| 840 842 62 33 1791 1325 1325 705 7 1319 1327 911 7 706 677 711 2 1389 63 62 33 1329 1325 1322 99 99 99 31 28 2 2 30 26 8 31 31 31 26 30 2 30 31 31 31 844 840 843 14 6 830 6 764 767 768 2 767 123 123 123 5 9 9 841 7 6 29 29 30 30 1055 20 11 328 1 963 966 841 842 840 768 7 766 763 761 8 764 764 763 123 123 122 122 121 1 122 122 1054 360 966 768 123 4557 4540 1 1052 1 6 6 6 32 32 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Functions related to segment and merge handling */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/blk-integrity.h> #include <linux/scatterlist.h> #include <linux/part_stat.h> #include <linux/blk-cgroup.h> #include <trace/events/block.h> #include "blk.h" #include "blk-mq-sched.h" #include "blk-rq-qos.h" #include "blk-throttle.h" static inline void bio_get_first_bvec(struct bio *bio, struct bio_vec *bv) { *bv = mp_bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter); } static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv) { struct bvec_iter iter = bio->bi_iter; int idx; bio_get_first_bvec(bio, bv); if (bv->bv_len == bio->bi_iter.bi_size) return; /* this bio only has a single bvec */ bio_advance_iter(bio, &iter, iter.bi_size); if (!iter.bi_bvec_done) idx = iter.bi_idx - 1; else /* in the middle of bvec */ idx = iter.bi_idx; *bv = bio->bi_io_vec[idx]; /* * iter.bi_bvec_done records actual length of the last bvec * if this bio ends in the middle of one io vector */ if (iter.bi_bvec_done) bv->bv_len = iter.bi_bvec_done; } static inline bool bio_will_gap(struct request_queue *q, struct request *prev_rq, struct bio *prev, struct bio *next) { struct bio_vec pb, nb; if (!bio_has_data(prev) || !queue_virt_boundary(q)) return false; /* * Don't merge if the 1st bio starts with non-zero offset, otherwise it * is quite difficult to respect the sg gap limit. We work hard to * merge a huge number of small single bios in case of mkfs. */ if (prev_rq) bio_get_first_bvec(prev_rq->bio, &pb); else bio_get_first_bvec(prev, &pb); if (pb.bv_offset & queue_virt_boundary(q)) return true; /* * We don't need to worry about the situation that the merged segment * ends in unaligned virt boundary: * * - if 'pb' ends aligned, the merged segment ends aligned * - if 'pb' ends unaligned, the next bio must include * one single bvec of 'nb', otherwise the 'nb' can't * merge with 'pb' */ bio_get_last_bvec(prev, &pb); bio_get_first_bvec(next, &nb); if (biovec_phys_mergeable(q, &pb, &nb)) return false; return __bvec_gap_to_prev(&q->limits, &pb, nb.bv_offset); } static inline bool req_gap_back_merge(struct request *req, struct bio *bio) { return bio_will_gap(req->q, req, req->biotail, bio); } static inline bool req_gap_front_merge(struct request *req, struct bio *bio) { return bio_will_gap(req->q, NULL, bio, req->bio); } /* * The max size one bio can handle is UINT_MAX becasue bvec_iter.bi_size * is defined as 'unsigned int', meantime it has to be aligned to with the * logical block size, which is the minimum accepted unit by hardware. */ static unsigned int bio_allowed_max_sectors(const struct queue_limits *lim) { return round_down(UINT_MAX, lim->logical_block_size) >> SECTOR_SHIFT; } static struct bio *bio_split_discard(struct bio *bio, const struct queue_limits *lim, unsigned *nsegs, struct bio_set *bs) { unsigned int max_discard_sectors, granularity; sector_t tmp; unsigned split_sectors; *nsegs = 1; granularity = max(lim->discard_granularity >> 9, 1U); max_discard_sectors = min(lim->max_discard_sectors, bio_allowed_max_sectors(lim)); max_discard_sectors -= max_discard_sectors % granularity; if (unlikely(!max_discard_sectors)) return NULL; if (bio_sectors(bio) <= max_discard_sectors) return NULL; split_sectors = max_discard_sectors; /* * If the next starting sector would be misaligned, stop the discard at * the previous aligned sector. */ tmp = bio->bi_iter.bi_sector + split_sectors - ((lim->discard_alignment >> 9) % granularity); tmp = sector_div(tmp, granularity); if (split_sectors > tmp) split_sectors -= tmp; return bio_split(bio, split_sectors, GFP_NOIO, bs); } static struct bio *bio_split_write_zeroes(struct bio *bio, const struct queue_limits *lim, unsigned *nsegs, struct bio_set *bs) { *nsegs = 0; if (!lim->max_write_zeroes_sectors) return NULL; if (bio_sectors(bio) <= lim->max_write_zeroes_sectors) return NULL; return bio_split(bio, lim->max_write_zeroes_sectors, GFP_NOIO, bs); } static inline unsigned int blk_boundary_sectors(const struct queue_limits *lim, bool is_atomic) { /* * chunk_sectors must be a multiple of atomic_write_boundary_sectors if * both non-zero. */ if (is_atomic && lim->atomic_write_boundary_sectors) return lim->atomic_write_boundary_sectors; return lim->chunk_sectors; } /* * Return the maximum number of sectors from the start of a bio that may be * submitted as a single request to a block device. If enough sectors remain, * align the end to the physical block size. Otherwise align the end to the * logical block size. This approach minimizes the number of non-aligned * requests that are submitted to a block device if the start of a bio is not * aligned to a physical block boundary. */ static inline unsigned get_max_io_size(struct bio *bio, const struct queue_limits *lim) { unsigned pbs = lim->physical_block_size >> SECTOR_SHIFT; unsigned lbs = lim->logical_block_size >> SECTOR_SHIFT; bool is_atomic = bio->bi_opf & REQ_ATOMIC; unsigned boundary_sectors = blk_boundary_sectors(lim, is_atomic); unsigned max_sectors, start, end; /* * We ignore lim->max_sectors for atomic writes because it may less * than the actual bio size, which we cannot tolerate. */ if (is_atomic) max_sectors = lim->atomic_write_max_sectors; else max_sectors = lim->max_sectors; if (boundary_sectors) { max_sectors = min(max_sectors, blk_boundary_sectors_left(bio->bi_iter.bi_sector, boundary_sectors)); } start = bio->bi_iter.bi_sector & (pbs - 1); end = (start + max_sectors) & ~(pbs - 1); if (end > start) return end - start; return max_sectors & ~(lbs - 1); } /** * get_max_segment_size() - maximum number of bytes to add as a single segment * @lim: Request queue limits. * @paddr: address of the range to add * @len: maximum length available to add at @paddr * * Returns the maximum number of bytes of the range starting at @paddr that can * be added to a single segment. */ static inline unsigned get_max_segment_size(const struct queue_limits *lim, phys_addr_t paddr, unsigned int len) { /* * Prevent an overflow if mask = ULONG_MAX and offset = 0 by adding 1 * after having calculated the minimum. */ return min_t(unsigned long, len, min(lim->seg_boundary_mask - (lim->seg_boundary_mask & paddr), (unsigned long)lim->max_segment_size - 1) + 1); } /** * bvec_split_segs - verify whether or not a bvec should be split in the middle * @lim: [in] queue limits to split based on * @bv: [in] bvec to examine * @nsegs: [in,out] Number of segments in the bio being built. Incremented * by the number of segments from @bv that may be appended to that * bio without exceeding @max_segs * @bytes: [in,out] Number of bytes in the bio being built. Incremented * by the number of bytes from @bv that may be appended to that * bio without exceeding @max_bytes * @max_segs: [in] upper bound for *@nsegs * @max_bytes: [in] upper bound for *@bytes * * When splitting a bio, it can happen that a bvec is encountered that is too * big to fit in a single segment and hence that it has to be split in the * middle. This function verifies whether or not that should happen. The value * %true is returned if and only if appending the entire @bv to a bio with * *@nsegs segments and *@sectors sectors would make that bio unacceptable for * the block driver. */ static bool bvec_split_segs(const struct queue_limits *lim, const struct bio_vec *bv, unsigned *nsegs, unsigned *bytes, unsigned max_segs, unsigned max_bytes) { unsigned max_len = min(max_bytes, UINT_MAX) - *bytes; unsigned len = min(bv->bv_len, max_len); unsigned total_len = 0; unsigned seg_size = 0; while (len && *nsegs < max_segs) { seg_size = get_max_segment_size(lim, bvec_phys(bv) + total_len, len); (*nsegs)++; total_len += seg_size; len -= seg_size; if ((bv->bv_offset + total_len) & lim->virt_boundary_mask) break; } *bytes += total_len; /* tell the caller to split the bvec if it is too big to fit */ return len > 0 || bv->bv_len > max_len; } /** * bio_split_rw - split a bio in two bios * @bio: [in] bio to be split * @lim: [in] queue limits to split based on * @segs: [out] number of segments in the bio with the first half of the sectors * @bs: [in] bio set to allocate the clone from * @max_bytes: [in] maximum number of bytes per bio * * Clone @bio, update the bi_iter of the clone to represent the first sectors * of @bio and update @bio->bi_iter to represent the remaining sectors. The * following is guaranteed for the cloned bio: * - That it has at most @max_bytes worth of data * - That it has at most queue_max_segments(@q) segments. * * Except for discard requests the cloned bio will point at the bi_io_vec of * the original bio. It is the responsibility of the caller to ensure that the * original bio is not freed before the cloned bio. The caller is also * responsible for ensuring that @bs is only destroyed after processing of the * split bio has finished. */ struct bio *bio_split_rw(struct bio *bio, const struct queue_limits *lim, unsigned *segs, struct bio_set *bs, unsigned max_bytes) { struct bio_vec bv, bvprv, *bvprvp = NULL; struct bvec_iter iter; unsigned nsegs = 0, bytes = 0; bio_for_each_bvec(bv, bio, iter) { /* * If the queue doesn't support SG gaps and adding this * offset would create a gap, disallow it. */ if (bvprvp && bvec_gap_to_prev(lim, bvprvp, bv.bv_offset)) goto split; if (nsegs < lim->max_segments && bytes + bv.bv_len <= max_bytes && bv.bv_offset + bv.bv_len <= PAGE_SIZE) { nsegs++; bytes += bv.bv_len; } else { if (bvec_split_segs(lim, &bv, &nsegs, &bytes, lim->max_segments, max_bytes)) goto split; } bvprv = bv; bvprvp = &bvprv; } *segs = nsegs; return NULL; split: if (bio->bi_opf & REQ_ATOMIC) { bio->bi_status = BLK_STS_INVAL; bio_endio(bio); return ERR_PTR(-EINVAL); } /* * We can't sanely support splitting for a REQ_NOWAIT bio. End it * with EAGAIN if splitting is required and return an error pointer. */ if (bio->bi_opf & REQ_NOWAIT) { bio->bi_status = BLK_STS_AGAIN; bio_endio(bio); return ERR_PTR(-EAGAIN); } *segs = nsegs; /* * Individual bvecs might not be logical block aligned. Round down the * split size so that each bio is properly block size aligned, even if * we do not use the full hardware limits. */ bytes = ALIGN_DOWN(bytes, lim->logical_block_size); /* * Bio splitting may cause subtle trouble such as hang when doing sync * iopoll in direct IO routine. Given performance gain of iopoll for * big IO can be trival, disable iopoll when split needed. */ bio_clear_polled(bio); return bio_split(bio, bytes >> SECTOR_SHIFT, GFP_NOIO, bs); } EXPORT_SYMBOL_GPL(bio_split_rw); /** * __bio_split_to_limits - split a bio to fit the queue limits * @bio: bio to be split * @lim: queue limits to split based on * @nr_segs: returns the number of segments in the returned bio * * Check if @bio needs splitting based on the queue limits, and if so split off * a bio fitting the limits from the beginning of @bio and return it. @bio is * shortened to the remainder and re-submitted. * * The split bio is allocated from @q->bio_split, which is provided by the * block layer. */ struct bio *__bio_split_to_limits(struct bio *bio, const struct queue_limits *lim, unsigned int *nr_segs) { struct bio_set *bs = &bio->bi_bdev->bd_disk->bio_split; struct bio *split; switch (bio_op(bio)) { case REQ_OP_DISCARD: case REQ_OP_SECURE_ERASE: split = bio_split_discard(bio, lim, nr_segs, bs); break; case REQ_OP_WRITE_ZEROES: split = bio_split_write_zeroes(bio, lim, nr_segs, bs); break; default: split = bio_split_rw(bio, lim, nr_segs, bs, get_max_io_size(bio, lim) << SECTOR_SHIFT); if (IS_ERR(split)) return NULL; break; } if (split) { /* there isn't chance to merge the split bio */ split->bi_opf |= REQ_NOMERGE; blkcg_bio_issue_init(split); bio_chain(split, bio); trace_block_split(split, bio->bi_iter.bi_sector); WARN_ON_ONCE(bio_zone_write_plugging(bio)); submit_bio_noacct(bio); return split; } return bio; } /** * bio_split_to_limits - split a bio to fit the queue limits * @bio: bio to be split * * Check if @bio needs splitting based on the queue limits of @bio->bi_bdev, and * if so split off a bio fitting the limits from the beginning of @bio and * return it. @bio is shortened to the remainder and re-submitted. * * The split bio is allocated from @q->bio_split, which is provided by the * block layer. */ struct bio *bio_split_to_limits(struct bio *bio) { const struct queue_limits *lim = &bdev_get_queue(bio->bi_bdev)->limits; unsigned int nr_segs; if (bio_may_exceed_limits(bio, lim)) return __bio_split_to_limits(bio, lim, &nr_segs); return bio; } EXPORT_SYMBOL(bio_split_to_limits); unsigned int blk_recalc_rq_segments(struct request *rq) { unsigned int nr_phys_segs = 0; unsigned int bytes = 0; struct req_iterator iter; struct bio_vec bv; if (!rq->bio) return 0; switch (bio_op(rq->bio)) { case REQ_OP_DISCARD: case REQ_OP_SECURE_ERASE: if (queue_max_discard_segments(rq->q) > 1) { struct bio *bio = rq->bio; for_each_bio(bio) nr_phys_segs++; return nr_phys_segs; } return 1; case REQ_OP_WRITE_ZEROES: return 0; default: break; } rq_for_each_bvec(bv, rq, iter) bvec_split_segs(&rq->q->limits, &bv, &nr_phys_segs, &bytes, UINT_MAX, UINT_MAX); return nr_phys_segs; } static inline struct scatterlist *blk_next_sg(struct scatterlist **sg, struct scatterlist *sglist) { if (!*sg) return sglist; /* * If the driver previously mapped a shorter list, we could see a * termination bit prematurely unless it fully inits the sg table * on each mapping. We KNOW that there must be more entries here * or the driver would be buggy, so force clear the termination bit * to avoid doing a full sg_init_table() in drivers for each command. */ sg_unmark_end(*sg); return sg_next(*sg); } static unsigned blk_bvec_map_sg(struct request_queue *q, struct bio_vec *bvec, struct scatterlist *sglist, struct scatterlist **sg) { unsigned nbytes = bvec->bv_len; unsigned nsegs = 0, total = 0; while (nbytes > 0) { unsigned offset = bvec->bv_offset + total; unsigned len = get_max_segment_size(&q->limits, bvec_phys(bvec) + total, nbytes); struct page *page = bvec->bv_page; /* * Unfortunately a fair number of drivers barf on scatterlists * that have an offset larger than PAGE_SIZE, despite other * subsystems dealing with that invariant just fine. For now * stick to the legacy format where we never present those from * the block layer, but the code below should be removed once * these offenders (mostly MMC/SD drivers) are fixed. */ page += (offset >> PAGE_SHIFT); offset &= ~PAGE_MASK; *sg = blk_next_sg(sg, sglist); sg_set_page(*sg, page, len, offset); total += len; nbytes -= len; nsegs++; } return nsegs; } static inline int __blk_bvec_map_sg(struct bio_vec bv, struct scatterlist *sglist, struct scatterlist **sg) { *sg = blk_next_sg(sg, sglist); sg_set_page(*sg, bv.bv_page, bv.bv_len, bv.bv_offset); return 1; } /* only try to merge bvecs into one sg if they are from two bios */ static inline bool __blk_segment_map_sg_merge(struct request_queue *q, struct bio_vec *bvec, struct bio_vec *bvprv, struct scatterlist **sg) { int nbytes = bvec->bv_len; if (!*sg) return false; if ((*sg)->length + nbytes > queue_max_segment_size(q)) return false; if (!biovec_phys_mergeable(q, bvprv, bvec)) return false; (*sg)->length += nbytes; return true; } static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio, struct scatterlist *sglist, struct scatterlist **sg) { struct bio_vec bvec, bvprv = { NULL }; struct bvec_iter iter; int nsegs = 0; bool new_bio = false; for_each_bio(bio) { bio_for_each_bvec(bvec, bio, iter) { /* * Only try to merge bvecs from two bios given we * have done bio internal merge when adding pages * to bio */ if (new_bio && __blk_segment_map_sg_merge(q, &bvec, &bvprv, sg)) goto next_bvec; if (bvec.bv_offset + bvec.bv_len <= PAGE_SIZE) nsegs += __blk_bvec_map_sg(bvec, sglist, sg); else nsegs += blk_bvec_map_sg(q, &bvec, sglist, sg); next_bvec: new_bio = false; } if (likely(bio->bi_iter.bi_size)) { bvprv = bvec; new_bio = true; } } return nsegs; } /* * map a request to scatterlist, return number of sg entries setup. Caller * must make sure sg can hold rq->nr_phys_segments entries */ int __blk_rq_map_sg(struct request_queue *q, struct request *rq, struct scatterlist *sglist, struct scatterlist **last_sg) { int nsegs = 0; if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) nsegs = __blk_bvec_map_sg(rq->special_vec, sglist, last_sg); else if (rq->bio) nsegs = __blk_bios_map_sg(q, rq->bio, sglist, last_sg); if (*last_sg) sg_mark_end(*last_sg); /* * Something must have been wrong if the figured number of * segment is bigger than number of req's physical segments */ WARN_ON(nsegs > blk_rq_nr_phys_segments(rq)); return nsegs; } EXPORT_SYMBOL(__blk_rq_map_sg); static inline unsigned int blk_rq_get_max_sectors(struct request *rq, sector_t offset) { struct request_queue *q = rq->q; struct queue_limits *lim = &q->limits; unsigned int max_sectors, boundary_sectors; bool is_atomic = rq->cmd_flags & REQ_ATOMIC; if (blk_rq_is_passthrough(rq)) return q->limits.max_hw_sectors; boundary_sectors = blk_boundary_sectors(lim, is_atomic); max_sectors = blk_queue_get_max_sectors(rq); if (!boundary_sectors || req_op(rq) == REQ_OP_DISCARD || req_op(rq) == REQ_OP_SECURE_ERASE) return max_sectors; return min(max_sectors, blk_boundary_sectors_left(offset, boundary_sectors)); } static inline int ll_new_hw_segment(struct request *req, struct bio *bio, unsigned int nr_phys_segs) { if (!blk_cgroup_mergeable(req, bio)) goto no_merge; if (blk_integrity_merge_bio(req->q, req, bio) == false) goto no_merge; /* discard request merge won't add new segment */ if (req_op(req) == REQ_OP_DISCARD) return 1; if (req->nr_phys_segments + nr_phys_segs > blk_rq_get_max_segments(req)) goto no_merge; /* * This will form the start of a new hw segment. Bump both * counters. */ req->nr_phys_segments += nr_phys_segs; return 1; no_merge: req_set_nomerge(req->q, req); return 0; } int ll_back_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs) { if (req_gap_back_merge(req, bio)) return 0; if (blk_integrity_rq(req) && integrity_req_gap_back_merge(req, bio)) return 0; if (!bio_crypt_ctx_back_mergeable(req, bio)) return 0; if (blk_rq_sectors(req) + bio_sectors(bio) > blk_rq_get_max_sectors(req, blk_rq_pos(req))) { req_set_nomerge(req->q, req); return 0; } return ll_new_hw_segment(req, bio, nr_segs); } static int ll_front_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs) { if (req_gap_front_merge(req, bio)) return 0; if (blk_integrity_rq(req) && integrity_req_gap_front_merge(req, bio)) return 0; if (!bio_crypt_ctx_front_mergeable(req, bio)) return 0; if (blk_rq_sectors(req) + bio_sectors(bio) > blk_rq_get_max_sectors(req, bio->bi_iter.bi_sector)) { req_set_nomerge(req->q, req); return 0; } return ll_new_hw_segment(req, bio, nr_segs); } static bool req_attempt_discard_merge(struct request_queue *q, struct request *req, struct request *next) { unsigned short segments = blk_rq_nr_discard_segments(req); if (segments >= queue_max_discard_segments(q)) goto no_merge; if (blk_rq_sectors(req) + bio_sectors(next->bio) > blk_rq_get_max_sectors(req, blk_rq_pos(req))) goto no_merge; req->nr_phys_segments = segments + blk_rq_nr_discard_segments(next); return true; no_merge: req_set_nomerge(q, req); return false; } static int ll_merge_requests_fn(struct request_queue *q, struct request *req, struct request *next) { int total_phys_segments; if (req_gap_back_merge(req, next->bio)) return 0; /* * Will it become too large? */ if ((blk_rq_sectors(req) + blk_rq_sectors(next)) > blk_rq_get_max_sectors(req, blk_rq_pos(req))) return 0; total_phys_segments = req->nr_phys_segments + next->nr_phys_segments; if (total_phys_segments > blk_rq_get_max_segments(req)) return 0; if (!blk_cgroup_mergeable(req, next->bio)) return 0; if (blk_integrity_merge_rq(q, req, next) == false) return 0; if (!bio_crypt_ctx_merge_rq(req, next)) return 0; /* Merge is OK... */ req->nr_phys_segments = total_phys_segments; return 1; } /** * blk_rq_set_mixed_merge - mark a request as mixed merge * @rq: request to mark as mixed merge * * Description: * @rq is about to be mixed merged. Make sure the attributes * which can be mixed are set in each bio and mark @rq as mixed * merged. */ static void blk_rq_set_mixed_merge(struct request *rq) { blk_opf_t ff = rq->cmd_flags & REQ_FAILFAST_MASK; struct bio *bio; if (rq->rq_flags & RQF_MIXED_MERGE) return; /* * @rq will no longer represent mixable attributes for all the * contained bios. It will just track those of the first one. * Distributes the attributs to each bio. */ for (bio = rq->bio; bio; bio = bio->bi_next) { WARN_ON_ONCE((bio->bi_opf & REQ_FAILFAST_MASK) && (bio->bi_opf & REQ_FAILFAST_MASK) != ff); bio->bi_opf |= ff; } rq->rq_flags |= RQF_MIXED_MERGE; } static inline blk_opf_t bio_failfast(const struct bio *bio) { if (bio->bi_opf & REQ_RAHEAD) return REQ_FAILFAST_MASK; return bio->bi_opf & REQ_FAILFAST_MASK; } /* * After we are marked as MIXED_MERGE, any new RA bio has to be updated * as failfast, and request's failfast has to be updated in case of * front merge. */ static inline void blk_update_mixed_merge(struct request *req, struct bio *bio, bool front_merge) { if (req->rq_flags & RQF_MIXED_MERGE) { if (bio->bi_opf & REQ_RAHEAD) bio->bi_opf |= REQ_FAILFAST_MASK; if (front_merge) { req->cmd_flags &= ~REQ_FAILFAST_MASK; req->cmd_flags |= bio->bi_opf & REQ_FAILFAST_MASK; } } } static void blk_account_io_merge_request(struct request *req) { if (blk_do_io_stat(req)) { part_stat_lock(); part_stat_inc(req->part, merges[op_stat_group(req_op(req))]); part_stat_local_dec(req->part, in_flight[op_is_write(req_op(req))]); part_stat_unlock(); } } static enum elv_merge blk_try_req_merge(struct request *req, struct request *next) { if (blk_discard_mergable(req)) return ELEVATOR_DISCARD_MERGE; else if (blk_rq_pos(req) + blk_rq_sectors(req) == blk_rq_pos(next)) return ELEVATOR_BACK_MERGE; return ELEVATOR_NO_MERGE; } static bool blk_atomic_write_mergeable_rq_bio(struct request *rq, struct bio *bio) { return (rq->cmd_flags & REQ_ATOMIC) == (bio->bi_opf & REQ_ATOMIC); } static bool blk_atomic_write_mergeable_rqs(struct request *rq, struct request *next) { return (rq->cmd_flags & REQ_ATOMIC) == (next->cmd_flags & REQ_ATOMIC); } /* * For non-mq, this has to be called with the request spinlock acquired. * For mq with scheduling, the appropriate queue wide lock should be held. */ static struct request *attempt_merge(struct request_queue *q, struct request *req, struct request *next) { if (!rq_mergeable(req) || !rq_mergeable(next)) return NULL; if (req_op(req) != req_op(next)) return NULL; if (rq_data_dir(req) != rq_data_dir(next)) return NULL; /* Don't merge requests with different write hints. */ if (req->write_hint != next->write_hint) return NULL; if (req->ioprio != next->ioprio) return NULL; if (!blk_atomic_write_mergeable_rqs(req, next)) return NULL; /* * If we are allowed to merge, then append bio list * from next to rq and release next. merge_requests_fn * will have updated segment counts, update sector * counts here. Handle DISCARDs separately, as they * have separate settings. */ switch (blk_try_req_merge(req, next)) { case ELEVATOR_DISCARD_MERGE: if (!req_attempt_discard_merge(q, req, next)) return NULL; break; case ELEVATOR_BACK_MERGE: if (!ll_merge_requests_fn(q, req, next)) return NULL; break; default: return NULL; } /* * If failfast settings disagree or any of the two is already * a mixed merge, mark both as mixed before proceeding. This * makes sure that all involved bios have mixable attributes * set properly. */ if (((req->rq_flags | next->rq_flags) & RQF_MIXED_MERGE) || (req->cmd_flags & REQ_FAILFAST_MASK) != (next->cmd_flags & REQ_FAILFAST_MASK)) { blk_rq_set_mixed_merge(req); blk_rq_set_mixed_merge(next); } /* * At this point we have either done a back merge or front merge. We * need the smaller start_time_ns of the merged requests to be the * current request for accounting purposes. */ if (next->start_time_ns < req->start_time_ns) req->start_time_ns = next->start_time_ns; req->biotail->bi_next = next->bio; req->biotail = next->biotail; req->__data_len += blk_rq_bytes(next); if (!blk_discard_mergable(req)) elv_merge_requests(q, req, next); blk_crypto_rq_put_keyslot(next); /* * 'next' is going away, so update stats accordingly */ blk_account_io_merge_request(next); trace_block_rq_merge(next); /* * ownership of bio passed from next to req, return 'next' for * the caller to free */ next->bio = NULL; return next; } static struct request *attempt_back_merge(struct request_queue *q, struct request *rq) { struct request *next = elv_latter_request(q, rq); if (next) return attempt_merge(q, rq, next); return NULL; } static struct request *attempt_front_merge(struct request_queue *q, struct request *rq) { struct request *prev = elv_former_request(q, rq); if (prev) return attempt_merge(q, prev, rq); return NULL; } /* * Try to merge 'next' into 'rq'. Return true if the merge happened, false * otherwise. The caller is responsible for freeing 'next' if the merge * happened. */ bool blk_attempt_req_merge(struct request_queue *q, struct request *rq, struct request *next) { return attempt_merge(q, rq, next); } bool blk_rq_merge_ok(struct request *rq, struct bio *bio) { if (!rq_mergeable(rq) || !bio_mergeable(bio)) return false; if (req_op(rq) != bio_op(bio)) return false; /* different data direction or already started, don't merge */ if (bio_data_dir(bio) != rq_data_dir(rq)) return false; /* don't merge across cgroup boundaries */ if (!blk_cgroup_mergeable(rq, bio)) return false; /* only merge integrity protected bio into ditto rq */ if (blk_integrity_merge_bio(rq->q, rq, bio) == false) return false; /* Only merge if the crypt contexts are compatible */ if (!bio_crypt_rq_ctx_compatible(rq, bio)) return false; /* Don't merge requests with different write hints. */ if (rq->write_hint != bio->bi_write_hint) return false; if (rq->ioprio != bio_prio(bio)) return false; if (blk_atomic_write_mergeable_rq_bio(rq, bio) == false) return false; return true; } enum elv_merge blk_try_merge(struct request *rq, struct bio *bio) { if (blk_discard_mergable(rq)) return ELEVATOR_DISCARD_MERGE; else if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector) return ELEVATOR_BACK_MERGE; else if (blk_rq_pos(rq) - bio_sectors(bio) == bio->bi_iter.bi_sector) return ELEVATOR_FRONT_MERGE; return ELEVATOR_NO_MERGE; } static void blk_account_io_merge_bio(struct request *req) { if (!blk_do_io_stat(req)) return; part_stat_lock(); part_stat_inc(req->part, merges[op_stat_group(req_op(req))]); part_stat_unlock(); } enum bio_merge_status bio_attempt_back_merge(struct request *req, struct bio *bio, unsigned int nr_segs) { const blk_opf_t ff = bio_failfast(bio); if (!ll_back_merge_fn(req, bio, nr_segs)) return BIO_MERGE_FAILED; trace_block_bio_backmerge(bio); rq_qos_merge(req->q, req, bio); if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) blk_rq_set_mixed_merge(req); blk_update_mixed_merge(req, bio, false); if (req->rq_flags & RQF_ZONE_WRITE_PLUGGING) blk_zone_write_plug_bio_merged(bio); req->biotail->bi_next = bio; req->biotail = bio; req->__data_len += bio->bi_iter.bi_size; bio_crypt_free_ctx(bio); blk_account_io_merge_bio(req); return BIO_MERGE_OK; } static enum bio_merge_status bio_attempt_front_merge(struct request *req, struct bio *bio, unsigned int nr_segs) { const blk_opf_t ff = bio_failfast(bio); /* * A front merge for writes to sequential zones of a zoned block device * can happen only if the user submitted writes out of order. Do not * merge such write to let it fail. */ if (req->rq_flags & RQF_ZONE_WRITE_PLUGGING) return BIO_MERGE_FAILED; if (!ll_front_merge_fn(req, bio, nr_segs)) return BIO_MERGE_FAILED; trace_block_bio_frontmerge(bio); rq_qos_merge(req->q, req, bio); if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) blk_rq_set_mixed_merge(req); blk_update_mixed_merge(req, bio, true); bio->bi_next = req->bio; req->bio = bio; req->__sector = bio->bi_iter.bi_sector; req->__data_len += bio->bi_iter.bi_size; bio_crypt_do_front_merge(req, bio); blk_account_io_merge_bio(req); return BIO_MERGE_OK; } static enum bio_merge_status bio_attempt_discard_merge(struct request_queue *q, struct request *req, struct bio *bio) { unsigned short segments = blk_rq_nr_discard_segments(req); if (segments >= queue_max_discard_segments(q)) goto no_merge; if (blk_rq_sectors(req) + bio_sectors(bio) > blk_rq_get_max_sectors(req, blk_rq_pos(req))) goto no_merge; rq_qos_merge(q, req, bio); req->biotail->bi_next = bio; req->biotail = bio; req->__data_len += bio->bi_iter.bi_size; req->nr_phys_segments = segments + 1; blk_account_io_merge_bio(req); return BIO_MERGE_OK; no_merge: req_set_nomerge(q, req); return BIO_MERGE_FAILED; } static enum bio_merge_status blk_attempt_bio_merge(struct request_queue *q, struct request *rq, struct bio *bio, unsigned int nr_segs, bool sched_allow_merge) { if (!blk_rq_merge_ok(rq, bio)) return BIO_MERGE_NONE; switch (blk_try_merge(rq, bio)) { case ELEVATOR_BACK_MERGE: if (!sched_allow_merge || blk_mq_sched_allow_merge(q, rq, bio)) return bio_attempt_back_merge(rq, bio, nr_segs); break; case ELEVATOR_FRONT_MERGE: if (!sched_allow_merge || blk_mq_sched_allow_merge(q, rq, bio)) return bio_attempt_front_merge(rq, bio, nr_segs); break; case ELEVATOR_DISCARD_MERGE: return bio_attempt_discard_merge(q, rq, bio); default: return BIO_MERGE_NONE; } return BIO_MERGE_FAILED; } /** * blk_attempt_plug_merge - try to merge with %current's plugged list * @q: request_queue new bio is being queued at * @bio: new bio being queued * @nr_segs: number of segments in @bio * from the passed in @q already in the plug list * * Determine whether @bio being queued on @q can be merged with the previous * request on %current's plugged list. Returns %true if merge was successful, * otherwise %false. * * Plugging coalesces IOs from the same issuer for the same purpose without * going through @q->queue_lock. As such it's more of an issuing mechanism * than scheduling, and the request, while may have elvpriv data, is not * added on the elevator at this point. In addition, we don't have * reliable access to the elevator outside queue lock. Only check basic * merging parameters without querying the elevator. * * Caller must ensure !blk_queue_nomerges(q) beforehand. */ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs) { struct blk_plug *plug = current->plug; struct request *rq; if (!plug || rq_list_empty(plug->mq_list)) return false; rq_list_for_each(&plug->mq_list, rq) { if (rq->q == q) { if (blk_attempt_bio_merge(q, rq, bio, nr_segs, false) == BIO_MERGE_OK) return true; break; } /* * Only keep iterating plug list for merges if we have multiple * queues */ if (!plug->multiple_queues) break; } return false; } /* * Iterate list of requests and see if we can merge this bio with any * of them. */ bool blk_bio_list_merge(struct request_queue *q, struct list_head *list, struct bio *bio, unsigned int nr_segs) { struct request *rq; int checked = 8; list_for_each_entry_reverse(rq, list, queuelist) { if (!checked--) break; switch (blk_attempt_bio_merge(q, rq, bio, nr_segs, true)) { case BIO_MERGE_NONE: continue; case BIO_MERGE_OK: return true; case BIO_MERGE_FAILED: return false; } } return false; } EXPORT_SYMBOL_GPL(blk_bio_list_merge); bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs, struct request **merged_request) { struct request *rq; switch (elv_merge(q, &rq, bio)) { case ELEVATOR_BACK_MERGE: if (!blk_mq_sched_allow_merge(q, rq, bio)) return false; if (bio_attempt_back_merge(rq, bio, nr_segs) != BIO_MERGE_OK) return false; *merged_request = attempt_back_merge(q, rq); if (!*merged_request) elv_merged_request(q, rq, ELEVATOR_BACK_MERGE); return true; case ELEVATOR_FRONT_MERGE: if (!blk_mq_sched_allow_merge(q, rq, bio)) return false; if (bio_attempt_front_merge(rq, bio, nr_segs) != BIO_MERGE_OK) return false; *merged_request = attempt_front_merge(q, rq); if (!*merged_request) elv_merged_request(q, rq, ELEVATOR_FRONT_MERGE); return true; case ELEVATOR_DISCARD_MERGE: return bio_attempt_discard_merge(q, rq, bio) == BIO_MERGE_OK; default: return false; } } EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge); |
| 11 2 13 13 2183 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_WAIT_H #define _LINUX_WAIT_H /* * Linux wait queue related types and methods */ #include <linux/list.h> #include <linux/stddef.h> #include <linux/spinlock.h> #include <asm/current.h> typedef struct wait_queue_entry wait_queue_entry_t; typedef int (*wait_queue_func_t)(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key); int default_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key); /* wait_queue_entry::flags */ #define WQ_FLAG_EXCLUSIVE 0x01 #define WQ_FLAG_WOKEN 0x02 #define WQ_FLAG_CUSTOM 0x04 #define WQ_FLAG_DONE 0x08 #define WQ_FLAG_PRIORITY 0x10 /* * A single wait-queue entry structure: */ struct wait_queue_entry { unsigned int flags; void *private; wait_queue_func_t func; struct list_head entry; }; struct wait_queue_head { spinlock_t lock; struct list_head head; }; typedef struct wait_queue_head wait_queue_head_t; struct task_struct; /* * Macros for declaration and initialisaton of the datatypes */ #define __WAITQUEUE_INITIALIZER(name, tsk) { \ .private = tsk, \ .func = default_wake_function, \ .entry = { NULL, NULL } } #define DECLARE_WAITQUEUE(name, tsk) \ struct wait_queue_entry name = __WAITQUEUE_INITIALIZER(name, tsk) #define __WAIT_QUEUE_HEAD_INITIALIZER(name) { \ .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ .head = LIST_HEAD_INIT(name.head) } #define DECLARE_WAIT_QUEUE_HEAD(name) \ struct wait_queue_head name = __WAIT_QUEUE_HEAD_INITIALIZER(name) extern void __init_waitqueue_head(struct wait_queue_head *wq_head, const char *name, struct lock_class_key *); #define init_waitqueue_head(wq_head) \ do { \ static struct lock_class_key __key; \ \ __init_waitqueue_head((wq_head), #wq_head, &__key); \ } while (0) #ifdef CONFIG_LOCKDEP # define __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) \ ({ init_waitqueue_head(&name); name; }) # define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) \ struct wait_queue_head name = __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) #else # define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) DECLARE_WAIT_QUEUE_HEAD(name) #endif static inline void init_waitqueue_entry(struct wait_queue_entry *wq_entry, struct task_struct *p) { wq_entry->flags = 0; wq_entry->private = p; wq_entry->func = default_wake_function; } static inline void init_waitqueue_func_entry(struct wait_queue_entry *wq_entry, wait_queue_func_t func) { wq_entry->flags = 0; wq_entry->private = NULL; wq_entry->func = func; } /** * waitqueue_active -- locklessly test for waiters on the queue * @wq_head: the waitqueue to test for waiters * * returns true if the wait list is not empty * * NOTE: this function is lockless and requires care, incorrect usage _will_ * lead to sporadic and non-obvious failure. * * Use either while holding wait_queue_head::lock or when used for wakeups * with an extra smp_mb() like:: * * CPU0 - waker CPU1 - waiter * * for (;;) { * @cond = true; prepare_to_wait(&wq_head, &wait, state); * smp_mb(); // smp_mb() from set_current_state() * if (waitqueue_active(wq_head)) if (@cond) * wake_up(wq_head); break; * schedule(); * } * finish_wait(&wq_head, &wait); * * Because without the explicit smp_mb() it's possible for the * waitqueue_active() load to get hoisted over the @cond store such that we'll * observe an empty wait list while the waiter might not observe @cond. * * Also note that this 'optimization' trades a spin_lock() for an smp_mb(), * which (when the lock is uncontended) are of roughly equal cost. */ static inline int waitqueue_active(struct wait_queue_head *wq_head) { return !list_empty(&wq_head->head); } /** * wq_has_single_sleeper - check if there is only one sleeper * @wq_head: wait queue head * * Returns true of wq_head has only one sleeper on the list. * * Please refer to the comment for waitqueue_active. */ static inline bool wq_has_single_sleeper(struct wait_queue_head *wq_head) { return list_is_singular(&wq_head->head); } /** * wq_has_sleeper - check if there are any waiting processes * @wq_head: wait queue head * * Returns true if wq_head has waiting processes * * Please refer to the comment for waitqueue_active. */ static inline bool wq_has_sleeper(struct wait_queue_head *wq_head) { /* * We need to be sure we are in sync with the * add_wait_queue modifications to the wait queue. * * This memory barrier should be paired with one on the * waiting side. */ smp_mb(); return waitqueue_active(wq_head); } extern void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); extern void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); extern void add_wait_queue_priority(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); extern void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); static inline void __add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { struct list_head *head = &wq_head->head; struct wait_queue_entry *wq; list_for_each_entry(wq, &wq_head->head, entry) { if (!(wq->flags & WQ_FLAG_PRIORITY)) break; head = &wq->entry; } list_add(&wq_entry->entry, head); } /* * Used for wake-one threads: */ static inline void __add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { wq_entry->flags |= WQ_FLAG_EXCLUSIVE; __add_wait_queue(wq_head, wq_entry); } static inline void __add_wait_queue_entry_tail(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { list_add_tail(&wq_entry->entry, &wq_head->head); } static inline void __add_wait_queue_entry_tail_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { wq_entry->flags |= WQ_FLAG_EXCLUSIVE; __add_wait_queue_entry_tail(wq_head, wq_entry); } static inline void __remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { list_del(&wq_entry->entry); } int __wake_up(struct wait_queue_head *wq_head, unsigned int mode, int nr, void *key); void __wake_up_on_current_cpu(struct wait_queue_head *wq_head, unsigned int mode, void *key); void __wake_up_locked_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); void __wake_up_locked_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr); void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode); void __wake_up_pollfree(struct wait_queue_head *wq_head); #define wake_up(x) __wake_up(x, TASK_NORMAL, 1, NULL) #define wake_up_nr(x, nr) __wake_up(x, TASK_NORMAL, nr, NULL) #define wake_up_all(x) __wake_up(x, TASK_NORMAL, 0, NULL) #define wake_up_locked(x) __wake_up_locked((x), TASK_NORMAL, 1) #define wake_up_all_locked(x) __wake_up_locked((x), TASK_NORMAL, 0) #define wake_up_interruptible(x) __wake_up(x, TASK_INTERRUPTIBLE, 1, NULL) #define wake_up_interruptible_nr(x, nr) __wake_up(x, TASK_INTERRUPTIBLE, nr, NULL) #define wake_up_interruptible_all(x) __wake_up(x, TASK_INTERRUPTIBLE, 0, NULL) #define wake_up_interruptible_sync(x) __wake_up_sync((x), TASK_INTERRUPTIBLE) /* * Wakeup macros to be used to report events to the targets. */ #define poll_to_key(m) ((void *)(__force uintptr_t)(__poll_t)(m)) #define key_to_poll(m) ((__force __poll_t)(uintptr_t)(void *)(m)) #define wake_up_poll(x, m) \ __wake_up(x, TASK_NORMAL, 1, poll_to_key(m)) #define wake_up_poll_on_current_cpu(x, m) \ __wake_up_on_current_cpu(x, TASK_NORMAL, poll_to_key(m)) #define wake_up_locked_poll(x, m) \ __wake_up_locked_key((x), TASK_NORMAL, poll_to_key(m)) #define wake_up_interruptible_poll(x, m) \ __wake_up(x, TASK_INTERRUPTIBLE, 1, poll_to_key(m)) #define wake_up_interruptible_sync_poll(x, m) \ __wake_up_sync_key((x), TASK_INTERRUPTIBLE, poll_to_key(m)) #define wake_up_interruptible_sync_poll_locked(x, m) \ __wake_up_locked_sync_key((x), TASK_INTERRUPTIBLE, poll_to_key(m)) /** * wake_up_pollfree - signal that a polled waitqueue is going away * @wq_head: the wait queue head * * In the very rare cases where a ->poll() implementation uses a waitqueue whose * lifetime is tied to a task rather than to the 'struct file' being polled, * this function must be called before the waitqueue is freed so that * non-blocking polls (e.g. epoll) are notified that the queue is going away. * * The caller must also RCU-delay the freeing of the wait_queue_head, e.g. via * an explicit synchronize_rcu() or call_rcu(), or via SLAB_TYPESAFE_BY_RCU. */ static inline void wake_up_pollfree(struct wait_queue_head *wq_head) { /* * For performance reasons, we don't always take the queue lock here. * Therefore, we might race with someone removing the last entry from * the queue, and proceed while they still hold the queue lock. * However, rcu_read_lock() is required to be held in such cases, so we * can safely proceed with an RCU-delayed free. */ if (waitqueue_active(wq_head)) __wake_up_pollfree(wq_head); } #define ___wait_cond_timeout(condition) \ ({ \ bool __cond = (condition); \ if (__cond && !__ret) \ __ret = 1; \ __cond || !__ret; \ }) #define ___wait_is_interruptible(state) \ (!__builtin_constant_p(state) || \ (state & (TASK_INTERRUPTIBLE | TASK_WAKEKILL))) extern void init_wait_entry(struct wait_queue_entry *wq_entry, int flags); /* * The below macro ___wait_event() has an explicit shadow of the __ret * variable when used from the wait_event_*() macros. * * This is so that both can use the ___wait_cond_timeout() construct * to wrap the condition. * * The type inconsistency of the wait_event_*() __ret variable is also * on purpose; we use long where we can return timeout values and int * otherwise. */ #define ___wait_event(wq_head, condition, state, exclusive, ret, cmd) \ ({ \ __label__ __out; \ struct wait_queue_entry __wq_entry; \ long __ret = ret; /* explicit shadow */ \ \ init_wait_entry(&__wq_entry, exclusive ? WQ_FLAG_EXCLUSIVE : 0); \ for (;;) { \ long __int = prepare_to_wait_event(&wq_head, &__wq_entry, state);\ \ if (condition) \ break; \ \ if (___wait_is_interruptible(state) && __int) { \ __ret = __int; \ goto __out; \ } \ \ cmd; \ } \ finish_wait(&wq_head, &__wq_entry); \ __out: __ret; \ }) #define __wait_event(wq_head, condition) \ (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ schedule()) /** * wait_event - sleep until a condition gets true * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. */ #define wait_event(wq_head, condition) \ do { \ might_sleep(); \ if (condition) \ break; \ __wait_event(wq_head, condition); \ } while (0) #define __io_wait_event(wq_head, condition) \ (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ io_schedule()) /* * io_wait_event() -- like wait_event() but with io_schedule() */ #define io_wait_event(wq_head, condition) \ do { \ might_sleep(); \ if (condition) \ break; \ __io_wait_event(wq_head, condition); \ } while (0) #define __wait_event_freezable(wq_head, condition) \ ___wait_event(wq_head, condition, (TASK_INTERRUPTIBLE|TASK_FREEZABLE), \ 0, 0, schedule()) /** * wait_event_freezable - sleep (or freeze) until a condition gets true * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE -- so as not to contribute * to system load) until the @condition evaluates to true. The * @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. */ #define wait_event_freezable(wq_head, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_freezable(wq_head, condition); \ __ret; \ }) #define __wait_event_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_UNINTERRUPTIBLE, 0, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_timeout - sleep until a condition gets true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * Returns: * 0 if the @condition evaluated to %false after the @timeout elapsed, * 1 if the @condition evaluated to %true after the @timeout elapsed, * or the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed. */ #define wait_event_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_timeout(wq_head, condition, timeout); \ __ret; \ }) #define __wait_event_freezable_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ (TASK_INTERRUPTIBLE|TASK_FREEZABLE), 0, timeout, \ __ret = schedule_timeout(__ret)) /* * like wait_event_timeout() -- except it uses TASK_INTERRUPTIBLE to avoid * increasing load and is freezable. */ #define wait_event_freezable_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_freezable_timeout(wq_head, condition, timeout); \ __ret; \ }) #define __wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2) \ (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 1, 0, \ cmd1; schedule(); cmd2) /* * Just like wait_event_cmd(), except it sets exclusive flag */ #define wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2) \ do { \ if (condition) \ break; \ __wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2); \ } while (0) #define __wait_event_cmd(wq_head, condition, cmd1, cmd2) \ (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ cmd1; schedule(); cmd2) /** * wait_event_cmd - sleep until a condition gets true * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @cmd1: the command will be executed before sleep * @cmd2: the command will be executed after sleep * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. */ #define wait_event_cmd(wq_head, condition, cmd1, cmd2) \ do { \ if (condition) \ break; \ __wait_event_cmd(wq_head, condition, cmd1, cmd2); \ } while (0) #define __wait_event_interruptible(wq_head, condition) \ ___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \ schedule()) /** * wait_event_interruptible - sleep until a condition gets true * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_interruptible(wq_head, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_interruptible(wq_head, condition); \ __ret; \ }) #define __wait_event_interruptible_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_INTERRUPTIBLE, 0, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_interruptible_timeout - sleep until a condition gets true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * Returns: * 0 if the @condition evaluated to %false after the @timeout elapsed, * 1 if the @condition evaluated to %true after the @timeout elapsed, * the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed, or -%ERESTARTSYS if it was * interrupted by a signal. */ #define wait_event_interruptible_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_interruptible_timeout(wq_head, \ condition, timeout); \ __ret; \ }) #define __wait_event_hrtimeout(wq_head, condition, timeout, state) \ ({ \ int __ret = 0; \ struct hrtimer_sleeper __t; \ \ hrtimer_init_sleeper_on_stack(&__t, CLOCK_MONOTONIC, \ HRTIMER_MODE_REL); \ if ((timeout) != KTIME_MAX) { \ hrtimer_set_expires_range_ns(&__t.timer, timeout, \ current->timer_slack_ns); \ hrtimer_sleeper_start_expires(&__t, HRTIMER_MODE_REL); \ } \ \ __ret = ___wait_event(wq_head, condition, state, 0, 0, \ if (!__t.task) { \ __ret = -ETIME; \ break; \ } \ schedule()); \ \ hrtimer_cancel(&__t.timer); \ destroy_hrtimer_on_stack(&__t.timer); \ __ret; \ }) /** * wait_event_hrtimeout - sleep until a condition gets true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, as a ktime_t * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * The function returns 0 if @condition became true, or -ETIME if the timeout * elapsed. */ #define wait_event_hrtimeout(wq_head, condition, timeout) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_hrtimeout(wq_head, condition, timeout, \ TASK_UNINTERRUPTIBLE); \ __ret; \ }) /** * wait_event_interruptible_hrtimeout - sleep until a condition gets true or a timeout elapses * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, as a ktime_t * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * The function returns 0 if @condition became true, -ERESTARTSYS if it was * interrupted by a signal, or -ETIME if the timeout elapsed. */ #define wait_event_interruptible_hrtimeout(wq, condition, timeout) \ ({ \ long __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_hrtimeout(wq, condition, timeout, \ TASK_INTERRUPTIBLE); \ __ret; \ }) #define __wait_event_interruptible_exclusive(wq, condition) \ ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0, \ schedule()) #define wait_event_interruptible_exclusive(wq, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_interruptible_exclusive(wq, condition); \ __ret; \ }) #define __wait_event_killable_exclusive(wq, condition) \ ___wait_event(wq, condition, TASK_KILLABLE, 1, 0, \ schedule()) #define wait_event_killable_exclusive(wq, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_killable_exclusive(wq, condition); \ __ret; \ }) #define __wait_event_freezable_exclusive(wq, condition) \ ___wait_event(wq, condition, (TASK_INTERRUPTIBLE|TASK_FREEZABLE), 1, 0,\ schedule()) #define wait_event_freezable_exclusive(wq, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_freezable_exclusive(wq, condition); \ __ret; \ }) /** * wait_event_idle - wait for a condition without contributing to system load * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_IDLE) until the * @condition evaluates to true. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * */ #define wait_event_idle(wq_head, condition) \ do { \ might_sleep(); \ if (!(condition)) \ ___wait_event(wq_head, condition, TASK_IDLE, 0, 0, schedule()); \ } while (0) /** * wait_event_idle_exclusive - wait for a condition with contributing to system load * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_IDLE) until the * @condition evaluates to true. * The @condition is checked each time the waitqueue @wq_head is woken up. * * The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag * set thus if other processes wait on the same list, when this * process is woken further processes are not considered. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * */ #define wait_event_idle_exclusive(wq_head, condition) \ do { \ might_sleep(); \ if (!(condition)) \ ___wait_event(wq_head, condition, TASK_IDLE, 1, 0, schedule()); \ } while (0) #define __wait_event_idle_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_IDLE, 0, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_idle_timeout - sleep without load until a condition becomes true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_IDLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * Returns: * 0 if the @condition evaluated to %false after the @timeout elapsed, * 1 if the @condition evaluated to %true after the @timeout elapsed, * or the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed. */ #define wait_event_idle_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_idle_timeout(wq_head, condition, timeout); \ __ret; \ }) #define __wait_event_idle_exclusive_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_IDLE, 1, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_idle_exclusive_timeout - sleep without load until a condition becomes true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_IDLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag * set thus if other processes wait on the same list, when this * process is woken further processes are not considered. