = sizeof(*dopt) + opt->optlen; dopt = kmalloc(opt_size, GFP_ATOMIC); if (dopt && __ip_options_echo(net, &dopt->opt, skb, opt)) { kfree(dopt); dopt = NULL; } } return dopt; } /* locally generated TCP pure ACKs have skb->truesize == 2 * (check tcp_send_ack() in net/ipv4/tcp_output.c ) * This is much faster than dissecting the packet to find out. * (Think of GRE encapsulations, IPv4, IPv6, ...) */ static inline bool skb_is_tcp_pure_ack(const struct sk_buff *skb) { return skb->truesize == 2; } static inline void skb_set_tcp_pure_ack(struct sk_buff *skb) { skb->truesize = 2; } static inline int tcp_inq(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); int answ; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { answ = 0; } else if (sock_flag(sk, SOCK_URGINLINE) || !tp->urg_data || before(tp->urg_seq, tp->copied_seq) || !before(tp->urg_seq, tp->rcv_nxt)) { answ = tp->rcv_nxt - tp->copied_seq; /* Subtract 1, if FIN was received */ if (answ && sock_flag(sk, SOCK_DONE)) answ--; } else { answ = tp->urg_seq - tp->copied_seq; } return answ; } int tcp_peek_len(struct socket *sock); static inline void tcp_segs_in(struct tcp_sock *tp, const struct sk_buff *skb) { u16 segs_in; segs_in = max_t(u16, 1, skb_shinfo(skb)->gso_segs); tp->segs_in += segs_in; if (skb->len > tcp_hdrlen(skb)) tp->data_segs_in += segs_in; } /* * TCP listen path runs lockless. * We forced "struct sock" to be const qualified to make sure * we don't modify one of its field by mistake. * Here, we increment sk_drops which is an atomic_t, so we can safely * make sock writable again. */ static inline void tcp_listendrop(const struct sock *sk) { atomic_inc(&((struct sock *)sk)->sk_drops); __NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENDROPS); } enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer); /* * Interface for adding Upper Level Protocols over TCP */ #define TCP_ULP_NAME_MAX 16 #define TCP_ULP_MAX 128 #define TCP_ULP_BUF_MAX (TCP_ULP_NAME_MAX*TCP_ULP_MAX) struct tcp_ulp_ops { struct list_head list; /* initialize ulp */ int (*init)(struct sock *sk); /* update ulp */ void (*update)(struct sock *sk, struct proto *p, void (*write_space)(struct sock *sk)); /* cleanup ulp */ void (*release)(struct sock *sk); /* diagnostic */ int (*get_info)(const struct sock *sk, struct sk_buff *skb); size_t (*get_info_size)(const struct sock *sk); /* clone ulp */ void (*clone)(const struct request_sock *req, struct sock *newsk, const gfp_t priority); char name[TCP_ULP_NAME_MAX]; struct module *owner; }; int tcp_register_ulp(struct tcp_ulp_ops *type); void tcp_unregister_ulp(struct tcp_ulp_ops *type); int tcp_set_ulp(struct sock *sk, const char *name); void tcp_get_available_ulp(char *buf, size_t len); void tcp_cleanup_ulp(struct sock *sk); void tcp_update_ulp(struct sock *sk, struct proto *p, void (*write_space)(struct sock *sk)); #define MODULE_ALIAS_TCP_ULP(name) \ __MODULE_INFO(alias, alias_userspace, name); \ __MODULE_INFO(alias, alias_tcp_ulp, "tcp-ulp-" name) struct sk_msg; struct sk_psock; #ifdef CONFIG_BPF_STREAM_PARSER struct proto *tcp_bpf_get_proto(struct sock *sk, struct sk_psock *psock); void tcp_bpf_clone(const struct sock *sk, struct sock *newsk); #else static inline void tcp_bpf_clone(const struct sock *sk, struct sock *newsk) { } #endif /* CONFIG_BPF_STREAM_PARSER */ #ifdef CONFIG_NET_SOCK_MSG int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, u32 bytes, int flags); int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags); #endif /* CONFIG_NET_SOCK_MSG */ #ifdef CONFIG_CGROUP_BPF static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, struct sk_buff *skb, unsigned int end_offset) { skops->skb = skb; skops->skb_data_end = skb->data + end_offset; } #else static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, struct sk_buff *skb, unsigned int end_offset) { } #endif /* Call BPF_SOCK_OPS program that returns an int. If the return value * is < 0, then the BPF op failed (for example if the loaded BPF * program does not support the chosen operation or there is no BPF * program loaded). */ #ifdef CONFIG_BPF static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args) { struct bpf_sock_ops_kern sock_ops; int ret; memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); if (sk_fullsock(sk)) { sock_ops.is_fullsock = 1; sock_owned_by_me(sk); } sock_ops.sk = sk; sock_ops.op = op; if (nargs > 0) memcpy(sock_ops.args, args, nargs * sizeof(*args)); ret = BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops); if (ret == 0) ret = sock_ops.reply; else ret = -1; return ret; } static inline int tcp_call_bpf_2arg(struct sock *sk, int op, u32 arg1, u32 arg2) { u32 args[2] = {arg1, arg2}; return tcp_call_bpf(sk, op, 2, args); } static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2, u32 arg3) { u32 args[3] = {arg1, arg2, arg3}; return tcp_call_bpf(sk, op, 3, args); } #else static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args) { return -EPERM; } static inline int tcp_call_bpf_2arg(struct sock *sk, int op, u32 arg1, u32 arg2) { return -EPERM; } static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2, u32 arg3) { return -EPERM; } #endif static inline u32 tcp_timeout_init(struct sock *sk) { int timeout; timeout = tcp_call_bpf(sk, BPF_SOCK_OPS_TIMEOUT_INIT, 0, NULL); if (timeout <= 0) timeout = TCP_TIMEOUT_INIT; return timeout; } static inline u32 tcp_rwnd_init_bpf(struct sock *sk) { int rwnd; rwnd = tcp_call_bpf(sk, BPF_SOCK_OPS_RWND_INIT, 0, NULL); if (rwnd < 0) rwnd = 0; return rwnd; } static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk) { return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN, 0, NULL) == 1); } static inline void tcp_bpf_rtt(struct sock *sk) { if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_RTT_CB_FLAG)) tcp_call_bpf(sk, BPF_SOCK_OPS_RTT_CB, 0, NULL); } #if IS_ENABLED(CONFIG_SMC) extern struct static_key_false tcp_have_smc; #endif #if IS_ENABLED(CONFIG_TLS_DEVICE) void clean_acked_data_enable(struct inet_connection_sock *icsk, void (*cad)(struct sock *sk, u32 ack_seq)); void clean_acked_data_disable(struct inet_connection_sock *icsk); void clean_acked_data_flush(void); #endif DECLARE_STATIC_KEY_FALSE(tcp_tx_delay_enabled); static inline void tcp_add_tx_delay(struct sk_buff *skb, const struct tcp_sock *tp) { if (static_branch_unlikely(&tcp_tx_delay_enabled)) skb->skb_mstamp_ns += (u64)tp->tcp_tx_delay * NSEC_PER_USEC; } /* Compute Earliest Departure Time for some control packets * like ACK or RST for TIME_WAIT or non ESTABLISHED sockets. */ static inline u64 tcp_transmit_time(const struct sock *sk) { if (static_branch_unlikely(&tcp_tx_delay_enabled)) { u32 delay = (sk->sk_state == TCP_TIME_WAIT) ? tcp_twsk(sk)->tw_tx_delay : tcp_sk(sk)->tcp_tx_delay; return tcp_clock_ns() + (u64)delay * NSEC_PER_USEC; } return 0; } #endif /* _TCP_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 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* user-type.h: User-defined key type * * Copyright (C) 2005 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef _KEYS_USER_TYPE_H #define _KEYS_USER_TYPE_H #include <linux/key.h> #include <linux/rcupdate.h> #ifdef CONFIG_KEYS /*****************************************************************************/ /* * the payload for a key of type "user" or "logon" * - once filled in and attached to a key: * - the payload struct is invariant may not be changed, only replaced * - the payload must be read with RCU procedures or with the key semaphore * held * - the payload may only be replaced with the key semaphore write-locked * - the key's data length is the size of the actual data, not including the * payload wrapper */ struct user_key_payload { struct rcu_head rcu; /* RCU destructor */ unsigned short datalen; /* length of this data */ char data[] __aligned(__alignof__(u64)); /* actual data */ }; extern struct key_type key_type_user; extern struct key_type key_type_logon; struct key_preparsed_payload; extern int user_preparse(struct key_preparsed_payload *prep); extern void user_free_preparse(struct key_preparsed_payload *prep); extern int user_update(struct key *key, struct key_preparsed_payload *prep); extern void user_revoke(struct key *key); extern void user_destroy(struct key *key); extern void user_describe(const struct key *user, struct seq_file *m); extern long user_read(const struct key *key, char *buffer, size_t buflen); static inline const struct user_key_payload *user_key_payload_rcu(const struct key *key) { return (struct user_key_payload *)dereference_key_rcu(key); } static inline struct user_key_payload *user_key_payload_locked(const struct key *key) { return (struct user_key_payload *)dereference_key_locked((struct key *)key); } #endif /* CONFIG_KEYS */ #endif /* _KEYS_USER_TYPE_H */