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * Returns: * 0 if the @condition evaluated to %false after the @timeout elapsed, * 1 if the @condition evaluated to %true after the @timeout elapsed, * or the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed. */ #define wait_event_idle_exclusive_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_idle_exclusive_timeout(wq_head, condition, timeout);\ __ret; \ }) extern int do_wait_intr(wait_queue_head_t *, wait_queue_entry_t *); extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_entry_t *); #define __wait_event_interruptible_locked(wq, condition, exclusive, fn) \ ({ \ int __ret; \ DEFINE_WAIT(__wait); \ if (exclusive) \ __wait.flags |= WQ_FLAG_EXCLUSIVE; \ do { \ __ret = fn(&(wq), &__wait); \ if (__ret) \ break; \ } while (!(condition)); \ __remove_wait_queue(&(wq), &__wait); \ __set_current_state(TASK_RUNNING); \ __ret; \ }) /** * wait_event_interruptible_locked - sleep until a condition gets true * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq is woken up. * * It must be called with wq.lock being held. This spinlock is * unlocked while sleeping but @condition testing is done while lock * is held and when this macro exits the lock is held. * * The lock is locked/unlocked using spin_lock()/spin_unlock() * functions which must match the way they are locked/unlocked outside * of this macro. * * wake_up_locked() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_interruptible_locked(wq, condition) \ ((condition) \ ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr)) /** * wait_event_interruptible_locked_irq - sleep until a condition gets true * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq is woken up. * * It must be called with wq.lock being held. This spinlock is * unlocked while sleeping but @condition testing is done while lock * is held and when this macro exits the lock is held. * * The lock is locked/unlocked using spin_lock_irq()/spin_unlock_irq() * functions which must match the way they are locked/unlocked outside * of this macro. * * wake_up_locked() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_interruptible_locked_irq(wq, condition) \ ((condition) \ ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr_irq)) /** * wait_event_interruptible_exclusive_locked - sleep exclusively until a condition gets true * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq is woken up. * * It must be called with wq.lock being held. This spinlock is * unlocked while sleeping but @condition testing is done while lock * is held and when this macro exits the lock is held. * * The lock is locked/unlocked using spin_lock()/spin_unlock() * functions which must match the way they are locked/unlocked outside * of this macro. * * The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag * set thus when other process waits process on the list if this * process is awaken further processes are not considered. * * wake_up_locked() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_interruptible_exclusive_locked(wq, condition) \ ((condition) \ ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr)) /** * wait_event_interruptible_exclusive_locked_irq - sleep until a condition gets true * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq is woken up. * * It must be called with wq.lock being held. This spinlock is * unlocked while sleeping but @condition testing is done while lock * is held and when this macro exits the lock is held. * * The lock is locked/unlocked using spin_lock_irq()/spin_unlock_irq() * functions which must match the way they are locked/unlocked outside * of this macro. * * The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag * set thus when other process waits process on the list if this * process is awaken further processes are not considered. * * wake_up_locked() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_interruptible_exclusive_locked_irq(wq, condition) \ ((condition) \ ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr_irq)) #define __wait_event_killable(wq, condition) \ ___wait_event(wq, condition, TASK_KILLABLE, 0, 0, schedule()) /** * wait_event_killable - sleep until a condition gets true * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_KILLABLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_killable(wq_head, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_killable(wq_head, condition); \ __ret; \ }) #define __wait_event_state(wq, condition, state) \ ___wait_event(wq, condition, state, 0, 0, schedule()) /** * wait_event_state - sleep until a condition gets true * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @state: state to sleep in * * The process is put to sleep (@state) until the @condition evaluates to true * or a signal is received (when allowed by @state). The @condition is checked * each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a signal * (when allowed by @state) and 0 if @condition evaluated to true. */ #define wait_event_state(wq_head, condition, state) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_state(wq_head, condition, state); \ __ret; \ }) #define __wait_event_killable_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_KILLABLE, 0, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_killable_timeout - sleep until a condition gets true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_KILLABLE) until the * @condition evaluates to true or a kill signal is received. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * Returns: * 0 if the @condition evaluated to %false after the @timeout elapsed, * 1 if the @condition evaluated to %true after the @timeout elapsed, * the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed, or -%ERESTARTSYS if it was * interrupted by a kill signal. * * Only kill signals interrupt this process. */ #define wait_event_killable_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_killable_timeout(wq_head, \ condition, timeout); \ __ret; \ }) #define __wait_event_lock_irq(wq_head, condition, lock, cmd) \ (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ spin_unlock_irq(&lock); \ cmd; \ schedule(); \ spin_lock_irq(&lock)) /** * wait_event_lock_irq_cmd - sleep until a condition gets true. The * condition is checked under the lock. This * is expected to be called with the lock * taken. * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before cmd * and schedule() and reacquired afterwards. * @cmd: a command which is invoked outside the critical section before * sleep * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * This is supposed to be called while holding the lock. The lock is * dropped before invoking the cmd and going to sleep and is reacquired * afterwards. */ #define wait_event_lock_irq_cmd(wq_head, condition, lock, cmd) \ do { \ if (condition) \ break; \ __wait_event_lock_irq(wq_head, condition, lock, cmd); \ } while (0) /** * wait_event_lock_irq - sleep until a condition gets true. The * condition is checked under the lock. This * is expected to be called with the lock * taken. * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before schedule() * and reacquired afterwards. * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * This is supposed to be called while holding the lock. The lock is * dropped before going to sleep and is reacquired afterwards. */ #define wait_event_lock_irq(wq_head, condition, lock) \ do { \ if (condition) \ break; \ __wait_event_lock_irq(wq_head, condition, lock, ); \ } while (0) #define __wait_event_interruptible_lock_irq(wq_head, condition, lock, cmd) \ ___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \ spin_unlock_irq(&lock); \ cmd; \ schedule(); \ spin_lock_irq(&lock)) /** * wait_event_interruptible_lock_irq_cmd - sleep until a condition gets true. * The condition is checked under the lock. This is expected to * be called with the lock taken. * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before cmd and * schedule() and reacquired afterwards. * @cmd: a command which is invoked outside the critical section before * sleep * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. The @condition is * checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * This is supposed to be called while holding the lock. The lock is * dropped before invoking the cmd and going to sleep and is reacquired * afterwards. * * The macro will return -ERESTARTSYS if it was interrupted by a signal * and 0 if @condition evaluated to true. */ #define wait_event_interruptible_lock_irq_cmd(wq_head, condition, lock, cmd) \ ({ \ int __ret = 0; \ if (!(condition)) \ __ret = __wait_event_interruptible_lock_irq(wq_head, \ condition, lock, cmd); \ __ret; \ }) /** * wait_event_interruptible_lock_irq - sleep until a condition gets true. * The condition is checked under the lock. This is expected * to be called with the lock taken. * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before schedule() * and reacquired afterwards. * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or signal is received. The @condition is * checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * This is supposed to be called while holding the lock. The lock is * dropped before going to sleep and is reacquired afterwards. * * The macro will return -ERESTARTSYS if it was interrupted by a signal * and 0 if @condition evaluated to true. */ #define wait_event_interruptible_lock_irq(wq_head, condition, lock) \ ({ \ int __ret = 0; \ if (!(condition)) \ __ret = __wait_event_interruptible_lock_irq(wq_head, \ condition, lock,); \ __ret; \ }) #define __wait_event_lock_irq_timeout(wq_head, condition, lock, timeout, state) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ state, 0, timeout, \ spin_unlock_irq(&lock); \ __ret = schedule_timeout(__ret); \ spin_lock_irq(&lock)); /** * wait_event_interruptible_lock_irq_timeout - sleep until a condition gets * true or a timeout elapses. The condition is checked under * the lock. This is expected to be called with the lock taken. * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before schedule() * and reacquired afterwards. * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or signal is received. The @condition is * checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * This is supposed to be called while holding the lock. The lock is * dropped before going to sleep and is reacquired afterwards. * * The function returns 0 if the @timeout elapsed, -ERESTARTSYS if it * was interrupted by a signal, and the remaining jiffies otherwise * if the condition evaluated to true before the timeout elapsed. */ #define wait_event_interruptible_lock_irq_timeout(wq_head, condition, lock, \ timeout) \ ({ \ long __ret = timeout; \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_lock_irq_timeout( \ wq_head, condition, lock, timeout, \ TASK_INTERRUPTIBLE); \ __ret; \ }) #define wait_event_lock_irq_timeout(wq_head, condition, lock, timeout) \ ({ \ long __ret = timeout; \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_lock_irq_timeout( \ wq_head, condition, lock, timeout, \ TASK_UNINTERRUPTIBLE); \ __ret; \ }) /* * Waitqueues which are removed from the waitqueue_head at wakeup time */ void prepare_to_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); bool prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); long prepare_to_wait_event(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); void finish_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout); int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key); int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key); #define DEFINE_WAIT_FUNC(name, function) \ struct wait_queue_entry name = { \ .private = current, \ .func = function, \ .entry = LIST_HEAD_INIT((name).entry), \ } #define DEFINE_WAIT(name) DEFINE_WAIT_FUNC(name, autoremove_wake_function) #define init_wait(wait) \ do { \ (wait)->private = current; \ (wait)->func = autoremove_wake_function; \ INIT_LIST_HEAD(&(wait)->entry); \ (wait)->flags = 0; \ } while (0) typedef int (*task_call_f)(struct task_struct *p, void *arg); extern int task_call_func(struct task_struct *p, task_call_f func, void *arg); #endif /* _LINUX_WAIT_H */ |
| 97 4763 4776 97 4764 91 4771 856 26 650 20 967 14 828 468 95 1100 8 90 470 93 86 93 4387 4761 4762 4759 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef BLK_INTERNAL_H #define BLK_INTERNAL_H #include <linux/bio-integrity.h> #include <linux/blk-crypto.h> #include <linux/memblock.h> /* for max_pfn/max_low_pfn */ #include <linux/sched/sysctl.h> #include <linux/timekeeping.h> #include <xen/xen.h> #include "blk-crypto-internal.h" struct elevator_type; /* Max future timer expiry for timeouts */ #define BLK_MAX_TIMEOUT (5 * HZ) extern struct dentry *blk_debugfs_root; struct blk_flush_queue { spinlock_t mq_flush_lock; unsigned int flush_pending_idx:1; unsigned int flush_running_idx:1; blk_status_t rq_status; unsigned long flush_pending_since; struct list_head flush_queue[2]; unsigned long flush_data_in_flight; struct request *flush_rq; }; bool is_flush_rq(struct request *req); struct blk_flush_queue *blk_alloc_flush_queue(int node, int cmd_size, gfp_t flags); void blk_free_flush_queue(struct blk_flush_queue *q); void blk_freeze_queue(struct request_queue *q); void __blk_mq_unfreeze_queue(struct request_queue *q, bool force_atomic); void blk_queue_start_drain(struct request_queue *q); int __bio_queue_enter(struct request_queue *q, struct bio *bio); void submit_bio_noacct_nocheck(struct bio *bio); void bio_await_chain(struct bio *bio); static inline bool blk_try_enter_queue(struct request_queue *q, bool pm) { rcu_read_lock(); if (!percpu_ref_tryget_live_rcu(&q->q_usage_counter)) goto fail; /* * The code that increments the pm_only counter must ensure that the * counter is globally visible before the queue is unfrozen. */ if (blk_queue_pm_only(q) && (!pm || queue_rpm_status(q) == RPM_SUSPENDED)) goto fail_put; rcu_read_unlock(); return true; fail_put: blk_queue_exit(q); fail: rcu_read_unlock(); return false; } static inline int bio_queue_enter(struct bio *bio) { struct request_queue *q = bdev_get_queue(bio->bi_bdev); if (blk_try_enter_queue(q, false)) return 0; return __bio_queue_enter(q, bio); } static inline void blk_wait_io(struct completion *done) { /* Prevent hang_check timer from firing at us during very long I/O */ unsigned long timeout = sysctl_hung_task_timeout_secs * HZ / 2; if (timeout) while (!wait_for_completion_io_timeout(done, timeout)) ; else wait_for_completion_io(done); } #define BIO_INLINE_VECS 4 struct bio_vec *bvec_alloc(mempool_t *pool, unsigned short *nr_vecs, gfp_t gfp_mask); void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned short nr_vecs); bool bvec_try_merge_hw_page(struct request_queue *q, struct bio_vec *bv, struct page *page, unsigned len, unsigned offset, bool *same_page); static inline bool biovec_phys_mergeable(struct request_queue *q, struct bio_vec *vec1, struct bio_vec *vec2) { unsigned long mask = queue_segment_boundary(q); phys_addr_t addr1 = bvec_phys(vec1); phys_addr_t addr2 = bvec_phys(vec2); /* * Merging adjacent physical pages may not work correctly under KMSAN * if their metadata pages aren't adjacent. Just disable merging. */ if (IS_ENABLED(CONFIG_KMSAN)) return false; if (addr1 + vec1->bv_len != addr2) return false; if (xen_domain() && !xen_biovec_phys_mergeable(vec1, vec2->bv_page)) return false; if ((addr1 | mask) != ((addr2 + vec2->bv_len - 1) | mask)) return false; return true; } static inline bool __bvec_gap_to_prev(const struct queue_limits *lim, struct bio_vec *bprv, unsigned int offset) { return (offset & lim->virt_boundary_mask) || ((bprv->bv_offset + bprv->bv_len) & lim->virt_boundary_mask); } /* * Check if adding a bio_vec after bprv with offset would create a gap in * the SG list. Most drivers don't care about this, but some do. */ static inline bool bvec_gap_to_prev(const struct queue_limits *lim, struct bio_vec *bprv, unsigned int offset) { if (!lim->virt_boundary_mask) return false; return __bvec_gap_to_prev(lim, bprv, offset); } static inline bool rq_mergeable(struct request *rq) { if (blk_rq_is_passthrough(rq)) return false; if (req_op(rq) == REQ_OP_FLUSH) return false; if (req_op(rq) == REQ_OP_WRITE_ZEROES) return false; if (req_op(rq) == REQ_OP_ZONE_APPEND) return false; if (rq->cmd_flags & REQ_NOMERGE_FLAGS) return false; if (rq->rq_flags & RQF_NOMERGE_FLAGS) return false; return true; } /* * There are two different ways to handle DISCARD merges: * 1) If max_discard_segments > 1, the driver treats every bio as a range and * send the bios to controller together. The ranges don't need to be * contiguous. * 2) Otherwise, the request will be normal read/write requests. The ranges * need to be contiguous. */ static inline bool blk_discard_mergable(struct request *req) { if (req_op(req) == REQ_OP_DISCARD && queue_max_discard_segments(req->q) > 1) return true; return false; } static inline unsigned int blk_rq_get_max_segments(struct request *rq) { if (req_op(rq) == REQ_OP_DISCARD) return queue_max_discard_segments(rq->q); return queue_max_segments(rq->q); } static inline unsigned int blk_queue_get_max_sectors(struct request *rq) { struct request_queue *q = rq->q; enum req_op op = req_op(rq); if (unlikely(op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE)) return min(q->limits.max_discard_sectors, UINT_MAX >> SECTOR_SHIFT); if (unlikely(op == REQ_OP_WRITE_ZEROES)) return q->limits.max_write_zeroes_sectors; if (rq->cmd_flags & REQ_ATOMIC) return q->limits.atomic_write_max_sectors; return q->limits.max_sectors; } #ifdef CONFIG_BLK_DEV_INTEGRITY void blk_flush_integrity(void); void bio_integrity_free(struct bio *bio); /* * Integrity payloads can either be owned by the submitter, in which case * bio_uninit will free them, or owned and generated by the block layer, * in which case we'll verify them here (for reads) and free them before * the bio is handed back to the submitted. */ bool __bio_integrity_endio(struct bio *bio); static inline bool bio_integrity_endio(struct bio *bio) { struct bio_integrity_payload *bip = bio_integrity(bio); if (bip && (bip->bip_flags & BIP_BLOCK_INTEGRITY)) return __bio_integrity_endio(bio); return true; } bool blk_integrity_merge_rq(struct request_queue *, struct request *, struct request *); bool blk_integrity_merge_bio(struct request_queue *, struct request *, struct bio *); static inline bool integrity_req_gap_back_merge(struct request *req, struct bio *next) { struct bio_integrity_payload *bip = bio_integrity(req->bio); struct bio_integrity_payload *bip_next = bio_integrity(next); return bvec_gap_to_prev(&req->q->limits, &bip->bip_vec[bip->bip_vcnt - 1], bip_next->bip_vec[0].bv_offset); } static inline bool integrity_req_gap_front_merge(struct request *req, struct bio *bio) { struct bio_integrity_payload *bip = bio_integrity(bio); struct bio_integrity_payload *bip_next = bio_integrity(req->bio); return bvec_gap_to_prev(&req->q->limits, &bip->bip_vec[bip->bip_vcnt - 1], bip_next->bip_vec[0].bv_offset); } extern const struct attribute_group blk_integrity_attr_group; #else /* CONFIG_BLK_DEV_INTEGRITY */ static inline bool blk_integrity_merge_rq(struct request_queue *rq, struct request *r1, struct request *r2) { return true; } static inline bool blk_integrity_merge_bio(struct request_queue *rq, struct request *r, struct bio *b) { return true; } static inline bool integrity_req_gap_back_merge(struct request *req, struct bio *next) { return false; } static inline bool integrity_req_gap_front_merge(struct request *req, struct bio *bio) { return false; } static inline void blk_flush_integrity(void) { } static inline bool bio_integrity_endio(struct bio *bio) { return true; } static inline void bio_integrity_free(struct bio *bio) { } #endif /* CONFIG_BLK_DEV_INTEGRITY */ unsigned long blk_rq_timeout(unsigned long timeout); void blk_add_timer(struct request *req); enum bio_merge_status { BIO_MERGE_OK, BIO_MERGE_NONE, BIO_MERGE_FAILED, }; enum bio_merge_status bio_attempt_back_merge(struct request *req, struct bio *bio, unsigned int nr_segs); bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs); bool blk_bio_list_merge(struct request_queue *q, struct list_head *list, struct bio *bio, unsigned int nr_segs); /* * Plug flush limits */ #define BLK_MAX_REQUEST_COUNT 32 #define BLK_PLUG_FLUSH_SIZE (128 * 1024) /* * Internal elevator interface */ #define ELV_ON_HASH(rq) ((rq)->rq_flags & RQF_HASHED) bool blk_insert_flush(struct request *rq); int elevator_switch(struct request_queue *q, struct elevator_type *new_e); void elevator_disable(struct request_queue *q); void elevator_exit(struct request_queue *q); int elv_register_queue(struct request_queue *q, bool uevent); void elv_unregister_queue(struct request_queue *q); ssize_t part_size_show(struct device *dev, struct device_attribute *attr, char *buf); ssize_t part_stat_show(struct device *dev, struct device_attribute *attr, char *buf); ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr, char *buf); ssize_t part_fail_show(struct device *dev, struct device_attribute *attr, char *buf); ssize_t part_fail_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); ssize_t part_timeout_show(struct device *, struct device_attribute *, char *); ssize_t part_timeout_store(struct device *, struct device_attribute *, const char *, size_t); static inline bool bio_may_exceed_limits(struct bio *bio, const struct queue_limits *lim) { switch (bio_op(bio)) { case REQ_OP_DISCARD: case REQ_OP_SECURE_ERASE: case REQ_OP_WRITE_ZEROES: return true; /* non-trivial splitting decisions */ default: break; } /* * All drivers must accept single-segments bios that are <= PAGE_SIZE. * This is a quick and dirty check that relies on the fact that * bi_io_vec[0] is always valid if a bio has data. The check might * lead to occasional false negatives when bios are cloned, but compared * to the performance impact of cloned bios themselves the loop below * doesn't matter anyway. */ return lim->chunk_sectors || bio->bi_vcnt != 1 || bio->bi_io_vec->bv_len + bio->bi_io_vec->bv_offset > PAGE_SIZE; } struct bio *__bio_split_to_limits(struct bio *bio, const struct queue_limits *lim, unsigned int *nr_segs); int ll_back_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs); bool blk_attempt_req_merge(struct request_queue *q, struct request *rq, struct request *next); unsigned int blk_recalc_rq_segments(struct request *rq); bool blk_rq_merge_ok(struct request *rq, struct bio *bio); enum elv_merge blk_try_merge(struct request *rq, struct bio *bio); int blk_set_default_limits(struct queue_limits *lim); void blk_apply_bdi_limits(struct backing_dev_info *bdi, struct queue_limits *lim); int blk_dev_init(void); /* * Contribute to IO statistics IFF: * * a) it's attached to a gendisk, and * b) the queue had IO stats enabled when this request was started */ static inline bool blk_do_io_stat(struct request *rq) { return (rq->rq_flags & RQF_IO_STAT) && !blk_rq_is_passthrough(rq); } void update_io_ticks(struct block_device *part, unsigned long now, bool end); unsigned int part_in_flight(struct block_device *part); static inline void req_set_nomerge(struct request_queue *q, struct request *req) { req->cmd_flags |= REQ_NOMERGE; if (req == q->last_merge) q->last_merge = NULL; } /* * Internal io_context interface */ struct io_cq *ioc_find_get_icq(struct request_queue *q); struct io_cq *ioc_lookup_icq(struct request_queue *q); #ifdef CONFIG_BLK_ICQ void ioc_clear_queue(struct request_queue *q); #else static inline void ioc_clear_queue(struct request_queue *q) { } #endif /* CONFIG_BLK_ICQ */ struct bio *__blk_queue_bounce(struct bio *bio, struct request_queue *q); static inline bool blk_queue_may_bounce(struct request_queue *q) { return IS_ENABLED(CONFIG_BOUNCE) && (q->limits.features & BLK_FEAT_BOUNCE_HIGH) && max_low_pfn >= max_pfn; } static inline struct bio *blk_queue_bounce(struct bio *bio, struct request_queue *q) { if (unlikely(blk_queue_may_bounce(q) && bio_has_data(bio))) return __blk_queue_bounce(bio, q); return bio; } #ifdef CONFIG_BLK_DEV_ZONED void disk_init_zone_resources(struct gendisk *disk); void disk_free_zone_resources(struct gendisk *disk); static inline bool bio_zone_write_plugging(struct bio *bio) { return bio_flagged(bio, BIO_ZONE_WRITE_PLUGGING); } static inline bool bio_is_zone_append(struct bio *bio) { return bio_op(bio) == REQ_OP_ZONE_APPEND || bio_flagged(bio, BIO_EMULATES_ZONE_APPEND); } void blk_zone_write_plug_bio_merged(struct bio *bio); void blk_zone_write_plug_init_request(struct request *rq); static inline void blk_zone_update_request_bio(struct request *rq, struct bio *bio) { /* * For zone append requests, the request sector indicates the location * at which the BIO data was written. Return this value to the BIO * issuer through the BIO iter sector. * For plugged zone writes, which include emulated zone append, we need * the original BIO sector so that blk_zone_write_plug_bio_endio() can * lookup the zone write plug. */ if (req_op(rq) == REQ_OP_ZONE_APPEND || bio_zone_write_plugging(bio)) bio->bi_iter.bi_sector = rq->__sector; } void blk_zone_write_plug_bio_endio(struct bio *bio); static inline void blk_zone_bio_endio(struct bio *bio) { /* * For write BIOs to zoned devices, signal the completion of the BIO so * that the next write BIO can be submitted by zone write plugging. */ if (bio_zone_write_plugging(bio)) blk_zone_write_plug_bio_endio(bio); } void blk_zone_write_plug_finish_request(struct request *rq); static inline void blk_zone_finish_request(struct request *rq) { if (rq->rq_flags & RQF_ZONE_WRITE_PLUGGING) blk_zone_write_plug_finish_request(rq); } int blkdev_report_zones_ioctl(struct block_device *bdev, unsigned int cmd, unsigned long arg); int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg); #else /* CONFIG_BLK_DEV_ZONED */ static inline void disk_init_zone_resources(struct gendisk *disk) { } static inline void disk_free_zone_resources(struct gendisk *disk) { } static inline bool bio_zone_write_plugging(struct bio *bio) { return false; } static inline bool bio_is_zone_append(struct bio *bio) { return false; } static inline void blk_zone_write_plug_bio_merged(struct bio *bio) { } static inline void blk_zone_write_plug_init_request(struct request *rq) { } static inline void blk_zone_update_request_bio(struct request *rq, struct bio *bio) { } static inline void blk_zone_bio_endio(struct bio *bio) { } static inline void blk_zone_finish_request(struct request *rq) { } static inline int blkdev_report_zones_ioctl(struct block_device *bdev, unsigned int cmd, unsigned long arg) { return -ENOTTY; } static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { return -ENOTTY; } #endif /* CONFIG_BLK_DEV_ZONED */ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno); void bdev_add(struct block_device *bdev, dev_t dev); void bdev_unhash(struct block_device *bdev); void bdev_drop(struct block_device *bdev); int blk_alloc_ext_minor(void); void blk_free_ext_minor(unsigned int minor); #define ADDPART_FLAG_NONE 0 #define ADDPART_FLAG_RAID 1 #define ADDPART_FLAG_WHOLEDISK 2 int bdev_add_partition(struct gendisk *disk, int partno, sector_t start, sector_t length); int bdev_del_partition(struct gendisk *disk, int partno); int bdev_resize_partition(struct gendisk *disk, int partno, sector_t start, sector_t length); void drop_partition(struct block_device *part); void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors); struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, struct lock_class_key *lkclass); int bio_add_hw_page(struct request_queue *q, struct bio *bio, struct page *page, unsigned int len, unsigned int offset, unsigned int max_sectors, bool *same_page); /* * Clean up a page appropriately, where the page may be pinned, may have a * ref taken on it or neither. */ static inline void bio_release_page(struct bio *bio, struct page *page) { if (bio_flagged(bio, BIO_PAGE_PINNED)) unpin_user_page(page); } struct request_queue *blk_alloc_queue(struct queue_limits *lim, int node_id); int disk_scan_partitions(struct gendisk *disk, blk_mode_t mode); int disk_alloc_events(struct gendisk *disk); void disk_add_events(struct gendisk *disk); void disk_del_events(struct gendisk *disk); void disk_release_events(struct gendisk *disk); void disk_block_events(struct gendisk *disk); void disk_unblock_events(struct gendisk *disk); void disk_flush_events(struct gendisk *disk, unsigned int mask); extern struct device_attribute dev_attr_events; extern struct device_attribute dev_attr_events_async; extern struct device_attribute dev_attr_events_poll_msecs; extern struct attribute_group blk_trace_attr_group; blk_mode_t file_to_blk_mode(struct file *file); int truncate_bdev_range(struct block_device *bdev, blk_mode_t mode, loff_t lstart, loff_t lend); long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg); long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg); extern const struct address_space_operations def_blk_aops; int disk_register_independent_access_ranges(struct gendisk *disk); void disk_unregister_independent_access_ranges(struct gendisk *disk); #ifdef CONFIG_FAIL_MAKE_REQUEST bool should_fail_request(struct block_device *part, unsigned int bytes); #else /* CONFIG_FAIL_MAKE_REQUEST */ static inline bool should_fail_request(struct block_device *part, unsigned int bytes) { return false; } #endif /* CONFIG_FAIL_MAKE_REQUEST */ /* * Optimized request reference counting. Ideally we'd make timeouts be more * clever, as that's the only reason we need references at all... But until * this happens, this is faster than using refcount_t. Also see: * * abc54d634334 ("io_uring: switch to atomic_t for io_kiocb reference count") */ #define req_ref_zero_or_close_to_overflow(req) \ ((unsigned int) atomic_read(&(req->ref)) + 127u <= 127u) static inline bool req_ref_inc_not_zero(struct request *req) { return atomic_inc_not_zero(&req->ref); } static inline bool req_ref_put_and_test(struct request *req) { WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req)); return atomic_dec_and_test(&req->ref); } static inline void req_ref_set(struct request *req, int value) { atomic_set(&req->ref, value); } static inline int req_ref_read(struct request *req) { return atomic_read(&req->ref); } static inline u64 blk_time_get_ns(void) { struct blk_plug *plug = current->plug; if (!plug || !in_task()) return ktime_get_ns(); /* * 0 could very well be a valid time, but rather than flag "this is * a valid timestamp" separately, just accept that we'll do an extra * ktime_get_ns() if we just happen to get 0 as the current time. */ if (!plug->cur_ktime) { plug->cur_ktime = ktime_get_ns(); current->flags |= PF_BLOCK_TS; } return plug->cur_ktime; } static inline ktime_t blk_time_get(void) { return ns_to_ktime(blk_time_get_ns()); } /* * From most significant bit: * 1 bit: reserved for other usage, see below * 12 bits: original size of bio * 51 bits: issue time of bio */ #define BIO_ISSUE_RES_BITS 1 #define BIO_ISSUE_SIZE_BITS 12 #define BIO_ISSUE_RES_SHIFT (64 - BIO_ISSUE_RES_BITS) #define BIO_ISSUE_SIZE_SHIFT (BIO_ISSUE_RES_SHIFT - BIO_ISSUE_SIZE_BITS) #define BIO_ISSUE_TIME_MASK ((1ULL << BIO_ISSUE_SIZE_SHIFT) - 1) #define BIO_ISSUE_SIZE_MASK \ (((1ULL << BIO_ISSUE_SIZE_BITS) - 1) << BIO_ISSUE_SIZE_SHIFT) #define BIO_ISSUE_RES_MASK (~((1ULL << BIO_ISSUE_RES_SHIFT) - 1)) /* Reserved bit for blk-throtl */ #define BIO_ISSUE_THROTL_SKIP_LATENCY (1ULL << 63) static inline u64 __bio_issue_time(u64 time) { return time & BIO_ISSUE_TIME_MASK; } static inline u64 bio_issue_time(struct bio_issue *issue) { return __bio_issue_time(issue->value); } static inline sector_t bio_issue_size(struct bio_issue *issue) { return ((issue->value & BIO_ISSUE_SIZE_MASK) >> BIO_ISSUE_SIZE_SHIFT); } static inline void bio_issue_init(struct bio_issue *issue, sector_t size) { size &= (1ULL << BIO_ISSUE_SIZE_BITS) - 1; issue->value = ((issue->value & BIO_ISSUE_RES_MASK) | (blk_time_get_ns() & BIO_ISSUE_TIME_MASK) | ((u64)size << BIO_ISSUE_SIZE_SHIFT)); } void bdev_release(struct file *bdev_file); int bdev_open(struct block_device *bdev, blk_mode_t mode, void *holder, const struct blk_holder_ops *hops, struct file *bdev_file); int bdev_permission(dev_t dev, blk_mode_t mode, void *holder); void blk_integrity_generate(struct bio *bio); void blk_integrity_verify(struct bio *bio); void blk_integrity_prepare(struct request *rq); void blk_integrity_complete(struct request *rq, unsigned int nr_bytes); #endif /* BLK_INTERNAL_H */ |
| 490 179 1 109 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef BTRFS_SPACE_INFO_H #define BTRFS_SPACE_INFO_H #include <trace/events/btrfs.h> #include <linux/spinlock.h> #include <linux/list.h> #include <linux/kobject.h> #include <linux/lockdep.h> #include <linux/wait.h> #include <linux/rwsem.h> #include "volumes.h" struct btrfs_fs_info; struct btrfs_block_group; /* * Different levels for to flush space when doing space reservations. * * The higher the level, the more methods we try to reclaim space. */ enum btrfs_reserve_flush_enum { /* If we are in the transaction, we can't flush anything.*/ BTRFS_RESERVE_NO_FLUSH, /* * Flush space by: * - Running delayed inode items * - Allocating a new chunk */ BTRFS_RESERVE_FLUSH_LIMIT, /* * Flush space by: * - Running delayed inode items * - Running delayed refs * - Running delalloc and waiting for ordered extents * - Allocating a new chunk * - Committing transaction */ BTRFS_RESERVE_FLUSH_EVICT, /* * Flush space by above mentioned methods and by: * - Running delayed iputs * - Committing transaction * * Can be interrupted by a fatal signal. */ BTRFS_RESERVE_FLUSH_DATA, BTRFS_RESERVE_FLUSH_FREE_SPACE_INODE, BTRFS_RESERVE_FLUSH_ALL, /* * Pretty much the same as FLUSH_ALL, but can also steal space from * global rsv. * * Can be interrupted by a fatal signal. */ BTRFS_RESERVE_FLUSH_ALL_STEAL, /* * This is for btrfs_use_block_rsv only. We have exhausted our block * rsv and our global block rsv. This can happen for things like * delalloc where we are overwriting a lot of extents with a single * extent and didn't reserve enough space. Alternatively it can happen * with delalloc where we reserve 1 extents worth for a large extent but * fragmentation leads to multiple extents being created. This will * give us the reservation in the case of * * if (num_bytes < (space_info->total_bytes - * btrfs_space_info_used(space_info, false)) * * Which ignores bytes_may_use. This is potentially dangerous, but our * reservation system is generally pessimistic so is able to absorb this * style of mistake. */ BTRFS_RESERVE_FLUSH_EMERGENCY, }; enum btrfs_flush_state { FLUSH_DELAYED_ITEMS_NR = 1, FLUSH_DELAYED_ITEMS = 2, FLUSH_DELAYED_REFS_NR = 3, FLUSH_DELAYED_REFS = 4, FLUSH_DELALLOC = 5, FLUSH_DELALLOC_WAIT = 6, FLUSH_DELALLOC_FULL = 7, ALLOC_CHUNK = 8, ALLOC_CHUNK_FORCE = 9, RUN_DELAYED_IPUTS = 10, COMMIT_TRANS = 11, }; struct btrfs_space_info { struct btrfs_fs_info *fs_info; spinlock_t lock; u64 total_bytes; /* total bytes in the space, this doesn't take mirrors into account */ u64 bytes_used; /* total bytes used, this doesn't take mirrors into account */ u64 bytes_pinned; /* total bytes pinned, will be freed when the transaction finishes */ u64 bytes_reserved; /* total bytes the allocator has reserved for current allocations */ u64 bytes_may_use; /* number of bytes that may be used for delalloc/allocations */ u64 bytes_readonly; /* total bytes that are read only */ u64 bytes_zone_unusable; /* total bytes that are unusable until resetting the device zone */ u64 max_extent_size; /* This will hold the maximum extent size of the space info if we had an ENOSPC in the allocator. */ /* Chunk size in bytes */ u64 chunk_size; /* * Once a block group drops below this threshold (percents) we'll * schedule it for reclaim. */ int bg_reclaim_threshold; int clamp; /* Used to scale our threshold for preemptive flushing. The value is >> clamp, so turns out to be a 2^clamp divisor. */ unsigned int full:1; /* indicates that we cannot allocate any more chunks for this space */ unsigned int chunk_alloc:1; /* set if we are allocating a chunk */ unsigned int flush:1; /* set if we are trying to make space */ unsigned int force_alloc; /* set if we need to force a chunk alloc for this space */ u64 disk_used; /* total bytes used on disk */ u64 disk_total; /* total bytes on disk, takes mirrors into account */ u64 flags; struct list_head list; /* Protected by the spinlock 'lock'. */ struct list_head ro_bgs; struct list_head priority_tickets; struct list_head tickets; /* * Size of space that needs to be reclaimed in order to satisfy pending * tickets */ u64 reclaim_size; /* * tickets_id just indicates the next ticket will be handled, so note * it's not stored per ticket. */ u64 tickets_id; struct rw_semaphore groups_sem; /* for block groups in our same type */ struct list_head block_groups[BTRFS_NR_RAID_TYPES]; struct kobject kobj; struct kobject *block_group_kobjs[BTRFS_NR_RAID_TYPES]; /* * Monotonically increasing counter of block group reclaim attempts * Exposed in /sys/fs/<uuid>/allocation/<type>/reclaim_count */ u64 reclaim_count; /* * Monotonically increasing counter of reclaimed bytes * Exposed in /sys/fs/<uuid>/allocation/<type>/reclaim_bytes */ u64 reclaim_bytes; /* * Monotonically increasing counter of reclaim errors * Exposed in /sys/fs/<uuid>/allocation/<type>/reclaim_errors */ u64 reclaim_errors; /* * If true, use the dynamic relocation threshold, instead of the * fixed bg_reclaim_threshold. */ bool dynamic_reclaim; /* * Periodically check all block groups against the reclaim * threshold in the cleaner thread. */ bool periodic_reclaim; /* * Periodic reclaim should be a no-op if a space_info hasn't * freed any space since the last time we tried. */ bool periodic_reclaim_ready; /* * Net bytes freed or allocated since the last reclaim pass. */ s64 reclaimable_bytes; }; struct reserve_ticket { u64 bytes; int error; bool steal; struct list_head list; wait_queue_head_t wait; }; static inline bool btrfs_mixed_space_info(struct btrfs_space_info *space_info) { return ((space_info->flags & BTRFS_BLOCK_GROUP_METADATA) && (space_info->flags & BTRFS_BLOCK_GROUP_DATA)); } /* * * Declare a helper function to detect underflow of various space info members */ #define DECLARE_SPACE_INFO_UPDATE(name, trace_name) \ static inline void \ btrfs_space_info_update_##name(struct btrfs_fs_info *fs_info, \ struct btrfs_space_info *sinfo, \ s64 bytes) \ { \ const u64 abs_bytes = (bytes < 0) ? -bytes : bytes; \ lockdep_assert_held(&sinfo->lock); \ trace_update_##name(fs_info, sinfo, sinfo->name, bytes); \ trace_btrfs_space_reservation(fs_info, trace_name, \ sinfo->flags, abs_bytes, \ bytes > 0); \ if (bytes < 0 && sinfo->name < -bytes) { \ WARN_ON(1); \ sinfo->name = 0; \ return; \ } \ sinfo->name += bytes; \ } DECLARE_SPACE_INFO_UPDATE(bytes_may_use, "space_info"); DECLARE_SPACE_INFO_UPDATE(bytes_pinned, "pinned"); DECLARE_SPACE_INFO_UPDATE(bytes_zone_unusable, "zone_unusable"); int btrfs_init_space_info(struct btrfs_fs_info *fs_info); void btrfs_add_bg_to_space_info(struct btrfs_fs_info *info, struct btrfs_block_group *block_group); void btrfs_update_space_info_chunk_size(struct btrfs_space_info *space_info, u64 chunk_size); struct btrfs_space_info *btrfs_find_space_info(struct btrfs_fs_info *info, u64 flags); u64 __pure btrfs_space_info_used(struct btrfs_space_info *s_info, bool may_use_included); void btrfs_clear_space_info_full(struct btrfs_fs_info *info); void btrfs_dump_space_info(struct btrfs_fs_info *fs_info, struct btrfs_space_info *info, u64 bytes, int dump_block_groups); int btrfs_reserve_metadata_bytes(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 orig_bytes, enum btrfs_reserve_flush_enum flush); void btrfs_try_granting_tickets(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info); int btrfs_can_overcommit(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 bytes, enum btrfs_reserve_flush_enum flush); static inline void btrfs_space_info_free_bytes_may_use( struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 num_bytes) { spin_lock(&space_info->lock); btrfs_space_info_update_bytes_may_use(fs_info, space_info, -num_bytes); btrfs_try_granting_tickets(fs_info, space_info); spin_unlock(&space_info->lock); } int btrfs_reserve_data_bytes(struct btrfs_fs_info *fs_info, u64 bytes, enum btrfs_reserve_flush_enum flush); void btrfs_dump_space_info_for_trans_abort(struct btrfs_fs_info *fs_info); void btrfs_init_async_reclaim_work(struct btrfs_fs_info *fs_info); u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo); void btrfs_space_info_update_reclaimable(struct btrfs_space_info *space_info, s64 bytes); void btrfs_set_periodic_reclaim_ready(struct btrfs_space_info *space_info, bool ready); bool btrfs_should_periodic_reclaim(struct btrfs_space_info *space_info); int btrfs_calc_reclaim_threshold(struct btrfs_space_info *space_info); int btrfs_reclaim_sweep(struct btrfs_fs_info *fs_info); #endif /* BTRFS_SPACE_INFO_H */ |
| 5 5 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/dsa/user.c - user device handling * Copyright (c) 2008-2009 Marvell Semiconductor */ #include <linux/list.h> #include <linux/etherdevice.h> #include <linux/netdevice.h> #include <linux/phy.h> #include <linux/phy_fixed.h> #include <linux/phylink.h> #include <linux/of_net.h> #include <linux/of_mdio.h> #include <linux/mdio.h> #include <net/rtnetlink.h> #include <net/pkt_cls.h> #include <net/selftests.h> #include <net/tc_act/tc_mirred.h> #include <linux/if_bridge.h> #include <linux/if_hsr.h> #include <net/dcbnl.h> #include <linux/netpoll.h> #include <linux/string.h> #include "conduit.h" #include "dsa.h" #include "netlink.h" #include "port.h" #include "switch.h" #include "tag.h" #include "user.h" struct dsa_switchdev_event_work { struct net_device *dev; struct net_device *orig_dev; struct work_struct work; unsigned long event; /* Specific for SWITCHDEV_FDB_ADD_TO_DEVICE and * SWITCHDEV_FDB_DEL_TO_DEVICE */ unsigned char addr[ETH_ALEN]; u16 vid; bool host_addr; }; enum dsa_standalone_event { DSA_UC_ADD, DSA_UC_DEL, DSA_MC_ADD, DSA_MC_DEL, }; struct dsa_standalone_event_work { struct work_struct work; struct net_device *dev; enum dsa_standalone_event event; unsigned char addr[ETH_ALEN]; u16 vid; }; struct dsa_host_vlan_rx_filtering_ctx { struct net_device *dev; const unsigned char *addr; enum dsa_standalone_event event; }; static bool dsa_switch_supports_uc_filtering(struct dsa_switch *ds) { return ds->ops->port_fdb_add && ds->ops->port_fdb_del && ds->fdb_isolation && !ds->vlan_filtering_is_global && !ds->needs_standalone_vlan_filtering; } static bool dsa_switch_supports_mc_filtering(struct dsa_switch *ds) { return ds->ops->port_mdb_add && ds->ops->port_mdb_del && ds->fdb_isolation && !ds->vlan_filtering_is_global && !ds->needs_standalone_vlan_filtering; } static void dsa_user_standalone_event_work(struct work_struct *work) { struct dsa_standalone_event_work *standalone_work = container_of(work, struct dsa_standalone_event_work, work); const unsigned char *addr = standalone_work->addr; struct net_device *dev = standalone_work->dev; struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_mdb mdb; struct dsa_switch *ds = dp->ds; u16 vid = standalone_work->vid; int err; switch (standalone_work->event) { case DSA_UC_ADD: err = dsa_port_standalone_host_fdb_add(dp, addr, vid); if (err) { dev_err(ds->dev, "port %d failed to add %pM vid %d to fdb: %d\n", dp->index, addr, vid, err); break; } break; case DSA_UC_DEL: err = dsa_port_standalone_host_fdb_del(dp, addr, vid); if (err) { dev_err(ds->dev, "port %d failed to delete %pM vid %d from fdb: %d\n", dp->index, addr, vid, err); } break; case DSA_MC_ADD: ether_addr_copy(mdb.addr, addr); mdb.vid = vid; err = dsa_port_standalone_host_mdb_add(dp, &mdb); if (err) { dev_err(ds->dev, "port %d failed to add %pM vid %d to mdb: %d\n", dp->index, addr, vid, err); break; } break; case DSA_MC_DEL: ether_addr_copy(mdb.addr, addr); mdb.vid = vid; err = dsa_port_standalone_host_mdb_del(dp, &mdb); if (err) { dev_err(ds->dev, "port %d failed to delete %pM vid %d from mdb: %d\n", dp->index, addr, vid, err); } break; } kfree(standalone_work); } static int dsa_user_schedule_standalone_work(struct net_device *dev, enum dsa_standalone_event event, const unsigned char *addr, u16 vid) { struct dsa_standalone_event_work *standalone_work; standalone_work = kzalloc(sizeof(*standalone_work), GFP_ATOMIC); if (!standalone_work) return -ENOMEM; INIT_WORK(&standalone_work->work, dsa_user_standalone_event_work); standalone_work->event = event; standalone_work->dev = dev; ether_addr_copy(standalone_work->addr, addr); standalone_work->vid = vid; dsa_schedule_work(&standalone_work->work); return 0; } static int dsa_user_host_vlan_rx_filtering(void *arg, int vid) { struct dsa_host_vlan_rx_filtering_ctx *ctx = arg; return dsa_user_schedule_standalone_work(ctx->dev, ctx->event, ctx->addr, vid); } static int dsa_user_vlan_for_each(struct net_device *dev, int (*cb)(void *arg, int vid), void *arg) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_vlan *v; int err; lockdep_assert_held(&dev->addr_list_lock); err = cb(arg, 0); if (err) return err; list_for_each_entry(v, &dp->user_vlans, list) { err = cb(arg, v->vid); if (err) return err; } return 0; } static int dsa_user_sync_uc(struct net_device *dev, const unsigned char *addr) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_host_vlan_rx_filtering_ctx ctx = { .dev = dev, .addr = addr, .event = DSA_UC_ADD, }; dev_uc_add(conduit, addr); if (!dsa_switch_supports_uc_filtering(dp->ds)) return 0; return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, &ctx); } static int dsa_user_unsync_uc(struct net_device *dev, const unsigned char *addr) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_host_vlan_rx_filtering_ctx ctx = { .dev = dev, .addr = addr, .event = DSA_UC_DEL, }; dev_uc_del(conduit, addr); if (!dsa_switch_supports_uc_filtering(dp->ds)) return 0; return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, &ctx); } static int dsa_user_sync_mc(struct net_device *dev, const unsigned char *addr) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_host_vlan_rx_filtering_ctx ctx = { .dev = dev, .addr = addr, .event = DSA_MC_ADD, }; dev_mc_add(conduit, addr); if (!dsa_switch_supports_mc_filtering(dp->ds)) return 0; return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, &ctx); } static int dsa_user_unsync_mc(struct net_device *dev, const unsigned char *addr) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_host_vlan_rx_filtering_ctx ctx = { .dev = dev, .addr = addr, .event = DSA_MC_DEL, }; dev_mc_del(conduit, addr); if (!dsa_switch_supports_mc_filtering(dp->ds)) return 0; return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, &ctx); } void dsa_user_sync_ha(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct netdev_hw_addr *ha; netif_addr_lock_bh(dev); netdev_for_each_synced_mc_addr(ha, dev) dsa_user_sync_mc(dev, ha->addr); netdev_for_each_synced_uc_addr(ha, dev) dsa_user_sync_uc(dev, ha->addr); netif_addr_unlock_bh(dev); if (dsa_switch_supports_uc_filtering(ds) || dsa_switch_supports_mc_filtering(ds)) dsa_flush_workqueue(); } void dsa_user_unsync_ha(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct netdev_hw_addr *ha; netif_addr_lock_bh(dev); netdev_for_each_synced_uc_addr(ha, dev) dsa_user_unsync_uc(dev, ha->addr); netdev_for_each_synced_mc_addr(ha, dev) dsa_user_unsync_mc(dev, ha->addr); netif_addr_unlock_bh(dev); if (dsa_switch_supports_uc_filtering(ds) || dsa_switch_supports_mc_filtering(ds)) dsa_flush_workqueue(); } /* user mii_bus handling ***************************************************/ static int dsa_user_phy_read(struct mii_bus *bus, int addr, int reg) { struct dsa_switch *ds = bus->priv; if (ds->phys_mii_mask & (1 << addr)) return ds->ops->phy_read(ds, addr, reg); return 0xffff; } static int dsa_user_phy_write(struct mii_bus *bus, int addr, int reg, u16 val) { struct dsa_switch *ds = bus->priv; if (ds->phys_mii_mask & (1 << addr)) return ds->ops->phy_write(ds, addr, reg, val); return 0; } void dsa_user_mii_bus_init(struct dsa_switch *ds) { ds->user_mii_bus->priv = (void *)ds; ds->user_mii_bus->name = "dsa user smi"; ds->user_mii_bus->read = dsa_user_phy_read; ds->user_mii_bus->write = dsa_user_phy_write; snprintf(ds->user_mii_bus->id, MII_BUS_ID_SIZE, "dsa-%d.%d", ds->dst->index, ds->index); ds->user_mii_bus->parent = ds->dev; ds->user_mii_bus->phy_mask = ~ds->phys_mii_mask; } /* user device handling ****************************************************/ static int dsa_user_get_iflink(const struct net_device *dev) { return READ_ONCE(dsa_user_to_conduit(dev)->ifindex); } int dsa_user_host_uc_install(struct net_device *dev, const u8 *addr) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int err; if (dsa_switch_supports_uc_filtering(ds)) { err = dsa_port_standalone_host_fdb_add(dp, addr, 0); if (err) goto out; } if (!ether_addr_equal(addr, conduit->dev_addr)) { err = dev_uc_add(conduit, addr); if (err < 0) goto del_host_addr; } return 0; del_host_addr: if (dsa_switch_supports_uc_filtering(ds)) dsa_port_standalone_host_fdb_del(dp, addr, 0); out: return err; } void dsa_user_host_uc_uninstall(struct net_device *dev) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ether_addr_equal(dev->dev_addr, conduit->dev_addr)) dev_uc_del(conduit, dev->dev_addr); if (dsa_switch_supports_uc_filtering(ds)) dsa_port_standalone_host_fdb_del(dp, dev->dev_addr, 0); } static int dsa_user_open(struct net_device *dev) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); int err; err = dev_open(conduit, NULL); if (err < 0) { netdev_err(dev, "failed to open conduit %s\n", conduit->name); goto out; } err = dsa_user_host_uc_install(dev, dev->dev_addr); if (err) goto out; err = dsa_port_enable_rt(dp, dev->phydev); if (err) goto out_del_host_uc; return 0; out_del_host_uc: dsa_user_host_uc_uninstall(dev); out: return err; } static int dsa_user_close(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); dsa_port_disable_rt(dp); dsa_user_host_uc_uninstall(dev); return 0; } static void dsa_user_manage_host_flood(struct net_device *dev) { bool mc = dev->flags & (IFF_PROMISC | IFF_ALLMULTI); struct dsa_port *dp = dsa_user_to_port(dev); bool uc = dev->flags & IFF_PROMISC; dsa_port_set_host_flood(dp, uc, mc); } static void dsa_user_change_rx_flags(struct net_device *dev, int change) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (change & IFF_ALLMULTI) dev_set_allmulti(conduit, dev->flags & IFF_ALLMULTI ? 1 : -1); if (change & IFF_PROMISC) dev_set_promiscuity(conduit, dev->flags & IFF_PROMISC ? 1 : -1); if (dsa_switch_supports_uc_filtering(ds) && dsa_switch_supports_mc_filtering(ds)) dsa_user_manage_host_flood(dev); } static void dsa_user_set_rx_mode(struct net_device *dev) { __dev_mc_sync(dev, dsa_user_sync_mc, dsa_user_unsync_mc); __dev_uc_sync(dev, dsa_user_sync_uc, dsa_user_unsync_uc); } static int dsa_user_set_mac_address(struct net_device *dev, void *a) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct sockaddr *addr = a; int err; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; if (ds->ops->port_set_mac_address) { err = ds->ops->port_set_mac_address(ds, dp->index, addr->sa_data); if (err) return err; } /* If the port is down, the address isn't synced yet to hardware or * to the DSA conduit, so there is nothing to change. */ if (!