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 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 // SPDX-License-Identifier: GPL-2.0-only #include <crypto/hash.h> #include <linux/export.h> #include <linux/bvec.h> #include <linux/fault-inject-usercopy.h> #include <linux/uio.h> #include <linux/pagemap.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/splice.h> #include <linux/compat.h> #include <net/checksum.h> #include <linux/scatterlist.h> #include <linux/instrumented.h> #define PIPE_PARANOIA /* for now */ #define iterate_iovec(i, n, __v, __p, skip, STEP) { \ size_t left; \ size_t wanted = n; \ __p = i->iov; \ __v.iov_len = min(n, __p->iov_len - skip); \ if (likely(__v.iov_len)) { \ __v.iov_base = __p->iov_base + skip; \ left = (STEP); \ __v.iov_len -= left; \ skip += __v.iov_len; \ n -= __v.iov_len; \ } else { \ left = 0; \ } \ while (unlikely(!left && n)) { \ __p++; \ __v.iov_len = min(n, __p->iov_len); \ if (unlikely(!__v.iov_len)) \ continue; \ __v.iov_base = __p->iov_base; \ left = (STEP); \ __v.iov_len -= left; \ skip = __v.iov_len; \ n -= __v.iov_len; \ } \ n = wanted - n; \ } #define iterate_kvec(i, n, __v, __p, skip, STEP) { \ size_t wanted = n; \ __p = i->kvec; \ __v.iov_len = min(n, __p->iov_len - skip); \ if (likely(__v.iov_len)) { \ __v.iov_base = __p->iov_base + skip; \ (void)(STEP); \ skip += __v.iov_len; \ n -= __v.iov_len; \ } \ while (unlikely(n)) { \ __p++; \ __v.iov_len = min(n, __p->iov_len); \ if (unlikely(!__v.iov_len)) \ continue; \ __v.iov_base = __p->iov_base; \ (void)(STEP); \ skip = __v.iov_len; \ n -= __v.iov_len; \ } \ n = wanted; \ } #define iterate_bvec(i, n, __v, __bi, skip, STEP) { \ struct bvec_iter __start; \ __start.bi_size = n; \ __start.bi_bvec_done = skip; \ __start.bi_idx = 0; \ for_each_bvec(__v, i->bvec, __bi, __start) { \ if (!__v.bv_len) \ continue; \ (void)(STEP); \ } \ } #define iterate_all_kinds(i, n, v, I, B, K) { \ if (likely(n)) { \ size_t skip = i->iov_offset; \ if (unlikely(i->type & ITER_BVEC)) { \ struct bio_vec v; \ struct bvec_iter __bi; \ iterate_bvec(i, n, v, __bi, skip, (B)) \ } else if (unlikely(i->type & ITER_KVEC)) { \ const struct kvec *kvec; \ struct kvec v; \ iterate_kvec(i, n, v, kvec, skip, (K)) \ } else if (unlikely(i->type & ITER_DISCARD)) { \ } else { \ const struct iovec *iov; \ struct iovec v; \ iterate_iovec(i, n, v, iov, skip, (I)) \ } \ } \ } #define iterate_and_advance(i, n, v, I, B, K) { \ if (unlikely(i->count < n)) \ n = i->count; \ if (i->count) { \ size_t skip = i->iov_offset; \ if (unlikely(i->type & ITER_BVEC)) { \ const struct bio_vec *bvec = i->bvec; \ struct bio_vec v; \ struct bvec_iter __bi; \ iterate_bvec(i, n, v, __bi, skip, (B)) \ i->bvec = __bvec_iter_bvec(i->bvec, __bi); \ i->nr_segs -= i->bvec - bvec; \ skip = __bi.bi_bvec_done; \ } else if (unlikely(i->type & ITER_KVEC)) { \ const struct kvec *kvec; \ struct kvec v; \ iterate_kvec(i, n, v, kvec, skip, (K)) \ if (skip == kvec->iov_len) { \ kvec++; \ skip = 0; \ } \ i->nr_segs -= kvec - i->kvec; \ i->kvec = kvec; \ } else if (unlikely(i->type & ITER_DISCARD)) { \ skip += n; \ } else { \ const struct iovec *iov; \ struct iovec v; \ iterate_iovec(i, n, v, iov, skip, (I)) \ if (skip == iov->iov_len) { \ iov++; \ skip = 0; \ } \ i->nr_segs -= iov - i->iov; \ i->iov = iov; \ } \ i->count -= n; \ i->iov_offset = skip; \ } \ } static int copyout(void __user *to, const void *from, size_t n) { if (should_fail_usercopy()) return n; if (access_ok(to, n)) { instrument_copy_to_user(to, from, n); n = raw_copy_to_user(to, from, n); } return n; } static int copyin(void *to, const void __user *from, size_t n) { if (should_fail_usercopy()) return n; if (access_ok(from, n)) { instrument_copy_from_user(to, from, n); n = raw_copy_from_user(to, from, n); } return n; } static size_t copy_page_to_iter_iovec(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { size_t skip, copy, left, wanted; const struct iovec *iov; char __user *buf; void *kaddr, *from; if (unlikely(bytes > i->count)) bytes = i->count; if (unlikely(!bytes)) return 0; might_fault(); wanted = bytes; iov = i->iov; skip = i->iov_offset; buf = iov->iov_base + skip; copy = min(bytes, iov->iov_len - skip); if (IS_ENABLED(CONFIG_HIGHMEM) && !fault_in_pages_writeable(buf, copy)) { kaddr = kmap_atomic(page); from = kaddr + offset; /* first chunk, usually the only one */ left = copyout(buf, from, copy); copy -= left; skip += copy; from += copy; bytes -= copy; while (unlikely(!left && bytes)) { iov++; buf = iov->iov_base; copy = min(bytes, iov->iov_len); left = copyout(buf, from, copy); copy -= left; skip = copy; from += copy; bytes -= copy; } if (likely(!bytes)) { kunmap_atomic(kaddr); goto done; } offset = from - kaddr; buf += copy; kunmap_atomic(kaddr); copy = min(bytes, iov->iov_len - skip); } /* Too bad - revert to non-atomic kmap */ kaddr = kmap(page); from = kaddr + offset; left = copyout(buf, from, copy); copy -= left; skip += copy; from += copy; bytes -= copy; while (unlikely(!left && bytes)) { iov++; buf = iov->iov_base; copy = min(bytes, iov->iov_len); left = copyout(buf, from, copy); copy -= left; skip = copy; from += copy; bytes -= copy; } kunmap(page); done: if (skip == iov->iov_len) { iov++; skip = 0; } i->count -= wanted - bytes; i->nr_segs -= iov - i->iov; i->iov = iov; i->iov_offset = skip; return wanted - bytes; } static size_t copy_page_from_iter_iovec(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { size_t skip, copy, left, wanted; const struct iovec *iov; char __user *buf; void *kaddr, *to; if (unlikely(bytes > i->count)) bytes = i->count; if (unlikely(!bytes)) return 0; might_fault(); wanted = bytes; iov = i->iov; skip = i->iov_offset; buf = iov->iov_base + skip; copy = min(bytes, iov->iov_len - skip); if (IS_ENABLED(CONFIG_HIGHMEM) && !fault_in_pages_readable(buf, copy)) { kaddr = kmap_atomic(page); to = kaddr + offset; /* first chunk, usually the only one */ left = copyin(to, buf, copy); copy -= left; skip += copy; to += copy; bytes -= copy; while (unlikely(!left && bytes)) { iov++; buf = iov->iov_base; copy = min(bytes, iov->iov_len); left = copyin(to, buf, copy); copy -= left; skip = copy; to += copy; bytes -= copy; } if (likely(!bytes)) { kunmap_atomic(kaddr); goto done; } offset = to - kaddr; buf += copy; kunmap_atomic(kaddr); copy = min(bytes, iov->iov_len - skip); } /* Too bad - revert to non-atomic kmap */ kaddr = kmap(page); to = kaddr + offset; left = copyin(to, buf, copy); copy -= left; skip += copy; to += copy; bytes -= copy; while (unlikely(!left && bytes)) { iov++; buf = iov->iov_base; copy = min(bytes, iov->iov_len); left = copyin(to, buf, copy); copy -= left; skip = copy; to += copy; bytes -= copy; } kunmap(page); done: if (skip == iov->iov_len) { iov++; skip = 0; } i->count -= wanted - bytes; i->nr_segs -= iov - i->iov; i->iov = iov; i->iov_offset = skip; return wanted - bytes; } #ifdef PIPE_PARANOIA static bool sanity(const struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; unsigned int p_head = pipe->head; unsigned int p_tail = pipe->tail; unsigned int p_mask = pipe->ring_size - 1; unsigned int p_occupancy = pipe_occupancy(p_head, p_tail); unsigned int i_head = i->head; unsigned int idx; if (i->iov_offset) { struct pipe_buffer *p; if (unlikely(p_occupancy == 0)) goto Bad; // pipe must be non-empty if (unlikely(i_head != p_head - 1)) goto Bad; // must be at the last buffer... p = &pipe->bufs[i_head & p_mask]; if (unlikely(p->offset + p->len != i->iov_offset)) goto Bad; // ... at the end of segment } else { if (i_head != p_head) goto Bad; // must be right after the last buffer } return true; Bad: printk(KERN_ERR "idx = %d, offset = %zd\n", i_head, i->iov_offset); printk(KERN_ERR "head = %d, tail = %d, buffers = %d\n", p_head, p_tail, pipe->ring_size); for (idx = 0; idx < pipe->ring_size; idx++) printk(KERN_ERR "[%p %p %d %d]\n", pipe->bufs[idx].ops, pipe->bufs[idx].page, pipe->bufs[idx].offset, pipe->bufs[idx].len); WARN_ON(1); return false; } #else #define sanity(i) true #endif static size_t copy_page_to_iter_pipe(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; struct pipe_buffer *buf; unsigned int p_tail = pipe->tail; unsigned int p_mask = pipe->ring_size - 1; unsigned int i_head = i->head; size_t off; if (unlikely(bytes > i->count)) bytes = i->count; if (unlikely(!bytes)) return 0; if (!sanity(i)) return 0; off = i->iov_offset; buf = &pipe->bufs[i_head & p_mask]; if (off) { if (offset == off && buf->page == page) { /* merge with the last one */ buf->len += bytes; i->iov_offset += bytes; goto out; } i_head++; buf = &pipe->bufs[i_head & p_mask]; } if (pipe_full(i_head, p_tail, pipe->max_usage)) return 0; buf->ops = &page_cache_pipe_buf_ops; get_page(page); buf->page = page; buf->offset = offset; buf->len = bytes; pipe->head = i_head + 1; i->iov_offset = offset + bytes; i->head = i_head; out: i->count -= bytes; return bytes; } /* * Fault in one or more iovecs of the given iov_iter, to a maximum length of * bytes. For each iovec, fault in each page that constitutes the iovec. * * Return 0 on success, or non-zero if the memory could not be accessed (i.e. * because it is an invalid address). */ int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes) { size_t skip = i->iov_offset; const struct iovec *iov; int err; struct iovec v; if (iter_is_iovec(i)) { iterate_iovec(i, bytes, v, iov, skip, ({ err = fault_in_pages_readable(v.iov_base, v.iov_len); if (unlikely(err)) return err; 0;})) } return 0; } EXPORT_SYMBOL(iov_iter_fault_in_readable); void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov, unsigned long nr_segs, size_t count) { WARN_ON(direction & ~(READ | WRITE)); direction &= READ | WRITE; /* It will get better. Eventually... */ if (uaccess_kernel()) { i->type = ITER_KVEC | direction; i->kvec = (struct kvec *)iov; } else { i->type = ITER_IOVEC | direction; i->iov = iov; } i->nr_segs = nr_segs; i->iov_offset = 0; i->count = count; } EXPORT_SYMBOL(iov_iter_init); static void memcpy_from_page(char *to, struct page *page, size_t offset, size_t len) { char *from = kmap_atomic(page); memcpy(to, from + offset, len); kunmap_atomic(from); } static void memcpy_to_page(struct page *page, size_t offset, const char *from, size_t len) { char *to = kmap_atomic(page); memcpy(to + offset, from, len); kunmap_atomic(to); } static void memzero_page(struct page *page, size_t offset, size_t len) { char *addr = kmap_atomic(page); memset(addr + offset, 0, len); kunmap_atomic(addr); } static inline bool allocated(struct pipe_buffer *buf) { return buf->ops == &default_pipe_buf_ops; } static inline void data_start(const struct iov_iter *i, unsigned int *iter_headp, size_t *offp) { unsigned int p_mask = i->pipe->ring_size - 1; unsigned int iter_head = i->head; size_t off = i->iov_offset; if (off && (!allocated(&i->pipe->bufs[iter_head & p_mask]) || off == PAGE_SIZE)) { iter_head++; off = 0; } *iter_headp = iter_head; *offp = off; } static size_t push_pipe(struct iov_iter *i, size_t size, int *iter_headp, size_t *offp) { struct pipe_inode_info *pipe = i->pipe; unsigned int p_tail = pipe->tail; unsigned int p_mask = pipe->ring_size - 1; unsigned int iter_head; size_t off; ssize_t left; if (unlikely(size > i->count)) size = i->count; if (unlikely(!size)) return 0; left = size; data_start(i, &iter_head, &off); *iter_headp = iter_head; *offp = off; if (off) { left -= PAGE_SIZE - off; if (left <= 0) { pipe->bufs[iter_head & p_mask].len += size; return size; } pipe->bufs[iter_head & p_mask].len = PAGE_SIZE; iter_head++; } while (!pipe_full(iter_head, p_tail, pipe->max_usage)) { struct pipe_buffer *buf = &pipe->bufs[iter_head & p_mask]; struct page *page = alloc_page(GFP_USER); if (!page) break; buf->ops = &default_pipe_buf_ops; buf->page = page; buf->offset = 0; buf->len = min_t(ssize_t, left, PAGE_SIZE); left -= buf->len; iter_head++; pipe->head = iter_head; if (left == 0) return size; } return size - left; } static size_t copy_pipe_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; unsigned int p_mask = pipe->ring_size - 1; unsigned int i_head; size_t n, off; if (!sanity(i)) return 0; bytes = n = push_pipe(i, bytes, &i_head, &off); if (unlikely(!n)) return 0; do { size_t chunk = min_t(size_t, n, PAGE_SIZE - off); memcpy_to_page(pipe->bufs[i_head & p_mask].page, off, addr, chunk); i->head = i_head; i->iov_offset = off + chunk; n -= chunk; addr += chunk; off = 0; i_head++; } while (n); i->count -= bytes; return bytes; } static __wsum csum_and_memcpy(void *to, const void *from, size_t len, __wsum sum, size_t off) { __wsum next = csum_partial_copy_nocheck(from, to, len); return csum_block_add(sum, next, off); } static size_t csum_and_copy_to_pipe_iter(const void *addr, size_t bytes, struct csum_state *csstate, struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; unsigned int p_mask = pipe->ring_size - 1; __wsum sum = csstate->csum; size_t off = csstate->off; unsigned int i_head; size_t n, r; if (!sanity(i)) return 0; bytes = n = push_pipe(i, bytes, &i_head, &r); if (unlikely(!n)) return 0; do { size_t chunk = min_t(size_t, n, PAGE_SIZE - r); char *p = kmap_atomic(pipe->bufs[i_head & p_mask].page); sum = csum_and_memcpy(p + r, addr, chunk, sum, off); kunmap_atomic(p); i->head = i_head; i->iov_offset = r + chunk; n -= chunk; off += chunk; addr += chunk; r = 0; i_head++; } while (n); i->count -= bytes; csstate->csum = sum; csstate->off = off; return bytes; } size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { const char *from = addr; if (unlikely(iov_iter_is_pipe(i))) return copy_pipe_to_iter(addr, bytes, i); if (iter_is_iovec(i)) might_fault(); iterate_and_advance(i, bytes, v, copyout(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len), memcpy_to_page(v.bv_page, v.bv_offset, (from += v.bv_len) - v.bv_len, v.bv_len), memcpy(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len) ) return bytes; } EXPORT_SYMBOL(_copy_to_iter); #ifdef CONFIG_ARCH_HAS_COPY_MC static int copyout_mc(void __user *to, const void *from, size_t n) { if (access_ok(to, n)) { instrument_copy_to_user(to, from, n); n = copy_mc_to_user((__force void *) to, from, n); } return n; } static unsigned long copy_mc_to_page(struct page *page, size_t offset, const char *from, size_t len) { unsigned long ret; char *to; to = kmap_atomic(page); ret = copy_mc_to_kernel(to + offset, from, len); kunmap_atomic(to); return ret; } static size_t copy_mc_pipe_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; unsigned int p_mask = pipe->ring_size - 1; unsigned int i_head; size_t n, off, xfer = 0; if (!sanity(i)) return 0; bytes = n = push_pipe(i, bytes, &i_head, &off); if (unlikely(!n)) return 0; do { size_t chunk = min_t(size_t, n, PAGE_SIZE - off); unsigned long rem; rem = copy_mc_to_page(pipe->bufs[i_head & p_mask].page, off, addr, chunk); i->head = i_head; i->iov_offset = off + chunk - rem; xfer += chunk - rem; if (rem) break; n -= chunk; addr += chunk; off = 0; i_head++; } while (n); i->count -= xfer; return xfer; } /** * _copy_mc_to_iter - copy to iter with source memory error exception handling * @addr: source kernel address * @bytes: total transfer length * @iter: destination iterator * * The pmem driver deploys this for the dax operation * (dax_copy_to_iter()) for dax reads (bypass page-cache and the * block-layer). Upon #MC read(2) aborts and returns EIO or the bytes * successfully copied. * * The main differences between this and typical _copy_to_iter(). * * * Typical tail/residue handling after a fault retries the copy * byte-by-byte until the fault happens again. Re-triggering machine * checks is potentially fatal so the implementation uses source * alignment and poison alignment assumptions to avoid re-triggering * hardware exceptions. * * * ITER_KVEC, ITER_PIPE, and ITER_BVEC can return short copies. * Compare to copy_to_iter() where only ITER_IOVEC attempts might return * a short copy. */ size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { const char *from = addr; unsigned long rem, curr_addr, s_addr = (unsigned long) addr; if (unlikely(iov_iter_is_pipe(i))) return copy_mc_pipe_to_iter(addr, bytes, i); if (iter_is_iovec(i)) might_fault(); iterate_and_advance(i, bytes, v, copyout_mc(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len), ({ rem = copy_mc_to_page(v.bv_page, v.bv_offset, (from += v.bv_len) - v.bv_len, v.bv_len); if (rem) { curr_addr = (unsigned long) from; bytes = curr_addr - s_addr - rem; return bytes; } }), ({ rem = copy_mc_to_kernel(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len); if (rem) { curr_addr = (unsigned long) from; bytes = curr_addr - s_addr - rem; return bytes; } }) ) return bytes; } EXPORT_SYMBOL_GPL(_copy_mc_to_iter); #endif /* CONFIG_ARCH_HAS_COPY_MC */ size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return 0; } if (iter_is_iovec(i)) might_fault(); iterate_and_advance(i, bytes, v, copyin((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len), memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page, v.bv_offset, v.bv_len), memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len) ) return bytes; } EXPORT_SYMBOL(_copy_from_iter); bool _copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return false; } if (unlikely(i->count < bytes)) return false; if (iter_is_iovec(i)) might_fault(); iterate_all_kinds(i, bytes, v, ({ if (copyin((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len)) return false; 0;}), memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page, v.bv_offset, v.bv_len), memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len) ) iov_iter_advance(i, bytes); return true; } EXPORT_SYMBOL(_copy_from_iter_full); size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return 0; } iterate_and_advance(i, bytes, v, __copy_from_user_inatomic_nocache((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len), memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page, v.bv_offset, v.bv_len), memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len) ) return bytes; } EXPORT_SYMBOL(_copy_from_iter_nocache); #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE /** * _copy_from_iter_flushcache - write destination through cpu cache * @addr: destination kernel address * @bytes: total transfer length * @iter: source iterator * * The pmem driver arranges for filesystem-dax to use this facility via * dax_copy_from_iter() for ensuring that writes to persistent memory * are flushed through the CPU cache. It is differentiated from * _copy_from_iter_nocache() in that guarantees all data is flushed for * all iterator types. The _copy_from_iter_nocache() only attempts to * bypass the cache for the ITER_IOVEC case, and on some archs may use * instructions that strand dirty-data in the cache. */ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return 0; } iterate_and_advance(i, bytes, v, __copy_from_user_flushcache((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len), memcpy_page_flushcache((to += v.bv_len) - v.bv_len, v.bv_page, v.bv_offset, v.bv_len), memcpy_flushcache((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len) ) return bytes; } EXPORT_SYMBOL_GPL(_copy_from_iter_flushcache); #endif bool _copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return false; } if (unlikely(i->count < bytes)) return false; iterate_all_kinds(i, bytes, v, ({ if (__copy_from_user_inatomic_nocache((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len)) return false; 0;}), memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page, v.bv_offset, v.bv_len), memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len) ) iov_iter_advance(i, bytes); return true; } EXPORT_SYMBOL(_copy_from_iter_full_nocache); static inline bool page_copy_sane(struct page *page, size_t offset, size_t n) { struct page *head; size_t v = n + offset; /* * The general case needs to access the page order in order * to compute the page size. * However, we mostly deal with order-0 pages and thus can * avoid a possible cache line miss for requests that fit all * page orders. */ if (n <= v && v <= PAGE_SIZE) return true; head = compound_head(page); v += (page - head) << PAGE_SHIFT; if (likely(n <= v && v <= (page_size(head)))) return true; WARN_ON(1); return false; } size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { if (unlikely(!page_copy_sane(page, offset, bytes))) return 0; if (i->type & (ITER_BVEC|ITER_KVEC)) { void *kaddr = kmap_atomic(page); size_t wanted = copy_to_iter(kaddr + offset, bytes, i); kunmap_atomic(kaddr); return wanted; } else if (unlikely(iov_iter_is_discard(i))) { if (unlikely(i->count < bytes)) bytes = i->count; i->count -= bytes; return bytes; } else if (likely(!iov_iter_is_pipe(i))) return copy_page_to_iter_iovec(page, offset, bytes, i); else return copy_page_to_iter_pipe(page, offset, bytes, i); } EXPORT_SYMBOL(copy_page_to_iter); size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { if (unlikely(!page_copy_sane(page, offset, bytes))) return 0; if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) { WARN_ON(1); return 0; } if (i->type & (ITER_BVEC|ITER_KVEC)) { void *kaddr = kmap_atomic(page); size_t wanted = _copy_from_iter(kaddr + offset, bytes, i); kunmap_atomic(kaddr); return wanted; } else return copy_page_from_iter_iovec(page, offset, bytes, i); } EXPORT_SYMBOL(copy_page_from_iter); static size_t pipe_zero(size_t bytes, struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; unsigned int p_mask = pipe->ring_size - 1; unsigned int i_head; size_t n, off; if (!sanity(i)) return 0; bytes = n = push_pipe(i, bytes, &i_head, &off); if (unlikely(!n)) return 0; do { size_t chunk = min_t(size_t, n, PAGE_SIZE - off); memzero_page(pipe->bufs[i_head & p_mask].page, off, chunk); i->head = i_head; i->iov_offset = off + chunk; n -= chunk; off = 0; i_head++; } while (n); i->count -= bytes; return bytes; } size_t iov_iter_zero(size_t bytes, struct iov_iter *i) { if (unlikely(iov_iter_is_pipe(i))) return pipe_zero(bytes, i); iterate_and_advance(i, bytes, v, clear_user(v.iov_base, v.iov_len), memzero_page(v.bv_page, v.bv_offset, v.bv_len), memset(v.iov_base, 0, v.iov_len) ) return bytes; } EXPORT_SYMBOL(iov_iter_zero); size_t iov_iter_copy_from_user_atomic(struct page *page, struct iov_iter *i, unsigned long offset, size_t bytes) { char *kaddr = kmap_atomic(page), *p = kaddr + offset; if (unlikely(!page_copy_sane(page, offset, bytes))) { kunmap_atomic(kaddr); return 0; } if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) { kunmap_atomic(kaddr); WARN_ON(1); return 0; } iterate_all_kinds(i, bytes, v, copyin((p += v.iov_len) - v.iov_len, v.iov_base, v.iov_len), memcpy_from_page((p += v.bv_len) - v.bv_len, v.bv_page, v.bv_offset, v.bv_len), memcpy((p += v.iov_len) - v.iov_len, v.iov_base, v.iov_len) ) kunmap_atomic(kaddr); return bytes; } EXPORT_SYMBOL(iov_iter_copy_from_user_atomic); static inline void pipe_truncate(struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; unsigned int p_tail = pipe->tail; unsigned int p_head = pipe->head; unsigned int p_mask = pipe->ring_size - 1; if (!pipe_empty(p_head, p_tail)) { struct pipe_buffer *buf; unsigned int i_head = i->head; size_t off = i->iov_offset; if (off) { buf = &pipe->bufs[i_head & p_mask]; buf->len = off - buf->offset; i_head++; } while (p_head != i_head) { p_head--; pipe_buf_release(pipe, &pipe->bufs[p_head & p_mask]); } pipe->head = p_head; } } static void pipe_advance(struct iov_iter *i, size_t size) { struct pipe_inode_info *pipe = i->pipe; if (unlikely(i->count < size)) size = i->count; if (size) { struct pipe_buffer *buf; unsigned int p_mask = pipe->ring_size - 1; unsigned int i_head = i->head; size_t off = i->iov_offset, left = size; if (off) /* make it relative to the beginning of buffer */ left += off - pipe->bufs[i_head & p_mask].offset; while (1) { buf = &pipe->bufs[i_head & p_mask]; if (left <= buf->len) break; left -= buf->len; i_head++; } i->head = i_head; i->iov_offset = buf->offset + left; } i->count -= size; /* ... and discard everything past that point */ pipe_truncate(i); } void iov_iter_advance(struct iov_iter *i, size_t size) { if (unlikely(iov_iter_is_pipe(i))) { pipe_advance(i, size); return; } if (unlikely(iov_iter_is_discard(i))) { i->count -= size; return; } iterate_and_advance(i, size, v, 0, 0, 0) } EXPORT_SYMBOL(iov_iter_advance); void iov_iter_revert(struct iov_iter *i, size_t unroll) { if (!unroll) return; if (WARN_ON(unroll > MAX_RW_COUNT)) return; i->count += unroll; if (unlikely(iov_iter_is_pipe(i))) { struct pipe_inode_info *pipe = i->pipe; unsigned int p_mask = pipe->ring_size - 1; unsigned int i_head = i->head; size_t off = i->iov_offset; while (1) { struct pipe_buffer *b = &pipe->bufs[i_head & p_mask]; size_t n = off - b->offset; if (unroll < n) { off -= unroll; break; } unroll -= n; if (!unroll && i_head == i->start_head) { off = 0; break; } i_head--; b = &pipe->bufs[i_head & p_mask]; off = b->offset + b->len; } i->iov_offset = off; i->head = i_head; pipe_truncate(i); return; } if (unlikely(iov_iter_is_discard(i))) return; if (unroll <= i->iov_offset) { i->iov_offset -= unroll; return; } unroll -= i->iov_offset; if (iov_iter_is_bvec(i)) { const struct bio_vec *bvec = i->bvec; while (1) { size_t n = (--bvec)->bv_len; i->nr_segs++; if (unroll <= n) { i->bvec = bvec; i->iov_offset = n - unroll; return; } unroll -= n; } } else { /* same logics for iovec and kvec */ const struct iovec *iov = i->iov; while (1) { size_t n = (--iov)->iov_len; i->nr_segs++; if (unroll <= n) { i->iov = iov; i->iov_offset = n - unroll; return; } unroll -= n; } } } EXPORT_SYMBOL(iov_iter_revert); /* * Return the count of just the current iov_iter segment. */ size_t iov_iter_single_seg_count(const struct iov_iter *i) { if (unlikely(iov_iter_is_pipe(i))) return i->count; // it is a silly place, anyway if (i->nr_segs == 1) return i->count; if (unlikely(iov_iter_is_discard(i))) return i->count; else if (iov_iter_is_bvec(i)) return min(i->count, i->bvec->bv_len - i->iov_offset); else return min(i->count, i->iov->iov_len - i->iov_offset); } EXPORT_SYMBOL(iov_iter_single_seg_count); void iov_iter_kvec(struct iov_iter *i, unsigned int direction, const struct kvec *kvec, unsigned long nr_segs, size_t count) { WARN_ON(direction & ~(READ | WRITE)); i->type = ITER_KVEC | (direction & (READ | WRITE)); i->kvec = kvec; i->nr_segs = nr_segs; i->iov_offset = 0; i->count = count; } EXPORT_SYMBOL(iov_iter_kvec); void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_vec *bvec, unsigned long nr_segs, size_t count) { WARN_ON(direction & ~(READ | WRITE)); i->type = ITER_BVEC | (direction & (READ | WRITE)); i->bvec = bvec; i->nr_segs = nr_segs; i->iov_offset = 0; i->count = count; } EXPORT_SYMBOL(iov_iter_bvec); void iov_iter_pipe(struct iov_iter *i, unsigned int direction, struct pipe_inode_info *pipe, size_t count) { BUG_ON(direction != READ); WARN_ON(pipe_full(pipe->head, pipe->tail, pipe->ring_size)); i->type = ITER_PIPE | READ; i->pipe = pipe; i->head = pipe->head; i->iov_offset = 0; i->count = count; i->start_head = i->head; } EXPORT_SYMBOL(iov_iter_pipe); /** * iov_iter_discard - Initialise an I/O iterator that discards data * @i: The iterator to initialise. * @direction: The direction of the transfer. * @count: The size of the I/O buffer in bytes. * * Set up an I/O iterator that just discards everything that's written to it. * It's only available as a READ iterator. */ void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count) { BUG_ON(direction != READ); i->type = ITER_DISCARD | READ; i->count = count; i->iov_offset = 0; } EXPORT_SYMBOL(iov_iter_discard); unsigned long iov_iter_alignment(const struct iov_iter *i) { unsigned long res = 0; size_t size = i->count; if (unlikely(iov_iter_is_pipe(i))) { unsigned int p_mask = i->pipe->ring_size - 1; if (size && i->iov_offset && allocated(&i->pipe->bufs[i->head & p_mask])) return size | i->iov_offset; return size; } iterate_all_kinds(i, size, v, (res |= (unsigned long)v.iov_base | v.iov_len, 0), res |= v.bv_offset | v.bv_len, res |= (unsigned long)v.iov_base | v.iov_len ) return res; } EXPORT_SYMBOL(iov_iter_alignment); unsigned long iov_iter_gap_alignment(const struct iov_iter *i) { unsigned long res = 0; size_t size = i->count; if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) { WARN_ON(1); return ~0U; } iterate_all_kinds(i, size, v, (res |= (!res ? 0 : (unsigned long)v.iov_base) | (size != v.iov_len ? size : 0), 0), (res |= (!res ? 0 : (unsigned long)v.bv_offset) | (size != v.bv_len ? size : 0)), (res |= (!res ? 0 : (unsigned long)v.iov_base) | (size != v.iov_len ? size : 0)) ); return res; } EXPORT_SYMBOL(iov_iter_gap_alignment); static inline ssize_t __pipe_get_pages(struct iov_iter *i, size_t maxsize, struct page **pages, int iter_head, size_t *start) { struct pipe_inode_info *pipe = i->pipe; unsigned int p_mask = pipe->ring_size - 1; ssize_t n = push_pipe(i, maxsize, &iter_head, start); if (!n) return -EFAULT; maxsize = n; n += *start; while (n > 0) { get_page(*pages++ = pipe->bufs[iter_head & p_mask].page); iter_head++; n -= PAGE_SIZE; } return maxsize; } static ssize_t pipe_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start) { unsigned int iter_head, npages; size_t capacity; if (!maxsize) return 0; if (!sanity(i)) return -EFAULT; data_start(i, &iter_head, start); /* Amount of free space: some of this one + all after this one */ npages = pipe_space_for_user(iter_head, i->pipe->tail, i->pipe); capacity = min(npages, maxpages) * PAGE_SIZE - *start; return __pipe_get_pages(i, min(maxsize, capacity), pages, iter_head, start); } ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start) { if (maxsize > i->count) maxsize = i->count; if (unlikely(iov_iter_is_pipe(i))) return pipe_get_pages(i, pages, maxsize, maxpages, start); if (unlikely(iov_iter_is_discard(i))) return -EFAULT; iterate_all_kinds(i, maxsize, v, ({ unsigned long addr = (unsigned long)v.iov_base; size_t len = v.iov_len + (*start = addr & (PAGE_SIZE - 1)); int n; int res; if (len > maxpages * PAGE_SIZE) len = maxpages * PAGE_SIZE; addr &= ~(PAGE_SIZE - 1); n = DIV_ROUND_UP(len, PAGE_SIZE); res = get_user_pages_fast(addr, n, iov_iter_rw(i) != WRITE ? FOLL_WRITE : 0, pages); if (unlikely(res <= 0)) return res; return (res == n ? len : res * PAGE_SIZE) - *start; 0;}),({ /* can't be more than PAGE_SIZE */ *start = v.bv_offset; get_page(*pages = v.bv_page); return v.bv_len; }),({ return -EFAULT; }) ) return 0; } EXPORT_SYMBOL(iov_iter_get_pages); static struct page **get_pages_array(size_t n) { return kvmalloc_array(n, sizeof(struct page *), GFP_KERNEL); } static ssize_t pipe_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start) { struct page **p; unsigned int iter_head, npages; ssize_t n; if (!maxsize) return 0; if (!sanity(i)) return -EFAULT; data_start(i, &iter_head, start); /* Amount of free space: some of this one + all after this one */ npages = pipe_space_for_user(iter_head, i->pipe->tail, i->pipe); n = npages * PAGE_SIZE - *start; if (maxsize > n) maxsize = n; else npages = DIV_ROUND_UP(maxsize + *start, PAGE_SIZE); p = get_pages_array(npages); if (!p) return -ENOMEM; n = __pipe_get_pages(i, maxsize, p, iter_head, start); if (n > 0) *pages = p; else kvfree(p); return n; } ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start) { struct page **p; if (maxsize > i->count) maxsize = i->count; if (unlikely(iov_iter_is_pipe(i))) return pipe_get_pages_alloc(i, pages, maxsize, start); if (unlikely(iov_iter_is_discard(i))) return -EFAULT; iterate_all_kinds(i, maxsize, v, ({ unsigned long addr = (unsigned long)v.iov_base; size_t len = v.iov_len + (*start = addr & (PAGE_SIZE - 1)); int n; int res; addr &= ~(PAGE_SIZE - 1); n = DIV_ROUND_UP(len, PAGE_SIZE); p = get_pages_array(n); if (!p) return -ENOMEM; res = get_user_pages_fast(addr, n, iov_iter_rw(i) != WRITE ? FOLL_WRITE : 0, p); if (unlikely(res <= 0)) { kvfree(p); *pages = NULL; return res; } *pages = p; return (res == n ? len : res * PAGE_SIZE) - *start; 0;}),({ /* can't be more than PAGE_SIZE */ *start = v.bv_offset; *pages = p = get_pages_array(1); if (!p) return -ENOMEM; get_page(*p = v.bv_page); return v.bv_len; }),({ return -EFAULT; }) ) return 0; } EXPORT_SYMBOL(iov_iter_get_pages_alloc); size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i) { char *to = addr; __wsum sum, next; size_t off = 0; sum = *csum; if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) { WARN_ON(1); return 0; } iterate_and_advance(i, bytes, v, ({ next = csum_and_copy_from_user(v.iov_base, (to += v.iov_len) - v.iov_len, v.iov_len); if (next) { sum = csum_block_add(sum, next, off); off += v.iov_len; } next ? 