(dev->flags & IFF_UP)) goto out_change_dev_addr; err = dsa_user_host_uc_install(dev, addr->sa_data); if (err) return err; dsa_user_host_uc_uninstall(dev); out_change_dev_addr: eth_hw_addr_set(dev, addr->sa_data); return 0; } struct dsa_user_dump_ctx { struct net_device *dev; struct sk_buff *skb; struct netlink_callback *cb; int idx; }; static int dsa_user_port_fdb_do_dump(const unsigned char *addr, u16 vid, bool is_static, void *data) { struct dsa_user_dump_ctx *dump = data; u32 portid = NETLINK_CB(dump->cb->skb).portid; u32 seq = dump->cb->nlh->nlmsg_seq; struct nlmsghdr *nlh; struct ndmsg *ndm; if (dump->idx < dump->cb->args[2]) goto skip; nlh = nlmsg_put(dump->skb, portid, seq, RTM_NEWNEIGH, sizeof(*ndm), NLM_F_MULTI); if (!nlh) return -EMSGSIZE; ndm = nlmsg_data(nlh); ndm->ndm_family = AF_BRIDGE; ndm->ndm_pad1 = 0; ndm->ndm_pad2 = 0; ndm->ndm_flags = NTF_SELF; ndm->ndm_type = 0; ndm->ndm_ifindex = dump->dev->ifindex; ndm->ndm_state = is_static ? NUD_NOARP : NUD_REACHABLE; if (nla_put(dump->skb, NDA_LLADDR, ETH_ALEN, addr)) goto nla_put_failure; if (vid && nla_put_u16(dump->skb, NDA_VLAN, vid)) goto nla_put_failure; nlmsg_end(dump->skb, nlh); skip: dump->idx++; return 0; nla_put_failure: nlmsg_cancel(dump->skb, nlh); return -EMSGSIZE; } static int dsa_user_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, struct net_device *filter_dev, int *idx) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_user_dump_ctx dump = { .dev = dev, .skb = skb, .cb = cb, .idx = *idx, }; int err; err = dsa_port_fdb_dump(dp, dsa_user_port_fdb_do_dump, &dump); *idx = dump.idx; return err; } static int dsa_user_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct dsa_user_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->dp->ds; int port = p->dp->index; /* Pass through to switch driver if it supports timestamping */ switch (cmd) { case SIOCGHWTSTAMP: if (ds->ops->port_hwtstamp_get) return ds->ops->port_hwtstamp_get(ds, port, ifr); break; case SIOCSHWTSTAMP: if (ds->ops->port_hwtstamp_set) return ds->ops->port_hwtstamp_set(ds, port, ifr); break; } return phylink_mii_ioctl(p->dp->pl, ifr, cmd); } static int dsa_user_port_attr_set(struct net_device *dev, const void *ctx, const struct switchdev_attr *attr, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_user_to_port(dev); int ret; if (ctx && ctx != dp) return 0; switch (attr->id) { case SWITCHDEV_ATTR_ID_PORT_STP_STATE: if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_set_state(dp, attr->u.stp_state, true); break; case SWITCHDEV_ATTR_ID_PORT_MST_STATE: if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_set_mst_state(dp, &attr->u.mst_state, extack); break; case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING: if (!dsa_port_offloads_bridge_dev(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_vlan_filtering(dp, attr->u.vlan_filtering, extack); break; case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME: if (!dsa_port_offloads_bridge_dev(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_ageing_time(dp, attr->u.ageing_time); break; case SWITCHDEV_ATTR_ID_BRIDGE_MST: if (!dsa_port_offloads_bridge_dev(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_mst_enable(dp, attr->u.mst, extack); break; case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS: if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_pre_bridge_flags(dp, attr->u.brport_flags, extack); break; case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_bridge_flags(dp, attr->u.brport_flags, extack); break; case SWITCHDEV_ATTR_ID_VLAN_MSTI: if (!dsa_port_offloads_bridge_dev(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_vlan_msti(dp, &attr->u.vlan_msti); break; default: ret = -EOPNOTSUPP; break; } return ret; } /* Must be called under rcu_read_lock() */ static int dsa_user_vlan_check_for_8021q_uppers(struct net_device *user, const struct switchdev_obj_port_vlan *vlan) { struct net_device *upper_dev; struct list_head *iter; netdev_for_each_upper_dev_rcu(user, upper_dev, iter) { u16 vid; if (!is_vlan_dev(upper_dev)) continue; vid = vlan_dev_vlan_id(upper_dev); if (vid == vlan->vid) return -EBUSY; } return 0; } static int dsa_user_vlan_add(struct net_device *dev, const struct switchdev_obj *obj, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan *vlan; int err; if (dsa_port_skip_vlan_configuration(dp)) { NL_SET_ERR_MSG_MOD(extack, "skipping configuration of VLAN"); return 0; } vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); /* Deny adding a bridge VLAN when there is already an 802.1Q upper with * the same VID. */ if (br_vlan_enabled(dsa_port_bridge_dev_get(dp))) { rcu_read_lock(); err = dsa_user_vlan_check_for_8021q_uppers(dev, vlan); rcu_read_unlock(); if (err) { NL_SET_ERR_MSG_MOD(extack, "Port already has a VLAN upper with this VID"); return err; } } return dsa_port_vlan_add(dp, vlan, extack); } /* Offload a VLAN installed on the bridge or on a foreign interface by * installing it as a VLAN towards the CPU port. */ static int dsa_user_host_vlan_add(struct net_device *dev, const struct switchdev_obj *obj, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan vlan; /* Do nothing if this is a software bridge */ if (!dp->bridge) return -EOPNOTSUPP; if (dsa_port_skip_vlan_configuration(dp)) { NL_SET_ERR_MSG_MOD(extack, "skipping configuration of VLAN"); return 0; } vlan = *SWITCHDEV_OBJ_PORT_VLAN(obj); /* Even though drivers often handle CPU membership in special ways, * it doesn't make sense to program a PVID, so clear this flag. */ vlan.flags &= ~BRIDGE_VLAN_INFO_PVID; return dsa_port_host_vlan_add(dp, &vlan, extack); } static int dsa_user_port_obj_add(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_user_to_port(dev); int err; if (ctx && ctx != dp) return 0; switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_MDB: if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_HOST_MDB: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_bridge_host_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: if (dsa_port_offloads_bridge_port(dp, obj->orig_dev)) err = dsa_user_vlan_add(dev, obj, extack); else err = dsa_user_host_vlan_add(dev, obj, extack); break; case SWITCHDEV_OBJ_ID_MRP: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mrp_add(dp, SWITCHDEV_OBJ_MRP(obj)); break; case SWITCHDEV_OBJ_ID_RING_ROLE_MRP: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mrp_add_ring_role(dp, SWITCHDEV_OBJ_RING_ROLE_MRP(obj)); break; default: err = -EOPNOTSUPP; break; } return err; } static int dsa_user_vlan_del(struct net_device *dev, const struct switchdev_obj *obj) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan *vlan; if (dsa_port_skip_vlan_configuration(dp)) return 0; vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); return dsa_port_vlan_del(dp, vlan); } static int dsa_user_host_vlan_del(struct net_device *dev, const struct switchdev_obj *obj) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan *vlan; /* Do nothing if this is a software bridge */ if (!dp->bridge) return -EOPNOTSUPP; if (dsa_port_skip_vlan_configuration(dp)) return 0; vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); return dsa_port_host_vlan_del(dp, vlan); } static int dsa_user_port_obj_del(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj) { struct dsa_port *dp = dsa_user_to_port(dev); int err; if (ctx && ctx != dp) return 0; switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_MDB: if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_HOST_MDB: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_bridge_host_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: if (dsa_port_offloads_bridge_port(dp, obj->orig_dev)) err = dsa_user_vlan_del(dev, obj); else err = dsa_user_host_vlan_del(dev, obj); break; case SWITCHDEV_OBJ_ID_MRP: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mrp_del(dp, SWITCHDEV_OBJ_MRP(obj)); break; case SWITCHDEV_OBJ_ID_RING_ROLE_MRP: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mrp_del_ring_role(dp, SWITCHDEV_OBJ_RING_ROLE_MRP(obj)); break; default: err = -EOPNOTSUPP; break; } return err; } static netdev_tx_t dsa_user_netpoll_send_skb(struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_NET_POLL_CONTROLLER struct dsa_user_priv *p = netdev_priv(dev); return netpoll_send_skb(p->netpoll, skb); #else BUG(); return NETDEV_TX_OK; #endif } static void dsa_skb_tx_timestamp(struct dsa_user_priv *p, struct sk_buff *skb) { struct dsa_switch *ds = p->dp->ds; if (!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) return; if (!ds->ops->port_txtstamp) return; ds->ops->port_txtstamp(ds, p->dp->index, skb); } netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev) { /* SKB for netpoll still need to be mangled with the protocol-specific * tag to be successfully transmitted */ if (unlikely(netpoll_tx_running(dev))) return dsa_user_netpoll_send_skb(dev, skb); /* Queue the SKB for transmission on the parent interface, but * do not modify its EtherType */ skb->dev = dsa_user_to_conduit(dev); dev_queue_xmit(skb); return NETDEV_TX_OK; } EXPORT_SYMBOL_GPL(dsa_enqueue_skb); static netdev_tx_t dsa_user_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_user_priv *p = netdev_priv(dev); struct sk_buff *nskb; dev_sw_netstats_tx_add(dev, 1, skb->len); memset(skb->cb, 0, sizeof(skb->cb)); /* Handle tx timestamp if any */ dsa_skb_tx_timestamp(p, skb); if (skb_ensure_writable_head_tail(skb, dev)) { dev_kfree_skb_any(skb); return NETDEV_TX_OK; } /* needed_tailroom should still be 'warm' in the cache line from * skb_ensure_writable_head_tail(), which has also ensured that * padding is safe. */ if (dev->needed_tailroom) eth_skb_pad(skb); /* Transmit function may have to reallocate the original SKB, * in which case it must have freed it. Only free it here on error. */ nskb = p->xmit(skb, dev); if (!nskb) { kfree_skb(skb); return NETDEV_TX_OK; } return dsa_enqueue_skb(nskb, dev); } /* ethtool operations *******************************************************/ static void dsa_user_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->driver, "dsa", sizeof(drvinfo->driver)); strscpy(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version)); strscpy(drvinfo->bus_info, "platform", sizeof(drvinfo->bus_info)); } static int dsa_user_get_regs_len(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_regs_len) return ds->ops->get_regs_len(ds, dp->index); return -EOPNOTSUPP; } static void dsa_user_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *_p) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_regs) ds->ops->get_regs(ds, dp->index, regs, _p); } static int dsa_user_nway_reset(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); return phylink_ethtool_nway_reset(dp->pl); } static int dsa_user_get_eeprom_len(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->cd && ds->cd->eeprom_len) return ds->cd->eeprom_len; if (ds->ops->get_eeprom_len) return ds->ops->get_eeprom_len(ds); return 0; } static int dsa_user_get_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, u8 *data) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_eeprom) return ds->ops->get_eeprom(ds, eeprom, data); return -EOPNOTSUPP; } static int dsa_user_set_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, u8 *data) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->set_eeprom) return ds->ops->set_eeprom(ds, eeprom, data); return -EOPNOTSUPP; } static void dsa_user_get_strings(struct net_device *dev, uint32_t stringset, uint8_t *data) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (stringset == ETH_SS_STATS) { int len = ETH_GSTRING_LEN; strscpy_pad(data, "tx_packets", len); strscpy_pad(data + len, "tx_bytes", len); strscpy_pad(data + 2 * len, "rx_packets", len); strscpy_pad(data + 3 * len, "rx_bytes", len); if (ds->ops->get_strings) ds->ops->get_strings(ds, dp->index, stringset, data + 4 * len); } else if (stringset == ETH_SS_TEST) { net_selftest_get_strings(data); } } static void dsa_user_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, uint64_t *data) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct pcpu_sw_netstats *s; unsigned int start; int i; for_each_possible_cpu(i) { u64 tx_packets, tx_bytes, rx_packets, rx_bytes; s = per_cpu_ptr(dev->tstats, i); do { start = u64_stats_fetch_begin(&s->syncp); tx_packets = u64_stats_read(&s->tx_packets); tx_bytes = u64_stats_read(&s->tx_bytes); rx_packets = u64_stats_read(&s->rx_packets); rx_bytes = u64_stats_read(&s->rx_bytes); } while (u64_stats_fetch_retry(&s->syncp, start)); data[0] += tx_packets; data[1] += tx_bytes; data[2] += rx_packets; data[3] += rx_bytes; } if (ds->ops->get_ethtool_stats) ds->ops->get_ethtool_stats(ds, dp->index, data + 4); } static int dsa_user_get_sset_count(struct net_device *dev, int sset) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (sset == ETH_SS_STATS) { int count = 0; if (ds->ops->get_sset_count) { count = ds->ops->get_sset_count(ds, dp->index, sset); if (count < 0) return count; } return count + 4; } else if (sset == ETH_SS_TEST) { return net_selftest_get_count(); } return -EOPNOTSUPP; } static void dsa_user_get_eth_phy_stats(struct net_device *dev, struct ethtool_eth_phy_stats *phy_stats) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_eth_phy_stats) ds->ops->get_eth_phy_stats(ds, dp->index, phy_stats); } static void dsa_user_get_eth_mac_stats(struct net_device *dev, struct ethtool_eth_mac_stats *mac_stats) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_eth_mac_stats) ds->ops->get_eth_mac_stats(ds, dp->index, mac_stats); } static void dsa_user_get_eth_ctrl_stats(struct net_device *dev, struct ethtool_eth_ctrl_stats *ctrl_stats) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_eth_ctrl_stats) ds->ops->get_eth_ctrl_stats(ds, dp->index, ctrl_stats); } static void dsa_user_get_rmon_stats(struct net_device *dev, struct ethtool_rmon_stats *rmon_stats, const struct ethtool_rmon_hist_range **ranges) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_rmon_stats) ds->ops->get_rmon_stats(ds, dp->index, rmon_stats, ranges); } static void dsa_user_net_selftest(struct net_device *ndev, struct ethtool_test *etest, u64 *buf) { struct dsa_port *dp = dsa_user_to_port(ndev); struct dsa_switch *ds = dp->ds; if (ds->ops->self_test) { ds->ops->self_test(ds, dp->index, etest, buf); return; } net_selftest(ndev, etest, buf); } static int dsa_user_get_mm(struct net_device *dev, struct ethtool_mm_state *state) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ds->ops->get_mm) return -EOPNOTSUPP; return ds->ops->get_mm(ds, dp->index, state); } static int dsa_user_set_mm(struct net_device *dev, struct ethtool_mm_cfg *cfg, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ds->ops->set_mm) return -EOPNOTSUPP; return ds->ops->set_mm(ds, dp->index, cfg, extack); } static void dsa_user_get_mm_stats(struct net_device *dev, struct ethtool_mm_stats *stats) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_mm_stats) ds->ops->get_mm_stats(ds, dp->index, stats); } static void dsa_user_get_wol(struct net_device *dev, struct ethtool_wolinfo *w) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; phylink_ethtool_get_wol(dp->pl, w); if (ds->ops->get_wol) ds->ops->get_wol(ds, dp->index, w); } static int dsa_user_set_wol(struct net_device *dev, struct ethtool_wolinfo *w) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int ret = -EOPNOTSUPP; phylink_ethtool_set_wol(dp->pl, w); if (ds->ops->set_wol) ret = ds->ops->set_wol(ds, dp->index, w); return ret; } static int dsa_user_set_eee(struct net_device *dev, struct ethtool_keee *e) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int ret; /* Port's PHY and MAC both need to be EEE capable */ if (!dev->phydev || !dp->pl) return -ENODEV; if (!ds->ops->set_mac_eee) return -EOPNOTSUPP; ret = ds->ops->set_mac_eee(ds, dp->index, e); if (ret) return ret; return phylink_ethtool_set_eee(dp->pl, e); } static int dsa_user_get_eee(struct net_device *dev, struct ethtool_keee *e) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int ret; /* Port's PHY and MAC both need to be EEE capable */ if (!dev->phydev || !dp->pl) return -ENODEV; if (!ds->ops->get_mac_eee) return -EOPNOTSUPP; ret = ds->ops->get_mac_eee(ds, dp->index, e); if (ret) return ret; return phylink_ethtool_get_eee(dp->pl, e); } static int dsa_user_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { struct dsa_port *dp = dsa_user_to_port(dev); return phylink_ethtool_ksettings_get(dp->pl, cmd); } static int dsa_user_set_link_ksettings(struct net_device *dev, const struct ethtool_link_ksettings *cmd) { struct dsa_port *dp = dsa_user_to_port(dev); return phylink_ethtool_ksettings_set(dp->pl, cmd); } static void dsa_user_get_pause_stats(struct net_device *dev, struct ethtool_pause_stats *pause_stats) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_pause_stats) ds->ops->get_pause_stats(ds, dp->index, pause_stats); } static void dsa_user_get_pauseparam(struct net_device *dev, struct ethtool_pauseparam *pause) { struct dsa_port *dp = dsa_user_to_port(dev); phylink_ethtool_get_pauseparam(dp->pl, pause); } static int dsa_user_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam *pause) { struct dsa_port *dp = dsa_user_to_port(dev); return phylink_ethtool_set_pauseparam(dp->pl, pause); } #ifdef CONFIG_NET_POLL_CONTROLLER static int dsa_user_netpoll_setup(struct net_device *dev, struct netpoll_info *ni) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_user_priv *p = netdev_priv(dev); struct netpoll *netpoll; int err = 0; netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL); if (!netpoll) return -ENOMEM; err = __netpoll_setup(netpoll, conduit); if (err) { kfree(netpoll); goto out; } p->netpoll = netpoll; out: return err; } static void dsa_user_netpoll_cleanup(struct net_device *dev) { struct dsa_user_priv *p = netdev_priv(dev); struct netpoll *netpoll = p->netpoll; if (!netpoll) return; p->netpoll = NULL; __netpoll_free(netpoll); } static void dsa_user_poll_controller(struct net_device *dev) { } #endif static struct dsa_mall_tc_entry * dsa_user_mall_tc_entry_find(struct net_device *dev, unsigned long cookie) { struct dsa_user_priv *p = netdev_priv(dev); struct dsa_mall_tc_entry *mall_tc_entry; list_for_each_entry(mall_tc_entry, &p->mall_tc_list, list) if (mall_tc_entry->cookie == cookie) return mall_tc_entry; return NULL; } static int dsa_user_add_cls_matchall_mirred(struct net_device *dev, struct tc_cls_matchall_offload *cls, bool ingress) { struct netlink_ext_ack *extack = cls->common.extack; struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_user_priv *p = netdev_priv(dev); struct dsa_mall_mirror_tc_entry *mirror; struct dsa_mall_tc_entry *mall_tc_entry; struct dsa_switch *ds = dp->ds; struct flow_action_entry *act; struct dsa_port *to_dp; int err; if (!ds->ops->port_mirror_add) return -EOPNOTSUPP; if (!flow_action_basic_hw_stats_check(&cls->rule->action, cls->common.extack)) return -EOPNOTSUPP; act = &cls->rule->action.entries[0]; if (!act->dev) return -EINVAL; if (!dsa_user_dev_check(act->dev)) return -EOPNOTSUPP; mall_tc_entry = kzalloc(sizeof(*mall_tc_entry), GFP_KERNEL); if (!mall_tc_entry) return -ENOMEM; mall_tc_entry->cookie = cls->cookie; mall_tc_entry->type = DSA_PORT_MALL_MIRROR; mirror = &mall_tc_entry->mirror; to_dp = dsa_user_to_port(act->dev); mirror->to_local_port = to_dp->index; mirror->ingress = ingress; err = ds->ops->port_mirror_add(ds, dp->index, mirror, ingress, extack); if (err) { kfree(mall_tc_entry); return err; } list_add_tail(&mall_tc_entry->list, &p->mall_tc_list); return err; } static int dsa_user_add_cls_matchall_police(struct net_device *dev, struct tc_cls_matchall_offload *cls, bool ingress) { struct netlink_ext_ack *extack = cls->common.extack; struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_user_priv *p = netdev_priv(dev); struct dsa_mall_policer_tc_entry *policer; struct dsa_mall_tc_entry *mall_tc_entry; struct dsa_switch *ds = dp->ds; struct flow_action_entry *act; int err; if (!ds->ops->port_policer_add) { NL_SET_ERR_MSG_MOD(extack, "Policing offload not implemented"); return -EOPNOTSUPP; } if (!ingress) { NL_SET_ERR_MSG_MOD(extack, "Only supported on ingress qdisc"); return -EOPNOTSUPP; } if (!flow_action_basic_hw_stats_check(&cls->rule->action, cls->common.extack)) return -EOPNOTSUPP; list_for_each_entry(mall_tc_entry, &p->mall_tc_list, list) { if (mall_tc_entry->type == DSA_PORT_MALL_POLICER) { NL_SET_ERR_MSG_MOD(extack, "Only one port policer allowed"); return -EEXIST; } } act = &cls->rule->action.entries[0]; mall_tc_entry = kzalloc(sizeof(*mall_tc_entry), GFP_KERNEL); if (!mall_tc_entry) return -ENOMEM; mall_tc_entry->cookie = cls->cookie; mall_tc_entry->type = DSA_PORT_MALL_POLICER; policer = &mall_tc_entry->policer; policer->rate_bytes_per_sec = act->police.rate_bytes_ps; policer->burst = act->police.burst; err = ds->ops->port_policer_add(ds, dp->index, policer); if (err) { kfree(mall_tc_entry); return err; } list_add_tail(&mall_tc_entry->list, &p->mall_tc_list); return err; } static int dsa_user_add_cls_matchall(struct net_device *dev, struct tc_cls_matchall_offload *cls, bool ingress) { int err = -EOPNOTSUPP; if (cls->common.protocol == htons(ETH_P_ALL) && flow_offload_has_one_action(&cls->rule->action) && cls->rule->action.entries[0].id == FLOW_ACTION_MIRRED) err = dsa_user_add_cls_matchall_mirred(dev, cls, ingress); else if (flow_offload_has_one_action(&cls->rule->action) && cls->rule->action.entries[0].id == FLOW_ACTION_POLICE) err = dsa_user_add_cls_matchall_police(dev, cls, ingress); return err; } static void dsa_user_del_cls_matchall(struct net_device *dev, struct tc_cls_matchall_offload *cls) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_mall_tc_entry *mall_tc_entry; struct dsa_switch *ds = dp->ds; mall_tc_entry = dsa_user_mall_tc_entry_find(dev, cls->cookie); if (!mall_tc_entry) return; list_del(&mall_tc_entry->list); switch (mall_tc_entry->type) { case DSA_PORT_MALL_MIRROR: if (ds->ops->port_mirror_del) ds->ops->port_mirror_del(ds, dp->index, &mall_tc_entry->mirror); break; case DSA_PORT_MALL_POLICER: if (ds->ops->port_policer_del) ds->ops->port_policer_del(ds, dp->index); break; default: WARN_ON(1); } kfree(mall_tc_entry); } static int dsa_user_setup_tc_cls_matchall(struct net_device *dev, struct tc_cls_matchall_offload *cls, bool ingress) { if (cls->common.chain_index) return -EOPNOTSUPP; switch (cls->command) { case TC_CLSMATCHALL_REPLACE: return dsa_user_add_cls_matchall(dev, cls, ingress); case TC_CLSMATCHALL_DESTROY: dsa_user_del_cls_matchall(dev, cls); return 0; default: return -EOPNOTSUPP; } } static int dsa_user_add_cls_flower(struct net_device *dev, struct flow_cls_offload *cls, bool ingress) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; if (!ds->ops->cls_flower_add) return -EOPNOTSUPP; return ds->ops->cls_flower_add(ds, port, cls, ingress); } static int dsa_user_del_cls_flower(struct net_device *dev, struct flow_cls_offload *cls, bool ingress) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; if (!ds->ops->cls_flower_del) return -EOPNOTSUPP; return ds->ops->cls_flower_del(ds, port, cls, ingress); } static int dsa_user_stats_cls_flower(struct net_device *dev, struct flow_cls_offload *cls, bool ingress) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; if (!ds->ops->cls_flower_stats) return -EOPNOTSUPP; return ds->ops->cls_flower_stats(ds, port, cls, ingress); } static int dsa_user_setup_tc_cls_flower(struct net_device *dev, struct flow_cls_offload *cls, bool ingress) { switch (cls->command) { case FLOW_CLS_REPLACE: return dsa_user_add_cls_flower(dev, cls, ingress); case FLOW_CLS_DESTROY: return dsa_user_del_cls_flower(dev, cls, ingress); case FLOW_CLS_STATS: return dsa_user_stats_cls_flower(dev, cls, ingress); default: return -EOPNOTSUPP; } } static int dsa_user_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv, bool ingress) { struct net_device *dev = cb_priv; if (!tc_can_offload(dev)) return -EOPNOTSUPP; switch (type) { case TC_SETUP_CLSMATCHALL: return dsa_user_setup_tc_cls_matchall(dev, type_data, ingress); case TC_SETUP_CLSFLOWER: return dsa_user_setup_tc_cls_flower(dev, type_data, ingress); default: return -EOPNOTSUPP; } } static int dsa_user_setup_tc_block_cb_ig(enum tc_setup_type type, void *type_data, void *cb_priv) { return dsa_user_setup_tc_block_cb(type, type_data, cb_priv, true); } static int dsa_user_setup_tc_block_cb_eg(enum tc_setup_type type, void *type_data, void *cb_priv) { return dsa_user_setup_tc_block_cb(type, type_data, cb_priv, false); } static LIST_HEAD(dsa_user_block_cb_list); static int dsa_user_setup_tc_block(struct net_device *dev, struct flow_block_offload *f) { struct flow_block_cb *block_cb; flow_setup_cb_t *cb; if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS) cb = dsa_user_setup_tc_block_cb_ig; else if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS) cb = dsa_user_setup_tc_block_cb_eg; else return -EOPNOTSUPP; f->driver_block_list = &dsa_user_block_cb_list; switch (f->command) { case FLOW_BLOCK_BIND: if (flow_block_cb_is_busy(cb, dev, &dsa_user_block_cb_list)) return -EBUSY; block_cb = flow_block_cb_alloc(cb, dev, dev, NULL); if (IS_ERR(block_cb)) return PTR_ERR(block_cb); flow_block_cb_add(block_cb, f); list_add_tail(&block_cb->driver_list, &dsa_user_block_cb_list); return 0; case FLOW_BLOCK_UNBIND: block_cb = flow_block_cb_lookup(f->block, cb, dev); if (!block_cb) return -ENOENT; flow_block_cb_remove(block_cb, f); list_del(&block_cb->driver_list); return 0; default: return -EOPNOTSUPP; } } static int dsa_user_setup_ft_block(struct dsa_switch *ds, int port, void *type_data) { struct net_device *conduit = dsa_port_to_conduit(dsa_to_port(ds, port)); if (!conduit->netdev_ops->ndo_setup_tc) return -EOPNOTSUPP; return conduit->netdev_ops->ndo_setup_tc(conduit, TC_SETUP_FT, type_data); } static int dsa_user_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; switch (type) { case TC_SETUP_BLOCK: return dsa_user_setup_tc_block(dev, type_data); case TC_SETUP_FT: return dsa_user_setup_ft_block(ds, dp->index, type_data); default: break; } if (!ds->ops->port_setup_tc) return -EOPNOTSUPP; return ds->ops->port_setup_tc(ds, dp->index, type, type_data); } static int dsa_user_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *nfc, u32 *rule_locs) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ds->ops->get_rxnfc) return -EOPNOTSUPP; return ds->ops->get_rxnfc(ds, dp->index, nfc, rule_locs); } static int dsa_user_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *nfc) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ds->ops->set_rxnfc) return -EOPNOTSUPP; return ds->ops->set_rxnfc(ds, dp->index, nfc); } static int dsa_user_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *ts) { struct dsa_user_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->dp->ds; if (!ds->ops->get_ts_info) return -EOPNOTSUPP; return ds->ops->get_ts_info(ds, p->dp->index, ts); } static int dsa_user_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan vlan = { .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, .vid = vid, /* This API only allows programming tagged, non-PVID VIDs */ .flags = 0, }; struct netlink_ext_ack extack = {0}; struct dsa_switch *ds = dp->ds; struct netdev_hw_addr *ha; struct dsa_vlan *v; int ret; /* User port... */ ret = dsa_port_vlan_add(dp, &vlan, &extack); if (ret) { if (extack._msg) netdev_err(dev, "%s\n", extack._msg); return ret; } /* And CPU port... */ ret = dsa_port_host_vlan_add(dp, &vlan, &extack); if (ret) { if (extack._msg) netdev_err(dev, "CPU port %d: %s\n", dp->cpu_dp->index, extack._msg); return ret; } if (!dsa_switch_supports_uc_filtering(ds) && !dsa_switch_supports_mc_filtering(ds)) return 0; v = kzalloc(sizeof(*v), GFP_KERNEL); if (!v) { ret = -ENOMEM; goto rollback; } netif_addr_lock_bh(dev); v->vid = vid; list_add_tail(&v->list, &dp->user_vlans); if (dsa_switch_supports_mc_filtering(ds)) { netdev_for_each_synced_mc_addr(ha, dev) { dsa_user_schedule_standalone_work(dev, DSA_MC_ADD, ha->addr, vid); } } if (dsa_switch_supports_uc_filtering(ds)) { netdev_for_each_synced_uc_addr(ha, dev) { dsa_user_schedule_standalone_work(dev, DSA_UC_ADD, ha->addr, vid); } } netif_addr_unlock_bh(dev); dsa_flush_workqueue(); return 0; rollback: dsa_port_host_vlan_del(dp, &vlan); dsa_port_vlan_del(dp, &vlan); return ret; } static int dsa_user_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan vlan = { .vid = vid, /* This API only allows programming tagged, non-PVID VIDs */ .flags = 0, }; struct dsa_switch *ds = dp->ds; struct netdev_hw_addr *ha; struct dsa_vlan *v; int err; err = dsa_port_vlan_del(dp, &vlan); if (err) return err; err = dsa_port_host_vlan_del(dp, &vlan); if (err) return err; if (!dsa_switch_supports_uc_filtering(ds) && !dsa_switch_supports_mc_filtering(ds)) return 0; netif_addr_lock_bh(dev); v = dsa_vlan_find(&dp->user_vlans, &vlan); if (!v) { netif_addr_unlock_bh(dev); return -ENOENT; } list_del(&v->list); kfree(v); if (dsa_switch_supports_mc_filtering(ds)) { netdev_for_each_synced_mc_addr(ha, dev) { dsa_user_schedule_standalone_work(dev, DSA_MC_DEL, ha->addr, vid); } } if (dsa_switch_supports_uc_filtering(ds)) { netdev_for_each_synced_uc_addr(ha, dev) { dsa_user_schedule_standalone_work(dev, DSA_UC_DEL, ha->addr, vid); } } netif_addr_unlock_bh(dev); dsa_flush_workqueue(); return 0; } static int dsa_user_restore_vlan(struct net_device *vdev, int vid, void *arg) { __be16 proto = vdev ? vlan_dev_vlan_proto(vdev) : htons(ETH_P_8021Q); return dsa_user_vlan_rx_add_vid(arg, proto, vid); } static int dsa_user_clear_vlan(struct net_device *vdev, int vid, void *arg) { __be16 proto = vdev ? vlan_dev_vlan_proto(vdev) : htons(ETH_P_8021Q); return dsa_user_vlan_rx_kill_vid(arg, proto, vid); } /* Keep the VLAN RX filtering list in sync with the hardware only if VLAN * filtering is enabled. The baseline is that only ports that offload a * VLAN-aware bridge are VLAN-aware, and standalone ports are VLAN-unaware, * but there are exceptions for quirky hardware. * * If ds->vlan_filtering_is_global = true, then standalone ports which share * the same switch with other ports that offload a VLAN-aware bridge are also * inevitably VLAN-aware. * * To summarize, a DSA switch port offloads: * * - If standalone (this includes software bridge, software LAG): * - if ds->needs_standalone_vlan_filtering = true, OR if * (ds->vlan_filtering_is_global = true AND there are bridges spanning * this switch chip which have vlan_filtering=1) * - the 8021q upper VLANs * - else (standalone VLAN filtering is not needed, VLAN filtering is not * global, or it is, but no port is under a VLAN-aware bridge): * - no VLAN (any 8021q upper is a software VLAN) * * - If under a vlan_filtering=0 bridge which it offload: * - if ds->configure_vlan_while_not_filtering = true (default): * - the bridge VLANs. These VLANs are committed to hardware but inactive. * - else (deprecated): * - no VLAN. The bridge VLANs are not restored when VLAN awareness is * enabled, so this behavior is broken and discouraged. * * - If under a vlan_filtering=1 bridge which it offload: * - the bridge VLANs * - the 8021q upper VLANs */ int dsa_user_manage_vlan_filtering(struct net_device *user, bool vlan_filtering) { int err; if (vlan_filtering) { user->features |= NETIF_F_HW_VLAN_CTAG_FILTER; err = vlan_for_each(user, dsa_user_restore_vlan, user); if (err) { vlan_for_each(user, dsa_user_clear_vlan, user); user->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; return err; } } else { err = vlan_for_each(user, dsa_user_clear_vlan, user); if (err) return err; user->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; } return 0; } struct dsa_hw_port { struct list_head list; struct net_device *dev; int old_mtu; }; static int dsa_hw_port_list_set_mtu(struct list_head *hw_port_list, int mtu) { const struct dsa_hw_port *p; int err; list_for_each_entry(p, hw_port_list, list) { if (p->dev->mtu == mtu) continue; err = dev_set_mtu(p->dev, mtu); if (err) goto rollback; } return 0; rollback: list_for_each_entry_continue_reverse(p, hw_port_list, list) { if (p->dev->mtu == p->old_mtu) continue; if (dev_set_mtu(p->dev, p->old_mtu)) netdev_err(p->dev, "Failed to restore MTU\n"); } return err; } static void dsa_hw_port_list_free(struct list_head *hw_port_list) { struct dsa_hw_port *p, *n; list_for_each_entry_safe(p, n, hw_port_list, list) kfree(p); } /* Make the hardware datapath to/from @dev limited to a common MTU */ static void dsa_bridge_mtu_normalization(struct dsa_port *dp) { struct list_head hw_port_list; struct dsa_switch_tree *dst; int min_mtu = ETH_MAX_MTU; struct dsa_port *other_dp; int err; if (!dp->ds->mtu_enforcement_ingress) return; if (!dp->bridge) return; INIT_LIST_HEAD(&hw_port_list); /* Populate the list of ports that are part of the same bridge * as the newly added/modified port */ list_for_each_entry(dst, &dsa_tree_list, list) { list_for_each_entry(other_dp, &dst->ports, list) { struct dsa_hw_port *hw_port; struct net_device *user; if (other_dp->type != DSA_PORT_TYPE_USER) continue; if (!dsa_port_bridge_same(dp, other_dp)) continue; if (!other_dp->ds->mtu_enforcement_ingress) continue; user = other_dp->user; if (min_mtu > user->mtu) min_mtu = user->mtu; hw_port = kzalloc(sizeof(*hw_port), GFP_KERNEL); if (!hw_port) goto out; hw_port->dev = user; hw_port->old_mtu = user->mtu; list_add(&hw_port->list, &hw_port_list); } } /* Attempt to configure the entire hardware bridge to the newly added * interface's MTU first, regardless of whether the intention of the * user was to raise or lower it. */ err = dsa_hw_port_list_set_mtu(&hw_port_list, dp->user->mtu); if (!err) goto out; /* Clearly that didn't work out so well, so just set the minimum MTU on * all hardware bridge ports now. If this fails too, then all ports will * still have their old MTU rolled back anyway. */ dsa_hw_port_list_set_mtu(&hw_port_list, min_mtu); out: dsa_hw_port_list_free(&hw_port_list); } int dsa_user_change_mtu(struct net_device *dev, int new_mtu) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_port *cpu_dp = dp->cpu_dp; struct dsa_switch *ds = dp->ds; struct dsa_port *other_dp; int largest_mtu = 0; int new_conduit_mtu; int old_conduit_mtu; int mtu_limit; int overhead; int cpu_mtu; int err; if (!ds->ops->port_change_mtu) return -EOPNOTSUPP; dsa_tree_for_each_user_port(other_dp, ds->dst) { int user_mtu; /* During probe, this function will be called for each user * device, while not all of them have been allocated. That's * ok, it doesn't change what the maximum is, so ignore it. */ if (!other_dp->user) continue; /* Pretend that we already applied the setting, which we * actually haven't (still haven't done all integrity checks) */ if (dp == other_dp) user_mtu = new_mtu; else user_mtu = other_dp->user->mtu; if (largest_mtu < user_mtu) largest_mtu = user_mtu; } overhead = dsa_tag_protocol_overhead(cpu_dp->tag_ops); mtu_limit = min_t(int, conduit->max_mtu, dev->max_mtu + overhead); old_conduit_mtu = conduit->mtu; new_conduit_mtu = largest_mtu + overhead; if (new_conduit_mtu > mtu_limit) return -ERANGE; /* If the conduit MTU isn't over limit, there's no need to check the CPU * MTU, since that surely isn't either. */ cpu_mtu = largest_mtu; /* Start applying stuff */ if (new_conduit_mtu != old_conduit_mtu) { err = dev_set_mtu(conduit, new_conduit_mtu); if (err < 0) goto out_conduit_failed; /* We only need to propagate the MTU of the CPU port to * upstream switches, so emit a notifier which updates them. */ err = dsa_port_mtu_change(cpu_dp, cpu_mtu); if (err) goto out_cpu_failed; } err = ds->ops->port_change_mtu(ds, dp->index, new_mtu); if (err) goto out_port_failed; WRITE_ONCE(dev->mtu, new_mtu); dsa_bridge_mtu_normalization(dp); return 0; out_port_failed: if (new_conduit_mtu != old_conduit_mtu) dsa_port_mtu_change(cpu_dp, old_conduit_mtu - overhead); out_cpu_failed: if (new_conduit_mtu != old_conduit_mtu) dev_set_mtu(conduit, old_conduit_mtu); out_conduit_failed: return err; } static int __maybe_unused dsa_user_dcbnl_set_apptrust(struct net_device *dev, u8 *sel, int nsel) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; if (!ds->ops->port_set_apptrust) return -EOPNOTSUPP; return ds->ops->port_set_apptrust(ds, port, sel, nsel); } static int __maybe_unused dsa_user_dcbnl_get_apptrust(struct net_device *dev, u8 *sel, int *nsel) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; if (!ds->ops->port_get_apptrust) return -EOPNOTSUPP; return ds->ops->port_get_apptrust(ds, port, sel, nsel); } static int __maybe_unused dsa_user_dcbnl_set_default_prio(struct net_device *dev, struct dcb_app *app) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; unsigned long mask, new_prio; int err, port = dp->index; if (!ds->ops->port_set_default_prio) return -EOPNOTSUPP; err = dcb_ieee_setapp(dev, app); if (err) return err; mask = dcb_ieee_getapp_mask(dev, app); new_prio = __fls(mask); err = ds->ops->port_set_default_prio(ds, port, new_prio); if (err) { dcb_ieee_delapp(dev, app); return err; } return 0; } /* Update the DSCP prio entries on all user ports of the switch in case * the switch supports global DSCP prio instead of per port DSCP prios. */ static int dsa_user_dcbnl_ieee_global_dscp_setdel(struct net_device *dev, struct dcb_app *app, bool del) { int (*setdel)(struct net_device *dev, struct dcb_app *app); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct dsa_port *other_dp; int err, restore_err; if (del) setdel = dcb_ieee_delapp; else setdel = dcb_ieee_setapp; dsa_switch_for_each_user_port(other_dp, ds) { struct net_device *user = other_dp->user; if (!user || user == dev) continue; err = setdel(user, app); if (err) goto err_try_to_restore; } return 0; err_try_to_restore: /* Revert logic to restore previous state of app entries */ if (!del) setdel = dcb_ieee_delapp; else setdel = dcb_ieee_setapp; dsa_switch_for_each_user_port_continue_reverse(other_dp, ds) { struct net_device *user = other_dp->user; if (!user || user == dev) continue; restore_err = setdel(user, app); if (restore_err) netdev_err(user, "Failed to restore DSCP prio entry configuration\n"); } return err; } static int __maybe_unused dsa_user_dcbnl_add_dscp_prio(struct net_device *dev, struct dcb_app *app) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; unsigned long mask, new_prio; int err, port = dp->index; u8 dscp = app->protocol; if (!ds->ops->port_add_dscp_prio) return -EOPNOTSUPP; if (dscp >= 64) { netdev_err(dev, "DSCP APP entry with protocol value %u is invalid\n", dscp); return -EINVAL; } err = dcb_ieee_setapp(dev, app); if (err) return err; mask = dcb_ieee_getapp_mask(dev, app); new_prio = __fls(mask); err = ds->ops->port_add_dscp_prio(ds, port, dscp, new_prio); if (err) { dcb_ieee_delapp(dev, app); return err; } if (!ds->dscp_prio_mapping_is_global) return 0; err = dsa_user_dcbnl_ieee_global_dscp_setdel(dev, app, false); if (err) { if (ds->ops->port_del_dscp_prio) ds->ops->port_del_dscp_prio(ds, port, dscp, new_prio); dcb_ieee_delapp(dev, app); return err; } return 0; } static int __maybe_unused dsa_user_dcbnl_ieee_setapp(struct net_device *dev, struct dcb_app *app) { switch (app->selector) { case IEEE_8021QAZ_APP_SEL_ETHERTYPE: switch (app->protocol) { case 0: return dsa_user_dcbnl_set_default_prio(dev, app); default: return -EOPNOTSUPP; } break; case IEEE_8021QAZ_APP_SEL_DSCP: return dsa_user_dcbnl_add_dscp_prio(dev, app); default: return -EOPNOTSUPP; } } static int __maybe_unused dsa_user_dcbnl_del_default_prio(struct net_device *dev, struct dcb_app *app) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; unsigned long mask, new_prio; int err, port = dp->index; if (!ds->ops->port_set_default_prio) return -EOPNOTSUPP; err = dcb_ieee_delapp(dev, app); if (err) return err; mask = dcb_ieee_getapp_mask(dev, app); new_prio = mask ? __fls(mask) : 0; err = ds->ops->port_set_default_prio(ds, port, new_prio); if (err) { dcb_ieee_setapp(dev, app); return err; } return 0; } static int __maybe_unused dsa_user_dcbnl_del_dscp_prio(struct net_device *dev, struct dcb_app *app) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int err, port = dp->index; u8 dscp = app->protocol; if (!ds->ops->port_del_dscp_prio) return -EOPNOTSUPP; err = dcb_ieee_delapp(dev, app); if (err) return err; err = ds->ops->port_del_dscp_prio(ds, port, dscp, app->priority); if (err) { dcb_ieee_setapp(dev, app); return err; } if (!ds->dscp_prio_mapping_is_global) return 0; err = dsa_user_dcbnl_ieee_global_dscp_setdel(dev, app, true); if (err) { if (ds->ops->port_add_dscp_prio) ds->ops->port_add_dscp_prio(ds, port, dscp, app->priority); dcb_ieee_setapp(dev, app); return err; } return 0; } static int __maybe_unused dsa_user_dcbnl_ieee_delapp(struct net_device *dev, struct dcb_app *app) { switch (app->selector) { case IEEE_8021QAZ_APP_SEL_ETHERTYPE: switch (app->protocol) { case 0: return dsa_user_dcbnl_del_default_prio(dev, app); default: return -EOPNOTSUPP; } break; case IEEE_8021QAZ_APP_SEL_DSCP: return dsa_user_dcbnl_del_dscp_prio(dev, app); default: return -EOPNOTSUPP; } } /* Pre-populate the DCB application priority table with the priorities * configured during switch setup, which we read from hardware here. */ static int dsa_user_dcbnl_init(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; int err; if (ds->ops->port_get_default_prio) { int prio = ds->ops->port_get_default_prio(ds, port); struct dcb_app app = { .selector = IEEE_8021QAZ_APP_SEL_ETHERTYPE, .protocol = 0, .priority = prio, }; if (prio < 0) return prio; err = dcb_ieee_setapp(dev, &app); if (err) return err; } if (ds->ops->port_get_dscp_prio) { int protocol; for (protocol = 0; protocol < 64; protocol++) { struct dcb_app app = { .selector = IEEE_8021QAZ_APP_SEL_DSCP, .protocol = protocol, }; int prio; prio = ds->ops->port_get_dscp_prio(ds, port, protocol); if (prio == -EOPNOTSUPP) continue; if (prio < 0) return prio; app.priority = prio; err = dcb_ieee_setapp(dev, &app); if (err) return err; } } return 0; } static const struct ethtool_ops dsa_user_ethtool_ops = { .get_drvinfo = dsa_user_get_drvinfo, .get_regs_len = dsa_user_get_regs_len, .get_regs = dsa_user_get_regs, .nway_reset = dsa_user_nway_reset, .get_link = ethtool_op_get_link, .get_eeprom_len = dsa_user_get_eeprom_len, .get_eeprom = dsa_user_get_eeprom, .set_eeprom = dsa_user_set_eeprom, .get_strings = dsa_user_get_strings, .get_ethtool_stats = dsa_user_get_ethtool_stats, .get_sset_count = dsa_user_get_sset_count, .get_eth_phy_stats = dsa_user_get_eth_phy_stats, .get_eth_mac_stats = dsa_user_get_eth_mac_stats, .get_eth_ctrl_stats = dsa_user_get_eth_ctrl_stats, .get_rmon_stats = dsa_user_get_rmon_stats, .set_wol = dsa_user_set_wol, .get_wol = dsa_user_get_wol, .set_eee = dsa_user_set_eee, .get_eee = dsa_user_get_eee, .get_link_ksettings = dsa_user_get_link_ksettings, .set_link_ksettings = dsa_user_set_link_ksettings, .get_pause_stats = dsa_user_get_pause_stats, .get_pauseparam = dsa_user_get_pauseparam, .set_pauseparam = dsa_user_set_pauseparam, .get_rxnfc = dsa_user_get_rxnfc, .set_rxnfc = dsa_user_set_rxnfc, .get_ts_info = dsa_user_get_ts_info, .self_test = dsa_user_net_selftest, .get_mm = dsa_user_get_mm, .set_mm = dsa_user_set_mm, .get_mm_stats = dsa_user_get_mm_stats, }; static const struct dcbnl_rtnl_ops __maybe_unused dsa_user_dcbnl_ops = { .ieee_setapp = dsa_user_dcbnl_ieee_setapp, .ieee_delapp = dsa_user_dcbnl_ieee_delapp, .dcbnl_setapptrust = dsa_user_dcbnl_set_apptrust, .dcbnl_getapptrust = dsa_user_dcbnl_get_apptrust, }; static void dsa_user_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *s) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_stats64) ds->ops->get_stats64(ds, dp->index, s); else dev_get_tstats64(dev, s); } static int dsa_user_fill_forward_path(struct net_device_path_ctx *ctx, struct net_device_path *path) { struct dsa_port *dp = dsa_user_to_port(ctx->dev); struct net_device *conduit = dsa_port_to_conduit(dp); struct dsa_port *cpu_dp = dp->cpu_dp; path->dev = ctx->dev; path->type = DEV_PATH_DSA; path->dsa.proto = cpu_dp->tag_ops->proto; path->dsa.port = dp->index; ctx->dev = conduit; return 0; } static const struct net_device_ops dsa_user_netdev_ops = { .ndo_open = dsa_user_open, .ndo_stop = dsa_user_close, .ndo_start_xmit = dsa_user_xmit, .ndo_change_rx_flags = dsa_user_change_rx_flags, .ndo_set_rx_mode = dsa_user_set_rx_mode, .ndo_set_mac_address = dsa_user_set_mac_address, .ndo_fdb_dump = dsa_user_fdb_dump, .ndo_eth_ioctl = dsa_user_ioctl, .ndo_get_iflink = dsa_user_get_iflink, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_netpoll_setup = dsa_user_netpoll_setup, .ndo_netpoll_cleanup = dsa_user_netpoll_cleanup, .ndo_poll_controller = dsa_user_poll_controller, #endif .ndo_setup_tc = dsa_user_setup_tc, .ndo_get_stats64 = dsa_user_get_stats64, .ndo_vlan_rx_add_vid = dsa_user_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = dsa_user_vlan_rx_kill_vid, .ndo_change_mtu = dsa_user_change_mtu, .ndo_fill_forward_path = dsa_user_fill_forward_path, }; static const struct device_type dsa_type = { .name = "dsa", }; void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up) { const struct dsa_port *dp = dsa_to_port(ds, port); if (dp->pl) phylink_mac_change(dp->pl, up); } EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_change); static void dsa_user_phylink_fixed_state(struct phylink_config *config, struct phylink_link_state *state) { struct dsa_port *dp = dsa_phylink_to_port(config); struct dsa_switch *ds = dp->ds; /* No need to check that this operation is valid, the callback would * not be called if it was not. */ ds->ops->phylink_fixed_state(ds, dp->index, state); } /* user device setup *******************************************************/ static int dsa_user_phy_connect(struct net_device *user_dev, int addr, u32 flags) { struct dsa_port *dp = dsa_user_to_port(user_dev); struct dsa_switch *ds = dp->ds; user_dev->phydev = mdiobus_get_phy(ds->user_mii_bus, addr); if (!user_dev->phydev) { netdev_err(user_dev, "no phy at %d\n", addr); return -ENODEV; } user_dev->phydev->dev_flags |= flags; return phylink_connect_phy(dp->pl, user_dev->phydev); } static int dsa_user_phy_setup(struct net_device *user_dev) { struct dsa_port *dp = dsa_user_to_port(user_dev); struct device_node *port_dn = dp->dn; struct dsa_switch *ds = dp->ds; u32 phy_flags = 0; int ret; dp->pl_config.dev = &user_dev->dev; dp->pl_config.type = PHYLINK_NETDEV; /* The get_fixed_state callback takes precedence over polling the * link GPIO in PHYLINK (see phylink_get_fixed_state). Only set * this if the switch provides such a callback. */ if (ds->ops->phylink_fixed_state) { dp->pl_config.get_fixed_state = dsa_user_phylink_fixed_state; dp->pl_config.poll_fixed_state = true; } ret = dsa_port_phylink_create(dp); if (ret) return ret; if (ds->ops->get_phy_flags) phy_flags = ds->ops->get_phy_flags(ds, dp->index); ret = phylink_of_phy_connect(dp->pl, port_dn, phy_flags); if (ret == -ENODEV && ds->user_mii_bus) { /* We could not connect to a designated PHY or SFP, so try to * use the switch internal MDIO bus instead */ ret = dsa_user_phy_connect(user_dev, dp->index, phy_flags); } if (ret) { netdev_err(user_dev, "failed to connect to PHY: %pe\n", ERR_PTR(ret)); dsa_port_phylink_destroy(dp); } return ret; } void dsa_user_setup_tagger(struct net_device *user) { struct dsa_port *dp = dsa_user_to_port(user); struct net_device *conduit = dsa_port_to_conduit(dp); struct dsa_user_priv *p = netdev_priv(user); const struct dsa_port *cpu_dp = dp->cpu_dp; const struct dsa_switch *ds = dp->ds; user->needed_headroom = cpu_dp->tag_ops->needed_headroom; user->needed_tailroom = cpu_dp->tag_ops->needed_tailroom; /* Try to save one extra realloc later in the TX path (in the conduit) * by also inheriting the conduit's needed headroom and tailroom. * The 8021q driver also does this. */ user->needed_headroom += conduit->needed_headroom; user->needed_tailroom += conduit->needed_tailroom; p->xmit = cpu_dp->tag_ops->xmit; user->features = conduit->vlan_features | NETIF_F_HW_TC; user->hw_features |= NETIF_F_HW_TC; user->features |= NETIF_F_LLTX; if (user->needed_tailroom) user->features &= ~(NETIF_F_SG | NETIF_F_FRAGLIST); if (ds->needs_standalone_vlan_filtering) user->features |= NETIF_F_HW_VLAN_CTAG_FILTER; } int dsa_user_suspend(struct net_device *user_dev) { struct dsa_port *dp = dsa_user_to_port(user_dev); if (!netif_running(user_dev)) return 0; netif_device_detach(user_dev); rtnl_lock(); phylink_stop(dp->pl); rtnl_unlock(); return 0; } int dsa_user_resume(struct net_device *user_dev) { struct dsa_port *dp = dsa_user_to_port(user_dev); if (!netif_running(user_dev)) return 0; netif_device_attach(user_dev); rtnl_lock(); phylink_start(dp->pl); rtnl_unlock(); return 0; } int dsa_user_create(struct dsa_port *port) { struct net_device *conduit = dsa_port_to_conduit(port); struct dsa_switch *ds = port->ds; struct net_device *user_dev; struct dsa_user_priv *p; const char *name; int assign_type; int ret; if (!ds->num_tx_queues) ds->num_tx_queues = 1; if (port->name) { name = port->name; assign_type = NET_NAME_PREDICTABLE; } else { name = "eth%d"; assign_type = NET_NAME_ENUM; } user_dev = alloc_netdev_mqs(sizeof(struct dsa_user_priv), name, assign_type, ether_setup, ds->num_tx_queues, 1); if (user_dev == NULL) return -ENOMEM; user_dev->rtnl_link_ops = &dsa_link_ops; user_dev->ethtool_ops = &dsa_user_ethtool_ops; #if IS_ENABLED(CONFIG_DCB) user_dev->dcbnl_ops = &dsa_user_dcbnl_ops; #endif if (!is_zero_ether_addr(port->mac)) eth_hw_addr_set(user_dev, port->mac); else eth_hw_addr_inherit(user_dev, conduit); user_dev->priv_flags |= IFF_NO_QUEUE; if (dsa_switch_supports_uc_filtering(ds)) user_dev->priv_flags |= IFF_UNICAST_FLT; user_dev->netdev_ops = &dsa_user_netdev_ops; if (ds->ops->port_max_mtu) user_dev->max_mtu = ds->ops->port_max_mtu(ds, port->index); SET_NETDEV_DEVTYPE(user_dev, &dsa_type); SET_NETDEV_DEV(user_dev, port->ds->dev); SET_NETDEV_DEVLINK_PORT(user_dev, &port->devlink_port); user_dev->dev.of_node = port->dn; user_dev->vlan_features = conduit->vlan_features; p = netdev_priv(user_dev); user_dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; ret = gro_cells_init(&p->gcells, user_dev); if (ret) goto out_free; p->dp = port; INIT_LIST_HEAD(&p->mall_tc_list); port->user = user_dev; dsa_user_setup_tagger(user_dev); netif_carrier_off(user_dev); ret = dsa_user_phy_setup(user_dev); if (ret) { netdev_err(user_dev, "error %d setting up PHY for tree %d, switch %d, port %d\n", ret, ds->dst->index, ds->index, port->index); goto out_gcells; } rtnl_lock(); ret = dsa_user_change_mtu(user_dev, ETH_DATA_LEN); if (ret && ret != -EOPNOTSUPP) dev_warn(ds->dev, "nonfatal error %d setting MTU to %d on port %d\n", ret, ETH_DATA_LEN, port->index); ret = register_netdevice(user_dev); if (ret) { netdev_err(conduit, "error %d registering interface %s\n", ret, user_dev->name); rtnl_unlock(); goto out_phy; } if (IS_ENABLED(CONFIG_DCB)) { ret = dsa_user_dcbnl_init(user_dev); if (ret) { netdev_err(user_dev, "failed to initialize DCB: %pe\n", ERR_PTR(ret)); rtnl_unlock(); goto out_unregister; } } ret = netdev_upper_dev_link(conduit, user_dev, NULL); rtnl_unlock(); if (ret) goto out_unregister; return 0; out_unregister: unregister_netdev(user_dev); out_phy: rtnl_lock(); phylink_disconnect_phy(p->dp->pl); rtnl_unlock(); dsa_port_phylink_destroy(p->dp); out_gcells: gro_cells_destroy(&p->gcells); out_free: free_netdev(user_dev); port->user = NULL; return ret; } void dsa_user_destroy(struct net_device *user_dev) { struct net_device *conduit = dsa_user_to_conduit(user_dev); struct dsa_port *dp = dsa_user_to_port(user_dev); struct dsa_user_priv *p = netdev_priv(user_dev); netif_carrier_off(user_dev); rtnl_lock(); netdev_upper_dev_unlink(conduit, user_dev); unregister_netdevice(user_dev); phylink_disconnect_phy(dp->pl); rtnl_unlock(); dsa_port_phylink_destroy(dp); gro_cells_destroy(&p->gcells); free_netdev(user_dev); } int dsa_user_change_conduit(struct net_device *dev, struct net_device *conduit, struct netlink_ext_ack *extack) { struct net_device *old_conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct net_device *upper; struct list_head *iter; int err; if (conduit == old_conduit) return 0; if (!ds->ops->port_change_conduit) { NL_SET_ERR_MSG_MOD(extack, "Driver does not support changing DSA conduit"); return -EOPNOTSUPP; } if (!netdev_uses_dsa(conduit)) { NL_SET_ERR_MSG_MOD(extack, "Interface not eligible as DSA conduit"); return -EOPNOTSUPP; } netdev_for_each_upper_dev_rcu(conduit, upper, iter) { if (dsa_user_dev_check(upper)) continue; if (netif_is_bridge_master(upper)) continue; NL_SET_ERR_MSG_MOD(extack, "Cannot join conduit with unknown uppers"); return -EOPNOTSUPP; } /* Since we allow live-changing the DSA conduit, plus we auto-open the * DSA conduit when the user port opens => we need to ensure that the * new DSA conduit is open too. */ if (dev->flags & IFF_UP) { err = dev_open(conduit, extack); if (err) return err; } netdev_upper_dev_unlink(old_conduit, dev); err = netdev_upper_dev_link(conduit, dev, extack); if (err) goto out_revert_old_conduit_unlink; err = dsa_port_change_conduit(dp, conduit, extack); if (err) goto out_revert_conduit_link; /* Update the MTU of the new CPU port through cross-chip notifiers */ err = dsa_user_change_mtu(dev, dev->mtu); if (err && err != -EOPNOTSUPP) { netdev_warn(dev, "nonfatal error updating MTU with new conduit: %pe\n", ERR_PTR(err)); } return 0; out_revert_conduit_link: netdev_upper_dev_unlink(conduit, dev); out_revert_old_conduit_unlink: netdev_upper_dev_link(old_conduit, dev, NULL); return err; } bool dsa_user_dev_check(const struct net_device *dev) { return dev->netdev_ops == &dsa_user_netdev_ops; } EXPORT_SYMBOL_GPL(dsa_user_dev_check); static int dsa_user_changeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *extack; int err = NOTIFY_DONE; struct dsa_port *dp; if (!dsa_user_dev_check(dev)) return err; dp = dsa_user_to_port(dev); extack = netdev_notifier_info_to_extack(&info->info); if (netif_is_bridge_master(info->upper_dev)) { if (info->linking) { err = dsa_port_bridge_join(dp, info->upper_dev, extack); if (!err) dsa_bridge_mtu_normalization(dp); if (err == -EOPNOTSUPP) { NL_SET_ERR_MSG_WEAK_MOD(extack, "Offloading not supported"); err = 0; } err = notifier_from_errno(err); } else { dsa_port_bridge_leave(dp, info->upper_dev); err = NOTIFY_OK; } } else if (netif_is_lag_master(info->upper_dev)) { if (info->linking) { err = dsa_port_lag_join(dp, info->upper_dev, info->upper_info, extack); if (err == -EOPNOTSUPP) { NL_SET_ERR_MSG_WEAK_MOD(extack, "Offloading not supported"); err = 0; } err = notifier_from_errno(err); } else { dsa_port_lag_leave(dp, info->upper_dev); err = NOTIFY_OK; } } else if (is_hsr_master(info->upper_dev)) { if (info->linking) { err = dsa_port_hsr_join(dp, info->upper_dev, extack); if (err == -EOPNOTSUPP) { NL_SET_ERR_MSG_WEAK_MOD(extack, "Offloading not supported"); err = 0; } err = notifier_from_errno(err); } else { dsa_port_hsr_leave(dp, info->upper_dev); err = NOTIFY_OK; } } return err; } static int dsa_user_prechangeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct dsa_port *dp; if (!dsa_user_dev_check(dev)) return NOTIFY_DONE; dp = dsa_user_to_port(dev); if (netif_is_bridge_master(info->upper_dev) && !info->linking) dsa_port_pre_bridge_leave(dp, info->upper_dev); else if (netif_is_lag_master(info->upper_dev) && !info->linking) dsa_port_pre_lag_leave(dp, info->upper_dev); /* dsa_port_pre_hsr_leave is not yet necessary since hsr devices cannot * meaningfully placed under a bridge yet */ return NOTIFY_DONE; } static int dsa_user_lag_changeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct net_device *lower; struct list_head *iter; int err = NOTIFY_DONE; struct dsa_port *dp; if (!netif_is_lag_master(dev)) return err; netdev_for_each_lower_dev(dev, lower, iter) { if (!dsa_user_dev_check(lower)) continue; dp = dsa_user_to_port(lower); if (!dp->lag) /* Software LAG */ continue; err = dsa_user_changeupper(lower, info); if (notifier_to_errno(err)) break; } return err; } /* Same as dsa_user_lag_changeupper() except that it calls * dsa_user_prechangeupper() */ static int dsa_user_lag_prechangeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct net_device *lower; struct list_head *iter; int err = NOTIFY_DONE; struct dsa_port *dp; if (!netif_is_lag_master(dev)) return err; netdev_for_each_lower_dev(dev, lower, iter) { if (!dsa_user_dev_check(lower)) continue; dp = dsa_user_to_port(lower); if (!dp->lag) /* Software LAG */ continue; err = dsa_user_prechangeupper(lower, info); if (notifier_to_errno(err)) break; } return err; } static int dsa_prevent_bridging_8021q_upper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *ext_ack; struct net_device *user, *br; struct dsa_port *dp; ext_ack = netdev_notifier_info_to_extack(&info->info); if (!is_vlan_dev(dev)) return NOTIFY_DONE; user = vlan_dev_real_dev(dev); if (!dsa_user_dev_check(user)) return NOTIFY_DONE; dp = dsa_user_to_port(user); br = dsa_port_bridge_dev_get(dp); if (!br) return NOTIFY_DONE; /* Deny enslaving a VLAN device into a VLAN-aware bridge */ if (br_vlan_enabled(br) && netif_is_bridge_master(info->upper_dev) && info->linking) { NL_SET_ERR_MSG_MOD(ext_ack, "Cannot make VLAN device join VLAN-aware bridge"); return notifier_from_errno(-EINVAL); } return NOTIFY_DONE; } static int dsa_user_check_8021q_upper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct dsa_port *dp = dsa_user_to_port(dev); struct net_device *br = dsa_port_bridge_dev_get(dp); struct bridge_vlan_info br_info; struct netlink_ext_ack *extack; int err = NOTIFY_DONE; u16 vid; if (!br || !br_vlan_enabled(br)) return NOTIFY_DONE; extack = netdev_notifier_info_to_extack(&info->info); vid = vlan_dev_vlan_id(info->upper_dev); /* br_vlan_get_info() returns -EINVAL or -ENOENT if the * device, respectively the VID is not found, returning * 0 means success, which is a failure for us here. */ err = br_vlan_get_info(br, vid, &br_info); if (err == 0) { NL_SET_ERR_MSG_MOD(extack, "This VLAN is already configured by the bridge"); return notifier_from_errno(-EBUSY); } return NOTIFY_DONE; } static int dsa_user_prechangeupper_sanity_check(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct dsa_switch *ds; struct dsa_port *dp; int err; if (!dsa_user_dev_check(dev)) return dsa_prevent_bridging_8021q_upper(dev, info); dp = dsa_user_to_port(dev); ds = dp->ds; if (ds->ops->port_prechangeupper) { err = ds->ops->port_prechangeupper(ds, dp->index, info); if (err) return notifier_from_errno(err); } if (is_vlan_dev(info->upper_dev)) return dsa_user_check_8021q_upper(dev, info); return NOTIFY_DONE; } /* To be eligible as a DSA conduit, a LAG must have all lower interfaces be * eligible DSA conduits. Additionally, all LAG slaves must be DSA conduits of * switches in the same switch tree. */ static int dsa_lag_conduit_validate(struct net_device *lag_dev, struct netlink_ext_ack *extack) { struct net_device *lower1, *lower2; struct list_head *iter1, *iter2; netdev_for_each_lower_dev(lag_dev, lower1, iter1) { netdev_for_each_lower_dev(lag_dev, lower2, iter2) { if (!netdev_uses_dsa(lower1) || !netdev_uses_dsa(lower2)) { NL_SET_ERR_MSG_MOD(extack, "All LAG ports must be eligible as DSA conduits"); return notifier_from_errno(-EINVAL); } if (lower1 == lower2) continue; if (!dsa_port_tree_same(lower1->dsa_ptr, lower2->dsa_ptr)) { NL_SET_ERR_MSG_MOD(extack, "LAG contains DSA conduits of disjoint switch trees"); return notifier_from_errno(-EINVAL); } } } return NOTIFY_DONE; } static int dsa_conduit_prechangeupper_sanity_check(struct net_device *conduit, struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(&info->info); if (!netdev_uses_dsa(conduit)) return NOTIFY_DONE; if (!info->linking) return NOTIFY_DONE; /* Allow DSA switch uppers */ if (dsa_user_dev_check(info->upper_dev)) return NOTIFY_DONE; /* Allow bridge uppers of DSA conduits, subject to further * restrictions in dsa_bridge_prechangelower_sanity_check() */ if (netif_is_bridge_master(info->upper_dev)) return NOTIFY_DONE; /* Allow LAG uppers, subject to further restrictions in * dsa_lag_conduit_prechangelower_sanity_check() */ if (netif_is_lag_master(info->upper_dev)) return dsa_lag_conduit_validate(info->upper_dev, extack); NL_SET_ERR_MSG_MOD(extack, "DSA conduit cannot join unknown upper interfaces"); return notifier_from_errno(-EBUSY); } static int dsa_lag_conduit_prechangelower_sanity_check(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(&info->info); struct net_device *lag_dev = info->upper_dev; struct net_device *lower; struct list_head *iter; if (!netdev_uses_dsa(lag_dev) || !netif_is_lag_master(lag_dev)) return NOTIFY_DONE; if (!info->linking) return NOTIFY_DONE; if (!netdev_uses_dsa(dev)) { NL_SET_ERR_MSG(extack, "Only DSA conduits can join a LAG DSA conduit"); return notifier_from_errno(-EINVAL); } netdev_for_each_lower_dev(lag_dev, lower, iter) { if (!dsa_port_tree_same(dev->dsa_ptr, lower->dsa_ptr)) { NL_SET_ERR_MSG(extack, "Interface is DSA conduit for a different switch tree than this LAG"); return notifier_from_errno(-EINVAL); } break; } return NOTIFY_DONE; } /* Don't allow bridging of DSA conduits, since the bridge layer rx_handler * prevents the DSA fake ethertype handler to be invoked, so we don't get the * chance to strip off and parse the DSA switch tag protocol header (the bridge * layer just returns RX_HANDLER_CONSUMED, stopping RX processing for these * frames). * The only case where that would not be an issue is when bridging can already * be offloaded, such as when the DSA conduit is itself a DSA or plain switchdev * port, and is bridged only with other ports from the same hardware device. */ static int dsa_bridge_prechangelower_sanity_check(struct net_device *new_lower, struct netdev_notifier_changeupper_info *info) { struct net_device *br = info->upper_dev; struct netlink_ext_ack *extack; struct net_device *lower; struct list_head *iter; if (!netif_is_bridge_master(br)) return NOTIFY_DONE; if (!info->linking) return NOTIFY_DONE; extack = netdev_notifier_info_to_extack(&info->info); netdev_for_each_lower_dev(br, lower, iter) { if (!netdev_uses_dsa(new_lower) && !netdev_uses_dsa(lower)) continue; if (!netdev_port_same_parent_id(lower, new_lower)) { NL_SET_ERR_MSG(extack, "Cannot do software bridging with a DSA conduit"); return notifier_from_errno(-EINVAL); } } return NOTIFY_DONE; } static void dsa_tree_migrate_ports_from_lag_conduit(struct dsa_switch_tree *dst, struct net_device *lag_dev) { struct net_device *new_conduit = dsa_tree_find_first_conduit(dst); struct dsa_port *dp; int err; dsa_tree_for_each_user_port(dp, dst) { if (dsa_port_to_conduit(dp) != lag_dev) continue; err = dsa_user_change_conduit(dp->user, new_conduit, NULL); if (err) { netdev_err(dp->user, "failed to restore conduit to %s: %pe\n", new_conduit->name, ERR_PTR(err)); } } } static int dsa_conduit_lag_join(struct net_device *conduit, struct net_device *lag_dev, struct netdev_lag_upper_info *uinfo, struct netlink_ext_ack *extack) { struct dsa_port *cpu_dp = conduit->dsa_ptr; struct dsa_switch_tree *dst = cpu_dp->dst; struct dsa_port *dp; int err; err = dsa_conduit_lag_setup(lag_dev, cpu_dp, uinfo, extack); if (err) return err; dsa_tree_for_each_user_port(dp, dst) { if (dsa_port_to_conduit(dp) != conduit) continue; err = dsa_user_change_conduit(dp->user, lag_dev, extack); if (err) goto restore; } return 0; restore: dsa_tree_for_each_user_port_continue_reverse(dp, dst) { if (dsa_port_to_conduit(dp) != lag_dev) continue; err = dsa_user_change_conduit(dp->user, conduit, NULL); if (err) { netdev_err(dp->user, "failed to restore conduit to %s: %pe\n", conduit->name, ERR_PTR(err)); } } dsa_conduit_lag_teardown(lag_dev, conduit->dsa_ptr); return err; } static void dsa_conduit_lag_leave(struct net_device *conduit, struct net_device *lag_dev) { struct dsa_port *dp, *cpu_dp = lag_dev->dsa_ptr; struct dsa_switch_tree *dst = cpu_dp->dst; struct dsa_port *new_cpu_dp = NULL; struct net_device *lower; struct list_head *iter; netdev_for_each_lower_dev(lag_dev, lower, iter) { if (netdev_uses_dsa(lower)) { new_cpu_dp = lower->dsa_ptr; break; } } if (new_cpu_dp) { /* Update the CPU port of the user ports still under the LAG * so that dsa_port_to_conduit() continues to work properly */ dsa_tree_for_each_user_port(dp, dst) if (dsa_port_to_conduit(dp) == lag_dev) dp->cpu_dp = new_cpu_dp; /* Update the index of the virtual CPU port to match the lowest * physical CPU port */ lag_dev->dsa_ptr = new_cpu_dp; wmb(); } else { /* If the LAG DSA conduit has no ports left, migrate back all * user ports to the first physical CPU port */ dsa_tree_migrate_ports_from_lag_conduit(dst, lag_dev); } /* This DSA conduit has left its LAG in any case, so let * the CPU port leave the hardware LAG as well */ dsa_conduit_lag_teardown(lag_dev, conduit->dsa_ptr); } static int dsa_conduit_changeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *extack; int err = NOTIFY_DONE; if (!netdev_uses_dsa(dev)) return err; extack = netdev_notifier_info_to_extack(&info->info); if (netif_is_lag_master(info->upper_dev)) { if (info->linking) { err = dsa_conduit_lag_join(dev, info->upper_dev, info->upper_info, extack); err = notifier_from_errno(err); } else { dsa_conduit_lag_leave(dev, info->upper_dev); err = NOTIFY_OK; } } return err; } static int dsa_user_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); switch (event) { case NETDEV_PRECHANGEUPPER: { struct netdev_notifier_changeupper_info *info = ptr; int err; err = dsa_user_prechangeupper_sanity_check(dev, info); if (notifier_to_errno(err)) return err; err = dsa_conduit_prechangeupper_sanity_check(dev, info); if (notifier_to_errno(err)) return err; err = dsa_lag_conduit_prechangelower_sanity_check(dev, info); if (notifier_to_errno(err)) return err; err = dsa_bridge_prechangelower_sanity_check(dev, info); if (notifier_to_errno(err)) return err; err = dsa_user_prechangeupper(dev, ptr); if (notifier_to_errno(err)) return err; err = dsa_user_lag_prechangeupper(dev, ptr); if (notifier_to_errno(err)) return err; break; } case NETDEV_CHANGEUPPER: { int err; err = dsa_user_changeupper(dev, ptr); if (notifier_to_errno(err)) return err; err = dsa_user_lag_changeupper(dev, ptr); if (notifier_to_errno(err)) return err; err = dsa_conduit_changeupper(dev, ptr); if (notifier_to_errno(err)) return err; break; } case NETDEV_CHANGELOWERSTATE: { struct netdev_notifier_changelowerstate_info *info = ptr; struct dsa_port *dp; int err = 0; if (dsa_user_dev_check(dev)) { dp = dsa_user_to_port(dev); err = dsa_port_lag_change(dp, info->lower_state_info); } /* Mirror LAG port events on DSA conduits that are in * a LAG towards their respective switch CPU ports */ if (netdev_uses_dsa(dev)) { dp = dev->dsa_ptr; err = dsa_port_lag_change(dp, info->lower_state_info); } return notifier_from_errno(err); } case NETDEV_CHANGE: case NETDEV_UP: { /* Track state of conduit port. * DSA driver may require the conduit port (and indirectly * the tagger) to be available for some special operation. */ if (netdev_uses_dsa(dev)) { struct dsa_port *cpu_dp = dev->dsa_ptr; struct dsa_switch_tree *dst = cpu_dp->ds->dst; /* Track when the conduit port is UP */ dsa_tree_conduit_oper_state_change(dst, dev, netif_oper_up(dev)); /* Track when the conduit port is ready and can accept * packet. * NETDEV_UP event is not enough to flag a port as ready. * We also have to wait for linkwatch_do_dev to dev_activate * and emit a NETDEV_CHANGE event. * We check if a conduit port is ready by checking if the dev * have a qdisc assigned and is not noop. */ dsa_tree_conduit_admin_state_change(dst, dev, !qdisc_tx_is_noop(dev)); return NOTIFY_OK; } return NOTIFY_DONE; } case NETDEV_GOING_DOWN: { struct dsa_port *dp, *cpu_dp; struct dsa_switch_tree *dst; LIST_HEAD(close_list); if (!netdev_uses_dsa(dev)) return NOTIFY_DONE; cpu_dp = dev->dsa_ptr; dst = cpu_dp->ds->dst; dsa_tree_conduit_admin_state_change(dst, dev, false); list_for_each_entry(dp, &dst->ports, list) { if (!dsa_port_is_user(dp)) continue; if (dp->cpu_dp != cpu_dp) continue; list_add(&dp->user->close_list, &close_list); } dev_close_many(&close_list, true); return NOTIFY_OK; } default: break; } return NOTIFY_DONE; } static void dsa_fdb_offload_notify(struct dsa_switchdev_event_work *switchdev_work) { struct switchdev_notifier_fdb_info info = {}; info.addr = switchdev_work->addr; info.vid = switchdev_work->vid; info.offloaded = true; call_switchdev_notifiers(SWITCHDEV_FDB_OFFLOADED, switchdev_work->orig_dev, &info.info, NULL); } static void dsa_user_switchdev_event_work(struct work_struct *work) { struct dsa_switchdev_event_work *switchdev_work = container_of(work, struct dsa_switchdev_event_work, work); const unsigned char *addr = switchdev_work->addr; struct net_device *dev = switchdev_work->dev; u16 vid = switchdev_work->vid; struct dsa_switch *ds; struct dsa_port *dp; int err; dp = dsa_user_to_port(dev); ds = dp->ds; switch (switchdev_work->event) { case SWITCHDEV_FDB_ADD_TO_DEVICE: if (switchdev_work->host_addr) err = dsa_port_bridge_host_fdb_add(dp, addr, vid); else if (dp->lag) err = dsa_port_lag_fdb_add(dp, addr, vid); else err = dsa_port_fdb_add(dp, addr, vid); if (err) { dev_err(ds->dev, "port %d failed to add %pM vid %d to fdb: %d\n", dp->index, addr, vid, err); break; } dsa_fdb_offload_notify(switchdev_work); break; case SWITCHDEV_FDB_DEL_TO_DEVICE: if (switchdev_work->host_addr) err = dsa_port_bridge_host_fdb_del(dp, addr, vid); else if (dp->lag) err = dsa_port_lag_fdb_del(dp, addr, vid); else err = dsa_port_fdb_del(dp, addr, vid); if (err) { dev_err(ds->dev, "port %d failed to delete %pM vid %d from fdb: %d\n", dp->index, addr, vid, err); } break; } kfree(switchdev_work); } static bool dsa_foreign_dev_check(const struct net_device *dev, const struct net_device *foreign_dev) { const struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch_tree *dst = dp->ds->dst; if (netif_is_bridge_master(foreign_dev)) return !dsa_tree_offloads_bridge_dev(dst, foreign_dev); if (netif_is_bridge_port(foreign_dev)) return !dsa_tree_offloads_bridge_port(dst, foreign_dev); /* Everything else is foreign */ return true; } static int dsa_user_fdb_event(struct net_device *dev, struct net_device *orig_dev, unsigned long event, const void *ctx, const struct switchdev_notifier_fdb_info *fdb_info) { struct dsa_switchdev_event_work *switchdev_work; struct dsa_port *dp = dsa_user_to_port(dev); bool host_addr = fdb_info->is_local; struct dsa_switch *ds = dp->ds; if (ctx && ctx != dp) return 0; if (!dp->bridge) return 0; if (switchdev_fdb_is_dynamically_learned(fdb_info)) { if (dsa_port_offloads_bridge_port(dp, orig_dev)) return 0; /* FDB entries learned by the software bridge or by foreign * bridge ports should be installed as host addresses only if * the driver requests assisted learning. */ if (!ds->assisted_learning_on_cpu_port) return 0; } /* Also treat FDB entries on foreign interfaces bridged with us as host * addresses. */ if (dsa_foreign_dev_check(dev, orig_dev)) host_addr = true; /* Check early that we're not doing work in vain. * Host addresses on LAG ports still require regular FDB ops, * since the CPU port isn't in a LAG. */ if (dp->lag && !host_addr) { if (!ds->ops->lag_fdb_add || !ds->ops->lag_fdb_del) return -EOPNOTSUPP; } else { if (!ds->ops->port_fdb_add || !ds->ops->port_fdb_del) return -EOPNOTSUPP; } switchdev_work = kzalloc(sizeof(*switchdev_work), GFP_ATOMIC); if (!switchdev_work) return -ENOMEM; netdev_dbg(dev, "%s FDB entry towards %s, addr %pM vid %d%s\n", event == SWITCHDEV_FDB_ADD_TO_DEVICE ? "Adding" : "Deleting", orig_dev->name, fdb_info->addr, fdb_info->vid, host_addr ? " as host address" : ""); INIT_WORK(&switchdev_work->work, dsa_user_switchdev_event_work); switchdev_work->event = event; switchdev_work->dev = dev; switchdev_work->orig_dev = orig_dev; ether_addr_copy(switchdev_work->addr, fdb_info->addr); switchdev_work->vid = fdb_info->vid; switchdev_work->host_addr = host_addr; dsa_schedule_work(&switchdev_work->work); return 0; } /* Called under rcu_read_lock() */ static int dsa_user_switchdev_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = switchdev_notifier_info_to_dev(ptr); int err; switch (event) { case SWITCHDEV_PORT_ATTR_SET: err = switchdev_handle_port_attr_set(dev, ptr, dsa_user_dev_check, dsa_user_port_attr_set); return notifier_from_errno(err); case SWITCHDEV_FDB_ADD_TO_DEVICE: case SWITCHDEV_FDB_DEL_TO_DEVICE: err = switchdev_handle_fdb_event_to_device(dev, event, ptr, dsa_user_dev_check, dsa_foreign_dev_check, dsa_user_fdb_event); return notifier_from_errno(err); default: return NOTIFY_DONE; } return NOTIFY_OK; } static int dsa_user_switchdev_blocking_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = switchdev_notifier_info_to_dev(ptr); int err; switch (event) { case SWITCHDEV_PORT_OBJ_ADD: err = switchdev_handle_port_obj_add_foreign(dev, ptr, dsa_user_dev_check, dsa_foreign_dev_check, dsa_user_port_obj_add); return notifier_from_errno(err); case SWITCHDEV_PORT_OBJ_DEL: err = switchdev_handle_port_obj_del_foreign(dev, ptr, dsa_user_dev_check, dsa_foreign_dev_check, dsa_user_port_obj_del); return notifier_from_errno(err); case SWITCHDEV_PORT_ATTR_SET: err = switchdev_handle_port_attr_set(dev, ptr, dsa_user_dev_check, dsa_user_port_attr_set); return notifier_from_errno(err); } return NOTIFY_DONE; } static struct notifier_block dsa_user_nb __read_mostly = { .notifier_call = dsa_user_netdevice_event, }; struct notifier_block dsa_user_switchdev_notifier = { .notifier_call = dsa_user_switchdev_event, }; struct notifier_block dsa_user_switchdev_blocking_notifier = { .notifier_call = dsa_user_switchdev_blocking_event, }; int dsa_user_register_notifier(void) { struct notifier_block *nb; int err; err = register_netdevice_notifier(&dsa_user_nb); if (err) return err; err = register_switchdev_notifier(&dsa_user_switchdev_notifier); if (err) goto err_switchdev_nb; nb = &dsa_user_switchdev_blocking_notifier; err = register_switchdev_blocking_notifier(nb); if (err) goto err_switchdev_blocking_nb; return 0; err_switchdev_blocking_nb: unregister_switchdev_notifier(&dsa_user_switchdev_notifier); err_switchdev_nb: unregister_netdevice_notifier(&dsa_user_nb); return err; } void dsa_user_unregister_notifier(void) { struct notifier_block *nb; int err; nb = &dsa_user_switchdev_blocking_notifier; err = unregister_switchdev_blocking_notifier(nb); if (err) pr_err("DSA: failed to unregister switchdev blocking notifier (%d)\n", err); err = unregister_switchdev_notifier(&dsa_user_switchdev_notifier); if (err) pr_err("DSA: failed to unregister switchdev notifier (%d)\n", err); err = unregister_netdevice_notifier(&dsa_user_nb); if (err) pr_err("DSA: failed to unregister user notifier (%d)\n", err); } |
| 2 53 57 55 116 119 75 116 2 87 2 2 39 38 88 87 89 2 63 3 2 8 18 53 87 88 49 35 6 15 20 52 45 41 35 40 49 44 3 3 48 7 3 40 37 43 50 49 51 49 3 37 11 47 2 42 42 26 42 40 27 30 29 12 31 11 39 4 43 11 6 5 11 52 1 52 54 49 52 54 52 52 4 27 17 40 51 37 16 53 48 1 4 56 53 54 73 73 72 13 3 86 80 31 5 39 51 20 36 52 84 2 7 79 3 87 3 72 74 76 2 2 1 1 1 1 43 3 39 36 1 1 50 26 1 22 2 46 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * This file contains the procedures for the handling of select and poll * * Created for Linux based loosely upon Mathius Lattner's minix * patches by Peter MacDonald. Heavily edited by Linus. * * 4 February 1994 * COFF/ELF binary emulation. If the process has the STICKY_TIMEOUTS * flag set in its personality we do *not* modify the given timeout * parameter to reflect time remaining. * * 24 January 2000 * Changed sys_poll()/do_poll() to use PAGE_SIZE chunk-based allocation * of fds to overcome nfds < 16390 descriptors limit (Tigran Aivazian). */ #include <linux/compat.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/sched/rt.h> #include <linux/syscalls.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/poll.h> #include <linux/personality.h> /* for STICKY_TIMEOUTS */ #include <linux/file.h> #include <linux/fdtable.h> #include <linux/fs.h> #include <linux/rcupdate.h> #include <linux/hrtimer.h> #include <linux/freezer.h> #include <net/busy_poll.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> /* * Estimate expected accuracy in ns from a timeval. * * After quite a bit of churning around, we've settled on * a simple thing of taking 0.1% of the timeout as the * slack, with a cap of 100 msec. * "nice" tasks get a 0.5% slack instead. * * Consider this comment an open invitation to come up with even * better solutions.. */ #define MAX_SLACK (100 * NSEC_PER_MSEC) static long __estimate_accuracy(struct timespec64 *tv) { long slack; int divfactor = 1000; if (tv->tv_sec < 0) return 0; if (task_nice(current) > 0) divfactor = divfactor / 5; if (tv->tv_sec > MAX_SLACK / (NSEC_PER_SEC/divfactor)) return MAX_SLACK; slack = tv->tv_nsec / divfactor; slack += tv->tv_sec * (NSEC_PER_SEC/divfactor); if (slack > MAX_SLACK) return MAX_SLACK; return slack; } u64 select_estimate_accuracy(struct timespec64 *tv) { u64 ret; struct timespec64 now; /* * Realtime tasks get a slack of 0 for obvious reasons. */ if (rt_task(current)) return 0; ktime_get_ts64(&now); now = timespec64_sub(*tv, now); ret = __estimate_accuracy(&now); if (ret < current->timer_slack_ns) return current->timer_slack_ns; return ret; } struct poll_table_page { struct poll_table_page * next; struct poll_table_entry * entry; struct poll_table_entry entries[]; }; #define POLL_TABLE_FULL(table) \ ((unsigned long)((table)->entry+1) > PAGE_SIZE + (unsigned long)(table)) /* * Ok, Peter made a complicated, but straightforward multiple_wait() function. * I have rewritten this, taking some shortcuts: This code may not be easy to * follow, but it should be free of race-conditions, and it's practical. If you * understand what I'm doing here, then you understand how the linux * sleep/wakeup mechanism works. * * Two very simple procedures, poll_wait() and poll_freewait() make all the * work. poll_wait() is an inline-function defined in <linux/poll.h>, * as all select/poll functions have to call it to add an entry to the * poll table. */ static void __pollwait(struct file *filp, wait_queue_head_t *wait_address, poll_table *p); void poll_initwait(struct poll_wqueues *pwq) { init_poll_funcptr(&pwq->pt, __pollwait); pwq->polling_task = current; pwq->triggered = 0; pwq->error = 0; pwq->table = NULL; pwq->inline_index = 0; } EXPORT_SYMBOL(poll_initwait); static void free_poll_entry(struct poll_table_entry *entry) { remove_wait_queue(entry->wait_address, &entry->wait); fput(entry->filp); } void poll_freewait(struct poll_wqueues *pwq) { struct poll_table_page * p = pwq->table; int i; for (i = 0; i < pwq->inline_index; i++) free_poll_entry(pwq->inline_entries + i); while (p) { struct poll_table_entry * entry; struct poll_table_page *old; entry = p->entry; do { entry--; free_poll_entry(entry); } while (entry > p->entries); old = p; p = p->next; free_page((unsigned long) old); } } EXPORT_SYMBOL(poll_freewait); static struct poll_table_entry *poll_get_entry(struct poll_wqueues *p) { struct poll_table_page *table = p->table; if (p->inline_index < N_INLINE_POLL_ENTRIES) return p->inline_entries + p->inline_index++; if (!table || POLL_TABLE_FULL(table)) { struct poll_table_page *new_table; new_table = (struct poll_table_page *) __get_free_page(GFP_KERNEL); if (!new_table) { p->error = -ENOMEM; return NULL; } new_table->entry = new_table->entries; new_table->next = table; p->table = new_table; table = new_table; } return table->entry++; } static int __pollwake(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct poll_wqueues *pwq = wait->private; DECLARE_WAITQUEUE(dummy_wait, pwq->polling_task); /* * Although this function is called under waitqueue lock, LOCK * doesn't imply write barrier and the users expect write * barrier semantics on wakeup functions. The following * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up() * and is paired with smp_store_mb() in poll_schedule_timeout. */ smp_wmb(); pwq->triggered = 1; /* * Perform the default wake up operation using a dummy * waitqueue. * * TODO: This is hacky but there currently is no interface to * pass in @sync. @sync is scheduled to be removed and once * that happens, wake_up_process() can be used directly. */ return default_wake_function(&dummy_wait, mode, sync, key); } static int pollwake(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct poll_table_entry *entry; entry = container_of(wait, struct poll_table_entry, wait); if (key && !(key_to_poll(key) & entry->key)) return 0; return __pollwake(wait, mode, sync, key); } /* Add a new entry */ static void __pollwait(struct file *filp, wait_queue_head_t *wait_address, poll_table *p) { struct poll_wqueues *pwq = container_of(p, struct poll_wqueues, pt); struct poll_table_entry *entry = poll_get_entry(pwq); if (!entry) return; entry->filp = get_file(filp); entry->wait_address = wait_address; entry->key = p->_key; init_waitqueue_func_entry(&entry->wait, pollwake); entry->wait.private = pwq; add_wait_queue(wait_address, &entry->wait); } static int poll_schedule_timeout(struct poll_wqueues *pwq, int state, ktime_t *expires, unsigned long slack) { int rc = -EINTR; set_current_state(state); if (!pwq->triggered) rc = schedule_hrtimeout_range(expires, slack, HRTIMER_MODE_ABS); __set_current_state(TASK_RUNNING); /* * Prepare for the next iteration. * * The following smp_store_mb() serves two purposes. First, it's * the counterpart rmb of the wmb in pollwake() such that data * written before wake up is always visible after wake up. * Second, the full barrier guarantees that triggered clearing * doesn't pass event check of the next iteration. Note that * this problem doesn't exist for the first iteration as * add_wait_queue() has full barrier semantics. */ smp_store_mb(pwq->triggered, 0); return rc; } /** * poll_select_set_timeout - helper function to setup the timeout value * @to: pointer to timespec64 variable for the final timeout * @sec: seconds (from user space) * @nsec: nanoseconds (from user space) * * Note, we do not use a timespec for the user space value here, That * way we can use the function for timeval and compat interfaces as well. * * Returns -EINVAL if sec/nsec are not normalized. Otherwise 0. */ int poll_select_set_timeout(struct timespec64 *to, time64_t sec, long nsec) { struct timespec64 ts = {.tv_sec = sec, .tv_nsec = nsec}; if (!timespec64_valid(&ts)) return -EINVAL; /* Optimize for the zero timeout value here */ if (!sec && !nsec) { to->tv_sec = to->tv_nsec = 0; } else { ktime_get_ts64(to); *to = timespec64_add_safe(*to, ts); } return 0; } enum poll_time_type { PT_TIMEVAL = 0, PT_OLD_TIMEVAL = 1, PT_TIMESPEC = 2, PT_OLD_TIMESPEC = 3, }; static int poll_select_finish(struct timespec64 *end_time, void __user *p, enum poll_time_type pt_type, int ret) { struct timespec64 rts; restore_saved_sigmask_unless(ret == -ERESTARTNOHAND); if (!p) return ret; if (current->personality & STICKY_TIMEOUTS) goto sticky; /* No update for zero timeout */ if (!end_time->tv_sec && !end_time->tv_nsec) return ret; ktime_get_ts64(&rts); rts = timespec64_sub(*end_time, rts); if (rts.tv_sec < 0) rts.tv_sec = rts.tv_nsec = 0; switch (pt_type) { case PT_TIMEVAL: { struct __kernel_old_timeval rtv; if (sizeof(rtv) > sizeof(rtv.tv_sec) + sizeof(rtv.tv_usec)) memset(&rtv, 0, sizeof(rtv)); rtv.tv_sec = rts.tv_sec; rtv.tv_usec = rts.tv_nsec / NSEC_PER_USEC; if (!copy_to_user(p, &rtv, sizeof(rtv))) return ret; } break; case PT_OLD_TIMEVAL: { struct old_timeval32 rtv; rtv.tv_sec = rts.tv_sec; rtv.tv_usec = rts.tv_nsec / NSEC_PER_USEC; if (!copy_to_user(p, &rtv, sizeof(rtv))) return ret; } break; case PT_TIMESPEC: if (!put_timespec64(&rts, p)) return ret; break; case PT_OLD_TIMESPEC: if (!put_old_timespec32(&rts, p)) return ret; break; default: BUG(); } /* * If an application puts its timeval in read-only memory, we * don't want the Linux-specific update to the timeval to * cause a fault after the select has completed * successfully. However, because we're not updating the * timeval, we can't restart the system call. */ sticky: if (ret == -ERESTARTNOHAND) ret = -EINTR; return ret; } /* * Scalable version of the fd_set. */ typedef struct { unsigned long *in, *out, *ex; unsigned long *res_in, *res_out, *res_ex; } fd_set_bits; /* * How many longwords for "nr" bits? */ #define FDS_BITPERLONG (8*sizeof(long)) #define FDS_LONGS(nr) (((nr)+FDS_BITPERLONG-1)/FDS_BITPERLONG) #define FDS_BYTES(nr) (FDS_LONGS(nr)*sizeof(long)) /* * Use "unsigned long" accesses to let user-mode fd_set's be long-aligned. */ static inline int get_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset) { nr = FDS_BYTES(nr); if (ufdset) return copy_from_user(fdset, ufdset, nr) ? -EFAULT : 0; memset(fdset, 0, nr); return 0; } static inline unsigned long __must_check set_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset) { if (ufdset) return __copy_to_user(ufdset, fdset, FDS_BYTES(nr)); return 0; } static inline void zero_fd_set(unsigned long nr, unsigned long *fdset) { memset(fdset, 0, FDS_BYTES(nr)); } #define FDS_IN(fds, n) (fds->in + n) #define FDS_OUT(fds, n) (fds->out + n) #define FDS_EX(fds, n) (fds->ex + n) #define BITS(fds, n) (*FDS_IN(fds, n)|*FDS_OUT(fds, n)|*FDS_EX(fds, n)) static int max_select_fd(unsigned long n, fd_set_bits *fds) { unsigned long *open_fds; unsigned long set; int max; struct fdtable *fdt; /* handle last in-complete long-word first */ set = ~(~0UL << (n & (BITS_PER_LONG-1))); n /= BITS_PER_LONG; fdt = files_fdtable(current->files); open_fds = fdt->open_fds + n; max = 0; if (set) { set &= BITS(fds, n); if (set) { if (!(set & ~*open_fds)) goto get_max; return -EBADF; } } while (n) { open_fds--; n--; set = BITS(fds, n); if (!set) continue; if (set & ~*open_fds) return -EBADF; if (max) continue; get_max: do { max++; set >>= 1; } while (set); max += n * BITS_PER_LONG; } return max; } #define POLLIN_SET (EPOLLRDNORM | EPOLLRDBAND | EPOLLIN | EPOLLHUP | EPOLLERR |\ EPOLLNVAL) #define POLLOUT_SET (EPOLLWRBAND | EPOLLWRNORM | EPOLLOUT | EPOLLERR |\ EPOLLNVAL) #define POLLEX_SET (EPOLLPRI | EPOLLNVAL) static inline void wait_key_set(poll_table *wait, unsigned long in, unsigned long out, unsigned long bit, __poll_t ll_flag) { wait->_key = POLLEX_SET | ll_flag; if (in & bit) wait->_key |= POLLIN_SET; if (out & bit) wait->_key |= POLLOUT_SET; } static noinline_for_stack int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) { ktime_t expire, *to = NULL; struct poll_wqueues table; poll_table *wait; int retval, i, timed_out = 0; u64 slack = 0; __poll_t busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0; unsigned long busy_start = 0; rcu_read_lock(); retval = max_select_fd(n, fds); rcu_read_unlock(); if (retval < 0) return retval; n = retval; poll_initwait(&table); wait = &table.pt; if (end_time && !end_time->tv_sec && !end_time->tv_nsec) { wait->_qproc = NULL; timed_out = 1; } if (end_time && !timed_out) slack = select_estimate_accuracy(end_time); retval = 0; for (;;) { unsigned long *rinp, *routp, *rexp, *inp, *outp, *exp; bool can_busy_loop = false; inp = fds->in; outp = fds->out; exp = fds->ex; rinp = fds->res_in; routp = fds->res_out; rexp = fds->res_ex; for (i = 0; i < n; ++rinp, ++routp, ++rexp) { unsigned long in, out, ex, all_bits, bit = 1, j; unsigned long res_in = 0, res_out = 0, res_ex = 0; __poll_t mask; in = *inp++; out = *outp++; ex = *exp++; all_bits = in | out | ex; if (all_bits == 0) { i += BITS_PER_LONG; continue; } for (j = 0; j < BITS_PER_LONG; ++j, ++i, bit <<= 1) { struct fd f; if (i >= n) break; if (!(bit & all_bits)) continue; mask = EPOLLNVAL; f = fdget(i); if (f.file) { wait_key_set(wait, in, out, bit, busy_flag); mask = vfs_poll(f.file, wait); fdput(f); } if ((mask & POLLIN_SET) && (in & bit)) { res_in |= bit; retval++; wait->_qproc = NULL; } if ((mask & POLLOUT_SET) && (out & bit)) { res_out |= bit; retval++; wait->_qproc = NULL; } if ((mask & POLLEX_SET) && (ex & bit)) { res_ex |= bit; retval++; wait->_qproc = NULL; } /* got something, stop busy polling */ if (retval) { can_busy_loop = false; busy_flag = 0; /* * only remember a returned * POLL_BUSY_LOOP if we asked for it */ } else if (busy_flag & mask) can_busy_loop = true; } if (res_in) *rinp = res_in; if (res_out) *routp = res_out; if (res_ex) *rexp = res_ex; cond_resched(); } wait->_qproc = NULL; if (retval || timed_out || signal_pending(current)) break; if (table.error) { retval = table.error; break; } /* only if found POLL_BUSY_LOOP sockets && not out of time */ if (can_busy_loop && !need_resched()) { if (!busy_start) { busy_start = busy_loop_current_time(); continue; } if (!busy_loop_timeout(busy_start)) continue; } busy_flag = 0; /* * If this is the first loop and we have a timeout * given, then we convert to ktime_t and set the to * pointer to the expiry value. */ if (end_time && !to) { expire = timespec64_to_ktime(*end_time); to = &expire; } if (!poll_schedule_timeout(&table, TASK_INTERRUPTIBLE, to, slack)) timed_out = 1; } poll_freewait(&table); return retval; } /* * We can actually return ERESTARTSYS instead of EINTR, but I'd * like to be certain this leads to no problems. So I return * EINTR just for safety. * * Update: ERESTARTSYS breaks at least the xview clock binary, so * I'm trying ERESTARTNOHAND which restart only when you want to. */ int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timespec64 *end_time) { fd_set_bits fds; void *bits; int ret, max_fds; size_t size, alloc_size; struct fdtable *fdt; /* Allocate small arguments on the stack to save memory and be faster */ long stack_fds[SELECT_STACK_ALLOC/sizeof(long)]; ret = -EINVAL; if (n < 0) goto out_nofds; /* max_fds can increase, so grab it once to avoid race */ rcu_read_lock(); fdt = files_fdtable(current->files); max_fds = fdt->max_fds; rcu_read_unlock(); if (n > max_fds) n = max_fds; /* * We need 6 bitmaps (in/out/ex for both incoming and outgoing), * since we used fdset we need to allocate memory in units of * long-words. */ size = FDS_BYTES(n); bits = stack_fds; if (size > sizeof(stack_fds) / 6) { /* Not enough space in on-stack array; must use kmalloc */ ret = -ENOMEM; if (size > (SIZE_MAX / 6)) goto out_nofds; alloc_size = 6 * size; bits = kvmalloc(alloc_size, GFP_KERNEL); if (!bits) goto out_nofds; } fds.in = bits; fds.out = bits + size; fds.ex = bits + 2*size; fds.res_in = bits + 3*size; fds.res_out = bits + 4*size; fds.res_ex = bits + 5*size; if ((ret = get_fd_set(n, inp, fds.in)) || (ret = get_fd_set(n, outp, fds.out)) || (ret = get_fd_set(n, exp, fds.ex))) goto out; zero_fd_set(n, fds.res_in); zero_fd_set(n, fds.res_out); zero_fd_set(n, fds.res_ex); ret = do_select(n, &fds, end_time); if (ret < 0) goto out; if (!ret) { ret = -ERESTARTNOHAND; if (signal_pending(current)) goto out; ret = 0; } if (set_fd_set(n, inp, fds.res_in) || set_fd_set(n, outp, fds.res_out) || set_fd_set(n, exp, fds.res_ex)) ret = -EFAULT; out: if (bits != stack_fds) kvfree(bits); out_nofds: return ret; } static int kern_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct __kernel_old_timeval __user *tvp) { struct timespec64 end_time, *to = NULL; struct __kernel_old_timeval tv; int ret; if (tvp) { if (copy_from_user(&tv, tvp, sizeof(tv))) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, tv.tv_sec + (tv.tv_usec / USEC_PER_SEC), (tv.tv_usec % USEC_PER_SEC) * NSEC_PER_USEC)) return -EINVAL; } ret = core_sys_select(n, inp, outp, exp, to); return poll_select_finish(&end_time, tvp, PT_TIMEVAL, ret); } SYSCALL_DEFINE5(select, int, n, fd_set __user *, inp, fd_set __user *, outp, fd_set __user *, exp, struct __kernel_old_timeval __user *, tvp) { return kern_select(n, inp, outp, exp, tvp); } static long do_pselect(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, void __user *tsp, const sigset_t __user *sigmask, size_t sigsetsize, enum poll_time_type type) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { switch (type) { case PT_TIMESPEC: if (get_timespec64(&ts, tsp)) return -EFAULT; break; case PT_OLD_TIMESPEC: if (get_old_timespec32(&ts, tsp)) return -EFAULT; break; default: BUG(); } to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = core_sys_select(n, inp, outp, exp, to); return poll_select_finish(&end_time, tsp, type, ret); } /* * Most architectures can't handle 7-argument syscalls. So we provide a * 6-argument version where the sixth argument is a pointer to a structure * which has a pointer to the sigset_t itself followed by a size_t containing * the sigset size. */ struct sigset_argpack { sigset_t __user *p; size_t size; }; static inline int get_sigset_argpack(struct sigset_argpack *to, struct sigset_argpack __user *from) { // the path is hot enough for overhead of copy_from_user() to matter if (from) { if (!user_read_access_begin(from, sizeof(*from))) return -EFAULT; unsafe_get_user(to->p, &from->p, Efault); unsafe_get_user(to->size, &from->size, Efault); user_read_access_end(); } return 0; Efault: user_access_end(); return -EFAULT; } SYSCALL_DEFINE6(pselect6, int, n, fd_set __user *, inp, fd_set __user *, outp, fd_set __user *, exp, struct __kernel_timespec __user *, tsp, void __user *, sig) { struct sigset_argpack x = {NULL, 0}; if (get_sigset_argpack(&x, sig)) return -EFAULT; return do_pselect(n, inp, outp, exp, tsp, x.p, x.size, PT_TIMESPEC); } #if defined(CONFIG_COMPAT_32BIT_TIME) && !defined(CONFIG_64BIT) SYSCALL_DEFINE6(pselect6_time32, int, n, fd_set __user *, inp, fd_set __user *, outp, fd_set __user *, exp, struct old_timespec32 __user *, tsp, void __user *, sig) { struct sigset_argpack x = {NULL, 0}; if (get_sigset_argpack(&x, sig)) return -EFAULT; return do_pselect(n, inp, outp, exp, tsp, x.p, x.size, PT_OLD_TIMESPEC); } #endif #ifdef __ARCH_WANT_SYS_OLD_SELECT struct sel_arg_struct { unsigned long n; fd_set __user *inp, *outp, *exp; struct __kernel_old_timeval __user *tvp; }; SYSCALL_DEFINE1(old_select, struct sel_arg_struct __user *, arg) { struct sel_arg_struct a; if (copy_from_user(&a, arg, sizeof(a))) return -EFAULT; return kern_select(a.n, a.inp, a.outp, a.exp, a.tvp); } #endif struct poll_list { struct poll_list *next; unsigned int len; struct pollfd entries[]; }; #define POLLFD_PER_PAGE ((PAGE_SIZE-sizeof(struct poll_list)) / sizeof(struct pollfd)) /* * Fish for pollable events on the pollfd->fd file descriptor. We're only * interested in events matching the pollfd->events mask, and the result * matching that mask is both recorded in pollfd->revents and returned. The * pwait poll_table will be used by the fd-provided poll handler for waiting, * if pwait->_qproc is non-NULL. */ static inline __poll_t do_pollfd(struct pollfd *pollfd, poll_table *pwait, bool *can_busy_poll, __poll_t busy_flag) { int fd = pollfd->fd; __poll_t mask = 0, filter; struct fd f; if (fd < 0) goto out; mask = EPOLLNVAL; f = fdget(fd); if (!f.file) goto out; /* userland u16 ->events contains POLL... bitmap */ filter = demangle_poll(pollfd->events) | EPOLLERR | EPOLLHUP; pwait->_key = filter | busy_flag; mask = vfs_poll(f.file, pwait); if (mask & busy_flag) *can_busy_poll = true; mask &= filter; /* Mask out unneeded events. */ fdput(f); out: /* ... and so does ->revents */ pollfd->revents = mangle_poll(mask); return mask; } static int do_poll(struct poll_list *list, struct poll_wqueues *wait, struct timespec64 *end_time) { poll_table* pt = &wait->pt; ktime_t expire, *to = NULL; int timed_out = 0, count = 0; u64 slack = 0; __poll_t busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0; unsigned long busy_start = 0; /* Optimise the no-wait case */ if (end_time && !end_time->tv_sec && !end_time->tv_nsec) { pt->_qproc = NULL; timed_out = 1; } if (end_time && !timed_out) slack = select_estimate_accuracy(end_time); for (;;) { struct poll_list *walk; bool can_busy_loop = false; for (walk = list; walk != NULL; walk = walk->next) { struct pollfd * pfd, * pfd_end; pfd = walk->entries; pfd_end = pfd + walk->len; for (; pfd != pfd_end; pfd++) { /* * Fish for events. If we found one, record it * and kill poll_table->_qproc, so we don't * needlessly register any other waiters after * this. They'll get immediately deregistered * when we break out and return. */ if (do_pollfd(pfd, pt, &can_busy_loop, busy_flag)) { count++; pt->_qproc = NULL; /* found something, stop busy polling */ busy_flag = 0; can_busy_loop = false; } } } /* * All waiters have already been registered, so don't provide * a poll_table->_qproc to them on the next loop iteration. */ pt->_qproc = NULL; if (!count) { count = wait->error; if (signal_pending(current)) count = -ERESTARTNOHAND; } if (count || timed_out) break; /* only if found POLL_BUSY_LOOP sockets && not out of time */ if (can_busy_loop && !need_resched()) { if (!busy_start) { busy_start = busy_loop_current_time(); continue; } if (!busy_loop_timeout(busy_start)) continue; } busy_flag = 0; /* * If this is the first loop and we have a timeout * given, then we convert to ktime_t and set the to * pointer to the expiry value. */ if (end_time && !to) { expire = timespec64_to_ktime(*end_time); to = &expire; } if (!poll_schedule_timeout(wait, TASK_INTERRUPTIBLE, to, slack)) timed_out = 1; } return count; } #define N_STACK_PPS ((sizeof(stack_pps) - sizeof(struct poll_list)) / \ sizeof(struct pollfd)) static int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds, struct timespec64 *end_time) { struct poll_wqueues table; int err = -EFAULT, fdcount; /* Allocate small arguments on the stack to save memory and be faster - use long to make sure the buffer is aligned properly on 64 bit archs to avoid unaligned access */ long stack_pps[POLL_STACK_ALLOC/sizeof(long)]; struct poll_list *const head = (struct poll_list *)stack_pps; struct poll_list *walk = head; unsigned int todo = nfds; unsigned int len; if (nfds > rlimit(RLIMIT_NOFILE)) return -EINVAL; len = min_t(unsigned int, nfds, N_STACK_PPS); for (;;) { walk->next = NULL; walk->len = len; if (!len) break; if (copy_from_user(walk->entries, ufds + nfds-todo, sizeof(struct pollfd) * walk->len)) goto out_fds; if (walk->len >= todo) break; todo -= walk->len; len = min(todo, POLLFD_PER_PAGE); walk = walk->next = kmalloc(struct_size(walk, entries, len), GFP_KERNEL); if (!walk) { err = -ENOMEM; goto out_fds; } } poll_initwait(&table); fdcount = do_poll(head, &table, end_time); poll_freewait(&table); if (!user_write_access_begin(ufds, nfds * sizeof(*ufds))) goto out_fds; for (walk = head; walk; walk = walk->next) { struct pollfd *fds = walk->entries; unsigned int j; for (j = walk->len; j; fds++, ufds++, j--) unsafe_put_user(fds->revents, &ufds->revents, Efault); } user_write_access_end(); err = fdcount; out_fds: walk = head->next; while (walk) { struct poll_list *pos = walk; walk = walk->next; kfree(pos); } return err; Efault: user_write_access_end(); err = -EFAULT; goto out_fds; } static long do_restart_poll(struct restart_block *restart_block) { struct pollfd __user *ufds = restart_block->poll.ufds; int nfds = restart_block->poll.nfds; struct timespec64 *to = NULL, end_time; int ret; if (restart_block->poll.has_timeout) { end_time.tv_sec = restart_block->poll.tv_sec; end_time.tv_nsec = restart_block->poll.tv_nsec; to = &end_time; } ret = do_sys_poll(ufds, nfds, to); if (ret == -ERESTARTNOHAND) ret = set_restart_fn(restart_block, do_restart_poll); return ret; } SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds, int, timeout_msecs) { struct timespec64 end_time, *to = NULL; int ret; if (timeout_msecs >= 0) { to = &end_time; poll_select_set_timeout(to, timeout_msecs / MSEC_PER_SEC, NSEC_PER_MSEC * (timeout_msecs % MSEC_PER_SEC)); } ret = do_sys_poll(ufds, nfds, to); if (ret == -ERESTARTNOHAND) { struct restart_block *restart_block; restart_block = ¤t->restart_block; restart_block->poll.ufds = ufds; restart_block->poll.nfds = nfds; if (timeout_msecs >= 0) { restart_block->poll.tv_sec = end_time.tv_sec; restart_block->poll.tv_nsec = end_time.tv_nsec; restart_block->poll.has_timeout = 1; } else restart_block->poll.has_timeout = 0; ret = set_restart_fn(restart_block, do_restart_poll); } return ret; } SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, unsigned int, nfds, struct __kernel_timespec __user *, tsp, const sigset_t __user *, sigmask, size_t, sigsetsize) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { if (get_timespec64(&ts, tsp)) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = do_sys_poll(ufds, nfds, to); return poll_select_finish(&end_time, tsp, PT_TIMESPEC, ret); } #if defined(CONFIG_COMPAT_32BIT_TIME) && !defined(CONFIG_64BIT) SYSCALL_DEFINE5(ppoll_time32, struct pollfd __user *, ufds, unsigned int, nfds, struct old_timespec32 __user *, tsp, const sigset_t __user *, sigmask, size_t, sigsetsize) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { if (get_old_timespec32(&ts, tsp)) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = do_sys_poll(ufds, nfds, to); return poll_select_finish(&end_time, tsp, PT_OLD_TIMESPEC, ret); } #endif #ifdef CONFIG_COMPAT #define __COMPAT_NFDBITS (8 * sizeof(compat_ulong_t)) /* * Ooo, nasty. We need here to frob 32-bit unsigned longs to * 64-bit unsigned longs. */ static int compat_get_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, unsigned long *fdset) { if (ufdset) { return compat_get_bitmap(fdset, ufdset, nr); } else { zero_fd_set(nr, fdset); return 0; } } static int compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, unsigned long *fdset) { if (!ufdset) return 0; return compat_put_bitmap(ufdset, fdset, nr); } /* * This is a virtual copy of sys_select from fs/select.c and probably * should be compared to it from time to time */ /* * We can actually return ERESTARTSYS instead of EINTR, but I'd * like to be certain this leads to no problems. So I return * EINTR just for safety. * * Update: ERESTARTSYS breaks at least the xview clock binary, so * I'm trying ERESTARTNOHAND which restart only when you want to. */ static int compat_core_sys_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct timespec64 *end_time) { fd_set_bits fds; void *bits; int size, max_fds, ret = -EINVAL; struct fdtable *fdt; long stack_fds[SELECT_STACK_ALLOC/sizeof(long)]; if (n < 0) goto out_nofds; /* max_fds can increase, so grab it once to avoid race */ rcu_read_lock(); fdt = files_fdtable(current->files); max_fds = fdt->max_fds; rcu_read_unlock(); if (n > max_fds) n = max_fds; /* * We need 6 bitmaps (in/out/ex for both incoming and outgoing), * since we used fdset we need to allocate memory in units of * long-words. */ size = FDS_BYTES(n); bits = stack_fds; if (size > sizeof(stack_fds) / 6) { bits = kmalloc_array(6, size, GFP_KERNEL); ret = -ENOMEM; if (!bits) goto out_nofds; } fds.in = (unsigned long *) bits; fds.out = (unsigned long *) (bits + size); fds.ex = (unsigned long *) (bits + 2*size); fds.res_in = (unsigned long *) (bits + 3*size); fds.res_out = (unsigned long *) (bits + 4*size); fds.res_ex = (unsigned long *) (bits + 5*size); if ((ret = compat_get_fd_set(n, inp, fds.in)) || (ret = compat_get_fd_set(n, outp, fds.out)) || (ret = compat_get_fd_set(n, exp, fds.ex))) goto out; zero_fd_set(n, fds.res_in); zero_fd_set(n, fds.res_out); zero_fd_set(n, fds.res_ex); ret = do_select(n, &fds, end_time); if (ret < 0) goto out; if (!ret) { ret = -ERESTARTNOHAND; if (signal_pending(current)) goto out; ret = 0; } if (compat_set_fd_set(n, inp, fds.res_in) || compat_set_fd_set(n, outp, fds.res_out) || compat_set_fd_set(n, exp, fds.res_ex)) ret = -EFAULT; out: if (bits != stack_fds) kfree(bits); out_nofds: return ret; } static int do_compat_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct old_timeval32 __user *tvp) { struct timespec64 end_time, *to = NULL; struct old_timeval32 tv; int ret; if (tvp) { if (copy_from_user(&tv, tvp, sizeof(tv))) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, tv.tv_sec + (tv.tv_usec / USEC_PER_SEC), (tv.tv_usec % USEC_PER_SEC) * NSEC_PER_USEC)) return -EINVAL; } ret = compat_core_sys_select(n, inp, outp, exp, to); return poll_select_finish(&end_time, tvp, PT_OLD_TIMEVAL, ret); } COMPAT_SYSCALL_DEFINE5(select, int, n, compat_ulong_t __user *, inp, compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, struct old_timeval32 __user *, tvp) { return do_compat_select(n, inp, outp, exp, tvp); } struct compat_sel_arg_struct { compat_ulong_t n; compat_uptr_t inp; compat_uptr_t outp; compat_uptr_t exp; compat_uptr_t tvp; }; COMPAT_SYSCALL_DEFINE1(old_select, struct compat_sel_arg_struct __user *, arg) { struct compat_sel_arg_struct a; if (copy_from_user(&a, arg, sizeof(a))) return -EFAULT; return do_compat_select(a.n, compat_ptr(a.inp), compat_ptr(a.outp), compat_ptr(a.exp), compat_ptr(a.tvp)); } static long do_compat_pselect(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, void __user *tsp, compat_sigset_t __user *sigmask, compat_size_t sigsetsize, enum poll_time_type type) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { switch (type) { case PT_OLD_TIMESPEC: if (get_old_timespec32(&ts, tsp)) return -EFAULT; break; case PT_TIMESPEC: if (get_timespec64(&ts, tsp)) return -EFAULT; break; default: BUG(); } to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_compat_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = compat_core_sys_select(n, inp, outp, exp, to); return poll_select_finish(&end_time, tsp, type, ret); } struct compat_sigset_argpack { compat_uptr_t p; compat_size_t size; }; static inline int get_compat_sigset_argpack(struct compat_sigset_argpack *to, struct compat_sigset_argpack __user *from) { if (from) { if (!user_read_access_begin(from, sizeof(*from))) return -EFAULT; unsafe_get_user(to->p, &from->p, Efault); unsafe_get_user(to->size, &from->size, Efault); user_read_access_end(); } return 0; Efault: user_access_end(); return -EFAULT; } COMPAT_SYSCALL_DEFINE6(pselect6_time64, int, n, compat_ulong_t __user *, inp, compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, struct __kernel_timespec __user *, tsp, void __user *, sig) { struct compat_sigset_argpack x = {0, 0}; if (get_compat_sigset_argpack(&x, sig)) return -EFAULT; return do_compat_pselect(n, inp, outp, exp, tsp, compat_ptr(x.p), x.size, PT_TIMESPEC); } #if defined(CONFIG_COMPAT_32BIT_TIME) COMPAT_SYSCALL_DEFINE6(pselect6_time32, int, n, compat_ulong_t __user *, inp, compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, struct old_timespec32 __user *, tsp, void __user *, sig) { struct compat_sigset_argpack x = {0, 0}; if (get_compat_sigset_argpack(&x, sig)) return -EFAULT; return do_compat_pselect(n, inp, outp, exp, tsp, compat_ptr(x.p), x.size, PT_OLD_TIMESPEC); } #endif #if defined(CONFIG_COMPAT_32BIT_TIME) COMPAT_SYSCALL_DEFINE5(ppoll_time32, struct pollfd __user *, ufds, unsigned int, nfds, struct old_timespec32 __user *, tsp, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { if (get_old_timespec32(&ts, tsp)) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_compat_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = do_sys_poll(ufds, nfds, to); return poll_select_finish(&end_time, tsp, PT_OLD_TIMESPEC, ret); } #endif /* New compat syscall for 64 bit time_t*/ COMPAT_SYSCALL_DEFINE5(ppoll_time64, struct pollfd __user *, ufds, unsigned int, nfds, struct __kernel_timespec __user *, tsp, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { if (get_timespec64(&ts, tsp)) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_compat_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = do_sys_poll(ufds, nfds, to); return poll_select_finish(&end_time, tsp, PT_TIMESPEC, ret); } #endif |