0 : v.iov_len; }), ({ char *p = kmap_atomic(v.bv_page); sum = csum_and_memcpy((to += v.bv_len) - v.bv_len, p + v.bv_offset, v.bv_len, sum, off); kunmap_atomic(p); off += v.bv_len; }),({ sum = csum_and_memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len, sum, off); off += v.iov_len; }) ) *csum = sum; return bytes; } EXPORT_SYMBOL(csum_and_copy_from_iter); bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i) { char *to = addr; __wsum sum, next; size_t off = 0; sum = *csum; if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) { WARN_ON(1); return false; } if (unlikely(i->count < bytes)) return false; iterate_all_kinds(i, bytes, v, ({ next = csum_and_copy_from_user(v.iov_base, (to += v.iov_len) - v.iov_len, v.iov_len); if (!next) return false; sum = csum_block_add(sum, next, off); off += v.iov_len; 0; }), ({ char *p = kmap_atomic(v.bv_page); sum = csum_and_memcpy((to += v.bv_len) - v.bv_len, p + v.bv_offset, v.bv_len, sum, off); kunmap_atomic(p); off += v.bv_len; }),({ sum = csum_and_memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len, sum, off); off += v.iov_len; }) ) *csum = sum; iov_iter_advance(i, bytes); return true; } EXPORT_SYMBOL(csum_and_copy_from_iter_full); size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *_csstate, struct iov_iter *i) { struct csum_state *csstate = _csstate; const char *from = addr; __wsum sum, next; size_t off; if (unlikely(iov_iter_is_pipe(i))) return csum_and_copy_to_pipe_iter(addr, bytes, _csstate, i); sum = csstate->csum; off = csstate->off; if (unlikely(iov_iter_is_discard(i))) { WARN_ON(1); /* for now */ return 0; } iterate_and_advance(i, bytes, v, ({ next = csum_and_copy_to_user((from += v.iov_len) - v.iov_len, v.iov_base, v.iov_len); if (next) { sum = csum_block_add(sum, next, off); off += v.iov_len; } next ? 0 : v.iov_len; }), ({ char *p = kmap_atomic(v.bv_page); sum = csum_and_memcpy(p + v.bv_offset, (from += v.bv_len) - v.bv_len, v.bv_len, sum, off); kunmap_atomic(p); off += v.bv_len; }),({ sum = csum_and_memcpy(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len, sum, off); off += v.iov_len; }) ) csstate->csum = sum; csstate->off = off; return bytes; } EXPORT_SYMBOL(csum_and_copy_to_iter); size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp, struct iov_iter *i) { #ifdef CONFIG_CRYPTO_HASH struct ahash_request *hash = hashp; struct scatterlist sg; size_t copied; copied = copy_to_iter(addr, bytes, i); sg_init_one(&sg, addr, copied); ahash_request_set_crypt(hash, &sg, NULL, copied); crypto_ahash_update(hash); return copied; #else return 0; #endif } EXPORT_SYMBOL(hash_and_copy_to_iter); int iov_iter_npages(const struct iov_iter *i, int maxpages) { size_t size = i->count; int npages = 0; if (!size) return 0; if (unlikely(iov_iter_is_discard(i))) return 0; if (unlikely(iov_iter_is_pipe(i))) { struct pipe_inode_info *pipe = i->pipe; unsigned int iter_head; size_t off; if (!sanity(i)) return 0; data_start(i, &iter_head, &off); /* some of this one + all after this one */ npages = pipe_space_for_user(iter_head, pipe->tail, pipe); if (npages >= maxpages) return maxpages; } else iterate_all_kinds(i, size, v, ({ unsigned long p = (unsigned long)v.iov_base; npages += DIV_ROUND_UP(p + v.iov_len, PAGE_SIZE) - p / PAGE_SIZE; if (npages >= maxpages) return maxpages; 0;}),({ npages++; if (npages >= maxpages) return maxpages; }),({ unsigned long p = (unsigned long)v.iov_base; npages += DIV_ROUND_UP(p + v.iov_len, PAGE_SIZE) - p / PAGE_SIZE; if (npages >= maxpages) return maxpages; }) ) return npages; } EXPORT_SYMBOL(iov_iter_npages); const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags) { *new = *old; if (unlikely(iov_iter_is_pipe(new))) { WARN_ON(1); return NULL; } if (unlikely(iov_iter_is_discard(new))) return NULL; if (iov_iter_is_bvec(new)) return new->bvec = kmemdup(new->bvec, new->nr_segs * sizeof(struct bio_vec), flags); else /* iovec and kvec have identical layout */ return new->iov = kmemdup(new->iov, new->nr_segs * sizeof(struct iovec), flags); } EXPORT_SYMBOL(dup_iter); static int copy_compat_iovec_from_user(struct iovec *iov, const struct iovec __user *uvec, unsigned long nr_segs) { const struct compat_iovec __user *uiov = (const struct compat_iovec __user *)uvec; int ret = -EFAULT, i; if (!user_access_begin(uiov, nr_segs * sizeof(*uiov))) return -EFAULT; for (i = 0; i < nr_segs; i++) { compat_uptr_t buf; compat_ssize_t len; unsafe_get_user(len, &uiov[i].iov_len, uaccess_end); unsafe_get_user(buf, &uiov[i].iov_base, uaccess_end); /* check for compat_size_t not fitting in compat_ssize_t .. */ if (len < 0) { ret = -EINVAL; goto uaccess_end; } iov[i].iov_base = compat_ptr(buf); iov[i].iov_len = len; } ret = 0; uaccess_end: user_access_end(); return ret; } static int copy_iovec_from_user(struct iovec *iov, const struct iovec __user *uvec, unsigned long nr_segs) { unsigned long seg; if (copy_from_user(iov, uvec, nr_segs * sizeof(*uvec))) return -EFAULT; for (seg = 0; seg < nr_segs; seg++) { if ((ssize_t)iov[seg].iov_len < 0) return -EINVAL; } return 0; } struct iovec *iovec_from_user(const struct iovec __user *uvec, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_iov, bool compat) { struct iovec *iov = fast_iov; int ret; /* * SuS says "The readv() function *may* fail if the iovcnt argument was * less than or equal to 0, or greater than {IOV_MAX}. Linux has * traditionally returned zero for zero segments, so... */ if (nr_segs == 0) return iov; if (nr_segs > UIO_MAXIOV) return ERR_PTR(-EINVAL); if (nr_segs > fast_segs) { iov = kmalloc_array(nr_segs, sizeof(struct iovec), GFP_KERNEL); if (!iov) return ERR_PTR(-ENOMEM); } if (compat) ret = copy_compat_iovec_from_user(iov, uvec, nr_segs); else ret = copy_iovec_from_user(iov, uvec, nr_segs); if (ret) { if (iov != fast_iov) kfree(iov); return ERR_PTR(ret); } return iov; } ssize_t __import_iovec(int type, const struct iovec __user *uvec, unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, struct iov_iter *i, bool compat) { ssize_t total_len = 0; unsigned long seg; struct iovec *iov; iov = iovec_from_user(uvec, nr_segs, fast_segs, *iovp, compat); if (IS_ERR(iov)) { *iovp = NULL; return PTR_ERR(iov); } /* * According to the Single Unix Specification we should return EINVAL if * an element length is < 0 when cast to ssize_t or if the total length * would overflow the ssize_t return value of the system call. * * Linux caps all read/write calls to MAX_RW_COUNT, and avoids the * overflow case. */ for (seg = 0; seg < nr_segs; seg++) { ssize_t len = (ssize_t)iov[seg].iov_len; if (!access_ok(iov[seg].iov_base, len)) { if (iov != *iovp) kfree(iov); *iovp = NULL; return -EFAULT; } if (len > MAX_RW_COUNT - total_len) { len = MAX_RW_COUNT - total_len; iov[seg].iov_len = len; } total_len += len; } iov_iter_init(i, type, iov, nr_segs, total_len); if (iov == *iovp) *iovp = NULL; else *iovp = iov; return total_len; } /** * import_iovec() - Copy an array of &struct iovec from userspace * into the kernel, check that it is valid, and initialize a new * &struct iov_iter iterator to access it. * * @type: One of %READ or %WRITE. * @uvec: Pointer to the userspace array. * @nr_segs: Number of elements in userspace array. * @fast_segs: Number of elements in @iov. * @iovp: (input and output parameter) Pointer to pointer to (usually small * on-stack) kernel array. * @i: Pointer to iterator that will be initialized on success. * * If the array pointed to by *@iov is large enough to hold all @nr_segs, * then this function places %NULL in *@iov on return. Otherwise, a new * array will be allocated and the result placed in *@iov. This means that * the caller may call kfree() on *@iov regardless of whether the small * on-stack array was used or not (and regardless of whether this function * returns an error or not). * * Return: Negative error code on error, bytes imported on success */ ssize_t import_iovec(int type, const struct iovec __user *uvec, unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, struct iov_iter *i) { return __import_iovec(type, uvec, nr_segs, fast_segs, iovp, i, in_compat_syscall()); } EXPORT_SYMBOL(import_iovec); int import_single_range(int rw, void __user *buf, size_t len, struct iovec *iov, struct iov_iter *i) { if (len > MAX_RW_COUNT) len = MAX_RW_COUNT; if (unlikely(!access_ok(buf, len))) return -EFAULT; iov->iov_base = buf; iov->iov_len = len; iov_iter_init(i, rw, iov, 1, len); return 0; } EXPORT_SYMBOL(import_single_range); int iov_iter_for_each_range(struct iov_iter *i, size_t bytes, int (*f)(struct kvec *vec, void *context), void *context) { struct kvec w; int err = -EINVAL; if (!bytes) return 0; iterate_all_kinds(i, bytes, v, -EINVAL, ({ w.iov_base = kmap(v.bv_page) + v.bv_offset; w.iov_len = v.bv_len; err = f(&w, context); kunmap(v.bv_page); err;}), ({ w = v; err = f(&w, context);}) ) return err; } EXPORT_SYMBOL(iov_iter_for_each_range);