| 1 1 8 6 7 5 7 8 8 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef __SOUND_PCM_H #define __SOUND_PCM_H /* * Digital Audio (PCM) abstract layer * Copyright (c) by Jaroslav Kysela <perex@perex.cz> * Abramo Bagnara <abramo@alsa-project.org> */ #include <sound/asound.h> #include <sound/memalloc.h> #include <sound/minors.h> #include <linux/poll.h> #include <linux/mm.h> #include <linux/bitops.h> #include <linux/pm_qos.h> #include <linux/refcount.h> #include <linux/uio.h> #define snd_pcm_substream_chip(substream) ((substream)->private_data) #define snd_pcm_chip(pcm) ((pcm)->private_data) #if IS_ENABLED(CONFIG_SND_PCM_OSS) #include <sound/pcm_oss.h> #endif /* * Hardware (lowlevel) section */ struct snd_pcm_hardware { unsigned int info; /* SNDRV_PCM_INFO_* */ u64 formats; /* SNDRV_PCM_FMTBIT_* */ u32 subformats; /* for S32_LE, SNDRV_PCM_SUBFMTBIT_* */ unsigned int rates; /* SNDRV_PCM_RATE_* */ unsigned int rate_min; /* min rate */ unsigned int rate_max; /* max rate */ unsigned int channels_min; /* min channels */ unsigned int channels_max; /* max channels */ size_t buffer_bytes_max; /* max buffer size */ size_t period_bytes_min; /* min period size */ size_t period_bytes_max; /* max period size */ unsigned int periods_min; /* min # of periods */ unsigned int periods_max; /* max # of periods */ size_t fifo_size; /* fifo size in bytes */ }; struct snd_pcm_status64; struct snd_pcm_substream; struct snd_pcm_audio_tstamp_config; /* definitions further down */ struct snd_pcm_audio_tstamp_report; struct snd_pcm_ops { int (*open)(struct snd_pcm_substream *substream); int (*close)(struct snd_pcm_substream *substream); int (*ioctl)(struct snd_pcm_substream * substream, unsigned int cmd, void *arg); int (*hw_params)(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params); int (*hw_free)(struct snd_pcm_substream *substream); int (*prepare)(struct snd_pcm_substream *substream); int (*trigger)(struct snd_pcm_substream *substream, int cmd); int (*sync_stop)(struct snd_pcm_substream *substream); snd_pcm_uframes_t (*pointer)(struct snd_pcm_substream *substream); int (*get_time_info)(struct snd_pcm_substream *substream, struct timespec64 *system_ts, struct timespec64 *audio_ts, struct snd_pcm_audio_tstamp_config *audio_tstamp_config, struct snd_pcm_audio_tstamp_report *audio_tstamp_report); int (*fill_silence)(struct snd_pcm_substream *substream, int channel, unsigned long pos, unsigned long bytes); int (*copy)(struct snd_pcm_substream *substream, int channel, unsigned long pos, struct iov_iter *iter, unsigned long bytes); struct page *(*page)(struct snd_pcm_substream *substream, unsigned long offset); int (*mmap)(struct snd_pcm_substream *substream, struct vm_area_struct *vma); int (*ack)(struct snd_pcm_substream *substream); }; /* * */ #if defined(CONFIG_SND_DYNAMIC_MINORS) #define SNDRV_PCM_DEVICES (SNDRV_OS_MINORS-2) #else #define SNDRV_PCM_DEVICES 8 #endif #define SNDRV_PCM_IOCTL1_RESET 0 /* 1 is absent slot. */ #define SNDRV_PCM_IOCTL1_CHANNEL_INFO 2 /* 3 is absent slot. */ #define SNDRV_PCM_IOCTL1_FIFO_SIZE 4 #define SNDRV_PCM_IOCTL1_SYNC_ID 5 #define SNDRV_PCM_TRIGGER_STOP 0 #define SNDRV_PCM_TRIGGER_START 1 #define SNDRV_PCM_TRIGGER_PAUSE_PUSH 3 #define SNDRV_PCM_TRIGGER_PAUSE_RELEASE 4 #define SNDRV_PCM_TRIGGER_SUSPEND 5 #define SNDRV_PCM_TRIGGER_RESUME 6 #define SNDRV_PCM_TRIGGER_DRAIN 7 #define SNDRV_PCM_POS_XRUN ((snd_pcm_uframes_t)-1) /* If you change this don't forget to change rates[] table in pcm_native.c */ #define SNDRV_PCM_RATE_5512 (1U<<0) /* 5512Hz */ #define SNDRV_PCM_RATE_8000 (1U<<1) /* 8000Hz */ #define SNDRV_PCM_RATE_11025 (1U<<2) /* 11025Hz */ #define SNDRV_PCM_RATE_16000 (1U<<3) /* 16000Hz */ #define SNDRV_PCM_RATE_22050 (1U<<4) /* 22050Hz */ #define SNDRV_PCM_RATE_32000 (1U<<5) /* 32000Hz */ #define SNDRV_PCM_RATE_44100 (1U<<6) /* 44100Hz */ #define SNDRV_PCM_RATE_48000 (1U<<7) /* 48000Hz */ #define SNDRV_PCM_RATE_64000 (1U<<8) /* 64000Hz */ #define SNDRV_PCM_RATE_88200 (1U<<9) /* 88200Hz */ #define SNDRV_PCM_RATE_96000 (1U<<10) /* 96000Hz */ #define SNDRV_PCM_RATE_176400 (1U<<11) /* 176400Hz */ #define SNDRV_PCM_RATE_192000 (1U<<12) /* 192000Hz */ #define SNDRV_PCM_RATE_352800 (1U<<13) /* 352800Hz */ #define SNDRV_PCM_RATE_384000 (1U<<14) /* 384000Hz */ #define SNDRV_PCM_RATE_705600 (1U<<15) /* 705600Hz */ #define SNDRV_PCM_RATE_768000 (1U<<16) /* 768000Hz */ #define SNDRV_PCM_RATE_CONTINUOUS (1U<<30) /* continuous range */ #define SNDRV_PCM_RATE_KNOT (1U<<31) /* supports more non-continuous rates */ #define SNDRV_PCM_RATE_8000_44100 (SNDRV_PCM_RATE_8000|SNDRV_PCM_RATE_11025|\ SNDRV_PCM_RATE_16000|SNDRV_PCM_RATE_22050|\ SNDRV_PCM_RATE_32000|SNDRV_PCM_RATE_44100) #define SNDRV_PCM_RATE_8000_48000 (SNDRV_PCM_RATE_8000_44100|SNDRV_PCM_RATE_48000) #define SNDRV_PCM_RATE_8000_96000 (SNDRV_PCM_RATE_8000_48000|SNDRV_PCM_RATE_64000|\ SNDRV_PCM_RATE_88200|SNDRV_PCM_RATE_96000) #define SNDRV_PCM_RATE_8000_192000 (SNDRV_PCM_RATE_8000_96000|SNDRV_PCM_RATE_176400|\ SNDRV_PCM_RATE_192000) #define SNDRV_PCM_RATE_8000_384000 (SNDRV_PCM_RATE_8000_192000|\ SNDRV_PCM_RATE_352800|\ SNDRV_PCM_RATE_384000) #define SNDRV_PCM_RATE_8000_768000 (SNDRV_PCM_RATE_8000_384000|\ SNDRV_PCM_RATE_705600|\ SNDRV_PCM_RATE_768000) #define _SNDRV_PCM_FMTBIT(fmt) (1ULL << (__force int)SNDRV_PCM_FORMAT_##fmt) #define SNDRV_PCM_FMTBIT_S8 _SNDRV_PCM_FMTBIT(S8) #define SNDRV_PCM_FMTBIT_U8 _SNDRV_PCM_FMTBIT(U8) #define SNDRV_PCM_FMTBIT_S16_LE _SNDRV_PCM_FMTBIT(S16_LE) #define SNDRV_PCM_FMTBIT_S16_BE _SNDRV_PCM_FMTBIT(S16_BE) #define SNDRV_PCM_FMTBIT_U16_LE _SNDRV_PCM_FMTBIT(U16_LE) #define SNDRV_PCM_FMTBIT_U16_BE _SNDRV_PCM_FMTBIT(U16_BE) #define SNDRV_PCM_FMTBIT_S24_LE _SNDRV_PCM_FMTBIT(S24_LE) #define SNDRV_PCM_FMTBIT_S24_BE _SNDRV_PCM_FMTBIT(S24_BE) #define SNDRV_PCM_FMTBIT_U24_LE _SNDRV_PCM_FMTBIT(U24_LE) #define SNDRV_PCM_FMTBIT_U24_BE _SNDRV_PCM_FMTBIT(U24_BE) // For S32/U32 formats, 'msbits' hardware parameter is often used to deliver information about the // available bit count in most significant bit. It's for the case of so-called 'left-justified' or // `right-padding` sample which has less width than 32 bit. #define SNDRV_PCM_FMTBIT_S32_LE _SNDRV_PCM_FMTBIT(S32_LE) #define SNDRV_PCM_FMTBIT_S32_BE _SNDRV_PCM_FMTBIT(S32_BE) #define SNDRV_PCM_FMTBIT_U32_LE _SNDRV_PCM_FMTBIT(U32_LE) #define SNDRV_PCM_FMTBIT_U32_BE _SNDRV_PCM_FMTBIT(U32_BE) #define SNDRV_PCM_FMTBIT_FLOAT_LE _SNDRV_PCM_FMTBIT(FLOAT_LE) #define SNDRV_PCM_FMTBIT_FLOAT_BE _SNDRV_PCM_FMTBIT(FLOAT_BE) #define SNDRV_PCM_FMTBIT_FLOAT64_LE _SNDRV_PCM_FMTBIT(FLOAT64_LE) #define SNDRV_PCM_FMTBIT_FLOAT64_BE _SNDRV_PCM_FMTBIT(FLOAT64_BE) #define SNDRV_PCM_FMTBIT_IEC958_SUBFRAME_LE _SNDRV_PCM_FMTBIT(IEC958_SUBFRAME_LE) #define SNDRV_PCM_FMTBIT_IEC958_SUBFRAME_BE _SNDRV_PCM_FMTBIT(IEC958_SUBFRAME_BE) #define SNDRV_PCM_FMTBIT_MU_LAW _SNDRV_PCM_FMTBIT(MU_LAW) #define SNDRV_PCM_FMTBIT_A_LAW _SNDRV_PCM_FMTBIT(A_LAW) #define SNDRV_PCM_FMTBIT_IMA_ADPCM _SNDRV_PCM_FMTBIT(IMA_ADPCM) #define SNDRV_PCM_FMTBIT_MPEG _SNDRV_PCM_FMTBIT(MPEG) #define SNDRV_PCM_FMTBIT_GSM _SNDRV_PCM_FMTBIT(GSM) #define SNDRV_PCM_FMTBIT_S20_LE _SNDRV_PCM_FMTBIT(S20_LE) #define SNDRV_PCM_FMTBIT_U20_LE _SNDRV_PCM_FMTBIT(U20_LE) #define SNDRV_PCM_FMTBIT_S20_BE _SNDRV_PCM_FMTBIT(S20_BE) #define SNDRV_PCM_FMTBIT_U20_BE _SNDRV_PCM_FMTBIT(U20_BE) #define SNDRV_PCM_FMTBIT_SPECIAL _SNDRV_PCM_FMTBIT(SPECIAL) #define SNDRV_PCM_FMTBIT_S24_3LE _SNDRV_PCM_FMTBIT(S24_3LE) #define SNDRV_PCM_FMTBIT_U24_3LE _SNDRV_PCM_FMTBIT(U24_3LE) #define SNDRV_PCM_FMTBIT_S24_3BE _SNDRV_PCM_FMTBIT(S24_3BE) #define SNDRV_PCM_FMTBIT_U24_3BE _SNDRV_PCM_FMTBIT(U24_3BE) #define SNDRV_PCM_FMTBIT_S20_3LE _SNDRV_PCM_FMTBIT(S20_3LE) #define SNDRV_PCM_FMTBIT_U20_3LE _SNDRV_PCM_FMTBIT(U20_3LE) #define SNDRV_PCM_FMTBIT_S20_3BE _SNDRV_PCM_FMTBIT(S20_3BE) #define SNDRV_PCM_FMTBIT_U20_3BE _SNDRV_PCM_FMTBIT(U20_3BE) #define SNDRV_PCM_FMTBIT_S18_3LE _SNDRV_PCM_FMTBIT(S18_3LE) #define SNDRV_PCM_FMTBIT_U18_3LE _SNDRV_PCM_FMTBIT(U18_3LE) #define SNDRV_PCM_FMTBIT_S18_3BE _SNDRV_PCM_FMTBIT(S18_3BE) #define SNDRV_PCM_FMTBIT_U18_3BE _SNDRV_PCM_FMTBIT(U18_3BE) #define SNDRV_PCM_FMTBIT_G723_24 _SNDRV_PCM_FMTBIT(G723_24) #define SNDRV_PCM_FMTBIT_G723_24_1B _SNDRV_PCM_FMTBIT(G723_24_1B) #define SNDRV_PCM_FMTBIT_G723_40 _SNDRV_PCM_FMTBIT(G723_40) #define SNDRV_PCM_FMTBIT_G723_40_1B _SNDRV_PCM_FMTBIT(G723_40_1B) #define SNDRV_PCM_FMTBIT_DSD_U8 _SNDRV_PCM_FMTBIT(DSD_U8) #define SNDRV_PCM_FMTBIT_DSD_U16_LE _SNDRV_PCM_FMTBIT(DSD_U16_LE) #define SNDRV_PCM_FMTBIT_DSD_U32_LE _SNDRV_PCM_FMTBIT(DSD_U32_LE) #define SNDRV_PCM_FMTBIT_DSD_U16_BE _SNDRV_PCM_FMTBIT(DSD_U16_BE) #define SNDRV_PCM_FMTBIT_DSD_U32_BE _SNDRV_PCM_FMTBIT(DSD_U32_BE) #ifdef SNDRV_LITTLE_ENDIAN #define SNDRV_PCM_FMTBIT_S16 SNDRV_PCM_FMTBIT_S16_LE #define SNDRV_PCM_FMTBIT_U16 SNDRV_PCM_FMTBIT_U16_LE #define SNDRV_PCM_FMTBIT_S24 SNDRV_PCM_FMTBIT_S24_LE #define SNDRV_PCM_FMTBIT_U24 SNDRV_PCM_FMTBIT_U24_LE #define SNDRV_PCM_FMTBIT_S32 SNDRV_PCM_FMTBIT_S32_LE #define SNDRV_PCM_FMTBIT_U32 SNDRV_PCM_FMTBIT_U32_LE #define SNDRV_PCM_FMTBIT_FLOAT SNDRV_PCM_FMTBIT_FLOAT_LE #define SNDRV_PCM_FMTBIT_FLOAT64 SNDRV_PCM_FMTBIT_FLOAT64_LE #define SNDRV_PCM_FMTBIT_IEC958_SUBFRAME SNDRV_PCM_FMTBIT_IEC958_SUBFRAME_LE #define SNDRV_PCM_FMTBIT_S20 SNDRV_PCM_FMTBIT_S20_LE #define SNDRV_PCM_FMTBIT_U20 SNDRV_PCM_FMTBIT_U20_LE #endif #ifdef SNDRV_BIG_ENDIAN #define SNDRV_PCM_FMTBIT_S16 SNDRV_PCM_FMTBIT_S16_BE #define SNDRV_PCM_FMTBIT_U16 SNDRV_PCM_FMTBIT_U16_BE #define SNDRV_PCM_FMTBIT_S24 SNDRV_PCM_FMTBIT_S24_BE #define SNDRV_PCM_FMTBIT_U24 SNDRV_PCM_FMTBIT_U24_BE #define SNDRV_PCM_FMTBIT_S32 SNDRV_PCM_FMTBIT_S32_BE #define SNDRV_PCM_FMTBIT_U32 SNDRV_PCM_FMTBIT_U32_BE #define SNDRV_PCM_FMTBIT_FLOAT SNDRV_PCM_FMTBIT_FLOAT_BE #define SNDRV_PCM_FMTBIT_FLOAT64 SNDRV_PCM_FMTBIT_FLOAT64_BE #define SNDRV_PCM_FMTBIT_IEC958_SUBFRAME SNDRV_PCM_FMTBIT_IEC958_SUBFRAME_BE #define SNDRV_PCM_FMTBIT_S20 SNDRV_PCM_FMTBIT_S20_BE #define SNDRV_PCM_FMTBIT_U20 SNDRV_PCM_FMTBIT_U20_BE #endif #define _SNDRV_PCM_SUBFMTBIT(fmt) BIT((__force int)SNDRV_PCM_SUBFORMAT_##fmt) #define SNDRV_PCM_SUBFMTBIT_STD _SNDRV_PCM_SUBFMTBIT(STD) #define SNDRV_PCM_SUBFMTBIT_MSBITS_MAX _SNDRV_PCM_SUBFMTBIT(MSBITS_MAX) #define SNDRV_PCM_SUBFMTBIT_MSBITS_20 _SNDRV_PCM_SUBFMTBIT(MSBITS_20) #define SNDRV_PCM_SUBFMTBIT_MSBITS_24 _SNDRV_PCM_SUBFMTBIT(MSBITS_24) struct snd_pcm_file { struct snd_pcm_substream *substream; int no_compat_mmap; unsigned int user_pversion; /* supported protocol version */ }; struct snd_pcm_hw_rule; typedef int (*snd_pcm_hw_rule_func_t)(struct snd_pcm_hw_params *params, struct snd_pcm_hw_rule *rule); struct snd_pcm_hw_rule { unsigned int cond; int var; int deps[5]; snd_pcm_hw_rule_func_t func; void *private; }; struct snd_pcm_hw_constraints { struct snd_mask masks[SNDRV_PCM_HW_PARAM_LAST_MASK - SNDRV_PCM_HW_PARAM_FIRST_MASK + 1]; struct snd_interval intervals[SNDRV_PCM_HW_PARAM_LAST_INTERVAL - SNDRV_PCM_HW_PARAM_FIRST_INTERVAL + 1]; unsigned int rules_num; unsigned int rules_all; struct snd_pcm_hw_rule *rules; }; static inline struct snd_mask *constrs_mask(struct snd_pcm_hw_constraints *constrs, snd_pcm_hw_param_t var) { return &constrs->masks[var - SNDRV_PCM_HW_PARAM_FIRST_MASK]; } static inline struct snd_interval *constrs_interval(struct snd_pcm_hw_constraints *constrs, snd_pcm_hw_param_t var) { return &constrs->intervals[var - SNDRV_PCM_HW_PARAM_FIRST_INTERVAL]; } struct snd_ratnum { unsigned int num; unsigned int den_min, den_max, den_step; }; struct snd_ratden { unsigned int num_min, num_max, num_step; unsigned int den; }; struct snd_pcm_hw_constraint_ratnums { int nrats; const struct snd_ratnum *rats; }; struct snd_pcm_hw_constraint_ratdens { int nrats; const struct snd_ratden *rats; }; struct snd_pcm_hw_constraint_list { const unsigned int *list; unsigned int count; unsigned int mask; }; struct snd_pcm_hw_constraint_ranges { unsigned int count; const struct snd_interval *ranges; unsigned int mask; }; /* * userspace-provided audio timestamp config to kernel, * structure is for internal use only and filled with dedicated unpack routine */ struct snd_pcm_audio_tstamp_config { /* 5 of max 16 bits used */ u32 type_requested:4; u32 report_delay:1; /* add total delay to A/D or D/A */ }; static inline void snd_pcm_unpack_audio_tstamp_config(__u32 data, struct snd_pcm_audio_tstamp_config *config) { config->type_requested = data & 0xF; config->report_delay = (data >> 4) & 1; } /* * kernel-provided audio timestamp report to user-space * structure is for internal use only and read by dedicated pack routine */ struct snd_pcm_audio_tstamp_report { /* 6 of max 16 bits used for bit-fields */ /* for backwards compatibility */ u32 valid:1; /* actual type if hardware could not support requested timestamp */ u32 actual_type:4; /* accuracy represented in ns units */ u32 accuracy_report:1; /* 0 if accuracy unknown, 1 if accuracy field is valid */ u32 accuracy; /* up to 4.29s, will be packed in separate field */ }; static inline void snd_pcm_pack_audio_tstamp_report(__u32 *data, __u32 *accuracy, const struct snd_pcm_audio_tstamp_report *report) { u32 tmp; tmp = report->accuracy_report; tmp <<= 4; tmp |= report->actual_type; tmp <<= 1; tmp |= report->valid; *data &= 0xffff; /* zero-clear MSBs */ *data |= (tmp << 16); *accuracy = report->accuracy; } struct snd_pcm_runtime { /* -- Status -- */ snd_pcm_state_t state; /* stream state */ snd_pcm_state_t suspended_state; /* suspended stream state */ struct snd_pcm_substream *trigger_master; struct timespec64 trigger_tstamp; /* trigger timestamp */ bool trigger_tstamp_latched; /* trigger timestamp latched in low-level driver/hardware */ int overrange; snd_pcm_uframes_t avail_max; snd_pcm_uframes_t hw_ptr_base; /* Position at buffer restart */ snd_pcm_uframes_t hw_ptr_interrupt; /* Position at interrupt time */ unsigned long hw_ptr_jiffies; /* Time when hw_ptr is updated */ unsigned long hw_ptr_buffer_jiffies; /* buffer time in jiffies */ snd_pcm_sframes_t delay; /* extra delay; typically FIFO size */ u64 hw_ptr_wrap; /* offset for hw_ptr due to boundary wrap-around */ /* -- HW params -- */ snd_pcm_access_t access; /* access mode */ snd_pcm_format_t format; /* SNDRV_PCM_FORMAT_* */ snd_pcm_subformat_t subformat; /* subformat */ unsigned int rate; /* rate in Hz */ unsigned int channels; /* channels */ snd_pcm_uframes_t period_size; /* period size */ unsigned int periods; /* periods */ snd_pcm_uframes_t buffer_size; /* buffer size */ snd_pcm_uframes_t min_align; /* Min alignment for the format */ size_t byte_align; unsigned int frame_bits; unsigned int sample_bits; unsigned int info; unsigned int rate_num; unsigned int rate_den; unsigned int no_period_wakeup: 1; /* -- SW params; see struct snd_pcm_sw_params for comments -- */ int tstamp_mode; unsigned int period_step; snd_pcm_uframes_t start_threshold; snd_pcm_uframes_t stop_threshold; snd_pcm_uframes_t silence_threshold; snd_pcm_uframes_t silence_size; snd_pcm_uframes_t boundary; /* internal data of auto-silencer */ snd_pcm_uframes_t silence_start; /* starting pointer to silence area */ snd_pcm_uframes_t silence_filled; /* already filled part of silence area */ bool std_sync_id; /* hardware synchronization - standard per card ID */ /* -- mmap -- */ struct snd_pcm_mmap_status *status; struct snd_pcm_mmap_control *control; /* -- locking / scheduling -- */ snd_pcm_uframes_t twake; /* do transfer (!poll) wakeup if non-zero */ wait_queue_head_t sleep; /* poll sleep */ wait_queue_head_t tsleep; /* transfer sleep */ struct snd_fasync *fasync; bool stop_operating; /* sync_stop will be called */ struct mutex buffer_mutex; /* protect for buffer changes */ atomic_t buffer_accessing; /* >0: in r/w operation, <0: blocked */ /* -- private section -- */ void *private_data; void (*private_free)(struct snd_pcm_runtime *runtime); /* -- hardware description -- */ struct snd_pcm_hardware hw; struct snd_pcm_hw_constraints hw_constraints; /* -- timer -- */ unsigned int timer_resolution; /* timer resolution */ int tstamp_type; /* timestamp type */ /* -- DMA -- */ unsigned char *dma_area; /* DMA area */ dma_addr_t dma_addr; /* physical bus address (not accessible from main CPU) */ size_t dma_bytes; /* size of DMA area */ struct snd_dma_buffer *dma_buffer_p; /* allocated buffer */ unsigned int buffer_changed:1; /* buffer allocation changed; set only in managed mode */ /* -- audio timestamp config -- */ struct snd_pcm_audio_tstamp_config audio_tstamp_config; struct snd_pcm_audio_tstamp_report audio_tstamp_report; struct timespec64 driver_tstamp; #if IS_ENABLED(CONFIG_SND_PCM_OSS) /* -- OSS things -- */ struct snd_pcm_oss_runtime oss; #endif }; struct snd_pcm_group { /* keep linked substreams */ spinlock_t lock; struct mutex mutex; struct list_head substreams; refcount_t refs; }; struct pid; struct snd_pcm_substream { struct snd_pcm *pcm; struct snd_pcm_str *pstr; void *private_data; /* copied from pcm->private_data */ int number; char name[32]; /* substream name */ int stream; /* stream (direction) */ struct pm_qos_request latency_pm_qos_req; /* pm_qos request */ size_t buffer_bytes_max; /* limit ring buffer size */ struct snd_dma_buffer dma_buffer; size_t dma_max; /* -- hardware operations -- */ const struct snd_pcm_ops *ops; /* -- runtime information -- */ struct snd_pcm_runtime *runtime; /* -- timer section -- */ struct snd_timer *timer; /* timer */ unsigned timer_running: 1; /* time is running */ long wait_time; /* time in ms for R/W to wait for avail */ /* -- next substream -- */ struct snd_pcm_substream *next; /* -- linked substreams -- */ struct list_head link_list; /* linked list member */ struct snd_pcm_group self_group; /* fake group for non linked substream (with substream lock inside) */ struct snd_pcm_group *group; /* pointer to current group */ /* -- assigned files -- */ int ref_count; atomic_t mmap_count; unsigned int f_flags; void (*pcm_release)(struct snd_pcm_substream *); struct pid *pid; #if IS_ENABLED(CONFIG_SND_PCM_OSS) /* -- OSS things -- */ struct snd_pcm_oss_substream oss; #endif #ifdef CONFIG_SND_VERBOSE_PROCFS struct snd_info_entry *proc_root; #endif /* CONFIG_SND_VERBOSE_PROCFS */ /* misc flags */ unsigned int hw_opened: 1; unsigned int managed_buffer_alloc:1; }; #define SUBSTREAM_BUSY(substream) ((substream)->ref_count > 0) struct snd_pcm_str { int stream; /* stream (direction) */ struct snd_pcm *pcm; /* -- substreams -- */ unsigned int substream_count; unsigned int substream_opened; struct snd_pcm_substream *substream; #if IS_ENABLED(CONFIG_SND_PCM_OSS) /* -- OSS things -- */ struct snd_pcm_oss_stream oss; #endif #ifdef CONFIG_SND_VERBOSE_PROCFS struct snd_info_entry *proc_root; #ifdef CONFIG_SND_PCM_XRUN_DEBUG unsigned int xrun_debug; /* 0 = disabled, 1 = verbose, 2 = stacktrace */ #endif #endif struct snd_kcontrol *chmap_kctl; /* channel-mapping controls */ struct device *dev; }; struct snd_pcm { struct snd_card *card; struct list_head list; int device; /* device number */ unsigned int info_flags; unsigned short dev_class; unsigned short dev_subclass; char id[64]; char name[80]; struct snd_pcm_str streams[2]; struct mutex open_mutex; wait_queue_head_t open_wait; void *private_data; void (*private_free) (struct snd_pcm *pcm); bool internal; /* pcm is for internal use only */ bool nonatomic; /* whole PCM operations are in non-atomic context */ bool no_device_suspend; /* don't invoke device PM suspend */ #if IS_ENABLED(CONFIG_SND_PCM_OSS) struct snd_pcm_oss oss; #endif }; /* * Registering */ extern const struct file_operations snd_pcm_f_ops[2]; int snd_pcm_new(struct snd_card *card, const char *id, int device, int playback_count, int capture_count, struct snd_pcm **rpcm); int snd_pcm_new_internal(struct snd_card *card, const char *id, int device, int playback_count, int capture_count, struct snd_pcm **rpcm); int snd_pcm_new_stream(struct snd_pcm *pcm, int stream, int substream_count); #if IS_ENABLED(CONFIG_SND_PCM_OSS) struct snd_pcm_notify { int (*n_register) (struct snd_pcm * pcm); int (*n_disconnect) (struct snd_pcm * pcm); int (*n_unregister) (struct snd_pcm * pcm); struct list_head list; }; int snd_pcm_notify(struct snd_pcm_notify *notify, int nfree); #endif /* * Native I/O */ int snd_pcm_info(struct snd_pcm_substream *substream, struct snd_pcm_info *info); int snd_pcm_info_user(struct snd_pcm_substream *substream, struct snd_pcm_info __user *info); int snd_pcm_status64(struct snd_pcm_substream *substream, struct snd_pcm_status64 *status); int snd_pcm_start(struct snd_pcm_substream *substream); int snd_pcm_stop(struct snd_pcm_substream *substream, snd_pcm_state_t status); int snd_pcm_drain_done(struct snd_pcm_substream *substream); int snd_pcm_stop_xrun(struct snd_pcm_substream *substream); #ifdef CONFIG_PM int snd_pcm_suspend_all(struct snd_pcm *pcm); #else static inline int snd_pcm_suspend_all(struct snd_pcm *pcm) { return 0; } #endif int snd_pcm_kernel_ioctl(struct snd_pcm_substream *substream, unsigned int cmd, void *arg); int snd_pcm_open_substream(struct snd_pcm *pcm, int stream, struct file *file, struct snd_pcm_substream **rsubstream); void snd_pcm_release_substream(struct snd_pcm_substream *substream); int snd_pcm_attach_substream(struct snd_pcm *pcm, int stream, struct file *file, struct snd_pcm_substream **rsubstream); void snd_pcm_detach_substream(struct snd_pcm_substream *substream); int snd_pcm_mmap_data(struct snd_pcm_substream *substream, struct file *file, struct vm_area_struct *area); #ifdef CONFIG_SND_DEBUG void snd_pcm_debug_name(struct snd_pcm_substream *substream, char *name, size_t len); #else static inline void snd_pcm_debug_name(struct snd_pcm_substream *substream, char *buf, size_t size) { *buf = 0; } #endif /* * PCM library */ /** * snd_pcm_stream_linked - Check whether the substream is linked with others * @substream: substream to check * * Return: true if the given substream is being linked with others */ static inline int snd_pcm_stream_linked(struct snd_pcm_substream *substream) { return substream->group != &substream->self_group; } void snd_pcm_stream_lock(struct snd_pcm_substream *substream); void snd_pcm_stream_unlock(struct snd_pcm_substream *substream); void snd_pcm_stream_lock_irq(struct snd_pcm_substream *substream); void snd_pcm_stream_unlock_irq(struct snd_pcm_substream *substream); unsigned long _snd_pcm_stream_lock_irqsave(struct snd_pcm_substream *substream); unsigned long _snd_pcm_stream_lock_irqsave_nested(struct snd_pcm_substream *substream); /** * snd_pcm_stream_lock_irqsave - Lock the PCM stream * @substream: PCM substream * @flags: irq flags * * This locks the PCM stream like snd_pcm_stream_lock() but with the local * IRQ (only when nonatomic is false). In nonatomic case, this is identical * as snd_pcm_stream_lock(). */ #define snd_pcm_stream_lock_irqsave(substream, flags) \ do { \ typecheck(unsigned long, flags); \ flags = _snd_pcm_stream_lock_irqsave(substream); \ } while (0) void snd_pcm_stream_unlock_irqrestore(struct snd_pcm_substream *substream, unsigned long flags); /** * snd_pcm_stream_lock_irqsave_nested - Single-nested PCM stream locking * @substream: PCM substream * @flags: irq flags * * This locks the PCM stream like snd_pcm_stream_lock_irqsave() but with * the single-depth lockdep subclass. */ #define snd_pcm_stream_lock_irqsave_nested(substream, flags) \ do { \ typecheck(unsigned long, flags); \ flags = _snd_pcm_stream_lock_irqsave_nested(substream); \ } while (0) /* definitions for guard(); use like guard(pcm_stream_lock) */ DEFINE_LOCK_GUARD_1(pcm_stream_lock, struct snd_pcm_substream, snd_pcm_stream_lock(_T->lock), snd_pcm_stream_unlock(_T->lock)) DEFINE_LOCK_GUARD_1(pcm_stream_lock_irq, struct snd_pcm_substream, snd_pcm_stream_lock_irq(_T->lock), snd_pcm_stream_unlock_irq(_T->lock)) DEFINE_LOCK_GUARD_1(pcm_stream_lock_irqsave, struct snd_pcm_substream, snd_pcm_stream_lock_irqsave(_T->lock, _T->flags), snd_pcm_stream_unlock_irqrestore(_T->lock, _T->flags), unsigned long flags) /** * snd_pcm_group_for_each_entry - iterate over the linked substreams * @s: the iterator * @substream: the substream * * Iterate over the all linked substreams to the given @substream. * When @substream isn't linked with any others, this gives returns @substream * itself once. */ #define snd_pcm_group_for_each_entry(s, substream) \ list_for_each_entry(s, &substream->group->substreams, link_list) #define for_each_pcm_streams(stream) \ for (stream = SNDRV_PCM_STREAM_PLAYBACK; \ stream <= SNDRV_PCM_STREAM_LAST; \ stream++) /** * snd_pcm_running - Check whether the substream is in a running state * @substream: substream to check * * Return: true if the given substream is in the state RUNNING, or in the * state DRAINING for playback. */ static inline int snd_pcm_running(struct snd_pcm_substream *substream) { return (substream->runtime->state == SNDRV_PCM_STATE_RUNNING || (substream->runtime->state == SNDRV_PCM_STATE_DRAINING && substream->stream == SNDRV_PCM_STREAM_PLAYBACK)); } /** * __snd_pcm_set_state - Change the current PCM state * @runtime: PCM runtime to set * @state: the current state to set * * Call within the stream lock */ static inline void __snd_pcm_set_state(struct snd_pcm_runtime *runtime, snd_pcm_state_t state) { runtime->state = state; runtime->status->state = state; /* copy for mmap */ } /** * bytes_to_samples - Unit conversion of the size from bytes to samples * @runtime: PCM runtime instance * @size: size in bytes * * Return: the size in samples */ static inline ssize_t bytes_to_samples(struct snd_pcm_runtime *runtime, ssize_t size) { return size * 8 / runtime->sample_bits; } /** * bytes_to_frames - Unit conversion of the size from bytes to frames * @runtime: PCM runtime instance * @size: size in bytes * * Return: the size in frames */ static inline snd_pcm_sframes_t bytes_to_frames(struct snd_pcm_runtime *runtime, ssize_t size) { return size * 8 / runtime->frame_bits; } /** * samples_to_bytes - Unit conversion of the size from samples to bytes * @runtime: PCM runtime instance * @size: size in samples * * Return: the byte size */ static inline ssize_t samples_to_bytes(struct snd_pcm_runtime *runtime, ssize_t size) { return size * runtime->sample_bits / 8; } /** * frames_to_bytes - Unit conversion of the size from frames to bytes * @runtime: PCM runtime instance * @size: size in frames * * Return: the byte size */ static inline ssize_t frames_to_bytes(struct snd_pcm_runtime *runtime, snd_pcm_sframes_t size) { return size * runtime->frame_bits / 8; } /** * frame_aligned - Check whether the byte size is aligned to frames * @runtime: PCM runtime instance * @bytes: size in bytes * * Return: true if aligned, or false if not */ static inline int frame_aligned(struct snd_pcm_runtime *runtime, ssize_t bytes) { return bytes % runtime->byte_align == 0; } /** * snd_pcm_lib_buffer_bytes - Get the buffer size of the current PCM in bytes * @substream: PCM substream * * Return: buffer byte size */ static inline size_t snd_pcm_lib_buffer_bytes(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; return frames_to_bytes(runtime, runtime->buffer_size); } /** * snd_pcm_lib_period_bytes - Get the period size of the current PCM in bytes * @substream: PCM substream * * Return: period byte size */ static inline size_t snd_pcm_lib_period_bytes(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; return frames_to_bytes(runtime, runtime->period_size); } /** * snd_pcm_playback_avail - Get the available (writable) space for playback * @runtime: PCM runtime instance * * Result is between 0 ... (boundary - 1) * * Return: available frame size */ static inline snd_pcm_uframes_t snd_pcm_playback_avail(struct snd_pcm_runtime *runtime) { snd_pcm_sframes_t avail = runtime->status->hw_ptr + runtime->buffer_size - runtime->control->appl_ptr; if (avail < 0) avail += runtime->boundary; else if ((snd_pcm_uframes_t) avail >= runtime->boundary) avail -= runtime->boundary; return avail; } /** * snd_pcm_capture_avail - Get the available (readable) space for capture * @runtime: PCM runtime instance * * Result is between 0 ... (boundary - 1) * * Return: available frame size */ static inline snd_pcm_uframes_t snd_pcm_capture_avail(struct snd_pcm_runtime *runtime) { snd_pcm_sframes_t avail = runtime->status->hw_ptr - runtime->control->appl_ptr; if (avail < 0) avail += runtime->boundary; return avail; } /** * snd_pcm_playback_hw_avail - Get the queued space for playback * @runtime: PCM runtime instance * * Return: available frame size */ static inline snd_pcm_sframes_t snd_pcm_playback_hw_avail(struct snd_pcm_runtime *runtime) { return runtime->buffer_size - snd_pcm_playback_avail(runtime); } /** * snd_pcm_capture_hw_avail - Get the free space for capture * @runtime: PCM runtime instance * * Return: available frame size */ static inline snd_pcm_sframes_t snd_pcm_capture_hw_avail(struct snd_pcm_runtime *runtime) { return runtime->buffer_size - snd_pcm_capture_avail(runtime); } /** * snd_pcm_playback_ready - check whether the playback buffer is available * @substream: the pcm substream instance * * Checks whether enough free space is available on the playback buffer. * * Return: Non-zero if available, or zero if not. */ static inline int snd_pcm_playback_ready(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; return snd_pcm_playback_avail(runtime) >= runtime->control->avail_min; } /** * snd_pcm_capture_ready - check whether the capture buffer is available * @substream: the pcm substream instance * * Checks whether enough capture data is available on the capture buffer. * * Return: Non-zero if available, or zero if not. */ static inline int snd_pcm_capture_ready(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; return snd_pcm_capture_avail(runtime) >= runtime->control->avail_min; } /** * snd_pcm_playback_data - check whether any data exists on the playback buffer * @substream: the pcm substream instance * * Checks whether any data exists on the playback buffer. * * Return: Non-zero if any data exists, or zero if not. If stop_threshold * is bigger or equal to boundary, then this function returns always non-zero. */ static inline int snd_pcm_playback_data(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; if (runtime->stop_threshold >= runtime->boundary) return 1; return snd_pcm_playback_avail(runtime) < runtime->buffer_size; } /** * snd_pcm_playback_empty - check whether the playback buffer is empty * @substream: the pcm substream instance * * Checks whether the playback buffer is empty. * * Return: Non-zero if empty, or zero if not. */ static inline int snd_pcm_playback_empty(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; return snd_pcm_playback_avail(runtime) >= runtime->buffer_size; } /** * snd_pcm_capture_empty - check whether the capture buffer is empty * @substream: the pcm substream instance * * Checks whether the capture buffer is empty. * * Return: Non-zero if empty, or zero if not. */ static inline int snd_pcm_capture_empty(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; return snd_pcm_capture_avail(runtime) == 0; } /** * snd_pcm_trigger_done - Mark the master substream * @substream: the pcm substream instance * @master: the linked master substream * * When multiple substreams of the same card are linked and the hardware * supports the single-shot operation, the driver calls this in the loop * in snd_pcm_group_for_each_entry() for marking the substream as "done". * Then most of trigger operations are performed only to the given master * substream. * * The trigger_master mark is cleared at timestamp updates at the end * of trigger operations. */ static inline void snd_pcm_trigger_done(struct snd_pcm_substream *substream, struct snd_pcm_substream *master) { substream->runtime->trigger_master = master; } static inline int hw_is_mask(int var) { return var >= SNDRV_PCM_HW_PARAM_FIRST_MASK && var <= SNDRV_PCM_HW_PARAM_LAST_MASK; } static inline int hw_is_interval(int var) { return var >= SNDRV_PCM_HW_PARAM_FIRST_INTERVAL && var <= SNDRV_PCM_HW_PARAM_LAST_INTERVAL; } static inline struct snd_mask *hw_param_mask(struct snd_pcm_hw_params *params, snd_pcm_hw_param_t var) { return ¶ms->masks[var - SNDRV_PCM_HW_PARAM_FIRST_MASK]; } static inline struct snd_interval *hw_param_interval(struct snd_pcm_hw_params *params, snd_pcm_hw_param_t var) { return ¶ms->intervals[var - SNDRV_PCM_HW_PARAM_FIRST_INTERVAL]; } static inline const struct snd_mask *hw_param_mask_c(const struct snd_pcm_hw_params *params, snd_pcm_hw_param_t var) { return ¶ms->masks[var - SNDRV_PCM_HW_PARAM_FIRST_MASK]; } static inline const struct snd_interval *hw_param_interval_c(const struct snd_pcm_hw_params *params, snd_pcm_hw_param_t var) { return ¶ms->intervals[var - SNDRV_PCM_HW_PARAM_FIRST_INTERVAL]; } /** * params_channels - Get the number of channels from the hw params * @p: hw params * * Return: the number of channels */ static inline unsigned int params_channels(const struct snd_pcm_hw_params *p) { return hw_param_interval_c(p, SNDRV_PCM_HW_PARAM_CHANNELS)->min; } /** * params_rate - Get the sample rate from the hw params * @p: hw params * * Return: the sample rate */ static inline unsigned int params_rate(const struct snd_pcm_hw_params *p) { return hw_param_interval_c(p, SNDRV_PCM_HW_PARAM_RATE)->min; } /** * params_period_size - Get the period size (in frames) from the hw params * @p: hw params * * Return: the period size in frames */ static inline unsigned int params_period_size(const struct snd_pcm_hw_params *p) { return hw_param_interval_c(p, SNDRV_PCM_HW_PARAM_PERIOD_SIZE)->min; } /** * params_periods - Get the number of periods from the hw params * @p: hw params * * Return: the number of periods */ static inline unsigned int params_periods(const struct snd_pcm_hw_params *p) { return hw_param_interval_c(p, SNDRV_PCM_HW_PARAM_PERIODS)->min; } /** * params_buffer_size - Get the buffer size (in frames) from the hw params * @p: hw params * * Return: the buffer size in frames */ static inline unsigned int params_buffer_size(const struct snd_pcm_hw_params *p) { return hw_param_interval_c(p, SNDRV_PCM_HW_PARAM_BUFFER_SIZE)->min; } /** * params_buffer_bytes - Get the buffer size (in bytes) from the hw params * @p: hw params * * Return: the buffer size in bytes */ static inline unsigned int params_buffer_bytes(const struct snd_pcm_hw_params *p) { return hw_param_interval_c(p, SNDRV_PCM_HW_PARAM_BUFFER_BYTES)->min; } int snd_interval_refine(struct snd_interval *i, const struct snd_interval *v); int snd_interval_list(struct snd_interval *i, unsigned int count, const unsigned int *list, unsigned int mask); int snd_interval_ranges(struct snd_interval *i, unsigned int count, const struct snd_interval *list, unsigned int mask); int snd_interval_ratnum(struct snd_interval *i, unsigned int rats_count, const struct snd_ratnum *rats, unsigned int *nump, unsigned int *denp); void _snd_pcm_hw_params_any(struct snd_pcm_hw_params *params); void _snd_pcm_hw_param_setempty(struct snd_pcm_hw_params *params, snd_pcm_hw_param_t var); int snd_pcm_hw_refine(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params); int snd_pcm_hw_constraint_mask64(struct snd_pcm_runtime *runtime, snd_pcm_hw_param_t var, u_int64_t mask); int snd_pcm_hw_constraint_minmax(struct snd_pcm_runtime *runtime, snd_pcm_hw_param_t var, unsigned int min, unsigned int max); int snd_pcm_hw_constraint_integer(struct snd_pcm_runtime *runtime, snd_pcm_hw_param_t var); int snd_pcm_hw_constraint_list(struct snd_pcm_runtime *runtime, unsigned int cond, snd_pcm_hw_param_t var, const struct snd_pcm_hw_constraint_list *l); int snd_pcm_hw_constraint_ranges(struct snd_pcm_runtime *runtime, unsigned int cond, snd_pcm_hw_param_t var, const struct snd_pcm_hw_constraint_ranges *r); int snd_pcm_hw_constraint_ratnums(struct snd_pcm_runtime *runtime, unsigned int cond, snd_pcm_hw_param_t var, const struct snd_pcm_hw_constraint_ratnums *r); int snd_pcm_hw_constraint_ratdens(struct snd_pcm_runtime *runtime, unsigned int cond, snd_pcm_hw_param_t var, const struct snd_pcm_hw_constraint_ratdens *r); int snd_pcm_hw_constraint_msbits(struct snd_pcm_runtime *runtime, unsigned int cond, unsigned int width, unsigned int msbits); int snd_pcm_hw_constraint_step(struct snd_pcm_runtime *runtime, unsigned int cond, snd_pcm_hw_param_t var, unsigned long step); int snd_pcm_hw_constraint_pow2(struct snd_pcm_runtime *runtime, unsigned int cond, snd_pcm_hw_param_t var); int snd_pcm_hw_rule_noresample(struct snd_pcm_runtime *runtime, unsigned int base_rate); int snd_pcm_hw_rule_add(struct snd_pcm_runtime *runtime, unsigned int cond, int var, snd_pcm_hw_rule_func_t func, void *private, int dep, ...); /** * snd_pcm_hw_constraint_single() - Constrain parameter to a single value * @runtime: PCM runtime instance * @var: The hw_params variable to constrain * @val: The value to constrain to * * Return: Positive if the value is changed, zero if it's not changed, or a * negative error code. */ static inline int snd_pcm_hw_constraint_single( struct snd_pcm_runtime *runtime, snd_pcm_hw_param_t var, unsigned int val) { return snd_pcm_hw_constraint_minmax(runtime, var, val, val); } int snd_pcm_format_signed(snd_pcm_format_t format); int snd_pcm_format_unsigned(snd_pcm_format_t format); int snd_pcm_format_linear(snd_pcm_format_t format); int snd_pcm_format_little_endian(snd_pcm_format_t format); int snd_pcm_format_big_endian(snd_pcm_format_t format); #if 0 /* just for kernel-doc */ /** * snd_pcm_format_cpu_endian - Check the PCM format is CPU-endian * @format: the format to check * * Return: 1 if the given PCM format is CPU-endian, 0 if * opposite, or a negative error code if endian not specified. */ int snd_pcm_format_cpu_endian(snd_pcm_format_t format); #endif /* DocBook */ #ifdef SNDRV_LITTLE_ENDIAN #define snd_pcm_format_cpu_endian(format) snd_pcm_format_little_endian(format) #else #define snd_pcm_format_cpu_endian(format) snd_pcm_format_big_endian(format) #endif int snd_pcm_format_width(snd_pcm_format_t format); /* in bits */ int snd_pcm_format_physical_width(snd_pcm_format_t format); /* in bits */ ssize_t snd_pcm_format_size(snd_pcm_format_t format, size_t samples); const unsigned char *snd_pcm_format_silence_64(snd_pcm_format_t format); int snd_pcm_format_set_silence(snd_pcm_format_t format, void *buf, unsigned int frames); void snd_pcm_set_ops(struct snd_pcm * pcm, int direction, const struct snd_pcm_ops *ops); void snd_pcm_set_sync_per_card(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params, const unsigned char *id, unsigned int len); /** * snd_pcm_set_sync - set the PCM sync id * @substream: the pcm substream * * Use the default PCM sync identifier for the specific card. */ static inline void snd_pcm_set_sync(struct snd_pcm_substream *substream) { substream->runtime->std_sync_id = true; } int snd_pcm_lib_ioctl(struct snd_pcm_substream *substream, unsigned int cmd, void *arg); void snd_pcm_period_elapsed_under_stream_lock(struct snd_pcm_substream *substream); void snd_pcm_period_elapsed(struct snd_pcm_substream *substream); snd_pcm_sframes_t __snd_pcm_lib_xfer(struct snd_pcm_substream *substream, void *buf, bool interleaved, snd_pcm_uframes_t frames, bool in_kernel); static inline snd_pcm_sframes_t snd_pcm_lib_write(struct snd_pcm_substream *substream, const void __user *buf, snd_pcm_uframes_t frames) { return __snd_pcm_lib_xfer(substream, (void __force *)buf, true, frames, false); } static inline snd_pcm_sframes_t snd_pcm_lib_read(struct snd_pcm_substream *substream, void __user *buf, snd_pcm_uframes_t frames) { return __snd_pcm_lib_xfer(substream, (void __force *)buf, true, frames, false); } static inline snd_pcm_sframes_t snd_pcm_lib_writev(struct snd_pcm_substream *substream, void __user **bufs, snd_pcm_uframes_t frames) { return __snd_pcm_lib_xfer(substream, (void *)bufs, false, frames, false); } static inline snd_pcm_sframes_t snd_pcm_lib_readv(struct snd_pcm_substream *substream, void __user **bufs, snd_pcm_uframes_t frames) { return __snd_pcm_lib_xfer(substream, (void *)bufs, false, frames, false); } static inline snd_pcm_sframes_t snd_pcm_kernel_write(struct snd_pcm_substream *substream, const void *buf, snd_pcm_uframes_t frames) { return __snd_pcm_lib_xfer(substream, (void *)buf, true, frames, true); } static inline snd_pcm_sframes_t snd_pcm_kernel_read(struct snd_pcm_substream *substream, void *buf, snd_pcm_uframes_t frames) { return __snd_pcm_lib_xfer(substream, buf, true, frames, true); } static inline snd_pcm_sframes_t snd_pcm_kernel_writev(struct snd_pcm_substream *substream, void **bufs, snd_pcm_uframes_t frames) { return __snd_pcm_lib_xfer(substream, bufs, false, frames, true); } static inline snd_pcm_sframes_t snd_pcm_kernel_readv(struct snd_pcm_substream *substream, void **bufs, snd_pcm_uframes_t frames) { return __snd_pcm_lib_xfer(substream, bufs, false, frames, true); } int snd_pcm_hw_limit_rates(struct snd_pcm_hardware *hw); static inline int snd_pcm_limit_hw_rates(struct snd_pcm_runtime *runtime) { return snd_pcm_hw_limit_rates(&runtime->hw); } unsigned int snd_pcm_rate_to_rate_bit(unsigned int rate); unsigned int snd_pcm_rate_bit_to_rate(unsigned int rate_bit); unsigned int snd_pcm_rate_mask_intersect(unsigned int rates_a, unsigned int rates_b); unsigned int snd_pcm_rate_range_to_bits(unsigned int rate_min, unsigned int rate_max); /** * snd_pcm_set_runtime_buffer - Set the PCM runtime buffer * @substream: PCM substream to set * @bufp: the buffer information, NULL to clear * * Copy the buffer information to runtime->dma_buffer when @bufp is non-NULL. * Otherwise it clears the current buffer information. */ static inline void snd_pcm_set_runtime_buffer(struct snd_pcm_substream *substream, struct snd_dma_buffer *bufp) { struct snd_pcm_runtime *runtime = substream->runtime; if (bufp) { runtime->dma_buffer_p = bufp; runtime->dma_area = bufp->area; runtime->dma_addr = bufp->addr; runtime->dma_bytes = bufp->bytes; } else { runtime->dma_buffer_p = NULL; runtime->dma_area = NULL; runtime->dma_addr = 0; runtime->dma_bytes = 0; } } /** * snd_pcm_gettime - Fill the timespec64 depending on the timestamp mode * @runtime: PCM runtime instance * @tv: timespec64 to fill */ static inline void snd_pcm_gettime(struct snd_pcm_runtime *runtime, struct timespec64 *tv) { switch (runtime->tstamp_type) { case SNDRV_PCM_TSTAMP_TYPE_MONOTONIC: ktime_get_ts64(tv); break; case SNDRV_PCM_TSTAMP_TYPE_MONOTONIC_RAW: ktime_get_raw_ts64(tv); break; default: ktime_get_real_ts64(tv); break; } } /* * Memory */ void snd_pcm_lib_preallocate_free(struct snd_pcm_substream *substream); void snd_pcm_lib_preallocate_free_for_all(struct snd_pcm *pcm); void snd_pcm_lib_preallocate_pages(struct snd_pcm_substream *substream, int type, struct device *data, size_t size, size_t max); void snd_pcm_lib_preallocate_pages_for_all(struct snd_pcm *pcm, int type, void *data, size_t size, size_t max); int snd_pcm_lib_malloc_pages(struct snd_pcm_substream *substream, size_t size); int snd_pcm_lib_free_pages(struct snd_pcm_substream *substream); int snd_pcm_set_managed_buffer(struct snd_pcm_substream *substream, int type, struct device *data, size_t size, size_t max); int snd_pcm_set_managed_buffer_all(struct snd_pcm *pcm, int type, struct device *data, size_t size, size_t max); /** * snd_pcm_set_fixed_buffer - Preallocate and set up the fixed size PCM buffer * @substream: the pcm substream instance * @type: DMA type (SNDRV_DMA_TYPE_*) * @data: DMA type dependent data * @size: the requested pre-allocation size in bytes * * This is a variant of snd_pcm_set_managed_buffer(), but this pre-allocates * only the given sized buffer and doesn't allow re-allocation nor dynamic * allocation of a larger buffer unlike the standard one. * The function may return -ENOMEM error, hence the caller must check it. * * Return: zero if successful, or a negative error code */ static inline int __must_check snd_pcm_set_fixed_buffer(struct snd_pcm_substream *substream, int type, struct device *data, size_t size) { return snd_pcm_set_managed_buffer(substream, type, data, size, 0); } /** * snd_pcm_set_fixed_buffer_all - Preallocate and set up the fixed size PCM buffer * @pcm: the pcm instance * @type: DMA type (SNDRV_DMA_TYPE_*) * @data: DMA type dependent data * @size: the requested pre-allocation size in bytes * * Apply the set up of the fixed buffer via snd_pcm_set_fixed_buffer() for * all substream. If any of allocation fails, it returns -ENOMEM, hence the * caller must check the return value. * * Return: zero if successful, or a negative error code */ static inline int __must_check snd_pcm_set_fixed_buffer_all(struct snd_pcm *pcm, int type, struct device *data, size_t size) { return snd_pcm_set_managed_buffer_all(pcm, type, data, size, 0); } int _snd_pcm_lib_alloc_vmalloc_buffer(struct snd_pcm_substream *substream, size_t size, gfp_t gfp_flags); int snd_pcm_lib_free_vmalloc_buffer(struct snd_pcm_substream *substream); struct page *snd_pcm_lib_get_vmalloc_page(struct snd_pcm_substream *substream, unsigned long offset); /** * snd_pcm_lib_alloc_vmalloc_buffer - allocate virtual DMA buffer * @substream: the substream to allocate the buffer to * @size: the requested buffer size, in bytes * * Allocates the PCM substream buffer using vmalloc(), i.e., the memory is * contiguous in kernel virtual space, but not in physical memory. Use this * if the buffer is accessed by kernel code but not by device DMA. * * Return: 1 if the buffer was changed, 0 if not changed, or a negative error * code. */ static inline int snd_pcm_lib_alloc_vmalloc_buffer (struct snd_pcm_substream *substream, size_t size) { return _snd_pcm_lib_alloc_vmalloc_buffer(substream, size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO); } /** * snd_pcm_lib_alloc_vmalloc_32_buffer - allocate 32-bit-addressable buffer * @substream: the substream to allocate the buffer to * @size: the requested buffer size, in bytes * * This function works like snd_pcm_lib_alloc_vmalloc_buffer(), but uses * vmalloc_32(), i.e., the pages are allocated from 32-bit-addressable memory. * * Return: 1 if the buffer was changed, 0 if not changed, or a negative error * code. */ static inline int snd_pcm_lib_alloc_vmalloc_32_buffer (struct snd_pcm_substream *substream, size_t size) { return _snd_pcm_lib_alloc_vmalloc_buffer(substream, size, GFP_KERNEL | GFP_DMA32 | __GFP_ZERO); } #define snd_pcm_get_dma_buf(substream) ((substream)->runtime->dma_buffer_p) /** * snd_pcm_sgbuf_get_addr - Get the DMA address at the corresponding offset * @substream: PCM substream * @ofs: byte offset * * Return: DMA address */ static inline dma_addr_t snd_pcm_sgbuf_get_addr(struct snd_pcm_substream *substream, unsigned int ofs) { return snd_sgbuf_get_addr(snd_pcm_get_dma_buf(substream), ofs); } /** * snd_pcm_sgbuf_get_chunk_size - Compute the max size that fits within the * contig. page from the given size * @substream: PCM substream * @ofs: byte offset * @size: byte size to examine * * Return: chunk size */ static inline unsigned int snd_pcm_sgbuf_get_chunk_size(struct snd_pcm_substream *substream, unsigned int ofs, unsigned int size) { return snd_sgbuf_get_chunk_size(snd_pcm_get_dma_buf(substream), ofs, size); } /** * snd_pcm_mmap_data_open - increase the mmap counter * @area: VMA * * PCM mmap callback should handle this counter properly */ static inline void snd_pcm_mmap_data_open(struct vm_area_struct *area) { struct snd_pcm_substream *substream = (struct snd_pcm_substream *)area->vm_private_data; atomic_inc(&substream->mmap_count); } /** * snd_pcm_mmap_data_close - decrease the mmap counter * @area: VMA * * PCM mmap callback should handle this counter properly */ static inline void snd_pcm_mmap_data_close(struct vm_area_struct *area) { struct snd_pcm_substream *substream = (struct snd_pcm_substream *)area->vm_private_data; atomic_dec(&substream->mmap_count); } int snd_pcm_lib_default_mmap(struct snd_pcm_substream *substream, struct vm_area_struct *area); /* mmap for io-memory area */ #if defined(CONFIG_X86) || defined(CONFIG_PPC) || defined(CONFIG_ALPHA) #define SNDRV_PCM_INFO_MMAP_IOMEM SNDRV_PCM_INFO_MMAP int snd_pcm_lib_mmap_iomem(struct snd_pcm_substream *substream, struct vm_area_struct *area); #else #define SNDRV_PCM_INFO_MMAP_IOMEM 0 #define snd_pcm_lib_mmap_iomem NULL #endif /** * snd_pcm_limit_isa_dma_size - Get the max size fitting with ISA DMA transfer * @dma: DMA number * @max: pointer to store the max size */ static inline void snd_pcm_limit_isa_dma_size(int dma, size_t *max) { *max = dma < 4 ? 