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 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 // SPDX-License-Identifier: GPL-2.0-only /* * 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. * * The Internet Protocol (IP) output module. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Donald Becker, <becker@super.org> * Alan Cox, <Alan.Cox@linux.org> * Richard Underwood * Stefan Becker, <stefanb@yello.ping.de> * Jorge Cwik, <jorge@laser.satlink.net> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * Hirokazu Takahashi, <taka@valinux.co.jp> * * See ip_input.c for original log * * Fixes: * Alan Cox : Missing nonblock feature in ip_build_xmit. * Mike Kilburn : htons() missing in ip_build_xmit. * Bradford Johnson: Fix faulty handling of some frames when * no route is found. * Alexander Demenshin: Missing sk/skb free in ip_queue_xmit * (in case if packet not accepted by * output firewall rules) * Mike McLagan : Routing by source * Alexey Kuznetsov: use new route cache * Andi Kleen: Fix broken PMTU recovery and remove * some redundant tests. * Vitaly E. Lavrov : Transparent proxy revived after year coma. * Andi Kleen : Replace ip_reply with ip_send_reply. * Andi Kleen : Split fast and slow ip_build_xmit path * for decreased register pressure on x86 * and more readibility. * Marc Boucher : When call_out_firewall returns FW_QUEUE, * silently drop skb instead of failing with -EPERM. * Detlev Wengorz : Copy protocol for fragments. * Hirokazu Takahashi: HW checksumming for outgoing UDP * datagrams. * Hirokazu Takahashi: sendfile() on UDP works now. */ #include <linux/uaccess.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/highmem.h> #include <linux/slab.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/proc_fs.h> #include <linux/stat.h> #include <linux/init.h> #include <net/snmp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> #include <net/xfrm.h> #include <linux/skbuff.h> #include <net/sock.h> #include <net/arp.h> #include <net/icmp.h> #include <net/checksum.h> #include <net/inetpeer.h> #include <net/inet_ecn.h> #include <net/lwtunnel.h> #include <linux/bpf-cgroup.h> #include <linux/igmp.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_bridge.h> #include <linux/netlink.h> #include <linux/tcp.h> static int ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu, int (*output)(struct net *, struct sock *, struct sk_buff *)); /* Generate a checksum for an outgoing IP datagram. */ void ip_send_check(struct iphdr *iph) { iph->check = 0; iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); } EXPORT_SYMBOL(ip_send_check); int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { struct iphdr *iph = ip_hdr(skb); iph->tot_len = htons(skb->len); ip_send_check(iph); /* if egress device is enslaved to an L3 master device pass the * skb to its handler for processing */ skb = l3mdev_ip_out(sk, skb); if (unlikely(!skb)) return 0; skb->protocol = htons(ETH_P_IP); return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); } int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; err = __ip_local_out(net, sk, skb); if (likely(err == 1)) err = dst_output(net, sk, skb); return err; } EXPORT_SYMBOL_GPL(ip_local_out); static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst) { int ttl = inet->uc_ttl; if (ttl < 0) ttl = ip4_dst_hoplimit(dst); return ttl; } /* * Add an ip header to a skbuff and send it out. * */ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, __be32 saddr, __be32 daddr, struct ip_options_rcu *opt, u8 tos) { struct inet_sock *inet = inet_sk(sk); struct rtable *rt = skb_rtable(skb); struct net *net = sock_net(sk); struct iphdr *iph; /* Build the IP header. */ skb_push(skb, sizeof(struct iphdr) + (opt ? opt->opt.optlen : 0)); skb_reset_network_header(skb); iph = ip_hdr(skb); iph->version = 4; iph->ihl = 5; iph->tos = tos; iph->ttl = ip_select_ttl(inet, &rt->dst); iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr); iph->saddr = saddr; iph->protocol = sk->sk_protocol; if (ip_dont_fragment(sk, &rt->dst)) { iph->frag_off = htons(IP_DF); iph->id = 0; } else { iph->frag_off = 0; __ip_select_ident(net, iph, 1); } if (opt && opt->opt.optlen) { iph->ihl += opt->opt.optlen>>2; ip_options_build(skb, &opt->opt, daddr, rt, 0); } skb->priority = sk->sk_priority; if (!skb->mark) skb->mark = sk->sk_mark; /* Send it out. */ return ip_local_out(net, skb->sk, skb); } EXPORT_SYMBOL_GPL(ip_build_and_send_pkt); static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct rtable *rt = (struct rtable *)dst; struct net_device *dev = dst->dev; unsigned int hh_len = LL_RESERVED_SPACE(dev); struct neighbour *neigh; bool is_v6gw = false; if (rt->rt_type == RTN_MULTICAST) { IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTMCAST, skb->len); } else if (rt->rt_type == RTN_BROADCAST) IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTBCAST, skb->len); /* Be paranoid, rather than too clever. */ if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { struct sk_buff *skb2; skb2 = skb_realloc_headroom(skb, LL_RESERVED_SPACE(dev)); if (!skb2) { kfree_skb(skb); return -ENOMEM; } if (skb->sk) skb_set_owner_w(skb2, skb->sk); consume_skb(skb); skb = skb2; } if (lwtunnel_xmit_redirect(dst->lwtstate)) { int res = lwtunnel_xmit(skb); if (res < 0 || res == LWTUNNEL_XMIT_DONE) return res; } rcu_read_lock_bh(); neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); if (!IS_ERR(neigh)) { int res; sock_confirm_neigh(skb, neigh); /* if crossing protocols, can not use the cached header */ res = neigh_output(neigh, skb, is_v6gw); rcu_read_unlock_bh(); return res; } rcu_read_unlock_bh(); net_dbg_ratelimited("%s: No header cache and no neighbour!\n", __func__); kfree_skb(skb); return -EINVAL; } static int ip_finish_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu) { struct sk_buff *segs, *nskb; netdev_features_t features; int ret = 0; /* common case: seglen is <= mtu */ if (skb_gso_validate_network_len(skb, mtu)) return ip_finish_output2(net, sk, skb); /* Slowpath - GSO segment length exceeds the egress MTU. * * This can happen in several cases: * - Forwarding of a TCP GRO skb, when DF flag is not set. * - Forwarding of an skb that arrived on a virtualization interface * (virtio-net/vhost/tap) with TSO/GSO size set by other network * stack. * - Local GSO skb transmitted on an NETIF_F_TSO tunnel stacked over an * interface with a smaller MTU. * - Arriving GRO skb (or GSO skb in a virtualized environment) that is * bridged to a NETIF_F_TSO tunnel stacked over an interface with an * insufficent MTU. */ features = netif_skb_features(skb); BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_GSO_CB_OFFSET); segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); if (IS_ERR_OR_NULL(segs)) { kfree_skb(skb); return -ENOMEM; } consume_skb(skb); skb_list_walk_safe(segs, segs, nskb) { int err; skb_mark_not_on_list(segs); err = ip_fragment(net, sk, segs, mtu, ip_finish_output2); if (err && ret == 0) ret = err; } return ret; } static int __ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { unsigned int mtu; #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) /* Policy lookup after SNAT yielded a new policy */ if (skb_dst(skb)->xfrm) { IPCB(skb)->flags |= IPSKB_REROUTED; return dst_output(net, sk, skb); } #endif mtu = ip_skb_dst_mtu(sk, skb); if (skb_is_gso(skb)) return ip_finish_output_gso(net, sk, skb, mtu); if (skb->len > mtu || IPCB(skb)->frag_max_size) return ip_fragment(net, sk, skb, mtu, ip_finish_output2); return ip_finish_output2(net, sk, skb); } static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { int ret; ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb); switch (ret) { case NET_XMIT_SUCCESS: return __ip_finish_output(net, sk, skb); case NET_XMIT_CN: return __ip_finish_output(net, sk, skb) ? : ret; default: kfree_skb(skb); return ret; } } static int ip_mc_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct rtable *new_rt; bool do_cn = false; int ret, err; ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb); switch (ret) { case NET_XMIT_CN: do_cn = true; fallthrough; case NET_XMIT_SUCCESS: break; default: kfree_skb(skb); return ret; } /* Reset rt_iif so that inet_iif() will return skb->skb_iif. Setting * this to non-zero causes ipi_ifindex in in_pktinfo to be overwritten, * see ipv4_pktinfo_prepare(). */ new_rt = rt_dst_clone(net->loopback_dev, skb_rtable(skb)); if (new_rt) { new_rt->rt_iif = 0; skb_dst_drop(skb); skb_dst_set(skb, &new_rt->dst); } err = dev_loopback_xmit(net, sk, skb); return (do_cn && err) ? ret : err; } int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); struct net_device *dev = rt->dst.dev; /* * If the indicated interface is up and running, send the packet. */ IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); skb->dev = dev; skb->protocol = htons(ETH_P_IP); /* * Multicasts are looped back for other local users */ if (rt->rt_flags&RTCF_MULTICAST) { if (sk_mc_loop(sk) #ifdef CONFIG_IP_MROUTE /* Small optimization: do not loopback not local frames, which returned after forwarding; they will be dropped by ip_mr_input in any case. Note, that local frames are looped back to be delivered to local recipients. This check is duplicated in ip_mr_input at the moment. */ && ((rt->rt_flags & RTCF_LOCAL) || !