64 * 1024 : 128 * 1024; } /* * Misc */ #define SNDRV_PCM_DEFAULT_CON_SPDIF (IEC958_AES0_CON_EMPHASIS_NONE|\ (IEC958_AES1_CON_ORIGINAL<<8)|\ (IEC958_AES1_CON_PCM_CODER<<8)|\ (IEC958_AES3_CON_FS_48000<<24)) const char *snd_pcm_format_name(snd_pcm_format_t format); /** * snd_pcm_direction_name - Get a string naming the direction of a stream * @direction: Stream's direction, one of SNDRV_PCM_STREAM_XXX * * Returns a string naming the direction of the stream. */ static inline const char *snd_pcm_direction_name(int direction) { if (direction == SNDRV_PCM_STREAM_PLAYBACK) return "Playback"; else return "Capture"; } /** * snd_pcm_stream_str - Get a string naming the direction of a stream * @substream: the pcm substream instance * * Return: A string naming the direction of the stream. */ static inline const char *snd_pcm_stream_str(struct snd_pcm_substream *substream) { return snd_pcm_direction_name(substream->stream); } /* * PCM channel-mapping control API */ /* array element of channel maps */ struct snd_pcm_chmap_elem { unsigned char channels; unsigned char map[15]; }; /* channel map information; retrieved via snd_kcontrol_chip() */ struct snd_pcm_chmap { struct snd_pcm *pcm; /* assigned PCM instance */ int stream; /* PLAYBACK or CAPTURE */ struct snd_kcontrol *kctl; const struct snd_pcm_chmap_elem *chmap; unsigned int max_channels; unsigned int channel_mask; /* optional: active channels bitmask */ void *private_data; /* optional: private data pointer */ }; /** * snd_pcm_chmap_substream - get the PCM substream assigned to the given chmap info * @info: chmap information * @idx: the substream number index * * Return: the matched PCM substream, or NULL if not found */ static inline struct snd_pcm_substream * snd_pcm_chmap_substream(struct snd_pcm_chmap *info, unsigned int idx) { struct snd_pcm_substream *s; for (s = info->pcm->streams[info->stream].substream; s; s = s->next) if (s->number == idx) return s; return NULL; } /* ALSA-standard channel maps (RL/RR prior to C/LFE) */ extern const struct snd_pcm_chmap_elem snd_pcm_std_chmaps[]; /* Other world's standard channel maps (C/LFE prior to RL/RR) */ extern const struct snd_pcm_chmap_elem snd_pcm_alt_chmaps[]; /* bit masks to be passed to snd_pcm_chmap.channel_mask field */ #define SND_PCM_CHMAP_MASK_24 ((1U << 2) | (1U << 4)) #define SND_PCM_CHMAP_MASK_246 (SND_PCM_CHMAP_MASK_24 | (1U << 6)) #define SND_PCM_CHMAP_MASK_2468 (SND_PCM_CHMAP_MASK_246 | (1U << 8)) int snd_pcm_add_chmap_ctls(struct snd_pcm *pcm, int stream, const struct snd_pcm_chmap_elem *chmap, int max_channels, unsigned long private_value, struct snd_pcm_chmap **info_ret); /** * pcm_format_to_bits - Strong-typed conversion of pcm_format to bitwise * @pcm_format: PCM format * * Return: 64bit mask corresponding to the given PCM format */ static inline u64 pcm_format_to_bits(snd_pcm_format_t pcm_format) { return 1ULL << (__force int) pcm_format; } /** * pcm_for_each_format - helper to iterate for each format type * @f: the iterator variable in snd_pcm_format_t type */ #define pcm_for_each_format(f) \ for ((f) = SNDRV_PCM_FORMAT_FIRST; \ (__force int)(f) <= (__force int)SNDRV_PCM_FORMAT_LAST; \ (f) = (__force snd_pcm_format_t)((__force int)(f) + 1)) /* printk helpers */ #define pcm_err(pcm, fmt, args...) \ dev_err((pcm)->card->dev, fmt, ##args) #define pcm_warn(pcm, fmt, args...) \ dev_warn((pcm)->card->dev, fmt, ##args) #define pcm_dbg(pcm, fmt, args...) \ dev_dbg((pcm)->card->dev, fmt, ##args) /* helpers for copying between iov_iter and iomem */ int copy_to_iter_fromio(struct iov_iter *itert, const void __iomem *src, size_t count); int copy_from_iter_toio(void __iomem *dst, struct iov_iter *iter, size_t count); struct snd_pcm_status64 { snd_pcm_state_t state; /* stream state */ u8 rsvd[4]; s64 trigger_tstamp_sec; /* time when stream was started/stopped/paused */ s64 trigger_tstamp_nsec; s64 tstamp_sec; /* reference timestamp */ s64 tstamp_nsec; snd_pcm_uframes_t appl_ptr; /* appl ptr */ snd_pcm_uframes_t hw_ptr; /* hw ptr */ snd_pcm_sframes_t delay; /* current delay in frames */ snd_pcm_uframes_t avail; /* number of frames available */ snd_pcm_uframes_t avail_max; /* max frames available on hw since last status */ snd_pcm_uframes_t overrange; /* count of ADC (capture) overrange detections from last status */ snd_pcm_state_t suspended_state; /* suspended stream state */ __u32 audio_tstamp_data; /* needed for 64-bit alignment, used for configs/report to/from userspace */ s64 audio_tstamp_sec; /* sample counter, wall clock, PHC or on-demand sync'ed */ s64 audio_tstamp_nsec; s64 driver_tstamp_sec; /* useful in case reference system tstamp is reported with delay */ s64 driver_tstamp_nsec; __u32 audio_tstamp_accuracy; /* in ns units, only valid if indicated in audio_tstamp_data */ unsigned char reserved[52-4*sizeof(s64)]; /* must be filled with zero */ }; #define SNDRV_PCM_IOCTL_STATUS64 _IOR('A', 0x20, struct snd_pcm_status64) #define SNDRV_PCM_IOCTL_STATUS_EXT64 _IOWR('A', 0x24, struct snd_pcm_status64) struct snd_pcm_status32 { snd_pcm_state_t state; /* stream state */ s32 trigger_tstamp_sec; /* time when stream was started/stopped/paused */ s32 trigger_tstamp_nsec; s32 tstamp_sec; /* reference timestamp */ s32 tstamp_nsec; u32 appl_ptr; /* appl ptr */ u32 hw_ptr; /* hw ptr */ s32 delay; /* current delay in frames */ u32 avail; /* number of frames available */ u32 avail_max; /* max frames available on hw since last status */ u32 overrange; /* count of ADC (capture) overrange detections from last status */ snd_pcm_state_t suspended_state; /* suspended stream state */ u32 audio_tstamp_data; /* needed for 64-bit alignment, used for configs/report to/from userspace */ s32 audio_tstamp_sec; /* sample counter, wall clock, PHC or on-demand sync'ed */ s32 audio_tstamp_nsec; s32 driver_tstamp_sec; /* useful in case reference system tstamp is reported with delay */ s32 driver_tstamp_nsec; u32 audio_tstamp_accuracy; /* in ns units, only valid if indicated in audio_tstamp_data */ unsigned char reserved[52-4*sizeof(s32)]; /* must be filled with zero */ }; #define SNDRV_PCM_IOCTL_STATUS32 _IOR('A', 0x20, struct snd_pcm_status32) #define SNDRV_PCM_IOCTL_STATUS_EXT32 _IOWR('A', 0x24, struct snd_pcm_status32) #endif /* __SOUND_PCM_H */ |
| 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 | // SPDX-License-Identifier: GPL-2.0 /* Copyright 2011-2014 Autronica Fire and Security AS * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * This file contains device methods for creating, using and destroying * virtual HSR or PRP devices. */ #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <linux/pkt_sched.h> #include "hsr_device.h" #include "hsr_slave.h" #include "hsr_framereg.h" #include "hsr_main.h" #include "hsr_forward.h" static bool is_admin_up(struct net_device *dev) { return dev && (dev->flags & IFF_UP); } static bool is_slave_up(struct net_device *dev) { return dev && is_admin_up(dev) && netif_oper_up(dev); } static void hsr_set_operstate(struct hsr_port *master, bool has_carrier) { struct net_device *dev = master->dev; if (!is_admin_up(dev)) { netdev_set_operstate(dev, IF_OPER_DOWN); return; } if (has_carrier) netdev_set_operstate(dev, IF_OPER_UP); else netdev_set_operstate(dev, IF_OPER_LOWERLAYERDOWN); } static bool hsr_check_carrier(struct hsr_port *master) { struct hsr_port *port; ASSERT_RTNL(); hsr_for_each_port(master->hsr, port) { if (port->type != HSR_PT_MASTER && is_slave_up(port->dev)) { netif_carrier_on(master->dev); return true; } } netif_carrier_off(master->dev); return false; } static void hsr_check_announce(struct net_device *hsr_dev) { struct hsr_priv *hsr; hsr = netdev_priv(hsr_dev); if (netif_running(hsr_dev) && netif_oper_up(hsr_dev)) { /* Enable announce timer and start sending supervisory frames */ if (!timer_pending(&hsr->announce_timer)) { hsr->announce_count = 0; mod_timer(&hsr->announce_timer, jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL)); } if (hsr->redbox && !timer_pending(&hsr->announce_proxy_timer)) mod_timer(&hsr->announce_proxy_timer, jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL) / 2); } else { /* Deactivate the announce timer */ timer_delete(&hsr->announce_timer); if (hsr->redbox) timer_delete(&hsr->announce_proxy_timer); } } void hsr_check_carrier_and_operstate(struct hsr_priv *hsr) { struct hsr_port *master; bool has_carrier; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); /* netif_stacked_transfer_operstate() cannot be used here since * it doesn't set IF_OPER_LOWERLAYERDOWN (?) */ has_carrier = hsr_check_carrier(master); hsr_set_operstate(master, has_carrier); hsr_check_announce(master->dev); } int hsr_get_max_mtu(struct hsr_priv *hsr) { unsigned int mtu_max; struct hsr_port *port; mtu_max = ETH_DATA_LEN; hsr_for_each_port(hsr, port) if (port->type != HSR_PT_MASTER) mtu_max = min(port->dev->mtu, mtu_max); if (mtu_max < HSR_HLEN) return 0; return mtu_max - HSR_HLEN; } static int hsr_dev_change_mtu(struct net_device *dev, int new_mtu) { struct hsr_priv *hsr; hsr = netdev_priv(dev); if (new_mtu > hsr_get_max_mtu(hsr)) { netdev_info(dev, "A HSR master's MTU cannot be greater than the smallest MTU of its slaves minus the HSR Tag length (%d octets).\n", HSR_HLEN); return -EINVAL; } WRITE_ONCE(dev->mtu, new_mtu); return 0; } static int hsr_dev_open(struct net_device *dev) { struct hsr_priv *hsr; struct hsr_port *port; const char *designation = NULL; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: designation = "Slave A"; break; case HSR_PT_SLAVE_B: designation = "Slave B"; break; case HSR_PT_INTERLINK: designation = "Interlink"; break; default: designation = "Unknown"; } if (!is_slave_up(port->dev)) netdev_warn(dev, "%s (%s) is not up; please bring it up to get a fully working HSR network\n", designation, port->dev->name); } if (!designation) netdev_warn(dev, "No slave devices configured\n"); return 0; } static int hsr_dev_close(struct net_device *dev) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: dev_uc_unsync(port->dev, dev); dev_mc_unsync(port->dev, dev); break; default: break; } } return 0; } static netdev_features_t hsr_features_recompute(struct hsr_priv *hsr, netdev_features_t features) { netdev_features_t mask; struct hsr_port *port; mask = features; /* Mask out all features that, if supported by one device, should be * enabled for all devices (see NETIF_F_ONE_FOR_ALL). * * Anything that's off in mask will not be enabled - so only things * that were in features originally, and also is in NETIF_F_ONE_FOR_ALL, * may become enabled. */ features &= ~NETIF_F_ONE_FOR_ALL; hsr_for_each_port(hsr, port) features = netdev_increment_features(features, port->dev->features, mask); return features; } static netdev_features_t hsr_fix_features(struct net_device *dev, netdev_features_t features) { struct hsr_priv *hsr = netdev_priv(dev); return hsr_features_recompute(hsr, features); } static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev) { struct hsr_priv *hsr = netdev_priv(dev); struct hsr_port *master; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (master) { skb->dev = master->dev; skb_reset_mac_header(skb); skb_reset_mac_len(skb); spin_lock_bh(&hsr->seqnr_lock); hsr_forward_skb(skb, master); spin_unlock_bh(&hsr->seqnr_lock); } else { dev_core_stats_tx_dropped_inc(dev); dev_kfree_skb_any(skb); } return NETDEV_TX_OK; } static const struct header_ops hsr_header_ops = { .create = eth_header, .parse = eth_header_parse, }; static struct sk_buff *hsr_init_skb(struct hsr_port *master) { struct hsr_priv *hsr = master->hsr; struct sk_buff *skb; int hlen, tlen; hlen = LL_RESERVED_SPACE(master->dev); tlen = master->dev->needed_tailroom; /* skb size is same for PRP/HSR frames, only difference * being, for PRP it is a trailer and for HSR it is a * header */ skb = dev_alloc_skb(sizeof(struct hsr_sup_tag) + sizeof(struct hsr_sup_payload) + hlen + tlen); if (!skb) return skb; skb_reserve(skb, hlen); skb->dev = master->dev; skb->priority = TC_PRIO_CONTROL; if (dev_hard_header(skb, skb->dev, ETH_P_PRP, hsr->sup_multicast_addr, skb->dev->dev_addr, skb->len) <= 0) goto out; skb_reset_mac_header(skb); skb_reset_mac_len(skb); skb_reset_network_header(skb); skb_reset_transport_header(skb); return skb; out: kfree_skb(skb); return NULL; } static void send_hsr_supervision_frame(struct hsr_port *port, unsigned long *interval, const unsigned char *addr) { struct hsr_priv *hsr = port->hsr; __u8 type = HSR_TLV_LIFE_CHECK; struct hsr_sup_payload *hsr_sp; struct hsr_sup_tlv *hsr_stlv; struct hsr_sup_tag *hsr_stag; struct sk_buff *skb; *interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); if (hsr->announce_count < 3 && hsr->prot_version == 0) { type = HSR_TLV_ANNOUNCE; *interval = msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); hsr->announce_count++; } skb = hsr_init_skb(port); if (!skb) { netdev_warn_once(port->dev, "HSR: Could not send supervision frame\n"); return; } hsr_stag = skb_put(skb, sizeof(struct hsr_sup_tag)); set_hsr_stag_path(hsr_stag, (hsr->prot_version ? 0x0 : 0xf)); set_hsr_stag_HSR_ver(hsr_stag, hsr->prot_version); /* From HSRv1 on we have separate supervision sequence numbers. */ spin_lock_bh(&hsr->seqnr_lock); if (hsr->prot_version > 0) { hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr); hsr->sup_sequence_nr++; } else { hsr_stag->sequence_nr = htons(hsr->sequence_nr); hsr->sequence_nr++; } hsr_stag->tlv.HSR_TLV_type = type; /* TODO: Why 12 in HSRv0? */ hsr_stag->tlv.HSR_TLV_length = hsr->prot_version ? sizeof(struct hsr_sup_payload) : 12; /* Payload: MacAddressA / SAN MAC from ProxyNodeTable */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, addr); if (hsr->redbox && hsr_is_node_in_db(&hsr->proxy_node_db, addr)) { hsr_stlv = skb_put(skb, sizeof(struct hsr_sup_tlv)); hsr_stlv->HSR_TLV_type = PRP_TLV_REDBOX_MAC; hsr_stlv->HSR_TLV_length = sizeof(struct hsr_sup_payload); /* Payload: MacAddressRedBox */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, hsr->macaddress_redbox); } if (skb_put_padto(skb, ETH_ZLEN)) { spin_unlock_bh(&hsr->seqnr_lock); return; } hsr_forward_skb(skb, port); spin_unlock_bh(&hsr->seqnr_lock); return; } static void send_prp_supervision_frame(struct hsr_port *master, unsigned long *interval, const unsigned char *addr) { struct hsr_priv *hsr = master->hsr; struct hsr_sup_payload *hsr_sp; struct hsr_sup_tag *hsr_stag; struct sk_buff *skb; skb = hsr_init_skb(master); if (!skb) { netdev_warn_once(master->dev, "PRP: Could not send supervision frame\n"); return; } *interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); hsr_stag = skb_put(skb, sizeof(struct hsr_sup_tag)); set_hsr_stag_path(hsr_stag, (hsr->prot_version ? 0x0 : 0xf)); set_hsr_stag_HSR_ver(hsr_stag, (hsr->prot_version ? 1 : 0)); /* From HSRv1 on we have separate supervision sequence numbers. */ spin_lock_bh(&hsr->seqnr_lock); hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr); hsr->sup_sequence_nr++; hsr_stag->tlv.HSR_TLV_type = PRP_TLV_LIFE_CHECK_DD; hsr_stag->tlv.HSR_TLV_length = sizeof(struct hsr_sup_payload); /* Payload: MacAddressA */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr); if (skb_put_padto(skb, ETH_ZLEN)) { spin_unlock_bh(&hsr->seqnr_lock); return; } hsr_forward_skb(skb, master); spin_unlock_bh(&hsr->seqnr_lock); } /* Announce (supervision frame) timer function */ static void hsr_announce(struct timer_list *t) { struct hsr_priv *hsr; struct hsr_port *master; unsigned long interval; hsr = from_timer(hsr, t, announce_timer); rcu_read_lock(); master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); hsr->proto_ops->send_sv_frame(master, &interval, master->dev->dev_addr); if (is_admin_up(master->dev)) mod_timer(&hsr->announce_timer, jiffies + interval); rcu_read_unlock(); } /* Announce (supervision frame) timer function for RedBox */ static void hsr_proxy_announce(struct timer_list *t) { struct hsr_priv *hsr = from_timer(hsr, t, announce_proxy_timer); struct hsr_port *interlink; unsigned long interval = 0; struct hsr_node *node; rcu_read_lock(); /* RedBOX sends supervisory frames to HSR network with MAC addresses * of SAN nodes stored in ProxyNodeTable. */ interlink = hsr_port_get_hsr(hsr, HSR_PT_INTERLINK); list_for_each_entry_rcu(node, &hsr->proxy_node_db, mac_list) { if (hsr_addr_is_redbox(hsr, node->macaddress_A)) continue; hsr->proto_ops->send_sv_frame(interlink, &interval, node->macaddress_A); } if (is_admin_up(interlink->dev)) { if (!interval) interval = msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); mod_timer(&hsr->announce_proxy_timer, jiffies + interval); } rcu_read_unlock(); } void hsr_del_ports(struct hsr_priv *hsr) { struct hsr_port *port; port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A); if (port) hsr_del_port(port); port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); if (port) hsr_del_port(port); port = hsr_port_get_hsr(hsr, HSR_PT_INTERLINK); if (port) hsr_del_port(port); port = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (port) hsr_del_port(port); } static void hsr_set_rx_mode(struct net_device *dev) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: dev_mc_sync_multiple(port->dev, dev); dev_uc_sync_multiple(port->dev, dev); break; default: break; } } } static void hsr_change_rx_flags(struct net_device *dev, int change) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: if (change & IFF_ALLMULTI) dev_set_allmulti(port->dev, dev->flags & IFF_ALLMULTI ? 1 : -1); break; default: break; } } } static const struct net_device_ops hsr_device_ops = { .ndo_change_mtu = hsr_dev_change_mtu, .ndo_open = hsr_dev_open, .ndo_stop = hsr_dev_close, .ndo_start_xmit = hsr_dev_xmit, .ndo_change_rx_flags = hsr_change_rx_flags, .ndo_fix_features = hsr_fix_features, .ndo_set_rx_mode = hsr_set_rx_mode, }; static const struct device_type hsr_type = { .name = "hsr", }; static struct hsr_proto_ops hsr_ops = { .send_sv_frame = send_hsr_supervision_frame, .create_tagged_frame = hsr_create_tagged_frame, .get_untagged_frame = hsr_get_untagged_frame, .drop_frame = hsr_drop_frame, .fill_frame_info = hsr_fill_frame_info, .invalid_dan_ingress_frame = hsr_invalid_dan_ingress_frame, }; static struct hsr_proto_ops prp_ops = { .send_sv_frame = send_prp_supervision_frame, .create_tagged_frame = prp_create_tagged_frame, .get_untagged_frame = prp_get_untagged_frame, .drop_frame = prp_drop_frame, .fill_frame_info = prp_fill_frame_info, .handle_san_frame = prp_handle_san_frame, .update_san_info = prp_update_san_info, }; void hsr_dev_setup(struct net_device *dev) { eth_hw_addr_random(dev); ether_setup(dev); dev->min_mtu = 0; dev->header_ops = &hsr_header_ops; dev->netdev_ops = &hsr_device_ops; SET_NETDEV_DEVTYPE(dev, &hsr_type); dev->priv_flags |= IFF_NO_QUEUE | IFF_DISABLE_NETPOLL; dev->needs_free_netdev = true; dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | NETIF_F_GSO_MASK | NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_TX; dev->features = dev->hw_features; /* Prevent recursive tx locking */ dev->features |= NETIF_F_LLTX; /* VLAN on top of HSR needs testing and probably some work on * hsr_header_create() etc. */ dev->features |= NETIF_F_VLAN_CHALLENGED; /* Not sure about this. Taken from bridge code. netdev_features.h says * it means "Does not change network namespaces". */ dev->features |= NETIF_F_NETNS_LOCAL; } /* Return true if dev is a HSR master; return false otherwise. */ bool is_hsr_master(struct net_device *dev) { return (dev->netdev_ops->ndo_start_xmit == hsr_dev_xmit); } EXPORT_SYMBOL(is_hsr_master); /* Default multicast address for HSR Supervision frames */ static const unsigned char def_multicast_addr[ETH_ALEN] __aligned(2) = { 0x01, 0x15, 0x4e, 0x00, 0x01, 0x00 }; int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], struct net_device *interlink, unsigned char multicast_spec, u8 protocol_version, struct netlink_ext_ack *extack) { bool unregister = false; struct hsr_priv *hsr; int res; hsr = netdev_priv(hsr_dev); INIT_LIST_HEAD(&hsr->ports); INIT_LIST_HEAD(&hsr->node_db); INIT_LIST_HEAD(&hsr->proxy_node_db); spin_lock_init(&hsr->list_lock); eth_hw_addr_set(hsr_dev, slave[0]->dev_addr); /* initialize protocol specific functions */ if (protocol_version == PRP_V1) { /* For PRP, lan_id has most significant 3 bits holding * the net_id of PRP_LAN_ID */ hsr->net_id = PRP_LAN_ID << 1; hsr->proto_ops = &prp_ops; } else { hsr->proto_ops = &hsr_ops; } /* Make sure we recognize frames from ourselves in hsr_rcv() */ res = hsr_create_self_node(hsr, hsr_dev->dev_addr, slave[1]->dev_addr); if (res < 0) return res; spin_lock_init(&hsr->seqnr_lock); /* Overflow soon to find bugs easier: */ hsr->sequence_nr = HSR_SEQNR_START; hsr->sup_sequence_nr = HSR_SUP_SEQNR_START; hsr->interlink_sequence_nr = HSR_SEQNR_START; timer_setup(&hsr->announce_timer, hsr_announce, 0); timer_setup(&hsr->prune_timer, hsr_prune_nodes, 0); timer_setup(&hsr->prune_proxy_timer, hsr_prune_proxy_nodes, 0); timer_setup(&hsr->announce_proxy_timer, hsr_proxy_announce, 0); ether_addr_copy(hsr->sup_multicast_addr, def_multicast_addr); hsr->sup_multicast_addr[ETH_ALEN - 1] = multicast_spec; hsr->prot_version = protocol_version; /* Make sure the 1st call to netif_carrier_on() gets through */ netif_carrier_off(hsr_dev); res = hsr_add_port(hsr, hsr_dev, HSR_PT_MASTER, extack); if (res) goto err_add_master; /* HSR forwarding offload supported in lower device? */ if ((slave[0]->features & NETIF_F_HW_HSR_FWD) && (slave[1]->features & NETIF_F_HW_HSR_FWD)) hsr->fwd_offloaded = true; res = register_netdevice(hsr_dev); if (res) goto err_unregister; unregister = true; res = hsr_add_port(hsr, slave[0], HSR_PT_SLAVE_A, extack); if (res) goto err_unregister; res = hsr_add_port(hsr, slave[1], HSR_PT_SLAVE_B, extack); if (res) goto err_unregister; if (interlink) { res = hsr_add_port(hsr, interlink, HSR_PT_INTERLINK, extack); if (res) goto err_unregister; hsr->redbox = true; ether_addr_copy(hsr->macaddress_redbox, interlink->dev_addr); mod_timer(&hsr->prune_proxy_timer, jiffies + msecs_to_jiffies(PRUNE_PROXY_PERIOD)); } hsr_debugfs_init(hsr, hsr_dev); mod_timer(&hsr->prune_timer, jiffies + msecs_to_jiffies(PRUNE_PERIOD)); return 0; err_unregister: hsr_del_ports(hsr); err_add_master: hsr_del_self_node(hsr); if (unregister) unregister_netdevice(hsr_dev); return res; } |
| 7 7 6 6 6 3 1 20 1 1 11 8 8 1 2 9 2 4 12 29 3 20 1 13 2 13 1 3 3 2 1 1 12 12 12 12 12 13 13 27 25 4 3 3 3 3 17 17 13 12 1 13 13 26 27 27 10 12 12 3 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 | /* AFS superblock handling * * Copyright (c) 2002, 2007, 2018 Red Hat, Inc. All rights reserved. * * This software may be freely redistributed under the terms of the * GNU General Public License. * * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. * * Authors: David Howells <dhowells@redhat.com> * David Woodhouse <dwmw2@infradead.org> * */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/mount.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/fs.h> #include <linux/pagemap.h> #include <linux/fs_parser.h> #include <linux/statfs.h> #include <linux/sched.h> #include <linux/nsproxy.h> #include <linux/magic.h> #include <net/net_namespace.h> #include "internal.h" static void afs_i_init_once(void *foo); static void afs_kill_super(struct super_block *sb); static struct inode *afs_alloc_inode(struct super_block *sb); static void afs_destroy_inode(struct inode *inode); static void afs_free_inode(struct inode *inode); static int afs_statfs(struct dentry *dentry, struct kstatfs *buf); static int afs_show_devname(struct seq_file *m, struct dentry *root); static int afs_show_options(struct seq_file *m, struct dentry *root); static int afs_init_fs_context(struct fs_context *fc); static const struct fs_parameter_spec afs_fs_parameters[]; struct file_system_type afs_fs_type = { .owner = THIS_MODULE, .name = "afs", .init_fs_context = afs_init_fs_context, .parameters = afs_fs_parameters, .kill_sb = afs_kill_super, .fs_flags = FS_RENAME_DOES_D_MOVE, }; MODULE_ALIAS_FS("afs"); int afs_net_id; static const struct super_operations afs_super_ops = { .statfs = afs_statfs, .alloc_inode = afs_alloc_inode, .write_inode = netfs_unpin_writeback, .drop_inode = afs_drop_inode, .destroy_inode = afs_destroy_inode, .free_inode = afs_free_inode, .evict_inode = afs_evict_inode, .show_devname = afs_show_devname, .show_options = afs_show_options, }; static struct kmem_cache *afs_inode_cachep; static atomic_t afs_count_active_inodes; enum afs_param { Opt_autocell, Opt_dyn, Opt_flock, Opt_source, }; static const struct constant_table afs_param_flock[] = { {"local", afs_flock_mode_local }, {"openafs", afs_flock_mode_openafs }, {"strict", afs_flock_mode_strict }, {"write", afs_flock_mode_write }, {} }; static const struct fs_parameter_spec afs_fs_parameters[] = { fsparam_flag ("autocell", Opt_autocell), fsparam_flag ("dyn", Opt_dyn), fsparam_enum ("flock", Opt_flock, afs_param_flock), fsparam_string("source", Opt_source), {} }; /* * initialise the filesystem */ int __init afs_fs_init(void) { int ret; _enter(""); /* create ourselves an inode cache */ atomic_set(&afs_count_active_inodes, 0); ret = -ENOMEM; afs_inode_cachep = kmem_cache_create("afs_inode_cache", sizeof(struct afs_vnode), 0, SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT, afs_i_init_once); if (!afs_inode_cachep) { printk(KERN_NOTICE "kAFS: Failed to allocate inode cache\n"); return ret; } /* now export our filesystem to lesser mortals */ ret = register_filesystem(&afs_fs_type); if (ret < 0) { kmem_cache_destroy(afs_inode_cachep); _leave(" = %d", ret); return ret; } _leave(" = 0"); return 0; } /* * clean up the filesystem */ void afs_fs_exit(void) { _enter(""); afs_mntpt_kill_timer(); unregister_filesystem(&afs_fs_type); if (atomic_read(&afs_count_active_inodes) != 0) { printk("kAFS: %d active inode objects still present\n", atomic_read(&afs_count_active_inodes)); BUG(); } /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(afs_inode_cachep); _leave(""); } /* * Display the mount device name in /proc/mounts. */ static int afs_show_devname(struct seq_file *m, struct dentry *root) { struct afs_super_info *as = AFS_FS_S(root->d_sb); struct afs_volume *volume = as->volume; struct afs_cell *cell = as->cell; const char *suf = ""; char pref = '%'; if (as->dyn_root) { seq_puts(m, "none"); return 0; } switch (volume->type) { case AFSVL_RWVOL: break; case AFSVL_ROVOL: pref = '#'; if (volume->type_force) suf = ".readonly"; break; case AFSVL_BACKVOL: pref = '#'; suf = ".backup"; break; } seq_printf(m, "%c%s:%s%s", pref, cell->name, volume->name, suf); return 0; } /* * Display the mount options in /proc/mounts. */ static int afs_show_options(struct seq_file *m, struct dentry *root) { struct afs_super_info *as = AFS_FS_S(root->d_sb); const char *p = NULL; if (as->dyn_root) seq_puts(m, ",dyn"); if (test_bit(AFS_VNODE_AUTOCELL, &AFS_FS_I(d_inode(root))->flags)) seq_puts(m, ",autocell"); switch (as->flock_mode) { case afs_flock_mode_unset: break; case afs_flock_mode_local: p = "local"; break; case afs_flock_mode_openafs: p = "openafs"; break; case afs_flock_mode_strict: p = "strict"; break; case afs_flock_mode_write: p = "write"; break; } if (p) seq_printf(m, ",flock=%s", p); return 0; } /* * Parse the source name to get cell name, volume name, volume type and R/W * selector. * * This can be one of the following: * "%[cell:]volume[.]" R/W volume * "#[cell:]volume[.]" R/O or R/W volume (R/O parent), * or R/W (R/W parent) volume * "%[cell:]volume.readonly" R/O volume * "#[cell:]volume.readonly" R/O volume * "%[cell:]volume.backup" Backup volume * "#[cell:]volume.backup" Backup volume */ static int afs_parse_source(struct fs_context *fc, struct fs_parameter *param) { struct afs_fs_context *ctx = fc->fs_private; struct afs_cell *cell; const char *cellname, *suffix, *name = param->string; int cellnamesz; _enter(",%s", name); if (fc->source) return invalf(fc, "kAFS: Multiple sources not supported"); if (!name) { printk(KERN_ERR "kAFS: no volume name specified\n"); return -EINVAL; } if ((name[0] != '%' && name[0] != '#') || !name[1]) { /* To use dynroot, we don't want to have to provide a source */ if (strcmp(name, "none") == 0) { ctx->no_cell = true; return 0; } printk(KERN_ERR "kAFS: unparsable volume name\n"); return -EINVAL; } /* determine the type of volume we're looking for */ if (name[0] == '%') { ctx->type = AFSVL_RWVOL; ctx->force = true; } name++; /* split the cell name out if there is one */ ctx->volname = strchr(name, ':'); if (ctx->volname) { cellname = name; cellnamesz = ctx->volname - name; ctx->volname++; } else { ctx->volname = name; cellname = NULL; cellnamesz = 0; } /* the volume type is further affected by a possible suffix */ suffix = strrchr(ctx->volname, '.'); if (suffix) { if (strcmp(suffix, ".readonly") == 0) { ctx->type = AFSVL_ROVOL; ctx->force = true; } else if (strcmp(suffix, ".backup") == 0) { ctx->type = AFSVL_BACKVOL; ctx->force = true; } else if (suffix[1] == 0) { } else { suffix = NULL; } } ctx->volnamesz = suffix ? suffix - ctx->volname : strlen(ctx->volname); _debug("cell %*.*s [%p]", cellnamesz, cellnamesz, cellname ?: "", ctx->cell); /* lookup the cell record */ if (cellname) { cell = afs_lookup_cell(ctx->net, cellname, cellnamesz, NULL, false); if (IS_ERR(cell)) { pr_err("kAFS: unable to lookup cell '%*.*s'\n", cellnamesz, cellnamesz, cellname ?: ""); return PTR_ERR(cell); } afs_unuse_cell(ctx->net, ctx->cell, afs_cell_trace_unuse_parse); afs_see_cell(cell, afs_cell_trace_see_source); ctx->cell = cell; } _debug("CELL:%s [%p] VOLUME:%*.*s SUFFIX:%s TYPE:%d%s", ctx->cell->name, ctx->cell, ctx->volnamesz, ctx->volnamesz, ctx->volname, suffix ?: "-", ctx->type, ctx->force ? " FORCE" : ""); fc->source = param->string; param->string = NULL; return 0; } /* * Parse a single mount parameter. */ static int afs_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct fs_parse_result result; struct afs_fs_context *ctx = fc->fs_private; int opt; opt = fs_parse(fc, afs_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_source: return afs_parse_source(fc, param); case Opt_autocell: ctx->autocell = true; break; case Opt_dyn: ctx->dyn_root = true; break; case Opt_flock: ctx->flock_mode = result.uint_32; break; default: return -EINVAL; } _leave(" = 0"); return 0; } /* * Validate the options, get the cell key and look up the volume. */ static int afs_validate_fc(struct fs_context *fc) { struct afs_fs_context *ctx = fc->fs_private; struct afs_volume *volume; struct afs_cell *cell; struct key *key; int ret; if (!ctx->dyn_root) { if (ctx->no_cell) { pr_warn("kAFS: Can only specify source 'none' with -o dyn\n"); return -EINVAL; } if (!ctx->cell) { pr_warn("kAFS: No cell specified\n"); return -EDESTADDRREQ; } reget_key: /* We try to do the mount securely. */ key = afs_request_key(ctx->cell); if (IS_ERR(key)) return PTR_ERR(key); ctx->key = key; if (ctx->volume) { afs_put_volume(ctx->volume, afs_volume_trace_put_validate_fc); ctx->volume = NULL; } if (test_bit(AFS_CELL_FL_CHECK_ALIAS, &ctx->cell->flags)) { ret = afs_cell_detect_alias(ctx->cell, key); if (ret < 0) return ret; if (ret == 1) { _debug("switch to alias"); key_put(ctx->key); ctx->key = NULL; cell = afs_use_cell(ctx->cell->alias_of, afs_cell_trace_use_fc_alias); afs_unuse_cell(ctx->net, ctx->cell, afs_cell_trace_unuse_fc); ctx->cell = cell; goto reget_key; } } volume = afs_create_volume(ctx); if (IS_ERR(volume)) return PTR_ERR(volume); ctx->volume = volume; if (volume->type != AFSVL_RWVOL) { ctx->flock_mode = afs_flock_mode_local; fc->sb_flags |= SB_RDONLY; } } return 0; } /* * check a superblock to see if it's the one we're looking for */ static int afs_test_super(struct super_block *sb, struct fs_context *fc) { struct afs_fs_context *ctx = fc->fs_private; struct afs_super_info *as = AFS_FS_S(sb); return (as->net_ns == fc->net_ns && as->volume && as->volume->vid == ctx->volume->vid && as->cell == ctx->cell && !as->dyn_root); } static int afs_dynroot_test_super(struct super_block *sb, struct fs_context *fc) { struct afs_super_info *as = AFS_FS_S(sb); return (as->net_ns == fc->net_ns && as->dyn_root); } static int afs_set_super(struct super_block *sb, struct fs_context *fc) { return set_anon_super(sb, NULL); } /* * fill in the superblock */ static int afs_fill_super(struct super_block *sb, struct afs_fs_context *ctx) { struct afs_super_info *as = AFS_FS_S(sb); struct inode *inode = NULL; int ret; _enter(""); /* fill in the superblock */ sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_magic = AFS_FS_MAGIC; sb->s_op = &afs_super_ops; if (!as->dyn_root) sb->s_xattr = afs_xattr_handlers; ret = super_setup_bdi(sb); if (ret) return ret; /* allocate the root inode and dentry */ if (as->dyn_root) { inode = afs_iget_pseudo_dir(sb, true); } else { sprintf(sb->s_id, "%llu", as->volume->vid); afs_activate_volume(as->volume); inode = afs_root_iget(sb, ctx->key); } if (IS_ERR(inode)) return PTR_ERR(inode); if (ctx->autocell || as->dyn_root) set_bit(AFS_VNODE_AUTOCELL, &AFS_FS_I(inode)->flags); ret = -ENOMEM; sb->s_root = d_make_root(inode); if (!sb->s_root) goto error; if (as->dyn_root) { sb->s_d_op = &afs_dynroot_dentry_operations; ret = afs_dynroot_populate(sb); if (ret < 0) goto error; } else { sb->s_d_op = &afs_fs_dentry_operations; rcu_assign_pointer(as->volume->sb, sb); } _leave(" = 0"); return 0; error: _leave(" = %d", ret); return ret; } static struct afs_super_info *afs_alloc_sbi(struct fs_context *fc) { struct afs_fs_context *ctx = fc->fs_private; struct afs_super_info *as; as = kzalloc(sizeof(struct afs_super_info), GFP_KERNEL); if (as) { as->net_ns = get_net(fc->net_ns); as->flock_mode = ctx->flock_mode; if (ctx->dyn_root) { as->dyn_root = true; } else { as->cell = afs_use_cell(ctx->cell, afs_cell_trace_use_sbi); as->volume = afs_get_volume(ctx->volume, afs_volume_trace_get_alloc_sbi); } } return as; } static void afs_destroy_sbi(struct afs_super_info *as) { if (as) { struct afs_net *net = afs_net(as->net_ns); afs_put_volume(as->volume, afs_volume_trace_put_destroy_sbi); afs_unuse_cell(net, as->cell, afs_cell_trace_unuse_sbi); put_net(as->net_ns); kfree(as); } } static void afs_kill_super(struct super_block *sb) { struct afs_super_info *as = AFS_FS_S(sb); if (as->dyn_root) afs_dynroot_depopulate(sb); /* Clear the callback interests (which will do ilookup5) before * deactivating the superblock. */ if (as->volume) rcu_assign_pointer(as->volume->sb, NULL); kill_anon_super(sb); if (as->volume) afs_deactivate_volume(as->volume); afs_destroy_sbi(as); } /* * Get an AFS superblock and root directory. */ static int afs_get_tree(struct fs_context *fc) { struct afs_fs_context *ctx = fc->fs_private; struct super_block *sb; struct afs_super_info *as; int ret; ret = afs_validate_fc(fc); if (ret) goto error; _enter(""); /* allocate a superblock info record */ ret = -ENOMEM; as = afs_alloc_sbi(fc); if (!as) goto error; fc->s_fs_info = as; /* allocate a deviceless superblock */ sb = sget_fc(fc, as->dyn_root ? afs_dynroot_test_super : afs_test_super, afs_set_super); if (IS_ERR(sb)) { ret = PTR_ERR(sb); goto error; } if (!sb->s_root) { /* initial superblock/root creation */ _debug("create"); ret = afs_fill_super(sb, ctx); if (ret < 0) goto error_sb; sb->s_flags |= SB_ACTIVE; } else { _debug("reuse"); ASSERTCMP(sb->s_flags, &, SB_ACTIVE); } fc->root = dget(sb->s_root); trace_afs_get_tree(as->cell, as->volume); _leave(" = 0 [%p]", sb); return 0; error_sb: deactivate_locked_super(sb); error: _leave(" = %d", ret); return ret; } static void afs_free_fc(struct fs_context *fc) { struct afs_fs_context *ctx = fc->fs_private; afs_destroy_sbi(fc->s_fs_info); afs_put_volume(ctx->volume, afs_volume_trace_put_free_fc); afs_unuse_cell(ctx->net, ctx->cell, afs_cell_trace_unuse_fc); key_put(ctx->key); kfree(ctx); } static const struct fs_context_operations afs_context_ops = { .free = afs_free_fc, .parse_param = afs_parse_param, .get_tree = afs_get_tree, }; /* * Set up the filesystem mount context. */ static int afs_init_fs_context(struct fs_context *fc) { struct afs_fs_context *ctx; struct afs_cell *cell; ctx = kzalloc(sizeof(struct afs_fs_context), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->type = AFSVL_ROVOL; ctx->net = afs_net(fc->net_ns); /* Default to the workstation cell. */ cell = afs_find_cell(ctx->net, NULL, 0, afs_cell_trace_use_fc); if (IS_ERR(cell)) cell = NULL; ctx->cell = cell; fc->fs_private = ctx; fc->ops = &afs_context_ops; return 0; } /* * Initialise an inode cache slab element prior to any use. Note that * afs_alloc_inode() *must* reset anything that could incorrectly leak from one * inode to another. */ static void afs_i_init_once(void *_vnode) { struct afs_vnode *vnode = _vnode; memset(vnode, 0, sizeof(*vnode)); inode_init_once(&vnode->netfs.inode); mutex_init(&vnode->io_lock); init_rwsem(&vnode->validate_lock); spin_lock_init(&vnode->wb_lock); spin_lock_init(&vnode->lock); INIT_LIST_HEAD(&vnode->wb_keys); INIT_LIST_HEAD(&vnode->pending_locks); INIT_LIST_HEAD(&vnode->granted_locks); INIT_DELAYED_WORK(&vnode->lock_work, afs_lock_work); INIT_LIST_HEAD(&vnode->cb_mmap_link); seqlock_init(&vnode->cb_lock); } /* * allocate an AFS inode struct from our slab cache */ static struct inode *afs_alloc_inode(struct super_block *sb) { struct afs_vnode *vnode; vnode = alloc_inode_sb(sb, afs_inode_cachep, GFP_KERNEL); if (!vnode) return NULL; atomic_inc(&afs_count_active_inodes); /* Reset anything that shouldn't leak from one inode to the next. */ memset(&vnode->fid, 0, sizeof(vnode->fid)); memset(&vnode->status, 0, sizeof(vnode->status)); afs_vnode_set_cache(vnode, NULL); vnode->volume = NULL; vnode->lock_key = NULL; vnode->permit_cache = NULL; vnode->flags = 1 << AFS_VNODE_UNSET; vnode->lock_state = AFS_VNODE_LOCK_NONE; init_rwsem(&vnode->rmdir_lock); INIT_WORK(&vnode->cb_work, afs_invalidate_mmap_work); _leave(" = %p", &vnode->netfs.inode); return &vnode->netfs.inode; } static void afs_free_inode(struct inode *inode) { kmem_cache_free(afs_inode_cachep, AFS_FS_I(inode)); } /* * destroy an AFS inode struct */ static void afs_destroy_inode(struct inode *inode) { struct afs_vnode *vnode = AFS_FS_I(inode); _enter("%p{%llx:%llu}", inode, vnode->fid.vid, vnode->fid.vnode); _debug("DESTROY INODE %p", inode); atomic_dec(&afs_count_active_inodes); } static void afs_get_volume_status_success(struct afs_operation *op) { struct afs_volume_status *vs = &op->volstatus.vs; struct kstatfs *buf = op->volstatus.buf; if (vs->max_quota == 0) buf->f_blocks = vs->part_max_blocks; else buf->f_blocks = vs->max_quota; if (buf->f_blocks > vs->blocks_in_use) buf->f_bavail = buf->f_bfree = buf->f_blocks - vs->blocks_in_use; } static const struct afs_operation_ops afs_get_volume_status_operation = { .issue_afs_rpc = afs_fs_get_volume_status, .issue_yfs_rpc = yfs_fs_get_volume_status, .success = afs_get_volume_status_success, }; /* * return information about an AFS volume */ static int afs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct afs_super_info *as = AFS_FS_S(dentry->d_sb); struct afs_operation *op; struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry)); buf->f_type = dentry->d_sb->s_magic; buf->f_bsize = AFS_BLOCK_SIZE; buf->f_namelen = AFSNAMEMAX - 1; if (as->dyn_root) { buf->f_blocks = 1; buf->f_bavail = 0; buf->f_bfree = 0; return 0; } op = afs_alloc_operation(NULL, as->volume); if (IS_ERR(op)) return PTR_ERR(op); afs_op_set_vnode(op, 0, vnode); op->nr_files = 1; op->volstatus.buf = buf; op->ops = &afs_get_volume_status_operation; return afs_do_sync_operation(op); } |
| 2 1 2 2 2 2 2 3 2 2 2 7 2 8 8 2 5 8 2 6 2 1 3 8 8 3 1 1 1 1 7 7 1 1 6 5 8 8 8 5 2 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 | /* * PCM Plug-In shared (kernel/library) code * Copyright (c) 1999 by Jaroslav Kysela <perex@perex.cz> * Copyright (c) 2000 by Abramo Bagnara <abramo@alsa-project.org> * * * This library is free software; you can redistribute it and/or modify * it under the terms of the GNU Library General Public License as * published by the Free Software Foundation; either version 2 of * the License, or (at your option) any later version. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU Library General Public License for more details. * * You should have received a copy of the GNU Library General Public * License along with this library; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA * */ #if 0 #define PLUGIN_DEBUG #endif #include <linux/slab.h> #include <linux/time.h> #include <linux/vmalloc.h> #include <sound/core.h> #include <sound/pcm.h> #include <sound/pcm_params.h> #include "pcm_plugin.h" #define snd_pcm_plug_first(plug) ((plug)->runtime->oss.plugin_first) #define snd_pcm_plug_last(plug) ((plug)->runtime->oss.plugin_last) /* * because some cards might have rates "very close", we ignore * all "resampling" requests within +-5% */ static int rate_match(unsigned int src_rate, unsigned int dst_rate) { unsigned int low = (src_rate * 95) / 100; unsigned int high = (src_rate * 105) / 100; return dst_rate >= low && dst_rate <= high; } static int snd_pcm_plugin_alloc(struct snd_pcm_plugin *plugin, snd_pcm_uframes_t frames) { struct snd_pcm_plugin_format *format; ssize_t width; size_t size; unsigned int channel; struct snd_pcm_plugin_channel *c; if (plugin->stream == SNDRV_PCM_STREAM_PLAYBACK) { format = &plugin->src_format; } else { format = &plugin->dst_format; } width = snd_pcm_format_physical_width(format->format); if (width < 0) return width; size = array3_size(frames, format->channels, width); /* check for too large period size once again */ if (size > 1024 * 1024) return -ENOMEM; if (snd_BUG_ON(size % 8)) return -ENXIO; size /= 8; if (plugin->buf_frames < frames) { kvfree(plugin->buf); plugin->buf = kvzalloc(size, GFP_KERNEL); plugin->buf_frames = frames; } if (!plugin->buf) { plugin->buf_frames = 0; return -ENOMEM; } c = plugin->buf_channels; if (plugin->access == SNDRV_PCM_ACCESS_RW_INTERLEAVED) { for (channel = 0; channel < format->channels; channel++, c++) { c->frames = frames; c->enabled = 1; c->wanted = 0; c->area.addr = plugin->buf; c->area.first = channel * width; c->area.step = format->channels * width; } } else if (plugin->access == SNDRV_PCM_ACCESS_RW_NONINTERLEAVED) { if (snd_BUG_ON(size % format->channels)) return -EINVAL; size /= format->channels; for (channel = 0; channel < format->channels; channel++, c++) { c->frames = frames; c->enabled = 1; c->wanted = 0; c->area.addr = plugin->buf + (channel * size); c->area.first = 0; c->area.step = width; } } else return -EINVAL; return 0; } int snd_pcm_plug_alloc(struct snd_pcm_substream *plug, snd_pcm_uframes_t frames) { int err; if (snd_BUG_ON(!snd_pcm_plug_first(plug))) return -ENXIO; if (snd_pcm_plug_stream(plug) == SNDRV_PCM_STREAM_PLAYBACK) { struct snd_pcm_plugin *plugin = snd_pcm_plug_first(plug); while (plugin->next) { if (plugin->dst_frames) frames = plugin->dst_frames(plugin, frames); if ((snd_pcm_sframes_t)frames <= 0) return -ENXIO; plugin = plugin->next; err = snd_pcm_plugin_alloc(plugin, frames); if (err < 0) return err; } } else { struct snd_pcm_plugin *plugin = snd_pcm_plug_last(plug); while (plugin->prev) { if (plugin->src_frames) frames = plugin->src_frames(plugin, frames); if ((snd_pcm_sframes_t)frames <= 0) return -ENXIO; plugin = plugin->prev; err = snd_pcm_plugin_alloc(plugin, frames); if (err < 0) return err; } } return 0; } snd_pcm_sframes_t snd_pcm_plugin_client_channels(struct snd_pcm_plugin *plugin, snd_pcm_uframes_t frames, struct snd_pcm_plugin_channel **channels) { *channels = plugin->buf_channels; return frames; } int snd_pcm_plugin_build(struct snd_pcm_substream *plug, const char *name, struct snd_pcm_plugin_format *src_format, struct snd_pcm_plugin_format *dst_format, size_t extra, struct snd_pcm_plugin **ret) { struct snd_pcm_plugin *plugin; unsigned int channels; if (snd_BUG_ON(!plug)) return -ENXIO; if (snd_BUG_ON(!src_format || !dst_format)) return -ENXIO; plugin = kzalloc(sizeof(*plugin) + extra, GFP_KERNEL); if (plugin == NULL) return -ENOMEM; plugin->name = name; plugin->plug = plug; plugin->stream = snd_pcm_plug_stream(plug); plugin->access = SNDRV_PCM_ACCESS_RW_INTERLEAVED; plugin->src_format = *src_format; plugin->src_width = snd_pcm_format_physical_width(src_format->format); snd_BUG_ON(plugin->src_width <= 0); plugin->dst_format = *dst_format; plugin->dst_width = snd_pcm_format_physical_width(dst_format->format); snd_BUG_ON(plugin->dst_width <= 0); if (plugin->stream == SNDRV_PCM_STREAM_PLAYBACK) channels = src_format->channels; else channels = dst_format->channels; plugin->buf_channels = kcalloc(channels, sizeof(*plugin->buf_channels), GFP_KERNEL); if (plugin->buf_channels == NULL) { snd_pcm_plugin_free(plugin); return -ENOMEM; } plugin->client_channels = snd_pcm_plugin_client_channels; *ret = plugin; return 0; } int snd_pcm_plugin_free(struct snd_pcm_plugin *plugin) { if (! plugin) return 0; if (plugin->private_free) plugin->private_free(plugin); kfree(plugin->buf_channels); kvfree(plugin->buf); kfree(plugin); return 0; } static snd_pcm_sframes_t calc_dst_frames(struct snd_pcm_substream *plug, snd_pcm_sframes_t frames, bool check_size) { struct snd_pcm_plugin *plugin, *plugin_next; plugin = snd_pcm_plug_first(plug); while (plugin && frames > 0) { plugin_next = plugin->next; if (check_size && plugin->buf_frames && frames > plugin->buf_frames) frames = plugin->buf_frames; if (plugin->dst_frames) { frames = plugin->dst_frames(plugin, frames); if (frames < 0) return frames; } plugin = plugin_next; } return frames; } static snd_pcm_sframes_t calc_src_frames(struct snd_pcm_substream *plug, snd_pcm_sframes_t frames, bool check_size) { struct snd_pcm_plugin *plugin, *plugin_prev; plugin = snd_pcm_plug_last(plug); while (plugin && frames > 0) { plugin_prev = plugin->prev; if (plugin->src_frames) { frames = plugin->src_frames(plugin, frames); if (frames < 0) return frames; } if (check_size && plugin->buf_frames && frames > plugin->buf_frames) frames = plugin->buf_frames; plugin = plugin_prev; } return frames; } snd_pcm_sframes_t snd_pcm_plug_client_size(struct snd_pcm_substream *plug, snd_pcm_uframes_t drv_frames) { if (snd_BUG_ON(!plug)) return -ENXIO; switch (snd_pcm_plug_stream(plug)) { case SNDRV_PCM_STREAM_PLAYBACK: return calc_src_frames(plug, drv_frames, false); case SNDRV_PCM_STREAM_CAPTURE: return calc_dst_frames(plug, drv_frames, false); default: snd_BUG(); return -EINVAL; } } snd_pcm_sframes_t snd_pcm_plug_slave_size(struct snd_pcm_substream *plug, snd_pcm_uframes_t clt_frames) { if (snd_BUG_ON(!plug)) return -ENXIO; switch (snd_pcm_plug_stream(plug)) { case SNDRV_PCM_STREAM_PLAYBACK: return calc_dst_frames(plug, clt_frames, false); case SNDRV_PCM_STREAM_CAPTURE: return calc_src_frames(plug, clt_frames, false); default: snd_BUG(); return -EINVAL; } } static int snd_pcm_plug_formats(const struct snd_mask *mask, snd_pcm_format_t format) { struct snd_mask formats = *mask; u64 linfmts = (SNDRV_PCM_FMTBIT_U8 | SNDRV_PCM_FMTBIT_S8 | SNDRV_PCM_FMTBIT_U16_LE | SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_U16_BE | SNDRV_PCM_FMTBIT_S16_BE | SNDRV_PCM_FMTBIT_U24_LE | SNDRV_PCM_FMTBIT_S24_LE | SNDRV_PCM_FMTBIT_U24_BE | SNDRV_PCM_FMTBIT_S24_BE | SNDRV_PCM_FMTBIT_U24_3LE | SNDRV_PCM_FMTBIT_S24_3LE | SNDRV_PCM_FMTBIT_U24_3BE | SNDRV_PCM_FMTBIT_S24_3BE | SNDRV_PCM_FMTBIT_U32_LE | SNDRV_PCM_FMTBIT_S32_LE | SNDRV_PCM_FMTBIT_U32_BE | SNDRV_PCM_FMTBIT_S32_BE); snd_mask_set(&formats, (__force int)SNDRV_PCM_FORMAT_MU_LAW); if (formats.bits[0] & lower_32_bits(linfmts)) formats.bits[0] |= lower_32_bits(linfmts); if (formats.bits[1] & upper_32_bits(linfmts)) formats.bits[1] |= upper_32_bits(linfmts); return snd_mask_test(&formats, (__force int)format); } static const snd_pcm_format_t preferred_formats[] = { SNDRV_PCM_FORMAT_S16_LE, SNDRV_PCM_FORMAT_S16_BE, SNDRV_PCM_FORMAT_U16_LE, SNDRV_PCM_FORMAT_U16_BE, SNDRV_PCM_FORMAT_S24_3LE, SNDRV_PCM_FORMAT_S24_3BE, SNDRV_PCM_FORMAT_U24_3LE, SNDRV_PCM_FORMAT_U24_3BE, SNDRV_PCM_FORMAT_S24_LE, SNDRV_PCM_FORMAT_S24_BE, SNDRV_PCM_FORMAT_U24_LE, SNDRV_PCM_FORMAT_U24_BE, SNDRV_PCM_FORMAT_S32_LE, SNDRV_PCM_FORMAT_S32_BE, SNDRV_PCM_FORMAT_U32_LE, SNDRV_PCM_FORMAT_U32_BE, SNDRV_PCM_FORMAT_S8, SNDRV_PCM_FORMAT_U8 }; snd_pcm_format_t snd_pcm_plug_slave_format(snd_pcm_format_t format, const struct snd_mask *format_mask) { int i; if (snd_mask_test(format_mask, (__force int)format)) return format; if (!snd_pcm_plug_formats(format_mask, format)) return (__force snd_pcm_format_t)-EINVAL; if (snd_pcm_format_linear(format)) { unsigned int width = snd_pcm_format_width(format); int unsignd = snd_pcm_format_unsigned(format) > 0; int big = snd_pcm_format_big_endian(format) > 0; unsigned int badness, best = -1; snd_pcm_format_t best_format = (__force snd_pcm_format_t)-1; for (i = 0; i < ARRAY_SIZE(preferred_formats); i++) { snd_pcm_format_t f = preferred_formats[i]; unsigned int w; if (!snd_mask_test(format_mask, (__force int)f)) continue; w = snd_pcm_format_width(f); if (w >= width) badness = w - width; else badness = width - w + 32; badness += snd_pcm_format_unsigned(f) != unsignd; badness += snd_pcm_format_big_endian(f) != big; if (badness < best) { best_format = f; best = badness; } } if ((__force int)best_format >= 0) return best_format; else return (__force snd_pcm_format_t)-EINVAL; } else { switch (format) { case SNDRV_PCM_FORMAT_MU_LAW: for (i = 0; i < ARRAY_SIZE(preferred_formats); ++i) { snd_pcm_format_t format1 = preferred_formats[i]; if (snd_mask_test(format_mask, (__force int)format1)) return format1; } fallthrough; default: return (__force snd_pcm_format_t)-EINVAL; } } } int snd_pcm_plug_format_plugins(struct snd_pcm_substream *plug, struct snd_pcm_hw_params *params, struct snd_pcm_hw_params *slave_params) { struct snd_pcm_plugin_format tmpformat; struct snd_pcm_plugin_format dstformat; struct snd_pcm_plugin_format srcformat; snd_pcm_access_t src_access, dst_access; struct snd_pcm_plugin *plugin = NULL; int err; int stream = snd_pcm_plug_stream(plug); int slave_interleaved = (params_channels(slave_params) == 1 || params_access(slave_params) == SNDRV_PCM_ACCESS_RW_INTERLEAVED); switch (stream) { case SNDRV_PCM_STREAM_PLAYBACK: dstformat.format = params_format(slave_params); dstformat.rate = params_rate(slave_params); dstformat.channels = params_channels(slave_params); srcformat.format = params_format(params); srcformat.rate = params_rate(params); srcformat.channels = params_channels(params); src_access = SNDRV_PCM_ACCESS_RW_INTERLEAVED; dst_access = (slave_interleaved ? SNDRV_PCM_ACCESS_RW_INTERLEAVED : SNDRV_PCM_ACCESS_RW_NONINTERLEAVED); break; case SNDRV_PCM_STREAM_CAPTURE: dstformat.format = params_format(params); dstformat.rate = params_rate(params); dstformat.channels = params_channels(params); srcformat.format = params_format(slave_params); srcformat.rate = params_rate(slave_params); srcformat.channels = params_channels(slave_params); src_access = (slave_interleaved ? SNDRV_PCM_ACCESS_RW_INTERLEAVED : SNDRV_PCM_ACCESS_RW_NONINTERLEAVED); dst_access = SNDRV_PCM_ACCESS_RW_INTERLEAVED; break; default: snd_BUG(); return -EINVAL; } tmpformat = srcformat; pdprintf("srcformat: format=%i, rate=%i, channels=%i\n", srcformat.format, srcformat.rate, srcformat.channels); pdprintf("dstformat: format=%i, rate=%i, channels=%i\n", dstformat.format, dstformat.rate, dstformat.channels); /* Format change (linearization) */ if (! rate_match(srcformat.rate, dstformat.rate) && ! snd_pcm_format_linear(srcformat.format)) { if (srcformat.format != SNDRV_PCM_FORMAT_MU_LAW) return -EINVAL; tmpformat.format = SNDRV_PCM_FORMAT_S16; err = snd_pcm_plugin_build_mulaw(plug, &srcformat, &tmpformat, &plugin); if (err < 0) return err; err = snd_pcm_plugin_append(plugin); if (err < 0) { snd_pcm_plugin_free(plugin); return err; } srcformat = tmpformat; src_access = dst_access; } /* channels reduction */ if (srcformat.channels > dstformat.channels) { tmpformat.channels = dstformat.channels; err = snd_pcm_plugin_build_route(plug, &srcformat, &tmpformat, &plugin); pdprintf("channels reduction: src=%i, dst=%i returns %i\n", srcformat.channels, tmpformat.channels, err); if (err < 0) return err; err = snd_pcm_plugin_append(plugin); if (err < 0) { snd_pcm_plugin_free(plugin); return err; } srcformat = tmpformat; src_access = dst_access; } /* rate resampling */ if (!rate_match(srcformat.rate, dstformat.rate)) { if (srcformat.format != SNDRV_PCM_FORMAT_S16) { /* convert to S16 for resampling */ tmpformat.format = SNDRV_PCM_FORMAT_S16; err = snd_pcm_plugin_build_linear(plug, &srcformat, &tmpformat, &plugin); if (err < 0) return err; err = snd_pcm_plugin_append(plugin); if (err < 0) { snd_pcm_plugin_free(plugin); return err; } srcformat = tmpformat; src_access = dst_access; } tmpformat.rate = dstformat.rate; err = snd_pcm_plugin_build_rate(plug, &srcformat, &tmpformat, &plugin); pdprintf("rate down resampling: src=%i, dst=%i returns %i\n", srcformat.rate, tmpformat.rate, err); if (err < 0) return err; err = snd_pcm_plugin_append(plugin); if (err < 0) { snd_pcm_plugin_free(plugin); return err; } srcformat = tmpformat; src_access = dst_access; } /* format change */ if (srcformat.format != dstformat.format) { tmpformat.format = dstformat.format; if (srcformat.format == SNDRV_PCM_FORMAT_MU_LAW || tmpformat.format == SNDRV_PCM_FORMAT_MU_LAW) { err = snd_pcm_plugin_build_mulaw(plug, &srcformat, &tmpformat, &plugin); } else if (snd_pcm_format_linear(srcformat.format) && snd_pcm_format_linear(tmpformat.format)) { err = snd_pcm_plugin_build_linear(plug, &srcformat, &tmpformat, &plugin); } else return -EINVAL; pdprintf("format change: src=%i, dst=%i returns %i\n", srcformat.format, tmpformat.format, err); if (err < 0) return err; err = snd_pcm_plugin_append(plugin); if (err < 0) { snd_pcm_plugin_free(plugin); return err; } srcformat = tmpformat; src_access = dst_access; } /* channels extension */ if (srcformat.channels < dstformat.channels) { tmpformat.channels = dstformat.channels; err = snd_pcm_plugin_build_route(plug, &srcformat, &tmpformat, &plugin); pdprintf("channels extension: src=%i, dst=%i returns %i\n", srcformat.channels, tmpformat.channels, err); if (err < 0) return err; err = snd_pcm_plugin_append(plugin); if (err < 0) { snd_pcm_plugin_free(plugin); return err; } srcformat = tmpformat; src_access = dst_access; } /* de-interleave */ if (src_access != dst_access) { err = snd_pcm_plugin_build_copy(plug, &srcformat, &tmpformat, &plugin); pdprintf("interleave change (copy: returns %i)\n", err); if (err < 0) return err; err = snd_pcm_plugin_append(plugin); if (err < 0) { snd_pcm_plugin_free(plugin); return err; } } return 0; } snd_pcm_sframes_t snd_pcm_plug_client_channels_buf(struct snd_pcm_substream *plug, char *buf, snd_pcm_uframes_t count, struct snd_pcm_plugin_channel **channels) { struct snd_pcm_plugin *plugin; struct snd_pcm_plugin_channel *v; struct snd_pcm_plugin_format *format; int width, nchannels, channel; int stream = snd_pcm_plug_stream(plug); if (snd_BUG_ON(!buf)) return -ENXIO; if (stream == SNDRV_PCM_STREAM_PLAYBACK) { plugin = snd_pcm_plug_first(plug); format = &plugin->src_format; } else { plugin = snd_pcm_plug_last(plug); format = &plugin->dst_format; } v = plugin->buf_channels; *channels = v; width = snd_pcm_format_physical_width(format->format); if (width < 0) return width; nchannels = format->channels; if (snd_BUG_ON(plugin->access != SNDRV_PCM_ACCESS_RW_INTERLEAVED && format->channels > 1)) return -ENXIO; for (channel = 0; channel < nchannels; channel++, v++) { v->frames = count; v->enabled = 1; v->wanted = (stream == SNDRV_PCM_STREAM_CAPTURE); v->area.addr = buf; v->area.first = channel * width; v->area.step = nchannels * width; } return count; } snd_pcm_sframes_t snd_pcm_plug_write_transfer(struct snd_pcm_substream *plug, struct snd_pcm_plugin_channel *src_channels, snd_pcm_uframes_t size) { struct snd_pcm_plugin *plugin, *next; struct snd_pcm_plugin_channel *dst_channels; int err; snd_pcm_sframes_t frames = size; plugin = snd_pcm_plug_first(plug); while (plugin) { if (frames <= 0) return frames; next = plugin->next; if (next) { snd_pcm_sframes_t frames1 = frames; if (plugin->dst_frames) { frames1 = plugin->dst_frames(plugin, frames); if (frames1 <= 0) return frames1; } err = next->client_channels(next, frames1, &dst_channels); if (err < 0) return err; if (err != frames1) { frames = err; if (plugin->src_frames) { frames = plugin->src_frames(plugin, frames1); if (frames <= 0) return frames; } } } else dst_channels = NULL; pdprintf("write plugin: %s, %li\n", plugin->name, frames); frames = plugin->transfer(plugin, src_channels, dst_channels, frames); if (frames < 0) return frames; src_channels = dst_channels; plugin = next; } return calc_src_frames(plug, frames, true); } snd_pcm_sframes_t snd_pcm_plug_read_transfer(struct snd_pcm_substream *plug, struct snd_pcm_plugin_channel *dst_channels_final, snd_pcm_uframes_t size) { struct snd_pcm_plugin *plugin, *next; struct snd_pcm_plugin_channel *src_channels, *dst_channels; snd_pcm_sframes_t frames = size; int err; frames = calc_src_frames(plug, frames, true); if (frames < 0) return frames; src_channels = NULL; plugin = snd_pcm_plug_first(plug); while (plugin && frames > 0) { next = plugin->next; if (next) { err = plugin->client_channels(plugin, frames, &dst_channels); if (err < 0) return err; frames = err; } else { dst_channels = dst_channels_final; } pdprintf("read plugin: %s, %li\n", plugin->name, frames); frames = plugin->transfer(plugin, src_channels, dst_channels, frames); if (frames < 0) return frames; plugin = next; src_channels = dst_channels; } return frames; } int snd_pcm_area_silence(const struct snd_pcm_channel_area *dst_area, size_t dst_offset, size_t samples, snd_pcm_format_t format) { /* FIXME: sub byte resolution and odd dst_offset */ unsigned char *dst; unsigned int dst_step; int width; const unsigned char *silence; if (!dst_area->addr) return 0; dst = dst_area->addr + (dst_area->first + dst_area->step * dst_offset) / 8; width = snd_pcm_format_physical_width(format); if (width <= 0) return -EINVAL; if (dst_area->step == (unsigned int) width && width >= 8) return snd_pcm_format_set_silence(format, dst, samples); silence = snd_pcm_format_silence_64(format); if (! silence) return -EINVAL; dst_step = dst_area->step / 8; if (width == 4) { /* Ima ADPCM */ int dstbit = dst_area->first % 8; int dstbit_step = dst_area->step % 8; while (samples-- > 0) { if (dstbit) *dst &= 0xf0; else *dst &= 0x0f; dst += dst_step; dstbit += dstbit_step; if (dstbit == 8) { dst++; dstbit = 0; } } } else { width /= 8; while (samples-- > 0) { memcpy(dst, silence, width); dst += dst_step; } } return 0; } int snd_pcm_area_copy(const struct snd_pcm_channel_area *src_area, size_t src_offset, const struct snd_pcm_channel_area *dst_area, size_t dst_offset, size_t samples, snd_pcm_format_t format) { /* FIXME: sub byte resolution and odd dst_offset */ char *src, *dst; int width; int src_step, dst_step; src = src_area->addr + (src_area->first + src_area->step * src_offset) / 8; if (!src_area->addr) return snd_pcm_area_silence(dst_area, dst_offset, samples, format); dst = dst_area->addr + (dst_area->first + dst_area->step * dst_offset) / 8; if (!dst_area->addr) return 0; width = snd_pcm_format_physical_width(format); if (width <= 0) return -EINVAL; if (src_area->step == (unsigned int) width && dst_area->step == (unsigned int) width && width >= 8) { size_t bytes = samples * width / 8; memcpy(dst, src, bytes); return 0; } src_step = src_area->step / 8; dst_step = dst_area->step / 8; if (width == 4) { /* Ima ADPCM */ int srcbit = src_area->first % 8; int srcbit_step = src_area->step % 8; int dstbit = dst_area->first % 8; int dstbit_step = dst_area->step % 8; while (samples-- > 0) { unsigned char srcval; if (srcbit) srcval = *src & 0x0f; else srcval = (*src & 0xf0) >> 4; if (dstbit) *dst = (*dst & 0xf0) | srcval; else *dst = (*dst & 0x0f) | (srcval << 4); src += src_step; srcbit += srcbit_step; if (srcbit == 8) { src++; srcbit = 0; } dst += dst_step; dstbit += dstbit_step; if (dstbit == 8) { dst++; dstbit = 0; } } } else { width /= 8; while (samples-- > 0) { memcpy(dst, src, width); src += src_step; dst += dst_step; } } return 0; } |
| 818 820 819 8 819 8 9762 9759 9768 819 816 702 225 816 819 8 7 8 8 3 8 1 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 9 8 8 8350 8344 8352 8350 8344 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include "cgroup-internal.h" #include <linux/sched/cputime.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/btf_ids.h> #include <trace/events/cgroup.h> static DEFINE_SPINLOCK(cgroup_rstat_lock); static DEFINE_PER_CPU(raw_spinlock_t, cgroup_rstat_cpu_lock); static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu); static struct cgroup_rstat_cpu *cgroup_rstat_cpu(struct cgroup *cgrp, int cpu) { return per_cpu_ptr(cgrp->rstat_cpu, cpu); } /* * Helper functions for rstat per CPU lock (cgroup_rstat_cpu_lock). * * This makes it easier to diagnose locking issues and contention in * production environments. The parameter @fast_path determine the * tracepoints being added, allowing us to diagnose "flush" related * operations without handling high-frequency fast-path "update" events. */ static __always_inline unsigned long _cgroup_rstat_cpu_lock(raw_spinlock_t *cpu_lock, int cpu, struct cgroup *cgrp, const bool fast_path) { unsigned long flags; bool contended; /* * The _irqsave() is needed because cgroup_rstat_lock is * spinlock_t which is a sleeping lock on PREEMPT_RT. Acquiring * this lock with the _irq() suffix only disables interrupts on * a non-PREEMPT_RT kernel. The raw_spinlock_t below disables * interrupts on both configurations. The _irqsave() ensures * that interrupts are always disabled and later restored. */ contended = !raw_spin_trylock_irqsave(cpu_lock, flags); if (contended) { if (fast_path) trace_cgroup_rstat_cpu_lock_contended_fastpath(cgrp, cpu, contended); else trace_cgroup_rstat_cpu_lock_contended(cgrp, cpu, contended); raw_spin_lock_irqsave(cpu_lock, flags); } if (fast_path) trace_cgroup_rstat_cpu_locked_fastpath(cgrp, cpu, contended); else trace_cgroup_rstat_cpu_locked(cgrp, cpu, contended); return flags; } static __always_inline void _cgroup_rstat_cpu_unlock(raw_spinlock_t *cpu_lock, int cpu, struct cgroup *cgrp, unsigned long flags, const bool fast_path) { if (fast_path) trace_cgroup_rstat_cpu_unlock_fastpath(cgrp, cpu, false); else trace_cgroup_rstat_cpu_unlock(cgrp, cpu, false); raw_spin_unlock_irqrestore(cpu_lock, flags); } /** * cgroup_rstat_updated - keep track of updated rstat_cpu * @cgrp: target cgroup * @cpu: cpu on which rstat_cpu was updated * * @cgrp's rstat_cpu on @cpu was updated. Put it on the parent's matching * rstat_cpu->updated_children list. See the comment on top of * cgroup_rstat_cpu definition for details. */ __bpf_kfunc void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) { raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu); unsigned long flags; /* * Speculative already-on-list test. This may race leading to * temporary inaccuracies, which is fine. * * Because @parent's updated_children is terminated with @parent * instead of NULL, we can tell whether @cgrp is on the list by * testing the next pointer for NULL. */ if (data_race(cgroup_rstat_cpu(cgrp, cpu)->updated_next)) return; flags = _cgroup_rstat_cpu_lock(cpu_lock, cpu, cgrp, true); /* put @cgrp and all ancestors on the corresponding updated lists */ while (true) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_rstat_cpu *prstatc; /* * Both additions and removals are bottom-up. If a cgroup * is already in the tree, all ancestors are. */ if (rstatc->updated_next) break; /* Root has no parent to link it to, but mark it busy */ if (!parent) { rstatc->updated_next = cgrp; break; } prstatc = cgroup_rstat_cpu(parent, cpu); rstatc->updated_next = prstatc->updated_children; prstatc->updated_children = cgrp; cgrp = parent; } _cgroup_rstat_cpu_unlock(cpu_lock, cpu, cgrp, flags, true); } /** * cgroup_rstat_push_children - push children cgroups into the given list * @head: current head of the list (= subtree root) * @child: first child of the root * @cpu: target cpu * Return: A new singly linked list of cgroups to be flush * * Iteratively traverse down the cgroup_rstat_cpu updated tree level by * level and push all the parents first before their next level children * into a singly linked list built from the tail backward like "pushing" * cgroups into a stack. The root is pushed by the caller. */ static struct cgroup *cgroup_rstat_push_children(struct cgroup *head, struct cgroup *child, int cpu) { struct cgroup *chead = child; /* Head of child cgroup level */ struct cgroup *ghead = NULL; /* Head of grandchild cgroup level */ struct cgroup *parent, *grandchild; struct cgroup_rstat_cpu *crstatc; child->rstat_flush_next = NULL; next_level: while (chead) { child = chead; chead = child->rstat_flush_next; parent = cgroup_parent(child); /* updated_next is parent cgroup terminated */ while (child != parent) { child->rstat_flush_next = head; head = child; crstatc = cgroup_rstat_cpu(child, cpu); grandchild = crstatc->updated_children; if (grandchild != child) { /* Push the grand child to the next level */ crstatc->updated_children = child; grandchild->rstat_flush_next = ghead; ghead = grandchild; } child = crstatc->updated_next; crstatc->updated_next = NULL; } } if (ghead) { chead = ghead; ghead = NULL; goto next_level; } return head; } /** * cgroup_rstat_updated_list - return a list of updated cgroups to be flushed * @root: root of the cgroup subtree to traverse * @cpu: target cpu * Return: A singly linked list of cgroups to be flushed * * Walks the updated rstat_cpu tree on @cpu from @root. During traversal, * each returned cgroup is unlinked from the updated tree. * * The only ordering guarantee is that, for a parent and a child pair * covered by a given traversal, the child is before its parent in * the list. * * Note that updated_children is self terminated and points to a list of * child cgroups if not empty. Whereas updated_next is like a sibling link * within the children list and terminated by the parent cgroup. An exception * here is the cgroup root whose updated_next can be self terminated. */ static struct cgroup *cgroup_rstat_updated_list(struct cgroup *root, int cpu) { raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu); struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(root, cpu); struct cgroup *head = NULL, *parent, *child; unsigned long flags; flags = _cgroup_rstat_cpu_lock(cpu_lock, cpu, root, false); /* Return NULL if this subtree is not on-list */ if (!rstatc->updated_next) goto unlock_ret; /* * Unlink @root from its parent. As the updated_children list is * singly linked, we have to walk it to find the removal point. */ parent = cgroup_parent(root); if (parent) { struct cgroup_rstat_cpu *prstatc; struct cgroup **nextp; prstatc = cgroup_rstat_cpu(parent, cpu); nextp = &prstatc->updated_children; while (*nextp != root) { struct cgroup_rstat_cpu *nrstatc; nrstatc = cgroup_rstat_cpu(*nextp, cpu); WARN_ON_ONCE(*nextp == parent); nextp = &nrstatc->updated_next; } *nextp = rstatc->updated_next; } rstatc->updated_next = NULL; /* Push @root to the list first before pushing the children */ head = root; root->rstat_flush_next = NULL; child = rstatc->updated_children; rstatc->updated_children = root; if (child != root) head = cgroup_rstat_push_children(head, child, cpu); unlock_ret: _cgroup_rstat_cpu_unlock(cpu_lock, cpu, root, flags, false); return head; } /* * A hook for bpf stat collectors to attach to and flush their stats. * Together with providing bpf kfuncs for cgroup_rstat_updated() and * cgroup_rstat_flush(), this enables a complete workflow where bpf progs that * collect cgroup stats can integrate with rstat for efficient flushing. * * A static noinline declaration here could cause the compiler to optimize away * the function. A global noinline declaration will keep the definition, but may * optimize away the callsite. Therefore, __weak is needed to ensure that the * call is still emitted, by telling the compiler that we don't know what the * function might eventually be. */ __bpf_hook_start(); __weak noinline void bpf_rstat_flush(struct cgroup *cgrp, struct cgroup *parent, int cpu) { } __bpf_hook_end(); /* * Helper functions for locking cgroup_rstat_lock. * * This makes it easier to diagnose locking issues and contention in * production environments. The parameter @cpu_in_loop indicate lock * was released and re-taken when collection data from the CPUs. The * value -1 is used when obtaining the main lock else this is the CPU * number processed last. */ static inline void __cgroup_rstat_lock(struct cgroup *cgrp, int cpu_in_loop) __acquires(&cgroup_rstat_lock) { bool contended; contended = !spin_trylock_irq(&cgroup_rstat_lock); if (contended) { trace_cgroup_rstat_lock_contended(cgrp, cpu_in_loop, contended); spin_lock_irq(&cgroup_rstat_lock); } trace_cgroup_rstat_locked(cgrp, cpu_in_loop, contended); } static inline void __cgroup_rstat_unlock(struct cgroup *cgrp, int cpu_in_loop) __releases(&cgroup_rstat_lock) { trace_cgroup_rstat_unlock(cgrp, cpu_in_loop, false); spin_unlock_irq(&cgroup_rstat_lock); } /* see cgroup_rstat_flush() */ static void cgroup_rstat_flush_locked(struct cgroup *cgrp) __releases(&cgroup_rstat_lock) __acquires(&cgroup_rstat_lock) { int cpu; lockdep_assert_held(&cgroup_rstat_lock); for_each_possible_cpu(cpu) { struct cgroup *pos = cgroup_rstat_updated_list(cgrp, cpu); for (; pos; pos = pos->rstat_flush_next) { struct cgroup_subsys_state *css; cgroup_base_stat_flush(pos, cpu); bpf_rstat_flush(pos, cgroup_parent(pos), cpu); rcu_read_lock(); list_for_each_entry_rcu(css, &pos->rstat_css_list, rstat_css_node) css->ss->css_rstat_flush(css, cpu); rcu_read_unlock(); } /* play nice and yield if necessary */ if (need_resched() || spin_needbreak(&cgroup_rstat_lock)) { __cgroup_rstat_unlock(cgrp, cpu); if (!cond_resched()) cpu_relax(); __cgroup_rstat_lock(cgrp, cpu); } } } /** * cgroup_rstat_flush - flush stats in @cgrp's subtree * @cgrp: target cgroup * * Collect all per-cpu stats in @cgrp's subtree into the global counters * and propagate them upwards. After this function returns, all cgroups in * the subtree have up-to-date ->stat. * * This also gets all cgroups in the subtree including @cgrp off the * ->updated_children lists. * * This function may block. */ __bpf_kfunc void cgroup_rstat_flush(struct cgroup *cgrp) { might_sleep(); __cgroup_rstat_lock(cgrp, -1); cgroup_rstat_flush_locked(cgrp); __cgroup_rstat_unlock(cgrp, -1); } /** * cgroup_rstat_flush_hold - flush stats in @cgrp's subtree and hold * @cgrp: target cgroup * * Flush stats in @cgrp's subtree and prevent further flushes. Must be * paired with cgroup_rstat_flush_release(). * * This function may block. */ void cgroup_rstat_flush_hold(struct cgroup *cgrp) __acquires(&cgroup_rstat_lock) { might_sleep(); __cgroup_rstat_lock(cgrp, -1); cgroup_rstat_flush_locked(cgrp); } /** * cgroup_rstat_flush_release - release cgroup_rstat_flush_hold() * @cgrp: cgroup used by tracepoint */ void cgroup_rstat_flush_release(struct cgroup *cgrp) __releases(&cgroup_rstat_lock) { __cgroup_rstat_unlock(cgrp, -1); } int cgroup_rstat_init(struct cgroup *cgrp) { int cpu; /* the root cgrp has rstat_cpu preallocated */ if (!cgrp->rstat_cpu) { cgrp->rstat_cpu = alloc_percpu(struct cgroup_rstat_cpu); if (!cgrp->rstat_cpu) return -ENOMEM; } /* ->updated_children list is self terminated */ for_each_possible_cpu(cpu) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); rstatc->updated_children = cgrp; u64_stats_init(&rstatc->bsync); } return 0; } void cgroup_rstat_exit(struct cgroup *cgrp) { int cpu; cgroup_rstat_flush(cgrp); /* sanity check */ for_each_possible_cpu(cpu) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); if (WARN_ON_ONCE(rstatc->updated_children != cgrp) || WARN_ON_ONCE(rstatc->updated_next)) return; } free_percpu(cgrp->rstat_cpu); cgrp->rstat_cpu = NULL; } void __init cgroup_rstat_boot(void) { int cpu; for_each_possible_cpu(cpu) raw_spin_lock_init(per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu)); } /* * Functions for cgroup basic resource statistics implemented on top of * rstat. */ static void cgroup_base_stat_add(struct cgroup_base_stat *dst_bstat, struct cgroup_base_stat *src_bstat) { dst_bstat->cputime.utime += src_bstat->cputime.utime; dst_bstat->cputime.stime += src_bstat->cputime.stime; dst_bstat->cputime.sum_exec_runtime += src_bstat->cputime.sum_exec_runtime; #ifdef CONFIG_SCHED_CORE dst_bstat->forceidle_sum += src_bstat->forceidle_sum; #endif } static void cgroup_base_stat_sub(struct cgroup_base_stat *dst_bstat, struct cgroup_base_stat *src_bstat) { dst_bstat->cputime.utime -= src_bstat->cputime.utime; dst_bstat->cputime.stime -= src_bstat->cputime.stime; dst_bstat->cputime.sum_exec_runtime -= src_bstat->cputime.sum_exec_runtime; #ifdef CONFIG_SCHED_CORE dst_bstat->forceidle_sum -= src_bstat->forceidle_sum; #endif } static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_rstat_cpu *prstatc; struct cgroup_base_stat delta; unsigned seq; /* Root-level stats are sourced from system-wide CPU stats */ if (!parent) return; /* fetch the current per-cpu values */ do { seq = __u64_stats_fetch_begin(&rstatc->bsync); delta = rstatc->bstat; } while (__u64_stats_fetch_retry(&rstatc->bsync, seq)); /* propagate per-cpu delta to cgroup and per-cpu global statistics */ cgroup_base_stat_sub(&delta, &rstatc->last_bstat); cgroup_base_stat_add(&cgrp->bstat, &delta); cgroup_base_stat_add(&rstatc->last_bstat, &delta); cgroup_base_stat_add(&rstatc->subtree_bstat, &delta); /* propagate cgroup and per-cpu global delta to parent (unless that's root) */ if (cgroup_parent(parent)) { delta = cgrp->bstat; cgroup_base_stat_sub(&delta, &cgrp->last_bstat); cgroup_base_stat_add(&parent->bstat, &delta); cgroup_base_stat_add(&cgrp->last_bstat, &delta); delta = rstatc->subtree_bstat; prstatc = cgroup_rstat_cpu(parent, cpu); cgroup_base_stat_sub(&delta, &rstatc->last_subtree_bstat); cgroup_base_stat_add(&prstatc->subtree_bstat, &delta); cgroup_base_stat_add(&rstatc->last_subtree_bstat, &delta); } } static struct cgroup_rstat_cpu * cgroup_base_stat_cputime_account_begin(struct cgroup *cgrp, unsigned long *flags) { struct cgroup_rstat_cpu *rstatc; rstatc = get_cpu_ptr(cgrp->rstat_cpu); *flags = u64_stats_update_begin_irqsave(&rstatc->bsync); return rstatc; } static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp, struct cgroup_rstat_cpu *rstatc, unsigned long flags) { u64_stats_update_end_irqrestore(&rstatc->bsync, flags); cgroup_rstat_updated(cgrp, smp_processor_id()); put_cpu_ptr(rstatc); } void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec) { struct cgroup_rstat_cpu *rstatc; unsigned long flags; rstatc = cgroup_base_stat_cputime_account_begin(cgrp, &flags); rstatc->bstat.cputime.sum_exec_runtime += delta_exec; cgroup_base_stat_cputime_account_end(cgrp, rstatc, flags); } void __cgroup_account_cputime_field(struct cgroup *cgrp, enum cpu_usage_stat index, u64 delta_exec) { struct cgroup_rstat_cpu *rstatc; unsigned long flags; rstatc = cgroup_base_stat_cputime_account_begin(cgrp, &flags); switch (index) { case CPUTIME_USER: case CPUTIME_NICE: rstatc->bstat.cputime.utime += delta_exec; break; case CPUTIME_SYSTEM: case CPUTIME_IRQ: case CPUTIME_SOFTIRQ: rstatc->bstat.cputime.stime += delta_exec; break; #ifdef CONFIG_SCHED_CORE case CPUTIME_FORCEIDLE: rstatc->bstat.forceidle_sum += delta_exec; break; #endif default: break; } cgroup_base_stat_cputime_account_end(cgrp, rstatc, flags); } /* * compute the cputime for the root cgroup by getting the per cpu data * at a global level, then categorizing the fields in a manner consistent * with how it is done by __cgroup_account_cputime_field for each bit of * cpu time attributed to a cgroup. */ static void root_cgroup_cputime(struct cgroup_base_stat *bstat) { struct task_cputime *cputime = &bstat->cputime; int i; memset(bstat, 0, sizeof(*bstat)); for_each_possible_cpu(i) { struct kernel_cpustat kcpustat; u64 *cpustat = kcpustat.cpustat; u64 user = 0; u64 sys = 0; kcpustat_cpu_fetch(&kcpustat, i); user += cpustat[CPUTIME_USER]; user += cpustat[CPUTIME_NICE]; cputime->utime += user; sys += cpustat[CPUTIME_SYSTEM]; sys += cpustat[CPUTIME_IRQ]; sys += cpustat[CPUTIME_SOFTIRQ]; cputime->stime += sys; cputime->sum_exec_runtime += user; cputime->sum_exec_runtime += sys; cputime->sum_exec_runtime += cpustat[CPUTIME_STEAL]; #ifdef CONFIG_SCHED_CORE bstat->forceidle_sum += cpustat[CPUTIME_FORCEIDLE]; #endif } } static void cgroup_force_idle_show(struct seq_file *seq, struct cgroup_base_stat *bstat) { #ifdef CONFIG_SCHED_CORE u64 forceidle_time = bstat->forceidle_sum; do_div(forceidle_time, NSEC_PER_USEC); seq_printf(seq, "core_sched.force_idle_usec %llu\n", forceidle_time); #endif } void cgroup_base_stat_cputime_show(struct seq_file *seq) { struct cgroup *cgrp = seq_css(seq)->cgroup; u64 usage, utime, stime; if (cgroup_parent(cgrp)) { cgroup_rstat_flush_hold(cgrp); usage = cgrp->bstat.cputime.sum_exec_runtime; cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime, &utime, &stime); cgroup_rstat_flush_release(cgrp); } else { /* cgrp->bstat of root is not actually used, reuse it */ root_cgroup_cputime(&cgrp->bstat); usage = cgrp->bstat.cputime.sum_exec_runtime; utime = cgrp->bstat.cputime.utime; stime = cgrp->bstat.cputime.stime; } do_div(usage, NSEC_PER_USEC); do_div(utime, NSEC_PER_USEC); do_div(stime, NSEC_PER_USEC); seq_printf(seq, "usage_usec %llu\n" "user_usec %llu\n" "system_usec %llu\n", usage, utime, stime); cgroup_force_idle_show(seq, &cgrp->bstat); } /* Add bpf kfuncs for cgroup_rstat_updated() and cgroup_rstat_flush() */ BTF_KFUNCS_START(bpf_rstat_kfunc_ids) BTF_ID_FLAGS(func, cgroup_rstat_updated) BTF_ID_FLAGS(func, cgroup_rstat_flush, KF_SLEEPABLE) BTF_KFUNCS_END(bpf_rstat_kfunc_ids) static const struct btf_kfunc_id_set bpf_rstat_kfunc_set = { .owner = THIS_MODULE, .set = &bpf_rstat_kfunc_ids, }; static int __init bpf_rstat_kfunc_init(void) { return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_rstat_kfunc_set); } late_initcall(bpf_rstat_kfunc_init); |
| 30 2 28 28 28 28 30 28 2 28 28 17 27 28 1 1 1 1 1 28 28 27 21 21 21 21 20 20 27 27 27 27 27 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/sched.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/completion.h> #include <linux/buffer_head.h> #include <linux/kallsyms.h> #include <linux/gfs2_ondisk.h> #include "gfs2.h" #include "incore.h" #include "glock.h" #include "inode.h" #include "log.h" #include "lops.h" #include "meta_io.h" #include "trans.h" #include "util.h" #include "trace_gfs2.h" static void gfs2_print_trans(struct gfs2_sbd *sdp, const struct gfs2_trans *tr) { fs_warn(sdp, "Transaction created at: %pSR\n", (void *)tr->tr_ip); fs_warn(sdp, "blocks=%u revokes=%u reserved=%u touched=%u\n", tr->tr_blocks, tr->tr_revokes, tr->tr_reserved, test_bit(TR_TOUCHED, &tr->tr_flags)); fs_warn(sdp, "Buf %u/%u Databuf %u/%u Revoke %u\n", tr->tr_num_buf_new, tr->tr_num_buf_rm, tr->tr_num_databuf_new, tr->tr_num_databuf_rm, tr->tr_num_revoke); } int __gfs2_trans_begin(struct gfs2_trans *tr, struct gfs2_sbd *sdp, unsigned int blocks, unsigned int revokes, unsigned long ip) { unsigned int extra_revokes; if (current->journal_info) { gfs2_print_trans(sdp, current->journal_info); BUG(); } BUG_ON(blocks == 0 && revokes == 0); if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) return -EROFS; tr->tr_ip = ip; tr->tr_blocks = blocks; tr->tr_revokes = revokes; tr->tr_reserved = GFS2_LOG_FLUSH_MIN_BLOCKS; if (blocks) { /* * The reserved blocks are either used for data or metadata. * We can have mixed data and metadata, each with its own log * descriptor block; see calc_reserved(). */ tr->tr_reserved += blocks + 1 + DIV_ROUND_UP(blocks - 1, databuf_limit(sdp)); } INIT_LIST_HEAD(&tr->tr_databuf); INIT_LIST_HEAD(&tr->tr_buf); INIT_LIST_HEAD(&tr->tr_list); INIT_LIST_HEAD(&tr->tr_ail1_list); INIT_LIST_HEAD(&tr->tr_ail2_list); if (gfs2_assert_warn(sdp, tr->tr_reserved <= sdp->sd_jdesc->jd_blocks)) return -EINVAL; sb_start_intwrite(sdp->sd_vfs); /* * Try the reservations under sd_log_flush_lock to prevent log flushes * from creating inconsistencies between the number of allocated and * reserved revokes. If that fails, do a full-block allocation outside * of the lock to avoid stalling log flushes. Then, allot the * appropriate number of blocks to revokes, use as many revokes locally * as needed, and "release" the surplus into the revokes pool. */ down_read(&sdp->sd_log_flush_lock); if (gfs2_log_try_reserve(sdp, tr, &extra_revokes)) goto reserved; up_read(&sdp->sd_log_flush_lock); gfs2_log_reserve(sdp, tr, &extra_revokes); down_read(&sdp->sd_log_flush_lock); reserved: gfs2_log_release_revokes(sdp, extra_revokes); if (unlikely(!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))) { gfs2_log_release_revokes(sdp, tr->tr_revokes); up_read(&sdp->sd_log_flush_lock); gfs2_log_release(sdp, tr->tr_reserved); sb_end_intwrite(sdp->sd_vfs); return -EROFS; } current->journal_info = tr; return 0; } int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks, unsigned int revokes) { struct gfs2_trans *tr; int error; tr = kmem_cache_zalloc(gfs2_trans_cachep, GFP_NOFS); if (!tr) return -ENOMEM; error = __gfs2_trans_begin(tr, sdp, blocks, revokes, _RET_IP_); if (error) kmem_cache_free(gfs2_trans_cachep, tr); return error; } void gfs2_trans_end(struct gfs2_sbd *sdp) { struct gfs2_trans *tr = current->journal_info; s64 nbuf; current->journal_info = NULL; if (!test_bit(TR_TOUCHED, &tr->tr_flags)) { gfs2_log_release_revokes(sdp, tr->tr_revokes); up_read(&sdp->sd_log_flush_lock); gfs2_log_release(sdp, tr->tr_reserved); if (!test_bit(TR_ONSTACK, &tr->tr_flags)) gfs2_trans_free(sdp, tr); sb_end_intwrite(sdp->sd_vfs); return; } gfs2_log_release_revokes(sdp, tr->tr_revokes - tr->tr_num_revoke); nbuf = tr->tr_num_buf_new + tr->tr_num_databuf_new; nbuf -= tr->tr_num_buf_rm; nbuf -= tr->tr_num_databuf_rm; if (gfs2_assert_withdraw(sdp, nbuf <= tr->tr_blocks) || gfs2_assert_withdraw(sdp, tr->tr_num_revoke <= tr->tr_revokes)) gfs2_print_trans(sdp, tr); gfs2_log_commit(sdp, tr); if (!test_bit(TR_ONSTACK, &tr->tr_flags) && !test_bit(TR_ATTACHED, &tr->tr_flags)) gfs2_trans_free(sdp, tr); up_read(&sdp->sd_log_flush_lock); if (sdp->sd_vfs->s_flags & SB_SYNCHRONOUS) gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL | GFS2_LFC_TRANS_END); sb_end_intwrite(sdp->sd_vfs); } static struct gfs2_bufdata *gfs2_alloc_bufdata(struct gfs2_glock *gl, struct buffer_head *bh) { struct gfs2_bufdata *bd; bd = kmem_cache_zalloc(gfs2_bufdata_cachep, GFP_NOFS | __GFP_NOFAIL); bd->bd_bh = bh; bd->bd_gl = gl; INIT_LIST_HEAD(&bd->bd_list); INIT_LIST_HEAD(&bd->bd_ail_st_list); INIT_LIST_HEAD(&bd->bd_ail_gl_list); bh->b_private = bd; return bd; } /** * gfs2_trans_add_data - Add a databuf to the transaction. * @gl: The inode glock associated with the buffer * @bh: The buffer to add * * This is used in journaled data mode. * We need to journal the data block in the same way as metadata in * the functions above. The difference is that here we have a tag * which is two __be64's being the block number (as per meta data) * and a flag which says whether the data block needs escaping or * not. This means we need a new log entry for each 251 or so data * blocks, which isn't an enormous overhead but twice as much as * for normal metadata blocks. */ void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh) { struct gfs2_trans *tr = current->journal_info; struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; struct gfs2_bufdata *bd; lock_buffer(bh); if (buffer_pinned(bh)) { set_bit(TR_TOUCHED, &tr->tr_flags); goto out; } gfs2_log_lock(sdp); bd = bh->b_private; if (bd == NULL) { gfs2_log_unlock(sdp); unlock_buffer(bh); if (bh->b_private == NULL) bd = gfs2_alloc_bufdata(gl, bh); else bd = bh->b_private; lock_buffer(bh); gfs2_log_lock(sdp); } gfs2_assert(sdp, bd->bd_gl == gl); set_bit(TR_TOUCHED, &tr->tr_flags); if (list_empty(&bd->bd_list)) { set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags); set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags); gfs2_pin(sdp, bd->bd_bh); tr->tr_num_databuf_new++; list_add_tail(&bd->bd_list, &tr->tr_databuf); } gfs2_log_unlock(sdp); out: unlock_buffer(bh); } void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh) { struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; struct super_block *sb = sdp->sd_vfs; struct gfs2_bufdata *bd; struct gfs2_meta_header *mh; struct gfs2_trans *tr = current->journal_info; bool withdraw = false; lock_buffer(bh); if (buffer_pinned(bh)) { set_bit(TR_TOUCHED, &tr->tr_flags); goto out; } gfs2_log_lock(sdp); bd = bh->b_private; if (bd == NULL) { gfs2_log_unlock(sdp); unlock_buffer(bh); lock_page(bh->b_page); if (bh->b_private == NULL) bd = gfs2_alloc_bufdata(gl, bh); else bd = bh->b_private; unlock_page(bh->b_page); lock_buffer(bh); gfs2_log_lock(sdp); } gfs2_assert(sdp, bd->bd_gl == gl); set_bit(TR_TOUCHED, &tr->tr_flags); if (!list_empty(&bd->bd_list)) goto out_unlock; set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags); set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags); mh = (struct gfs2_meta_header *)bd->bd_bh->b_data; if (unlikely(mh->mh_magic != cpu_to_be32(GFS2_MAGIC))) { fs_err(sdp, "Attempting to add uninitialised block to " "journal (inplace block=%lld)\n", (unsigned long long)bd->bd_bh->b_blocknr); BUG(); } if (gfs2_withdrawing_or_withdrawn(sdp)) { fs_info(sdp, "GFS2:adding buf while withdrawn! 0x%llx\n", (unsigned long long)bd->bd_bh->b_blocknr); goto out_unlock; } if (unlikely(sb->s_writers.frozen == SB_FREEZE_COMPLETE)) { fs_info(sdp, "GFS2:adding buf while frozen\n"); withdraw = true; goto out_unlock; } gfs2_pin(sdp, bd->bd_bh); mh->__pad0 = cpu_to_be64(0); mh->mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid); list_add(&bd->bd_list, &tr->tr_buf); tr->tr_num_buf_new++; out_unlock: gfs2_log_unlock(sdp); if (withdraw) gfs2_assert_withdraw(sdp, 0); out: unlock_buffer(bh); } void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) { struct gfs2_trans *tr = current->journal_info; BUG_ON(!list_empty(&bd->bd_list)); gfs2_add_revoke(sdp, bd); set_bit(TR_TOUCHED, &tr->tr_flags); tr->tr_num_revoke++; } void gfs2_trans_remove_revoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len) { struct gfs2_bufdata *bd, *tmp; unsigned int n = len; gfs2_log_lock(sdp); list_for_each_entry_safe(bd, tmp, &sdp->sd_log_revokes, bd_list) { if ((bd->bd_blkno >= blkno) && (bd->bd_blkno < (blkno + len))) { list_del_init(&bd->bd_list); gfs2_assert_withdraw(sdp, sdp->sd_log_num_revoke); sdp->sd_log_num_revoke--; if (bd->bd_gl) gfs2_glock_remove_revoke(bd->bd_gl); kmem_cache_free(gfs2_bufdata_cachep, bd); gfs2_log_release_revokes(sdp, 1); if (--n == 0) break; } } gfs2_log_unlock(sdp); } void gfs2_trans_free(struct gfs2_sbd *sdp, struct gfs2_trans *tr) { if (tr == NULL) return; gfs2_assert_warn(sdp, list_empty(&tr->tr_ail1_list)); gfs2_assert_warn(sdp, list_empty(&tr->tr_ail2_list)); gfs2_assert_warn(sdp, list_empty(&tr->tr_databuf)); gfs2_assert_warn(sdp, list_empty(&tr->tr_buf)); kmem_cache_free(gfs2_trans_cachep, tr); } |
| 15 15 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MEMREMAP_H_ #define _LINUX_MEMREMAP_H_ #include <linux/mmzone.h> #include <linux/range.h> #include <linux/ioport.h> #include <linux/percpu-refcount.h> struct resource; struct device; /** * struct vmem_altmap - pre-allocated storage for vmemmap_populate * @base_pfn: base of the entire dev_pagemap mapping * @reserve: pages mapped, but reserved for driver use (relative to @base) * @free: free pages set aside in the mapping for memmap storage * @align: pages reserved to meet allocation alignments * @alloc: track pages consumed, private to vmemmap_populate() */ struct vmem_altmap { unsigned long base_pfn; const unsigned long end_pfn; const unsigned long reserve; unsigned long free; unsigned long align; unsigned long alloc; bool inaccessible; }; /* * Specialize ZONE_DEVICE memory into multiple types each has a different * usage. * * MEMORY_DEVICE_PRIVATE: * Device memory that is not directly addressable by the CPU: CPU can neither * read nor write private memory. In this case, we do still have struct pages * backing the device memory. Doing so simplifies the implementation, but it is * important to remember that there are certain points at which the struct page * must be treated as an opaque object, rather than a "normal" struct page. * * A more complete discussion of unaddressable memory may be found in * include/linux/hmm.h and Documentation/mm/hmm.rst. * * MEMORY_DEVICE_COHERENT: * Device memory that is cache coherent from device and CPU point of view. This * is used on platforms that have an advanced system bus (like CAPI or CXL). A * driver can hotplug the device memory using ZONE_DEVICE and with that memory * type. Any page of a process can be migrated to such memory. However no one * should be allowed to pin such memory so that it can always be evicted. * * MEMORY_DEVICE_FS_DAX: * Host memory that has similar access semantics as System RAM i.e. DMA * coherent and supports page pinning. In support of coordinating page * pinning vs other operations MEMORY_DEVICE_FS_DAX arranges for a * wakeup event whenever a page is unpinned and becomes idle. This * wakeup is used to coordinate physical address space management (ex: * fs truncate/hole punch) vs pinned pages (ex: device dma). * * MEMORY_DEVICE_GENERIC: * Host memory that has similar access semantics as System RAM i.e. DMA * coherent and supports page pinning. This is for example used by DAX devices * that expose memory using a character device. * * MEMORY_DEVICE_PCI_P2PDMA: * Device memory residing in a PCI BAR intended for use with Peer-to-Peer * transactions. */ enum memory_type { /* 0 is reserved to catch uninitialized type fields */ MEMORY_DEVICE_PRIVATE = 1, MEMORY_DEVICE_COHERENT, MEMORY_DEVICE_FS_DAX, MEMORY_DEVICE_GENERIC, MEMORY_DEVICE_PCI_P2PDMA, }; struct dev_pagemap_ops { /* * Called once the page refcount reaches 0. The reference count will be * reset to one by the core code after the method is called to prepare * for handing out the page again. */ void (*page_free)(struct page *page); /* * Used for private (un-addressable) device memory only. Must migrate * the page back to a CPU accessible page. */ vm_fault_t (*migrate_to_ram)(struct vm_fault *vmf); /* * Handle the memory failure happens on a range of pfns. Notify the * processes who are using these pfns, and try to recover the data on * them if necessary. The mf_flags is finally passed to the recover * function through the whole notify routine. * * When this is not implemented, or it returns -EOPNOTSUPP, the caller * will fall back to a common handler called mf_generic_kill_procs(). */ int (*memory_failure)(struct dev_pagemap *pgmap, unsigned long pfn, unsigned long nr_pages, int mf_flags); }; #define PGMAP_ALTMAP_VALID (1 << 0) /** * struct dev_pagemap - metadata for ZONE_DEVICE mappings * @altmap: pre-allocated/reserved memory for vmemmap allocations * @ref: reference count that pins the devm_memremap_pages() mapping * @done: completion for @ref * @type: memory type: see MEMORY_* above in memremap.h * @flags: PGMAP_* flags to specify defailed behavior * @vmemmap_shift: structural definition of how the vmemmap page metadata * is populated, specifically the metadata page order. * A zero value (default) uses base pages as the vmemmap metadata * representation. A bigger value will set up compound struct pages * of the requested order value. * @ops: method table * @owner: an opaque pointer identifying the entity that manages this * instance. Used by various helpers to make sure that no * foreign ZONE_DEVICE memory is accessed. * @nr_range: number of ranges to be mapped * @range: range to be mapped when nr_range == 1 * @ranges: array of ranges to be mapped when nr_range > 1 */ struct dev_pagemap { struct vmem_altmap altmap; struct percpu_ref ref; struct completion done; enum memory_type type; unsigned int flags; unsigned long vmemmap_shift; const struct dev_pagemap_ops *ops; void *owner; int nr_range; union { struct range range; DECLARE_FLEX_ARRAY(struct range, ranges); }; }; static inline bool pgmap_has_memory_failure(struct dev_pagemap *pgmap) { return pgmap->ops && pgmap->ops->memory_failure; } static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap) { if (pgmap->flags & PGMAP_ALTMAP_VALID) return &pgmap->altmap; return NULL; } static inline unsigned long pgmap_vmemmap_nr(struct dev_pagemap *pgmap) { return 1 << pgmap->vmemmap_shift; } static inline bool is_device_private_page(const struct page *page) { return IS_ENABLED(CONFIG_DEVICE_PRIVATE) && is_zone_device_page(page) && page->pgmap->type == MEMORY_DEVICE_PRIVATE; } static inline bool folio_is_device_private(const struct folio *folio) { return is_device_private_page(&folio->page); } static inline bool is_pci_p2pdma_page(const struct page *page) { return IS_ENABLED(CONFIG_PCI_P2PDMA) && is_zone_device_page(page) && page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA; } static inline bool is_device_coherent_page(const struct page *page) { return is_zone_device_page(page) && page->pgmap->type == MEMORY_DEVICE_COHERENT; } static inline bool folio_is_device_coherent(const struct folio *folio) { return is_device_coherent_page(&folio->page); } #ifdef CONFIG_ZONE_DEVICE void zone_device_page_init(struct page *page); void *memremap_pages(struct dev_pagemap *pgmap, int nid); void memunmap_pages(struct dev_pagemap *pgmap); void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap); void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap); struct dev_pagemap *get_dev_pagemap(unsigned long pfn, struct dev_pagemap *pgmap); bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn); unsigned long memremap_compat_align(void); #else static inline void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) { /* * Fail attempts to call devm_memremap_pages() without * ZONE_DEVICE support enabled, this requires callers to fall * back to plain devm_memremap() based on config */ WARN_ON_ONCE(1); return ERR_PTR(-ENXIO); } static inline void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap) { } static inline struct dev_pagemap *get_dev_pagemap(unsigned long pfn, struct dev_pagemap *pgmap) { return NULL; } static inline bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn) { return false; } /* when memremap_pages() is disabled all archs can remap a single page */ static inline unsigned long memremap_compat_align(void) { return PAGE_SIZE; } #endif /* CONFIG_ZONE_DEVICE */ static inline void put_dev_pagemap(struct dev_pagemap *pgmap) { if (pgmap) percpu_ref_put(&pgmap->ref); } #endif /* _LINUX_MEMREMAP_H_ */ |