(IPCB(skb)->flags & IPSKB_FORWARDED)) #endif ) { struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); if (newskb) NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, newskb, NULL, newskb->dev, ip_mc_finish_output); } /* Multicasts with ttl 0 must not go beyond the host */ if (ip_hdr(skb)->ttl == 0) { kfree_skb(skb); return 0; } } if (rt->rt_flags&RTCF_BROADCAST) { struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); if (newskb) NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, newskb, NULL, newskb->dev, ip_mc_finish_output); } return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, NULL, skb->dev, ip_finish_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev, *indev = skb->dev; IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); skb->dev = dev; skb->protocol = htons(ETH_P_IP); return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, indev, dev, ip_finish_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } /* * copy saddr and daddr, possibly using 64bit load/stores * Equivalent to : * iph->saddr = fl4->saddr; * iph->daddr = fl4->daddr; */ static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4) { BUILD_BUG_ON(offsetof(typeof(*fl4), daddr) != offsetof(typeof(*fl4), saddr) + sizeof(fl4->saddr)); iph->saddr = fl4->saddr; iph->daddr = fl4->daddr; } /* Note: skb->sk can be different from sk, in case of tunnels */ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, __u8 tos) { struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); struct ip_options_rcu *inet_opt; struct flowi4 *fl4; struct rtable *rt; struct iphdr *iph; int res; /* Skip all of this if the packet is already routed, * f.e. by something like SCTP. */ rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); fl4 = &fl->u.ip4; rt = skb_rtable(skb); if (rt) goto packet_routed; /* Make sure we can route this packet. */ rt = (struct rtable *)__sk_dst_check(sk, 0); if (!rt) { __be32 daddr; /* Use correct destination address if we have options. */ daddr = inet->inet_daddr; if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; /* If this fails, retransmit mechanism of transport layer will * keep trying until route appears or the connection times * itself out. */ rt = ip_route_output_ports(net, fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk->sk_protocol, RT_CONN_FLAGS_TOS(sk, tos), sk->sk_bound_dev_if); if (IS_ERR(rt)) goto no_route; sk_setup_caps(sk, &rt->dst); } skb_dst_set_noref(skb, &rt->dst); packet_routed: if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_uses_gateway) goto no_route; /* OK, we know where to send it, allocate and build IP header. */ skb_push(skb, sizeof(struct iphdr) + (inet_opt ? inet_opt->opt.optlen : 0)); skb_reset_network_header(skb); iph = ip_hdr(skb); *((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (tos & 0xff)); if (ip_dont_fragment(sk, &rt->dst) && !skb->ignore_df) iph->frag_off = htons(IP_DF); else iph->frag_off = 0; iph->ttl = ip_select_ttl(inet, &rt->dst); iph->protocol = sk->sk_protocol; ip_copy_addrs(iph, fl4); /* Transport layer set skb->h.foo itself. */ if (inet_opt && inet_opt->opt.optlen) { iph->ihl += inet_opt->opt.optlen >> 2; ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0); } ip_select_ident_segs(net, skb, sk, skb_shinfo(skb)->gso_segs ?: 1); /* TODO : should we use skb->sk here instead of sk ? */ skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; res = ip_local_out(net, sk, skb); rcu_read_unlock(); return res; no_route: rcu_read_unlock(); IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); return -EHOSTUNREACH; } EXPORT_SYMBOL(__ip_queue_xmit); int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl) { return __ip_queue_xmit(sk, skb, fl, inet_sk(sk)->tos); } EXPORT_SYMBOL(ip_queue_xmit); static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) { to->pkt_type = from->pkt_type; to->priority = from->priority; to->protocol = from->protocol; to->skb_iif = from->skb_iif; skb_dst_drop(to); skb_dst_copy(to, from); to->dev = from->dev; to->mark = from->mark; skb_copy_hash(to, from); #ifdef CONFIG_NET_SCHED to->tc_index = from->tc_index; #endif nf_copy(to, from); skb_ext_copy(to, from); #if IS_ENABLED(CONFIG_IP_VS) to->ipvs_property = from->ipvs_property; #endif skb_copy_secmark(to, from); } static int ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu, int (*output)(struct net *, struct sock *, struct sk_buff *)) { struct iphdr *iph = ip_hdr(skb); if ((iph->frag_off & htons(IP_DF)) == 0) return ip_do_fragment(net, sk, skb, output); if (unlikely(!skb->ignore_df || (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size > mtu))) { IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); kfree_skb(skb); return -EMSGSIZE; } return ip_do_fragment(net, sk, skb, output); } void ip_fraglist_init(struct sk_buff *skb, struct iphdr *iph, unsigned int hlen, struct ip_fraglist_iter *iter) { unsigned int first_len = skb_pagelen(skb); iter->frag = skb_shinfo(skb)->frag_list; skb_frag_list_init(skb); iter->offset = 0; iter->iph = iph; iter->hlen = hlen; skb->data_len = first_len - skb_headlen(skb); skb->len = first_len; iph->tot_len = htons(first_len); iph->frag_off = htons(IP_MF); ip_send_check(iph); } EXPORT_SYMBOL(ip_fraglist_init); static void ip_fraglist_ipcb_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter) { struct sk_buff *to = iter->frag; /* Copy the flags to each fragment. */ IPCB(to)->flags = IPCB(skb)->flags; if (iter->offset == 0) ip_options_fragment(to); } void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter) { unsigned int hlen = iter->hlen; struct iphdr *iph = iter->iph; struct sk_buff *frag; frag = iter->frag; frag->ip_summed = CHECKSUM_NONE; skb_reset_transport_header(frag); __skb_push(frag, hlen); skb_reset_network_header(frag); memcpy(skb_network_header(frag), iph, hlen); iter->iph = ip_hdr(frag); iph = iter->iph; iph->tot_len = htons(frag->len); ip_copy_metadata(frag, skb); iter->offset += skb->len - hlen; iph->frag_off = htons(iter->offset >> 3); if (frag->next) iph->frag_off |= htons(IP_MF); /* Ready, complete checksum */ ip_send_check(iph); } EXPORT_SYMBOL(ip_fraglist_prepare); void ip_frag_init(struct sk_buff *skb, unsigned int hlen, unsigned int ll_rs, unsigned int mtu, bool DF, struct ip_frag_state *state) { struct iphdr *iph = ip_hdr(skb); state->DF = DF; state->hlen = hlen; state->ll_rs = ll_rs; state->mtu = mtu; state->left = skb->len - hlen; /* Space per frame */ state->ptr = hlen; /* Where to start from */ state->offset = (ntohs(iph->frag_off) & IP_OFFSET) << 3; state->not_last_frag = iph->frag_off & htons(IP_MF); } EXPORT_SYMBOL(ip_frag_init); static void ip_frag_ipcb(struct sk_buff *from, struct sk_buff *to, bool first_frag, struct ip_frag_state *state) { /* Copy the flags to each fragment. */ IPCB(to)->flags = IPCB(from)->flags; /* ANK: dirty, but effective trick. Upgrade options only if * the segment to be fragmented was THE FIRST (otherwise, * options are already fixed) and make it ONCE * on the initial skb, so that all the following fragments * will inherit fixed options. */ if (first_frag) ip_options_fragment(from); } struct sk_buff *ip_frag_next(struct sk_buff *skb, struct ip_frag_state *state) { unsigned int len = state->left; struct sk_buff *skb2; struct iphdr *iph; len = state->left; /* IF: it doesn't fit, use 'mtu' - the data space left */ if (len > state->mtu) len = state->mtu; /* IF: we are not sending up to and including the packet end then align the next start on an eight byte boundary */ if (len < state->left) { len &= ~7; } /* Allocate buffer */ skb2 = alloc_skb(len + state->hlen + state->ll_rs, GFP_ATOMIC); if (!skb2) return ERR_PTR(-ENOMEM); /* * Set up data on packet */ ip_copy_metadata(skb2, skb); skb_reserve(skb2, state->ll_rs); skb_put(skb2, len + state->hlen); skb_reset_network_header(skb2); skb2->transport_header = skb2->network_header + state->hlen; /* * Charge the memory for the fragment to any owner * it might possess */ if (skb->sk) skb_set_owner_w(skb2, skb->sk); /* * Copy the packet header into the new buffer. */ skb_copy_from_linear_data(skb, skb_network_header(skb2), state->hlen); /* * Copy a block of the IP datagram. */ if (skb_copy_bits(skb, state->ptr, skb_transport_header(skb2), len)) BUG(); state->left -= len; /* * Fill in the new header fields. */ iph = ip_hdr(skb2); iph->frag_off = htons((state->offset >> 3)); if (state->DF) iph->frag_off |= htons(IP_DF); /* * Added AC : If we are fragmenting a fragment that's not the * last fragment then keep MF on each bit */ if (state->left > 0 || state->not_last_frag) iph->frag_off |= htons(IP_MF); state->ptr += len; state->offset += len; iph->tot_len = htons(len + state->hlen); ip_send_check(iph); return skb2; } EXPORT_SYMBOL(ip_frag_next); /* * This IP datagram is too large to be sent in one piece. Break it up into * smaller pieces (each of size equal to IP header plus * a block of the data of the original IP data part) that will yet fit in a * single device frame, and queue such a frame for sending. */ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)) { struct iphdr *iph; struct sk_buff *skb2; struct rtable *rt = skb_rtable(skb); unsigned int mtu, hlen, ll_rs; struct ip_fraglist_iter iter; ktime_t tstamp = skb->tstamp; struct ip_frag_state state; int err = 0; /* for offloaded checksums cleanup checksum before fragmentation */ if (skb->ip_summed == CHECKSUM_PARTIAL && (err = skb_checksum_help(skb))) goto fail; /* * Point into the IP datagram header. */ iph = ip_hdr(skb); mtu = ip_skb_dst_mtu(sk, skb); if (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size < mtu) mtu = IPCB(skb)->frag_max_size; /* * Setup starting values. */ hlen = iph->ihl * 4; mtu = mtu - hlen; /* Size of data space */ IPCB(skb)->flags |= IPSKB_FRAG_COMPLETE; ll_rs = LL_RESERVED_SPACE(rt->dst.dev); /* When frag_list is given, use it. First, check its validity: * some transformers could create wrong frag_list or break existing * one, it is not prohibited. In this case fall back to copying. * * LATER: this step can be merged to real generation of fragments, * we can switch to copy when see the first bad fragment. */ if (skb_has_frag_list(skb)) { struct sk_buff *frag, *frag2; unsigned int first_len = skb_pagelen(skb); if (first_len - hlen > mtu || ((first_len - hlen) & 7) || ip_is_fragment(iph) || skb_cloned(skb) || skb_headroom(skb) < ll_rs) goto slow_path; skb_walk_frags(skb, frag) { /* Correct geometry. */ if (frag->len > mtu || ((frag->len & 7) && frag->next) || skb_headroom(frag) < hlen + ll_rs) goto slow_path_clean; /* Partially cloned skb? */ if (skb_shared(frag)) goto slow_path_clean; BUG_ON(frag->sk); if (skb->sk) { frag->sk = skb->sk; frag->destructor = sock_wfree; } skb->truesize -= frag->truesize; } /* Everything is OK. Generate! */ ip_fraglist_init(skb, iph, hlen, &iter); for (;;) { /* Prepare header of the next frame, * before previous one went down. */ if (iter.frag) { ip_fraglist_ipcb_prepare(skb, &iter); ip_fraglist_prepare(skb, &iter); } skb->tstamp = tstamp; err = output(net, sk, skb); if (!err) IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES); if (err || !iter.frag) break; skb = ip_fraglist_next(&iter); } if (err == 0) { IP_INC_STATS(net, IPSTATS_MIB_FRAGOKS); return 0; } kfree_skb_list(iter.frag); IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); return err; slow_path_clean: skb_walk_frags(skb, frag2) { if (frag2 == frag) break; frag2->sk = NULL; frag2->destructor = NULL; skb->truesize += frag2->truesize; } } slow_path: /* * Fragment the datagram. */ ip_frag_init(skb, hlen, ll_rs, mtu, IPCB(skb)->flags & IPSKB_FRAG_PMTU, &state); /* * Keep copying data until we run out. */ while (state.left > 0) { bool first_frag = (state.offset == 0); skb2 = ip_frag_next(skb, &state); if (IS_ERR(skb2)) { err = PTR_ERR(skb2); goto fail; } ip_frag_ipcb(skb, skb2, first_frag, &state); /* * Put this fragment into the sending queue. */ skb2->tstamp = tstamp; err = output(net, sk, skb2); if (err) goto fail; IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES); } consume_skb(skb); IP_INC_STATS(net, IPSTATS_MIB_FRAGOKS); return err; fail: kfree_skb(skb); IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); return err; } EXPORT_SYMBOL(ip_do_fragment); int ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { struct msghdr *msg = from; if (skb->ip_summed == CHECKSUM_PARTIAL) { if (!copy_from_iter_full(to, len, &msg->msg_iter)) return -EFAULT; } else { __wsum csum = 0; if (!csum_and_copy_from_iter_full(to, len, &csum, &msg->msg_iter)) return -EFAULT; skb->csum = csum_block_add(skb->csum, csum, odd); } return 0; } EXPORT_SYMBOL(ip_generic_getfrag); static inline __wsum csum_page(struct page *page, int offset, int copy) { char *kaddr; __wsum csum; kaddr = kmap(page); csum = csum_partial(kaddr + offset, copy, 0); kunmap(page); return csum; } static int __ip_append_data(struct sock *sk, struct flowi4 *fl4, struct sk_buff_head *queue, struct inet_cork *cork, struct page_frag *pfrag, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, unsigned int flags) { struct inet_sock *inet = inet_sk(sk); struct ubuf_info *uarg = NULL; struct sk_buff *skb; struct ip_options *opt = cork->opt; int hh_len; int exthdrlen; int mtu; int copy; int err; int offset = 0; unsigned int maxfraglen, fragheaderlen, maxnonfragsize; int csummode = CHECKSUM_NONE; struct rtable *rt = (struct rtable *)cork->dst; unsigned int wmem_alloc_delta = 0; bool paged, extra_uref = false; u32 tskey = 0; skb = skb_peek_tail(queue); exthdrlen = !skb ? rt->dst.header_len : 0; mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize; paged = !!cork->gso_size; if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP && sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) tskey = sk->sk_tskey++; hh_len = LL_RESERVED_SPACE(rt->dst.dev); fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; maxnonfragsize = ip_sk_ignore_df(sk) ? IP_MAX_MTU : mtu; if (cork->length + length > maxnonfragsize - fragheaderlen) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, mtu - (opt ? opt->optlen : 0)); return -EMSGSIZE; } /* * transhdrlen > 0 means that this is the first fragment and we wish * it won't be fragmented in the future. */ if (transhdrlen && length + fragheaderlen <= mtu && rt->dst.dev->features & (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM) && (!(flags & MSG_MORE) || cork->gso_size) && (!exthdrlen || (rt->dst.dev->features & NETIF_F_HW_ESP_TX_CSUM))) csummode = CHECKSUM_PARTIAL; if (flags & MSG_ZEROCOPY && length && sock_flag(sk, SOCK_ZEROCOPY)) { uarg = sock_zerocopy_realloc(sk, length, skb_zcopy(skb)); if (!uarg) return -ENOBUFS; extra_uref = !skb_zcopy(skb); /* only ref on new uarg */ if (rt->dst.dev->features & NETIF_F_SG && csummode == CHECKSUM_PARTIAL) { paged = true; } else { uarg->zerocopy = 0; skb_zcopy_set(skb, uarg, &extra_uref); } } cork->length += length; /* So, what's going on in the loop below? * * We use calculated fragment length to generate chained skb, * each of segments is IP fragment ready for sending to network after * adding appropriate IP header. */ if (!skb) goto alloc_new_skb; while (length > 0) { /* Check if the remaining data fits into current packet. */ copy = mtu - skb->len; if (copy < length) copy = maxfraglen - skb->len; if (copy <= 0) { char *data; unsigned int datalen; unsigned int fraglen; unsigned int fraggap; unsigned int alloclen, alloc_extra; unsigned int pagedlen; struct sk_buff *skb_prev; alloc_new_skb: skb_prev = skb; if (skb_prev) fraggap = skb_prev->len - maxfraglen; else fraggap = 0; /* * If remaining data exceeds the mtu, * we know we need more fragment(s). */ datalen = length + fraggap; if (datalen > mtu - fragheaderlen) datalen = maxfraglen - fragheaderlen; fraglen = datalen + fragheaderlen; pagedlen = 0; alloc_extra = hh_len + 15; alloc_extra += exthdrlen; /* The last fragment gets additional space at tail. * Note, with MSG_MORE we overallocate on fragments, * because we have no idea what fragment will be * the last. */ if (datalen == length + fraggap) alloc_extra += rt->dst.trailer_len; if ((flags & MSG_MORE) && !(rt->dst.dev->features&NETIF_F_SG)) alloclen = mtu; else if (!paged && (fraglen + alloc_extra < SKB_MAX_ALLOC || !(rt->dst.dev->features & NETIF_F_SG))) alloclen = fraglen; else { alloclen = min_t(int, fraglen, MAX_HEADER); pagedlen = fraglen - alloclen; } alloclen += alloc_extra; if (transhdrlen) { skb = sock_alloc_send_skb(sk, alloclen, (flags & MSG_DONTWAIT), &err); } else { skb = NULL; if (refcount_read(&sk->sk_wmem_alloc) + wmem_alloc_delta <= 2 * sk->sk_sndbuf) skb = alloc_skb(alloclen, sk->sk_allocation); if (unlikely(!skb)) err = -ENOBUFS; } if (!skb) goto error; /* * Fill in the control structures */ skb->ip_summed = csummode; skb->csum = 0; skb_reserve(skb, hh_len); /* * Find where to start putting bytes. */ data = skb_put(skb, fraglen + exthdrlen - pagedlen); skb_set_network_header(skb, exthdrlen); skb->transport_header = (skb->network_header + fragheaderlen); data += fragheaderlen + exthdrlen; if (fraggap) { skb->csum = skb_copy_and_csum_bits( skb_prev, maxfraglen, data + transhdrlen, fraggap); skb_prev->csum = csum_sub(skb_prev->csum, skb->csum); data += fraggap; pskb_trim_unique(skb_prev, maxfraglen); } copy = datalen - transhdrlen - fraggap - pagedlen; if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) { err = -EFAULT; kfree_skb(skb); goto error; } offset += copy; length -= copy + transhdrlen; transhdrlen = 0; exthdrlen = 0; csummode = CHECKSUM_NONE; /* only the initial fragment is time stamped */ skb_shinfo(skb)->tx_flags = cork->tx_flags; cork->tx_flags = 0; skb_shinfo(skb)->tskey = tskey; tskey = 0; skb_zcopy_set(skb, uarg, &extra_uref); if ((flags & MSG_CONFIRM) && !skb_prev) skb_set_dst_pending_confirm(skb, 1); /* * Put the packet on the pending queue. */ if (!skb->destructor) { skb->destructor = sock_wfree; skb->sk = sk; wmem_alloc_delta += skb->truesize; } __skb_queue_tail(queue, skb); continue; } if (copy > length) copy = length; if (!(rt->dst.dev->features&NETIF_F_SG) && skb_tailroom(skb) >= copy) { unsigned int off; off = skb->len; if (getfrag(from, skb_put(skb, copy), offset, copy, off, skb) < 0) { __skb_trim(skb, off); err = -EFAULT; goto error; } } else if (!uarg || !uarg->zerocopy) { int i = skb_shinfo(skb)->nr_frags; err = -ENOMEM; if (!sk_page_frag_refill(sk, pfrag)) goto error; if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { err = -EMSGSIZE; if (i == MAX_SKB_FRAGS) goto error; __skb_fill_page_desc(skb, i, pfrag->page, pfrag->offset, 0); skb_shinfo(skb)->nr_frags = ++i; get_page(pfrag->page); } copy = min_t(int, copy, pfrag->size - pfrag->offset); if (getfrag(from, page_address(pfrag->page) + pfrag->offset, offset, copy, skb->len, skb) < 0) goto error_efault; pfrag->offset += copy; skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); skb->len += copy; skb->data_len += copy; skb->truesize += copy; wmem_alloc_delta += copy; } else { err = skb_zerocopy_iter_dgram(skb, from, copy); if (err < 0) goto error; } offset += copy; length -= copy; } if (wmem_alloc_delta) refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); return 0; error_efault: err = -EFAULT; error: if (uarg) sock_zerocopy_put_abort(uarg, extra_uref); cork->length -= length; IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS); refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); return err; } static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, struct ipcm_cookie *ipc, struct rtable **rtp) { struct ip_options_rcu *opt; struct rtable *rt; rt = *rtp; if (unlikely(!rt)) return -EFAULT; /* * setup for corking. */ opt = ipc->opt; if (opt) { if (!cork->opt) { cork->opt = kmalloc(sizeof(struct ip_options) + 40, sk->sk_allocation); if (unlikely(!cork->opt)) return -ENOBUFS; } memcpy(cork->opt, &opt->opt, sizeof(struct ip_options) + opt->opt.optlen); cork->flags |= IPCORK_OPT; cork->addr = ipc->addr; } cork->fragsize = ip_sk_use_pmtu(sk) ? dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu); if (!inetdev_valid_mtu(cork->fragsize)) return -ENETUNREACH; cork->gso_size = ipc->gso_size; cork->dst = &rt->dst; /* We stole this route, caller should not release it. */ *rtp = NULL; cork->length = 0; cork->ttl = ipc->ttl; cork->tos = ipc->tos; cork->mark = ipc->sockc.mark; cork->priority = ipc->priority; cork->transmit_time = ipc->sockc.transmit_time; cork->tx_flags = 0; sock_tx_timestamp(sk, ipc->sockc.tsflags, &cork->tx_flags); return 0; } /* * ip_append_data() and ip_append_page() can make one large IP datagram * from many pieces of data. Each pieces will be holded on the socket * until ip_push_pending_frames() is called. Each piece can be a page * or non-page data. * * Not only UDP, other transport protocols - e.g. raw sockets - can use * this interface potentially. * * LATER: length must be adjusted by pad at tail, when it is required. */ int ip_append_data(struct sock *sk, struct flowi4 *fl4, int getfrag(void *from, char *to, int offset, int len,