| 32 28 1 1 927 2 3 3 2 2 5 5 91 91 91 925 926 3 6 6 193 194 4971 4980 1 1 1 4975 4970 4867 176 375 31 9 31 4759 4752 4767 4758 1 4765 1 1 4755 4757 4759 99 4771 98 4755 1 4978 4976 4980 1 4975 4749 31 4551 1367 1367 9 4755 4735 4728 61 33 4760 4976 4976 105 3723 2814 4976 4750 4767 2 22 31 4756 1160 1940 5145 2493 5146 5120 5117 5123 2469 1949 5119 162 164 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 1994, Karl Keyte: Added support for disk statistics * Elevator latency, (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE * Queue request tables / lock, selectable elevator, Jens Axboe <axboe@suse.de> * kernel-doc documentation started by NeilBrown <neilb@cse.unsw.edu.au> * - July2000 * bio rewrite, highmem i/o, etc, Jens Axboe <axboe@suse.de> - may 2001 */ /* * This handles all read/write requests to block devices */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/blk-pm.h> #include <linux/blk-integrity.h> #include <linux/highmem.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/kernel_stat.h> #include <linux/string.h> #include <linux/init.h> #include <linux/completion.h> #include <linux/slab.h> #include <linux/swap.h> #include <linux/writeback.h> #include <linux/task_io_accounting_ops.h> #include <linux/fault-inject.h> #include <linux/list_sort.h> #include <linux/delay.h> #include <linux/ratelimit.h> #include <linux/pm_runtime.h> #include <linux/t10-pi.h> #include <linux/debugfs.h> #include <linux/bpf.h> #include <linux/part_stat.h> #include <linux/sched/sysctl.h> #include <linux/blk-crypto.h> #define CREATE_TRACE_POINTS #include <trace/events/block.h> #include "blk.h" #include "blk-mq-sched.h" #include "blk-pm.h" #include "blk-cgroup.h" #include "blk-throttle.h" #include "blk-ioprio.h" struct dentry *blk_debugfs_root; EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap); EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap); EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete); EXPORT_TRACEPOINT_SYMBOL_GPL(block_split); EXPORT_TRACEPOINT_SYMBOL_GPL(block_unplug); EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_insert); static DEFINE_IDA(blk_queue_ida); /* * For queue allocation */ static struct kmem_cache *blk_requestq_cachep; /* * Controlling structure to kblockd */ static struct workqueue_struct *kblockd_workqueue; /** * blk_queue_flag_set - atomically set a queue flag * @flag: flag to be set * @q: request queue */ void blk_queue_flag_set(unsigned int flag, struct request_queue *q) { set_bit(flag, &q->queue_flags); } EXPORT_SYMBOL(blk_queue_flag_set); /** * blk_queue_flag_clear - atomically clear a queue flag * @flag: flag to be cleared * @q: request queue */ void blk_queue_flag_clear(unsigned int flag, struct request_queue *q) { clear_bit(flag, &q->queue_flags); } EXPORT_SYMBOL(blk_queue_flag_clear); #define REQ_OP_NAME(name) [REQ_OP_##name] = #name static const char *const blk_op_name[] = { REQ_OP_NAME(READ), REQ_OP_NAME(WRITE), REQ_OP_NAME(FLUSH), REQ_OP_NAME(DISCARD), REQ_OP_NAME(SECURE_ERASE), REQ_OP_NAME(ZONE_RESET), REQ_OP_NAME(ZONE_RESET_ALL), REQ_OP_NAME(ZONE_OPEN), REQ_OP_NAME(ZONE_CLOSE), REQ_OP_NAME(ZONE_FINISH), REQ_OP_NAME(ZONE_APPEND), REQ_OP_NAME(WRITE_ZEROES), REQ_OP_NAME(DRV_IN), REQ_OP_NAME(DRV_OUT), }; #undef REQ_OP_NAME /** * blk_op_str - Return string XXX in the REQ_OP_XXX. * @op: REQ_OP_XXX. * * Description: Centralize block layer function to convert REQ_OP_XXX into * string format. Useful in the debugging and tracing bio or request. For * invalid REQ_OP_XXX it returns string "UNKNOWN". */ inline const char *blk_op_str(enum req_op op) { const char *op_str = "UNKNOWN"; if (op < ARRAY_SIZE(blk_op_name) && blk_op_name[op]) op_str = blk_op_name[op]; return op_str; } EXPORT_SYMBOL_GPL(blk_op_str); static const struct { int errno; const char *name; } blk_errors[] = { [BLK_STS_OK] = { 0, "" }, [BLK_STS_NOTSUPP] = { -EOPNOTSUPP, "operation not supported" }, [BLK_STS_TIMEOUT] = { -ETIMEDOUT, "timeout" }, [BLK_STS_NOSPC] = { -ENOSPC, "critical space allocation" }, [BLK_STS_TRANSPORT] = { -ENOLINK, "recoverable transport" }, [BLK_STS_TARGET] = { -EREMOTEIO, "critical target" }, [BLK_STS_RESV_CONFLICT] = { -EBADE, "reservation conflict" }, [BLK_STS_MEDIUM] = { -ENODATA, "critical medium" }, [BLK_STS_PROTECTION] = { -EILSEQ, "protection" }, [BLK_STS_RESOURCE] = { -ENOMEM, "kernel resource" }, [BLK_STS_DEV_RESOURCE] = { -EBUSY, "device resource" }, [BLK_STS_AGAIN] = { -EAGAIN, "nonblocking retry" }, [BLK_STS_OFFLINE] = { -ENODEV, "device offline" }, /* device mapper special case, should not leak out: */ [BLK_STS_DM_REQUEUE] = { -EREMCHG, "dm internal retry" }, /* zone device specific errors */ [BLK_STS_ZONE_OPEN_RESOURCE] = { -ETOOMANYREFS, "open zones exceeded" }, [BLK_STS_ZONE_ACTIVE_RESOURCE] = { -EOVERFLOW, "active zones exceeded" }, /* Command duration limit device-side timeout */ [BLK_STS_DURATION_LIMIT] = { -ETIME, "duration limit exceeded" }, [BLK_STS_INVAL] = { -EINVAL, "invalid" }, /* everything else not covered above: */ [BLK_STS_IOERR] = { -EIO, "I/O" }, }; blk_status_t errno_to_blk_status(int errno) { int i; for (i = 0; i < ARRAY_SIZE(blk_errors); i++) { if (blk_errors[i].errno == errno) return (__force blk_status_t)i; } return BLK_STS_IOERR; } EXPORT_SYMBOL_GPL(errno_to_blk_status); int blk_status_to_errno(blk_status_t status) { int idx = (__force int)status; if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors))) return -EIO; return blk_errors[idx].errno; } EXPORT_SYMBOL_GPL(blk_status_to_errno); const char *blk_status_to_str(blk_status_t status) { int idx = (__force int)status; if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors))) return "<null>"; return blk_errors[idx].name; } EXPORT_SYMBOL_GPL(blk_status_to_str); /** * blk_sync_queue - cancel any pending callbacks on a queue * @q: the queue * * Description: * The block layer may perform asynchronous callback activity * on a queue, such as calling the unplug function after a timeout. * A block device may call blk_sync_queue to ensure that any * such activity is cancelled, thus allowing it to release resources * that the callbacks might use. The caller must already have made sure * that its ->submit_bio will not re-add plugging prior to calling * this function. * * This function does not cancel any asynchronous activity arising * out of elevator or throttling code. That would require elevator_exit() * and blkcg_exit_queue() to be called with queue lock initialized. * */ void blk_sync_queue(struct request_queue *q) { del_timer_sync(&q->timeout); cancel_work_sync(&q->timeout_work); } EXPORT_SYMBOL(blk_sync_queue); /** * blk_set_pm_only - increment pm_only counter * @q: request queue pointer */ void blk_set_pm_only(struct request_queue *q) { atomic_inc(&q->pm_only); } EXPORT_SYMBOL_GPL(blk_set_pm_only); void blk_clear_pm_only(struct request_queue *q) { int pm_only; pm_only = atomic_dec_return(&q->pm_only); WARN_ON_ONCE(pm_only < 0); if (pm_only == 0) wake_up_all(&q->mq_freeze_wq); } EXPORT_SYMBOL_GPL(blk_clear_pm_only); static void blk_free_queue_rcu(struct rcu_head *rcu_head) { struct request_queue *q = container_of(rcu_head, struct request_queue, rcu_head); percpu_ref_exit(&q->q_usage_counter); kmem_cache_free(blk_requestq_cachep, q); } static void blk_free_queue(struct request_queue *q) { blk_free_queue_stats(q->stats); if (queue_is_mq(q)) blk_mq_release(q); ida_free(&blk_queue_ida, q->id); call_rcu(&q->rcu_head, blk_free_queue_rcu); } /** * blk_put_queue - decrement the request_queue refcount * @q: the request_queue structure to decrement the refcount for * * Decrements the refcount of the request_queue and free it when the refcount * reaches 0. */ void blk_put_queue(struct request_queue *q) { if (refcount_dec_and_test(&q->refs)) blk_free_queue(q); } EXPORT_SYMBOL(blk_put_queue); void blk_queue_start_drain(struct request_queue *q) { /* * When queue DYING flag is set, we need to block new req * entering queue, so we call blk_freeze_queue_start() to * prevent I/O from crossing blk_queue_enter(). */ blk_freeze_queue_start(q); if (queue_is_mq(q)) blk_mq_wake_waiters(q); /* Make blk_queue_enter() reexamine the DYING flag. */ wake_up_all(&q->mq_freeze_wq); } /** * blk_queue_enter() - try to increase q->q_usage_counter * @q: request queue pointer * @flags: BLK_MQ_REQ_NOWAIT and/or BLK_MQ_REQ_PM */ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags) { const bool pm = flags & BLK_MQ_REQ_PM; while (!blk_try_enter_queue(q, pm)) { if (flags & BLK_MQ_REQ_NOWAIT) return -EAGAIN; /* * read pair of barrier in blk_freeze_queue_start(), we need to * order reading __PERCPU_REF_DEAD flag of .q_usage_counter and * reading .mq_freeze_depth or queue dying flag, otherwise the * following wait may never return if the two reads are * reordered. */ smp_rmb(); wait_event(q->mq_freeze_wq, (!q->mq_freeze_depth && blk_pm_resume_queue(pm, q)) || blk_queue_dying(q)); if (blk_queue_dying(q)) return -ENODEV; } return 0; } int __bio_queue_enter(struct request_queue *q, struct bio *bio) { while (!blk_try_enter_queue(q, false)) { struct gendisk *disk = bio->bi_bdev->bd_disk; if (bio->bi_opf & REQ_NOWAIT) { if (test_bit(GD_DEAD, &disk->state)) goto dead; bio_wouldblock_error(bio); return -EAGAIN; } /* * read pair of barrier in blk_freeze_queue_start(), we need to * order reading __PERCPU_REF_DEAD flag of .q_usage_counter and * reading .mq_freeze_depth or queue dying flag, otherwise the * following wait may never return if the two reads are * reordered. */ smp_rmb(); wait_event(q->mq_freeze_wq, (!q->mq_freeze_depth && blk_pm_resume_queue(false, q)) || test_bit(GD_DEAD, &disk->state)); if (test_bit(GD_DEAD, &disk->state)) goto dead; } return 0; dead: bio_io_error(bio); return -ENODEV; } void blk_queue_exit(struct request_queue *q) { percpu_ref_put(&q->q_usage_counter); } static void blk_queue_usage_counter_release(struct percpu_ref *ref) { struct request_queue *q = container_of(ref, struct request_queue, q_usage_counter); wake_up_all(&q->mq_freeze_wq); } static void blk_rq_timed_out_timer(struct timer_list *t) { struct request_queue *q = from_timer(q, t, timeout); kblockd_schedule_work(&q->timeout_work); } static void blk_timeout_work(struct work_struct *work) { } struct request_queue *blk_alloc_queue(struct queue_limits *lim, int node_id) { struct request_queue *q; int error; q = kmem_cache_alloc_node(blk_requestq_cachep, GFP_KERNEL | __GFP_ZERO, node_id); if (!q) return ERR_PTR(-ENOMEM); q->last_merge = NULL; q->id = ida_alloc(&blk_queue_ida, GFP_KERNEL); if (q->id < 0) { error = q->id; goto fail_q; } q->stats = blk_alloc_queue_stats(); if (!q->stats) { error = -ENOMEM; goto fail_id; } error = blk_set_default_limits(lim); if (error) goto fail_stats; q->limits = *lim; q->node = node_id; atomic_set(&q->nr_active_requests_shared_tags, 0); timer_setup(&q->timeout, blk_rq_timed_out_timer, 0); INIT_WORK(&q->timeout_work, blk_timeout_work); INIT_LIST_HEAD(&q->icq_list); refcount_set(&q->refs, 1); mutex_init(&q->debugfs_mutex); mutex_init(&q->sysfs_lock); mutex_init(&q->sysfs_dir_lock); mutex_init(&q->limits_lock); mutex_init(&q->rq_qos_mutex); spin_lock_init(&q->queue_lock); init_waitqueue_head(&q->mq_freeze_wq); mutex_init(&q->mq_freeze_lock); blkg_init_queue(q); /* * Init percpu_ref in atomic mode so that it's faster to shutdown. * See blk_register_queue() for details. */ error = percpu_ref_init(&q->q_usage_counter, blk_queue_usage_counter_release, PERCPU_REF_INIT_ATOMIC, GFP_KERNEL); if (error) goto fail_stats; q->nr_requests = BLKDEV_DEFAULT_RQ; return q; fail_stats: blk_free_queue_stats(q->stats); fail_id: ida_free(&blk_queue_ida, q->id); fail_q: kmem_cache_free(blk_requestq_cachep, q); return ERR_PTR(error); } /** * blk_get_queue - increment the request_queue refcount * @q: the request_queue structure to increment the refcount for * * Increment the refcount of the request_queue kobject. * * Context: Any context. */ bool blk_get_queue(struct request_queue *q) { if (unlikely(blk_queue_dying(q))) return false; refcount_inc(&q->refs); return true; } EXPORT_SYMBOL(blk_get_queue); #ifdef CONFIG_FAIL_MAKE_REQUEST static DECLARE_FAULT_ATTR(fail_make_request); static int __init setup_fail_make_request(char *str) { return setup_fault_attr(&fail_make_request, str); } __setup("fail_make_request=", setup_fail_make_request); bool should_fail_request(struct block_device *part, unsigned int bytes) { return bdev_test_flag(part, BD_MAKE_IT_FAIL) && should_fail(&fail_make_request, bytes); } static int __init fail_make_request_debugfs(void) { struct dentry *dir = fault_create_debugfs_attr("fail_make_request", NULL, &fail_make_request); return PTR_ERR_OR_ZERO(dir); } late_initcall(fail_make_request_debugfs); #endif /* CONFIG_FAIL_MAKE_REQUEST */ static inline void bio_check_ro(struct bio *bio) { if (op_is_write(bio_op(bio)) && bdev_read_only(bio->bi_bdev)) { if (op_is_flush(bio->bi_opf) && !bio_sectors(bio)) return; if (bdev_test_flag(bio->bi_bdev, BD_RO_WARNED)) return; bdev_set_flag(bio->bi_bdev, BD_RO_WARNED); /* * Use ioctl to set underlying disk of raid/dm to read-only * will trigger this. */ pr_warn("Trying to write to read-only block-device %pg\n", bio->bi_bdev); } } static noinline int should_fail_bio(struct bio *bio) { if (should_fail_request(bdev_whole(bio->bi_bdev), bio->bi_iter.bi_size)) return -EIO; return 0; } ALLOW_ERROR_INJECTION(should_fail_bio, ERRNO); /* * Check whether this bio extends beyond the end of the device or partition. * This may well happen - the kernel calls bread() without checking the size of * the device, e.g., when mounting a file system. */ static inline int bio_check_eod(struct bio *bio) { sector_t maxsector = bdev_nr_sectors(bio->bi_bdev); unsigned int nr_sectors = bio_sectors(bio); if (nr_sectors && (nr_sectors > maxsector || bio->bi_iter.bi_sector > maxsector - nr_sectors)) { pr_info_ratelimited("%s: attempt to access beyond end of device\n" "%pg: rw=%d, sector=%llu, nr_sectors = %u limit=%llu\n", current->comm, bio->bi_bdev, bio->bi_opf, bio->bi_iter.bi_sector, nr_sectors, maxsector); return -EIO; } return 0; } /* * Remap block n of partition p to block n+start(p) of the disk. */ static int blk_partition_remap(struct bio *bio) { struct block_device *p = bio->bi_bdev; if (unlikely(should_fail_request(p, bio->bi_iter.bi_size))) return -EIO; if (bio_sectors(bio)) { bio->bi_iter.bi_sector += p->bd_start_sect; trace_block_bio_remap(bio, p->bd_dev, bio->bi_iter.bi_sector - p->bd_start_sect); } bio_set_flag(bio, BIO_REMAPPED); return 0; } /* * Check write append to a zoned block device. */ static inline blk_status_t blk_check_zone_append(struct request_queue *q, struct bio *bio) { int nr_sectors = bio_sectors(bio); /* Only applicable to zoned block devices */ if (!bdev_is_zoned(bio->bi_bdev)) return BLK_STS_NOTSUPP; /* The bio sector must point to the start of a sequential zone */ if (!bdev_is_zone_start(bio->bi_bdev, bio->bi_iter.bi_sector)) return BLK_STS_IOERR; /* * Not allowed to cross zone boundaries. Otherwise, the BIO will be * split and could result in non-contiguous sectors being written in * different zones. */ if (nr_sectors > q->limits.chunk_sectors) return BLK_STS_IOERR; /* Make sure the BIO is small enough and will not get split */ if (nr_sectors > queue_max_zone_append_sectors(q)) return BLK_STS_IOERR; bio->bi_opf |= REQ_NOMERGE; return BLK_STS_OK; } static void __submit_bio(struct bio *bio) { /* If plug is not used, add new plug here to cache nsecs time. */ struct blk_plug plug; if (unlikely(!blk_crypto_bio_prep(&bio))) return; blk_start_plug(&plug); if (!bdev_test_flag(bio->bi_bdev, BD_HAS_SUBMIT_BIO)) { blk_mq_submit_bio(bio); } else if (likely(bio_queue_enter(bio) == 0)) { struct gendisk *disk = bio->bi_bdev->bd_disk; disk->fops->submit_bio(bio); blk_queue_exit(disk->queue); } blk_finish_plug(&plug); } /* * The loop in this function may be a bit non-obvious, and so deserves some * explanation: * * - Before entering the loop, bio->bi_next is NULL (as all callers ensure * that), so we have a list with a single bio. * - We pretend that we have just taken it off a longer list, so we assign * bio_list to a pointer to the bio_list_on_stack, thus initialising the * bio_list of new bios to be added. ->submit_bio() may indeed add some more * bios through a recursive call to submit_bio_noacct. If it did, we find a * non-NULL value in bio_list and re-enter the loop from the top. * - In this case we really did just take the bio of the top of the list (no * pretending) and so remove it from bio_list, and call into ->submit_bio() * again. * * bio_list_on_stack[0] contains bios submitted by the current ->submit_bio. * bio_list_on_stack[1] contains bios that were submitted before the current * ->submit_bio, but that haven't been processed yet. */ static void __submit_bio_noacct(struct bio *bio) { struct bio_list bio_list_on_stack[2]; BUG_ON(bio->bi_next); bio_list_init(&bio_list_on_stack[0]); current->bio_list = bio_list_on_stack; do { struct request_queue *q = bdev_get_queue(bio->bi_bdev); struct bio_list lower, same; /* * Create a fresh bio_list for all subordinate requests. */ bio_list_on_stack[1] = bio_list_on_stack[0]; bio_list_init(&bio_list_on_stack[0]); __submit_bio(bio); /* * Sort new bios into those for a lower level and those for the * same level. */ bio_list_init(&lower); bio_list_init(&same); while ((bio = bio_list_pop(&bio_list_on_stack[0])) != NULL) if (q == bdev_get_queue(bio->bi_bdev)) bio_list_add(&same, bio); else bio_list_add(&lower, bio); /* * Now assemble so we handle the lowest level first. */ bio_list_merge(&bio_list_on_stack[0], &lower); bio_list_merge(&bio_list_on_stack[0], &same); bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]); } while ((bio = bio_list_pop(&bio_list_on_stack[0]))); current->bio_list = NULL; } static void __submit_bio_noacct_mq(struct bio *bio) { struct bio_list bio_list[2] = { }; current->bio_list = bio_list; do { __submit_bio(bio); } while ((bio = bio_list_pop(&bio_list[0]))); current->bio_list = NULL; } void submit_bio_noacct_nocheck(struct bio *bio) { blk_cgroup_bio_start(bio); blkcg_bio_issue_init(bio); if (!bio_flagged(bio, BIO_TRACE_COMPLETION)) { trace_block_bio_queue(bio); /* * Now that enqueuing has been traced, we need to trace * completion as well. */ bio_set_flag(bio, BIO_TRACE_COMPLETION); } /* * We only want one ->submit_bio to be active at a time, else stack * usage with stacked devices could be a problem. Use current->bio_list * to collect a list of requests submited by a ->submit_bio method while * it is active, and then process them after it returned. */ if (current->bio_list) bio_list_add(¤t->bio_list[0], bio); else if (!bdev_test_flag(bio->bi_bdev, BD_HAS_SUBMIT_BIO)) __submit_bio_noacct_mq(bio); else __submit_bio_noacct(bio); } static blk_status_t blk_validate_atomic_write_op_size(struct request_queue *q, struct bio *bio) { if (bio->bi_iter.bi_size > queue_atomic_write_unit_max_bytes(q)) return BLK_STS_INVAL; if (bio->bi_iter.bi_size % queue_atomic_write_unit_min_bytes(q)) return BLK_STS_INVAL; return BLK_STS_OK; } /** * submit_bio_noacct - re-submit a bio to the block device layer for I/O * @bio: The bio describing the location in memory and on the device. * * This is a version of submit_bio() that shall only be used for I/O that is * resubmitted to lower level drivers by stacking block drivers. All file * systems and other upper level users of the block layer should use * submit_bio() instead. */ void submit_bio_noacct(struct bio *bio) { struct block_device *bdev = bio->bi_bdev; struct request_queue *q = bdev_get_queue(bdev); blk_status_t status = BLK_STS_IOERR; might_sleep(); /* * For a REQ_NOWAIT based request, return -EOPNOTSUPP * if queue does not support NOWAIT. */ if ((bio->bi_opf & REQ_NOWAIT) && !bdev_nowait(bdev)) goto not_supported; if (should_fail_bio(bio)) goto end_io; bio_check_ro(bio); if (!bio_flagged(bio, BIO_REMAPPED)) { if (unlikely(bio_check_eod(bio))) goto end_io; if (bdev_is_partition(bdev) && unlikely(blk_partition_remap(bio))) goto end_io; } /* * Filter flush bio's early so that bio based drivers without flush * support don't have to worry about them. */ if (op_is_flush(bio->bi_opf)) { if (WARN_ON_ONCE(bio_op(bio) != REQ_OP_WRITE && bio_op(bio) != REQ_OP_ZONE_APPEND)) goto end_io; if (!bdev_write_cache(bdev)) { bio->bi_opf &= ~(REQ_PREFLUSH | REQ_FUA); if (!bio_sectors(bio)) { status = BLK_STS_OK; goto end_io; } } } if (!(q->limits.features & BLK_FEAT_POLL) && (bio->bi_opf & REQ_POLLED)) { bio_clear_polled(bio); goto not_supported; } switch (bio_op(bio)) { case REQ_OP_READ: case REQ_OP_WRITE: if (bio->bi_opf & REQ_ATOMIC) { status = blk_validate_atomic_write_op_size(q, bio); if (status != BLK_STS_OK) goto end_io; } break; case REQ_OP_FLUSH: /* * REQ_OP_FLUSH can't be submitted through bios, it is only * synthetized in struct request by the flush state machine. */ goto not_supported; case REQ_OP_DISCARD: if (!bdev_max_discard_sectors(bdev)) goto not_supported; break; case REQ_OP_SECURE_ERASE: if (!bdev_max_secure_erase_sectors(bdev)) goto not_supported; break; case REQ_OP_ZONE_APPEND: status = blk_check_zone_append(q, bio); if (status != BLK_STS_OK) goto end_io; break; case REQ_OP_WRITE_ZEROES: if (!q->limits.max_write_zeroes_sectors) goto not_supported; break; case REQ_OP_ZONE_RESET: case REQ_OP_ZONE_OPEN: case REQ_OP_ZONE_CLOSE: case REQ_OP_ZONE_FINISH: case REQ_OP_ZONE_RESET_ALL: if (!bdev_is_zoned(bio->bi_bdev)) goto not_supported; break; case REQ_OP_DRV_IN: case REQ_OP_DRV_OUT: /* * Driver private operations are only used with passthrough * requests. */ fallthrough; default: goto not_supported; } if (blk_throtl_bio(bio)) return; submit_bio_noacct_nocheck(bio); return; not_supported: status = BLK_STS_NOTSUPP; end_io: bio->bi_status = status; bio_endio(bio); } EXPORT_SYMBOL(submit_bio_noacct); static void bio_set_ioprio(struct bio *bio) { /* Nobody set ioprio so far? Initialize it based on task's nice value */ if (IOPRIO_PRIO_CLASS(bio->bi_ioprio) == IOPRIO_CLASS_NONE) bio->bi_ioprio = get_current_ioprio(); blkcg_set_ioprio(bio); } /** * submit_bio - submit a bio to the block device layer for I/O * @bio: The &struct bio which describes the I/O * * submit_bio() is used to submit I/O requests to block devices. It is passed a * fully set up &struct bio that describes the I/O that needs to be done. The * bio will be send to the device described by the bi_bdev field. * * The success/failure status of the request, along with notification of * completion, is delivered asynchronously through the ->bi_end_io() callback * in @bio. The bio must NOT be touched by the caller until ->bi_end_io() has * been called. */ void submit_bio(struct bio *bio) { if (bio_op(bio) == REQ_OP_READ) { task_io_account_read(bio->bi_iter.bi_size); count_vm_events(PGPGIN, bio_sectors(bio)); } else if (bio_op(bio) == REQ_OP_WRITE) { count_vm_events(PGPGOUT, bio_sectors(bio)); } bio_set_ioprio(bio); submit_bio_noacct(bio); } EXPORT_SYMBOL(submit_bio); /** * bio_poll - poll for BIO completions * @bio: bio to poll for * @iob: batches of IO * @flags: BLK_POLL_* flags that control the behavior * * Poll for completions on queue associated with the bio. Returns number of * completed entries found. * * Note: the caller must either be the context that submitted @bio, or * be in a RCU critical section to prevent freeing of @bio. */ int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags) { blk_qc_t cookie = READ_ONCE(bio->bi_cookie); struct block_device *bdev; struct request_queue *q; int ret = 0; bdev = READ_ONCE(bio->bi_bdev); if (!bdev) return 0; q = bdev_get_queue(bdev); if (cookie == BLK_QC_T_NONE || !(q->limits.features & BLK_FEAT_POLL)) return 0; blk_flush_plug(current->plug, false); /* * We need to be able to enter a frozen queue, similar to how * timeouts also need to do that. If that is blocked, then we can * have pending IO when a queue freeze is started, and then the * wait for the freeze to finish will wait for polled requests to * timeout as the poller is preventer from entering the queue and * completing them. As long as we prevent new IO from being queued, * that should be all that matters. */ if (!percpu_ref_tryget(&q->q_usage_counter)) return 0; if (queue_is_mq(q)) { ret = blk_mq_poll(q, cookie, iob, flags); } else { struct gendisk *disk = q->disk; if (disk && disk->fops->poll_bio) ret = disk->fops->poll_bio(bio, iob, flags); } blk_queue_exit(q); return ret; } EXPORT_SYMBOL_GPL(bio_poll); /* * Helper to implement file_operations.iopoll. Requires the bio to be stored * in iocb->private, and cleared before freeing the bio. */ int iocb_bio_iopoll(struct kiocb *kiocb, struct io_comp_batch *iob, unsigned int flags) { struct bio *bio; int ret = 0; /* * Note: the bio cache only uses SLAB_TYPESAFE_BY_RCU, so bio can * point to a freshly allocated bio at this point. If that happens * we have a few cases to consider: * * 1) the bio is beeing initialized and bi_bdev is NULL. We can just * simply nothing in this case * 2) the bio points to a not poll enabled device. bio_poll will catch * this and return 0 * 3) the bio points to a poll capable device, including but not * limited to the one that the original bio pointed to. In this * case we will call into the actual poll method and poll for I/O, * even if we don't need to, but it won't cause harm either. * * For cases 2) and 3) above the RCU grace period ensures that bi_bdev * is still allocated. Because partitions hold a reference to the whole * device bdev and thus disk, the disk is also still valid. Grabbing * a reference to the queue in bio_poll() ensures the hctxs and requests * are still valid as well. */ rcu_read_lock(); bio = READ_ONCE(kiocb->private); if (bio) ret = bio_poll(bio, iob, flags); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(iocb_bio_iopoll); void update_io_ticks(struct block_device *part, unsigned long now, bool end) { unsigned long stamp; again: stamp = READ_ONCE(part->bd_stamp); if (unlikely(time_after(now, stamp)) && likely(try_cmpxchg(&part->bd_stamp, &stamp, now)) && (end || part_in_flight(part))) __part_stat_add(part, io_ticks, now - stamp); if (bdev_is_partition(part)) { part = bdev_whole(part); goto again; } } unsigned long bdev_start_io_acct(struct block_device *bdev, enum req_op op, unsigned long start_time) { part_stat_lock(); update_io_ticks(bdev, start_time, false); part_stat_local_inc(bdev, in_flight[op_is_write(op)]); part_stat_unlock(); return start_time; } EXPORT_SYMBOL(bdev_start_io_acct); /** * bio_start_io_acct - start I/O accounting for bio based drivers * @bio: bio to start account for * * Returns the start time that should be passed back to bio_end_io_acct(). */ unsigned long bio_start_io_acct(struct bio *bio) { return bdev_start_io_acct(bio->bi_bdev, bio_op(bio), jiffies); } EXPORT_SYMBOL_GPL(bio_start_io_acct); void bdev_end_io_acct(struct block_device *bdev, enum req_op op, unsigned int sectors, unsigned long start_time) { const int sgrp = op_stat_group(op); unsigned long now = READ_ONCE(jiffies); unsigned long duration = now - start_time; part_stat_lock(); update_io_ticks(bdev, now, true); part_stat_inc(bdev, ios[sgrp]); part_stat_add(bdev, sectors[sgrp], sectors); part_stat_add(bdev, nsecs[sgrp], jiffies_to_nsecs(duration)); part_stat_local_dec(bdev, in_flight[op_is_write(op)]); part_stat_unlock(); } EXPORT_SYMBOL(bdev_end_io_acct); void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time, struct block_device *orig_bdev) { bdev_end_io_acct(orig_bdev, bio_op(bio), bio_sectors(bio), start_time); } EXPORT_SYMBOL_GPL(bio_end_io_acct_remapped); /** * blk_lld_busy - Check if underlying low-level drivers of a device are busy * @q : the queue of the device being checked * * Description: * Check if underlying low-level drivers of a device are busy. * If the drivers want to export their busy state, they must set own * exporting function using blk_queue_lld_busy() first. * * Basically, this function is used only by request stacking drivers * to stop dispatching requests to underlying devices when underlying * devices are busy. This behavior helps more I/O merging on the queue * of the request stacking driver and prevents I/O throughput regression * on burst I/O load. * * Return: * 0 - Not busy (The request stacking driver should dispatch request) * 1 - Busy (The request stacking driver should stop dispatching request) */ int blk_lld_busy(struct request_queue *q) { if (queue_is_mq(q) && q->mq_ops->busy) return q->mq_ops->busy(q); return 0; } EXPORT_SYMBOL_GPL(blk_lld_busy); int kblockd_schedule_work(struct work_struct *work) { return queue_work(kblockd_workqueue, work); } EXPORT_SYMBOL(kblockd_schedule_work); int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay) { return mod_delayed_work_on(cpu, kblockd_workqueue, dwork, delay); } EXPORT_SYMBOL(kblockd_mod_delayed_work_on); void blk_start_plug_nr_ios(struct blk_plug *plug, unsigned short nr_ios) { struct task_struct *tsk = current; /* * If this is a nested plug, don't actually assign it. */ if (tsk->plug) return; plug->cur_ktime = 0; plug->mq_list = NULL; plug->cached_rq = NULL; plug->nr_ios = min_t(unsigned short, nr_ios, BLK_MAX_REQUEST_COUNT); plug->rq_count = 0; plug->multiple_queues = false; plug->has_elevator = false; INIT_LIST_HEAD(&plug->cb_list); /* * Store ordering should not be needed here, since a potential * preempt will imply a full memory barrier */ tsk->plug = plug; } /** * blk_start_plug - initialize blk_plug and track it inside the task_struct * @plug: The &struct blk_plug that needs to be initialized * * Description: * blk_start_plug() indicates to the block layer an intent by the caller * to submit multiple I/O requests in a batch. The block layer may use * this hint to defer submitting I/Os from the caller until blk_finish_plug() * is called. However, the block layer may choose to submit requests * before a call to blk_finish_plug() if the number of queued I/Os * exceeds %BLK_MAX_REQUEST_COUNT, or if the size of the I/O is larger than * %BLK_PLUG_FLUSH_SIZE. The queued I/Os may also be submitted early if * the task schedules (see below). * * Tracking blk_plug inside the task_struct will help with auto-flushing the * pending I/O should the task end up blocking between blk_start_plug() and * blk_finish_plug(). This is important from a performance perspective, but * also ensures that we don't deadlock. For instance, if the task is blocking * for a memory allocation, memory reclaim could end up wanting to free a * page belonging to that request that is currently residing in our private * plug. By flushing the pending I/O when the process goes to sleep, we avoid * this kind of deadlock. */ void blk_start_plug(struct blk_plug *plug) { blk_start_plug_nr_ios(plug, 1); } EXPORT_SYMBOL(blk_start_plug); static void flush_plug_callbacks(struct blk_plug *plug, bool from_schedule) { LIST_HEAD(callbacks); while (!list_empty(&plug->cb_list)) { list_splice_init(&plug->cb_list, &callbacks); while (!list_empty(&callbacks)) { struct blk_plug_cb *cb = list_first_entry(&callbacks, struct blk_plug_cb, list); list_del(&cb->list); cb->callback(cb, from_schedule); } } } struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug, void *data, int size) { struct blk_plug *plug = current->plug; struct blk_plug_cb *cb; if (!plug) return NULL; list_for_each_entry(cb, &plug->cb_list, list) if (cb->callback == unplug && cb->data == data) return cb; /* Not currently on the callback list */ BUG_ON(size < sizeof(*cb)); cb = kzalloc(size, GFP_ATOMIC); if (cb) { cb->data = data; cb->callback = unplug; list_add(&cb->list, &plug->cb_list); } return cb; } EXPORT_SYMBOL(blk_check_plugged); void __blk_flush_plug(struct blk_plug *plug, bool from_schedule) { if (!list_empty(&plug->cb_list)) flush_plug_callbacks(plug, from_schedule); blk_mq_flush_plug_list(plug, from_schedule); /* * Unconditionally flush out cached requests, even if the unplug * event came from schedule. Since we know hold references to the * queue for cached requests, we don't want a blocked task holding * up a queue freeze/quiesce event. */ if (unlikely(!rq_list_empty(plug->cached_rq))) blk_mq_free_plug_rqs(plug); plug->cur_ktime = 0; current->flags &= ~PF_BLOCK_TS; } /** * blk_finish_plug - mark the end of a batch of submitted I/O * @plug: The &struct blk_plug passed to blk_start_plug() * * Description: * Indicate that a batch of I/O submissions is complete. This function * must be paired with an initial call to blk_start_plug(). The intent * is to allow the block layer to optimize I/O submission. See the * documentation for blk_start_plug() for more information. */ void blk_finish_plug(struct blk_plug *plug) { if (plug == current->plug) { __blk_flush_plug(plug, false); current->plug = NULL; } } EXPORT_SYMBOL(blk_finish_plug); void blk_io_schedule(void) { /* Prevent hang_check timer from firing at us during very long I/O */ unsigned long timeout = sysctl_hung_task_timeout_secs * HZ / 2; if (timeout) io_schedule_timeout(timeout); else io_schedule(); } EXPORT_SYMBOL_GPL(blk_io_schedule); int __init blk_dev_init(void) { BUILD_BUG_ON((__force u32)REQ_OP_LAST >= (1 << REQ_OP_BITS)); BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 * sizeof_field(struct request, cmd_flags)); BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 * sizeof_field(struct bio, bi_opf)); /* used for unplugging and affects IO latency/throughput - HIGHPRI */ kblockd_workqueue = alloc_workqueue("kblockd", WQ_MEM_RECLAIM | WQ_HIGHPRI, 0); if (!kblockd_workqueue) panic("Failed to create kblockd\n"); blk_requestq_cachep = KMEM_CACHE(request_queue, SLAB_PANIC); blk_debugfs_root = debugfs_create_dir("block", NULL); return 0; } |
| 99 1662 122 4752 4748 93 4753 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright 2019 Google LLC */ #ifndef __LINUX_BLK_CRYPTO_INTERNAL_H #define __LINUX_BLK_CRYPTO_INTERNAL_H #include <linux/bio.h> #include <linux/blk-mq.h> /* Represents a crypto mode supported by blk-crypto */ struct blk_crypto_mode { const char *name; /* name of this mode, shown in sysfs */ const char *cipher_str; /* crypto API name (for fallback case) */ unsigned int keysize; /* key size in bytes */ unsigned int ivsize; /* iv size in bytes */ }; extern const struct blk_crypto_mode blk_crypto_modes[]; #ifdef CONFIG_BLK_INLINE_ENCRYPTION int blk_crypto_sysfs_register(struct gendisk *disk); void blk_crypto_sysfs_unregister(struct gendisk *disk); void bio_crypt_dun_increment(u64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE], unsigned int inc); bool bio_crypt_rq_ctx_compatible(struct request *rq, struct bio *bio); bool bio_crypt_ctx_mergeable(struct bio_crypt_ctx *bc1, unsigned int bc1_bytes, struct bio_crypt_ctx *bc2); static inline bool bio_crypt_ctx_back_mergeable(struct request *req, struct bio *bio) { return bio_crypt_ctx_mergeable(req->crypt_ctx, blk_rq_bytes(req), bio->bi_crypt_context); } static inline bool bio_crypt_ctx_front_mergeable(struct request *req, struct bio *bio) { return bio_crypt_ctx_mergeable(bio->bi_crypt_context, bio->bi_iter.bi_size, req->crypt_ctx); } static inline bool bio_crypt_ctx_merge_rq(struct request *req, struct request *next) { return bio_crypt_ctx_mergeable(req->crypt_ctx, blk_rq_bytes(req), next->crypt_ctx); } static inline void blk_crypto_rq_set_defaults(struct request *rq) { rq->crypt_ctx = NULL; rq->crypt_keyslot = NULL; } static inline bool blk_crypto_rq_is_encrypted(struct request *rq) { return rq->crypt_ctx; } static inline bool blk_crypto_rq_has_keyslot(struct request *rq) { return rq->crypt_keyslot; } blk_status_t blk_crypto_get_keyslot(struct blk_crypto_profile *profile, const struct blk_crypto_key *key, struct blk_crypto_keyslot **slot_ptr); void blk_crypto_put_keyslot(struct blk_crypto_keyslot *slot); int __blk_crypto_evict_key(struct blk_crypto_profile *profile, const struct blk_crypto_key *key); bool __blk_crypto_cfg_supported(struct blk_crypto_profile *profile, const struct blk_crypto_config *cfg); #else /* CONFIG_BLK_INLINE_ENCRYPTION */ static inline int blk_crypto_sysfs_register(struct gendisk *disk) { return 0; } static inline void blk_crypto_sysfs_unregister(struct gendisk *disk) { } static inline bool bio_crypt_rq_ctx_compatible(struct request *rq, struct bio *bio) { return true; } static inline bool bio_crypt_ctx_front_mergeable(struct request *req, struct bio *bio) { return true; } static inline bool bio_crypt_ctx_back_mergeable(struct request *req, struct bio *bio) { return true; } static inline bool bio_crypt_ctx_merge_rq(struct request *req, struct request *next) { return true; } static inline void blk_crypto_rq_set_defaults(struct request *rq) { } static inline bool blk_crypto_rq_is_encrypted(struct request *rq) { return false; } static inline bool blk_crypto_rq_has_keyslot(struct request *rq) { return false; } #endif /* CONFIG_BLK_INLINE_ENCRYPTION */ void __bio_crypt_advance(struct bio *bio, unsigned int bytes); static inline void bio_crypt_advance(struct bio *bio, unsigned int bytes) { if (bio_has_crypt_ctx(bio)) __bio_crypt_advance(bio, bytes); } void __bio_crypt_free_ctx(struct bio *bio); static inline void bio_crypt_free_ctx(struct bio *bio) { if (bio_has_crypt_ctx(bio)) __bio_crypt_free_ctx(bio); } static inline void bio_crypt_do_front_merge(struct request *rq, struct bio *bio) { #ifdef CONFIG_BLK_INLINE_ENCRYPTION if (bio_has_crypt_ctx(bio)) memcpy(rq->crypt_ctx->bc_dun, bio->bi_crypt_context->bc_dun, sizeof(rq->crypt_ctx->bc_dun)); #endif } bool __blk_crypto_bio_prep(struct bio **bio_ptr); static inline bool blk_crypto_bio_prep(struct bio **bio_ptr) { if (bio_has_crypt_ctx(*bio_ptr)) return __blk_crypto_bio_prep(bio_ptr); return true; } blk_status_t __blk_crypto_rq_get_keyslot(struct request *rq); static inline blk_status_t blk_crypto_rq_get_keyslot(struct request *rq) { if (blk_crypto_rq_is_encrypted(rq)) return __blk_crypto_rq_get_keyslot(rq); return BLK_STS_OK; } void __blk_crypto_rq_put_keyslot(struct request *rq); static inline void blk_crypto_rq_put_keyslot(struct request *rq) { if (blk_crypto_rq_has_keyslot(rq)) __blk_crypto_rq_put_keyslot(rq); } void __blk_crypto_free_request(struct request *rq); static inline void blk_crypto_free_request(struct request *rq) { if (blk_crypto_rq_is_encrypted(rq)) __blk_crypto_free_request(rq); } int __blk_crypto_rq_bio_prep(struct request *rq, struct bio *bio, gfp_t gfp_mask); /** * blk_crypto_rq_bio_prep - Prepare a request's crypt_ctx when its first bio * is inserted * @rq: The request to prepare * @bio: The first bio being inserted into the request * @gfp_mask: Memory allocation flags * * Return: 0 on success, -ENOMEM if out of memory. -ENOMEM is only possible if * @gfp_mask doesn't include %__GFP_DIRECT_RECLAIM. */ static inline int blk_crypto_rq_bio_prep(struct request *rq, struct bio *bio, gfp_t gfp_mask) { if (bio_has_crypt_ctx(bio)) return __blk_crypto_rq_bio_prep(rq, bio, gfp_mask); return 0; } #ifdef CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK int blk_crypto_fallback_start_using_mode(enum blk_crypto_mode_num mode_num); bool blk_crypto_fallback_bio_prep(struct bio **bio_ptr); int blk_crypto_fallback_evict_key(const struct blk_crypto_key *key); #else /* CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK */ static inline int blk_crypto_fallback_start_using_mode(enum blk_crypto_mode_num mode_num) { pr_warn_once("crypto API fallback is disabled\n"); return -ENOPKG; } static inline bool blk_crypto_fallback_bio_prep(struct bio **bio_ptr) { pr_warn_once("crypto API fallback disabled; failing request.\n"); (*bio_ptr)->bi_status = BLK_STS_NOTSUPP; return false; } static inline int blk_crypto_fallback_evict_key(const struct blk_crypto_key *key) { return 0; } #endif /* CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK */ #endif /* __LINUX_BLK_CRYPTO_INTERNAL_H */ |
| 2 2 2 2 2 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 | /* * linux/drivers/video/fbcon.c -- Low level frame buffer based console driver * * Copyright (C) 1995 Geert Uytterhoeven * * * This file is based on the original Amiga console driver (amicon.c): * * Copyright (C) 1993 Hamish Macdonald * Greg Harp * Copyright (C) 1994 David Carter [carter@compsci.bristol.ac.uk] * * with work by William Rucklidge (wjr@cs.cornell.edu) * Geert Uytterhoeven * Jes Sorensen (jds@kom.auc.dk) * Martin Apel * * and on the original Atari console driver (atacon.c): * * Copyright (C) 1993 Bjoern Brauel * Roman Hodek * * with work by Guenther Kelleter * Martin Schaller * Andreas Schwab * * Hardware cursor support added by Emmanuel Marty (core@ggi-project.org) * Smart redraw scrolling, arbitrary font width support, 512char font support * and software scrollback added by * Jakub Jelinek (jj@ultra.linux.cz) * * Random hacking by Martin Mares <mj@ucw.cz> * * 2001 - Documented with DocBook * - Brad Douglas <brad@neruo.com> * * The low level operations for the various display memory organizations are * now in separate source files. * * Currently the following organizations are supported: * * o afb Amiga bitplanes * o cfb{2,4,8,16,24,32} Packed pixels * o ilbm Amiga interleaved bitplanes * o iplan2p[248] Atari interleaved bitplanes * o mfb Monochrome * o vga VGA characters/attributes * * To do: * * - Implement 16 plane mode (iplan2p16) * * * This file is subject to the terms and conditions of the GNU General Public * License. See the file COPYING in the main directory of this archive for * more details. */ #include <linux/module.h> #include <linux/types.h> #include <linux/fs.h> #include <linux/kernel.h> #include <linux/delay.h> /* MSch: for IRQ probe */ #include <linux/console.h> #include <linux/string.h> #include <linux/kd.h> #include <linux/slab.h> #include <linux/fb.h> #include <linux/fbcon.h> #include <linux/vt_kern.h> #include <linux/selection.h> #include <linux/font.h> #include <linux/smp.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/crc32.h> /* For counting font checksums */ #include <linux/uaccess.h> #include <asm/irq.h> #include "fbcon.h" #include "fb_internal.h" /* * FIXME: Locking * * - fbcon state itself is protected by the console_lock, and the code does a * pretty good job at making sure that lock is held everywhere it's needed. * * - fbcon doesn't bother with fb_lock/unlock at all. This is buggy, since it * means concurrent access to the same fbdev from both fbcon and userspace * will blow up. To fix this all fbcon calls from fbmem.c need to be moved out * of fb_lock/unlock protected sections, since otherwise we'll recurse and * deadlock eventually. Aside: Due to these deadlock issues the fbdev code in * fbmem.c cannot use locking asserts, and there's lots of callers which get * the rules wrong, e.g. fbsysfs.c entirely missed fb_lock/unlock calls too. */ enum { FBCON_LOGO_CANSHOW = -1, /* the logo can be shown */ FBCON_LOGO_DRAW = -2, /* draw the logo to a console */ FBCON_LOGO_DONTSHOW = -3 /* do not show the logo */ }; static struct fbcon_display fb_display[MAX_NR_CONSOLES]; static struct fb_info *fbcon_registered_fb[FB_MAX]; static int fbcon_num_registered_fb; #define fbcon_for_each_registered_fb(i) \ for (i = 0; WARN_CONSOLE_UNLOCKED(), i < FB_MAX; i++) \ if (!fbcon_registered_fb[i]) {} else static signed char con2fb_map[MAX_NR_CONSOLES]; static signed char con2fb_map_boot[MAX_NR_CONSOLES]; static struct fb_info *fbcon_info_from_console(int console) { WARN_CONSOLE_UNLOCKED(); return fbcon_registered_fb[con2fb_map[console]]; } static int logo_lines; /* logo_shown is an index to vc_cons when >= 0; otherwise follows FBCON_LOGO enums. */ static int logo_shown = FBCON_LOGO_CANSHOW; /* console mappings */ static unsigned int first_fb_vc; static unsigned int last_fb_vc = MAX_NR_CONSOLES - 1; static int fbcon_is_default = 1; static int primary_device = -1; static int fbcon_has_console_bind; #ifdef CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY static int map_override; static inline void fbcon_map_override(void) { map_override = 1; } #else static inline void fbcon_map_override(void) { } #endif /* CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY */ #ifdef CONFIG_FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER static bool deferred_takeover = true; #else #define deferred_takeover false #endif /* font data */ static char fontname[40]; /* current fb_info */ static int info_idx = -1; /* console rotation */ static int initial_rotation = -1; static int fbcon_has_sysfs; static int margin_color; static const struct consw fb_con; #define advance_row(p, delta) (unsigned short *)((unsigned long)(p) + (delta) * vc->vc_size_row) static int fbcon_cursor_noblink; #define divides(a, b) ((!(a) || (b)%(a)) ? 0 : 1) /* * Interface used by the world */ static void fbcon_clear_margins(struct vc_data *vc, int bottom_only); static void fbcon_set_palette(struct vc_data *vc, const unsigned char *table); /* * Internal routines */ static void fbcon_set_disp(struct fb_info *info, struct fb_var_screeninfo *var, int unit); static void fbcon_redraw_move(struct vc_data *vc, struct fbcon_display *p, int line, int count, int dy); static void fbcon_modechanged(struct fb_info *info); static void fbcon_set_all_vcs(struct fb_info *info); static struct device *fbcon_device; #ifdef CONFIG_FRAMEBUFFER_CONSOLE_ROTATION static inline void fbcon_set_rotation(struct fb_info *info) { struct fbcon_ops *ops = info->fbcon_par; if (!(info->flags & FBINFO_MISC_TILEBLITTING) && ops->p->con_rotate < 4) ops->rotate = ops->p->con_rotate; else ops->rotate = 0; } static void fbcon_rotate(struct fb_info *info, u32 rotate) { struct fbcon_ops *ops= info->fbcon_par; struct fb_info *fb_info; if (!ops || ops->currcon == -1) return; fb_info = fbcon_info_from_console(ops->currcon); if (info == fb_info) { struct fbcon_display *p = &fb_display[ops->currcon]; if (rotate < 4) p->con_rotate = rotate; else p->con_rotate = 0; fbcon_modechanged(info); } } static void fbcon_rotate_all(struct fb_info *info, u32 rotate) { struct fbcon_ops *ops = info->fbcon_par; struct vc_data *vc; struct fbcon_display *p; int i; if (!ops || ops->currcon < 0 || rotate > 3) return; for (i = first_fb_vc; i <= last_fb_vc; i++) { vc = vc_cons[i].d; if (!vc || vc->vc_mode != KD_TEXT || fbcon_info_from_console(i) != info) continue; p = &fb_display[vc->vc_num]; p->con_rotate = rotate; } fbcon_set_all_vcs(info); } #else static inline void fbcon_set_rotation(struct fb_info *info) { struct fbcon_ops *ops = info->fbcon_par; ops->rotate = FB_ROTATE_UR; } static void fbcon_rotate(struct fb_info *info, u32 rotate) { return; } static void fbcon_rotate_all(struct fb_info *info, u32 rotate) { return; } #endif /* CONFIG_FRAMEBUFFER_CONSOLE_ROTATION */ static int fbcon_get_rotate(struct fb_info *info) { struct fbcon_ops *ops = info->fbcon_par; return (ops) ? ops->rotate : 0; } static inline int fbcon_is_inactive(struct vc_data *vc, struct fb_info *info) { struct fbcon_ops *ops = info->fbcon_par; return (info->state != FBINFO_STATE_RUNNING || vc->vc_mode != KD_TEXT || ops->graphics); } static int get_color(struct vc_data *vc, struct fb_info *info, u16 c, int is_fg) { int depth = fb_get_color_depth(&info->var, &info->fix); int color = 0; if (console_blanked) { unsigned short charmask = vc->vc_hi_font_mask ? 0x1ff : 0xff; c = vc->vc_video_erase_char & charmask; } if (depth != 1) color = (is_fg) ? attr_fgcol((vc->vc_hi_font_mask) ? 9 : 8, c) : attr_bgcol((vc->vc_hi_font_mask) ? 13 : 12, c); switch (depth) { case 1: { int col = mono_col(info); /* 0 or 1 */ int fg = (info->fix.visual != FB_VISUAL_MONO01) ? col : 0; int bg = (info->fix.visual != FB_VISUAL_MONO01) ? 0 : col; if (console_blanked) fg = bg; color = (is_fg) ? fg : bg; break; } case 2: /* * Scale down 16-colors to 4 colors. Default 4-color palette * is grayscale. However, simply dividing the values by 4 * will not work, as colors 1, 2 and 3 will be scaled-down * to zero rendering them invisible. So empirically convert * colors to a sane 4-level grayscale. */ switch (color) { case 0: color = 0; /* black */ break; case 1 ... 6: color = 2; /* white */ break; case 7 ... 8: color = 1; /* gray */ break; default: color = 3; /* intense white */ break; } break; case 3: /* * Last 8 entries of default 16-color palette is a more intense * version of the first 8 (i.e., same chrominance, different * luminance). */ color &= 7; break; } return color; } static void fb_flashcursor(struct work_struct *work) { struct fbcon_ops *ops = container_of(work, struct fbcon_ops, cursor_work.work); struct fb_info *info; struct vc_data *vc = NULL; int c; bool enable; int ret; /* FIXME: we should sort out the unbind locking instead */ /* instead we just fail to flash the cursor if we can't get * the lock instead of blocking fbcon deinit */ ret = console_trylock(); if (ret == 0) return; /* protected by console_lock */ info = ops->info; if (ops->currcon != -1) vc = vc_cons[ops->currcon].d; if (!vc || !con_is_visible(vc) || fbcon_info_from_console(vc->vc_num) != info || vc->vc_deccm != 1) { console_unlock(); return; } c = scr_readw((u16 *) vc->vc_pos); enable = ops->cursor_flash && !ops->cursor_state.enable; ops->cursor(vc, info, enable, get_color(vc, info, c, 1), get_color(vc, info, c, 0)); console_unlock(); queue_delayed_work(system_power_efficient_wq, &ops->cursor_work, ops->cur_blink_jiffies); } static void fbcon_add_cursor_work(struct fb_info *info) { struct fbcon_ops *ops = info->fbcon_par; if (!fbcon_cursor_noblink) queue_delayed_work(system_power_efficient_wq, &ops->cursor_work, ops->cur_blink_jiffies); } static void fbcon_del_cursor_work(struct fb_info *info) { struct fbcon_ops *ops = info->fbcon_par; cancel_delayed_work_sync(&ops->cursor_work); } #ifndef MODULE static int __init fb_console_setup(char *this_opt) { char *options; int i, j; if (!this_opt || !*this_opt) return 1; while ((options = strsep(&this_opt, ",")) != NULL) { if (!strncmp(options, "font:", 5)) { strscpy(fontname, options + 5, sizeof(fontname)); continue; } if (!strncmp(options, "scrollback:", 11)) { pr_warn("Ignoring scrollback size option\n"); continue; } if (!strncmp(options, "map:", 4)) { options += 4; if (*options) { for (i = 0, j = 0; i < MAX_NR_CONSOLES; i++) { if (!options[j]) j = 0; con2fb_map_boot[i] = (options[j++]-'0') % FB_MAX; } fbcon_map_override(); } continue; } if (!strncmp(options, "vc:", 3)) { options += 3; if (*options) first_fb_vc = simple_strtoul(options, &options, 10) - 1; if (first_fb_vc >= MAX_NR_CONSOLES) first_fb_vc = 0; if (*options++ == '-') last_fb_vc = simple_strtoul(options, &options, 10) - 1; if (last_fb_vc < first_fb_vc || last_fb_vc >= MAX_NR_CONSOLES) last_fb_vc = MAX_NR_CONSOLES - 1; fbcon_is_default = 0; continue; } if (!strncmp(options, "rotate:", 7)) { options += 7; if (*options) initial_rotation = simple_strtoul(options, &options, 0); if (initial_rotation > 3) initial_rotation = 0; continue; } if (!strncmp(options, "margin:", 7)) { options += 7; if (*options) margin_color = simple_strtoul(options, &options, 0); continue; } #ifdef CONFIG_FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER if (!strcmp(options, "nodefer")) { deferred_takeover = false; continue; } #endif #ifdef CONFIG_LOGO if (!strncmp(options, "logo-pos:", 9)) { options += 9; if (!strcmp(options, "center")) fb_center_logo = true; continue; } if (!strncmp(options, "logo-count:", 11)) { options += 11; if (*options) fb_logo_count = simple_strtol(options, &options, 0); continue; } #endif } return 1; } __setup("fbcon=", fb_console_setup); #endif static int search_fb_in_map(int idx) { int i, retval = 0; for (i = first_fb_vc; i <= last_fb_vc; i++) { if (con2fb_map[i] == idx) retval = 1; } return retval; } static int search_for_mapped_con(void) { int i, retval = 0; for (i = first_fb_vc; i <= last_fb_vc; i++) { if (con2fb_map[i] != -1) retval = 1; } return retval; } static int do_fbcon_takeover(int show_logo) { int err, i; if (!fbcon_num_registered_fb) return -ENODEV; if (!show_logo) logo_shown = FBCON_LOGO_DONTSHOW; for (i = first_fb_vc; i <= last_fb_vc; i++) con2fb_map[i] = info_idx; err = do_take_over_console(&fb_con, first_fb_vc, last_fb_vc, fbcon_is_default); if (err) { for (i = first_fb_vc; i <= last_fb_vc; i++) con2fb_map[i] = -1; info_idx = -1; } else { fbcon_has_console_bind = 1; } return err; } #ifdef MODULE static void fbcon_prepare_logo(struct vc_data *vc, struct fb_info *info, int cols, int rows, int new_cols, int new_rows) { logo_shown = FBCON_LOGO_DONTSHOW; } #else static void fbcon_prepare_logo(struct vc_data *vc, struct fb_info *info, int cols, int rows, int new_cols, int new_rows) { /* Need to make room for the logo */ struct fbcon_ops *ops = info->fbcon_par; int cnt, erase = vc->vc_video_erase_char, step; unsigned short *save = NULL, *r, *q; int logo_height; if (info->fbops->owner) { logo_shown = FBCON_LOGO_DONTSHOW; return; } /* * remove underline attribute from erase character * if black and white framebuffer. */ if (fb_get_color_depth(&info->var, &info->fix) == 1) erase &= ~0x400; logo_height = fb_prepare_logo(info, ops->rotate); logo_lines = DIV_ROUND_UP(logo_height, vc->vc_font.height); q = (unsigned short *) (vc->vc_origin + vc->vc_size_row * rows); step = logo_lines * cols; for (r = q - logo_lines * cols; r < q; r++) if (scr_readw(r) != vc->vc_video_erase_char) break; if (r != q && new_rows >= rows + logo_lines) { save = kmalloc(array3_size(logo_lines, new_cols, 2), GFP_KERNEL); if (save) { int i = min(cols, new_cols); scr_memsetw(save, erase, array3_size(logo_lines, new_cols, 2)); r = q - step; for (cnt = 0; cnt < logo_lines; cnt++, r += i) scr_memcpyw(save + cnt * new_cols, r, 2 * i); r = q; } } if (r == q) { /* We can scroll screen down */ r = q - step - cols; for (cnt = rows - logo_lines; cnt > 0; cnt--) { scr_memcpyw(r + step, r, vc->vc_size_row); r -= cols; } if (!save) { int lines; if (vc->state.y + logo_lines >= rows) lines = rows - vc->state.y - 1; else lines = logo_lines; vc->state.y += lines; vc->vc_pos += lines * vc->vc_size_row; } } scr_memsetw((unsigned short *) vc->vc_origin, erase, vc->vc_size_row * logo_lines); if (con_is_visible(vc) && vc->vc_mode == KD_TEXT) { fbcon_clear_margins(vc, 0); update_screen(vc); } if (save) { q = (unsigned short *) (vc->vc_origin + vc->vc_size_row * rows); scr_memcpyw(q, save, array3_size(logo_lines, new_cols, 2)); vc->state.y += logo_lines; vc->vc_pos += logo_lines * vc->vc_size_row; kfree(save); } if (logo_shown == FBCON_LOGO_DONTSHOW) return; if (logo_lines > vc->vc_bottom) { logo_shown = FBCON_LOGO_CANSHOW; pr_info("fbcon: disable boot-logo (boot-logo bigger than screen).\n"); } else { logo_shown = FBCON_LOGO_DRAW; vc->vc_top = logo_lines; } } #endif /* MODULE */ #ifdef CONFIG_FB_TILEBLITTING static void set_blitting_type(struct vc_data *vc, struct fb_info *info) { struct fbcon_ops *ops = info->fbcon_par; ops->p = &fb_display[vc->vc_num]; if ((info->flags & FBINFO_MISC_TILEBLITTING)) fbcon_set_tileops(vc, info); else { fbcon_set_rotation(info); fbcon_set_bitops(ops); } } static int fbcon_invalid_charcount(struct fb_info *info, unsigned charcount) { int err = 0; if (info->flags & FBINFO_MISC_TILEBLITTING && info->tileops->fb_get_tilemax(info) < charcount) err = 1; return err; } #else static void set_blitting_type(struct vc_data *vc, struct fb_info *info) { struct fbcon_ops *ops = info->fbcon_par; info->flags &= ~FBINFO_MISC_TILEBLITTING; ops->p = &fb_display[vc->vc_num]; fbcon_set_rotation(info); fbcon_set_bitops(ops); } static int fbcon_invalid_charcount(struct fb_info *info, unsigned charcount) { return 0; } #endif /* CONFIG_MISC_TILEBLITTING */ static void fbcon_release(struct fb_info *info) { lock_fb_info(info); if (info->fbops->fb_release) info->fbops->fb_release(info, 0); unlock_fb_info(info); module_put(info->fbops->owner); if (info->fbcon_par) { struct fbcon_ops *ops = info->fbcon_par; fbcon_del_cursor_work(info); kfree(ops->cursor_state.mask); kfree(ops->cursor_data); kfree(ops->cursor_src); kfree(ops->fontbuffer); kfree(info->fbcon_par); info->fbcon_par = NULL; } } static int fbcon_open(struct fb_info *info) { struct fbcon_ops *ops; if (!try_module_get(info->fbops->owner)) return -ENODEV; lock_fb_info(info); if (info->fbops->fb_open && info->fbops->fb_open(info, 0)) { unlock_fb_info(info); module_put(info->fbops->owner); return -ENODEV; } unlock_fb_info(info); ops = kzalloc(sizeof(struct fbcon_ops), GFP_KERNEL); if (!ops) { fbcon_release(info); return -ENOMEM; } INIT_DELAYED_WORK(&ops->cursor_work, fb_flashcursor); ops->info = info; info->fbcon_par = ops; ops->cur_blink_jiffies = HZ / 5; return 0; } static int con2fb_acquire_newinfo(struct vc_data *vc, struct fb_info *info, int unit) { int err; err = fbcon_open(info); if (err) return err; if (vc) set_blitting_type(vc, info); return err; } static void con2fb_release_oldinfo(struct vc_data *vc, struct fb_info *oldinfo, struct fb_info *newinfo) { int ret; fbcon_release(oldinfo); /* If oldinfo and newinfo are driving the same hardware, the fb_release() method of oldinfo may attempt to restore the hardware state. This will leave the newinfo in an undefined state. Thus, a call to fb_set_par() may be needed for the newinfo. */ if (newinfo && newinfo->fbops->fb_set_par) { ret = newinfo->fbops->fb_set_par(newinfo); if (ret) printk(KERN_ERR "con2fb_release_oldinfo: " "detected unhandled fb_set_par error, " "error code %d\n", ret); } } static void con2fb_init_display(struct vc_data *vc, struct fb_info *info, int unit, int show_logo) { struct fbcon_ops *ops = info->fbcon_par; int ret; ops->currcon = fg_console; if (info->fbops->fb_set_par && !ops->initialized) { ret = info->fbops->fb_set_par(info); if (ret) printk(KERN_ERR "con2fb_init_display: detected " "unhandled fb_set_par error, " "error code %d\n", ret); } ops->initialized = true; ops->graphics = 0; fbcon_set_disp(info, &info->var, unit); if (show_logo) { struct vc_data *fg_vc = vc_cons[fg_console].d; struct fb_info *fg_info = fbcon_info_from_console(fg_console); fbcon_prepare_logo(fg_vc, fg_info, fg_vc->vc_cols, fg_vc->vc_rows, fg_vc->vc_cols, fg_vc->vc_rows); } update_screen(vc_cons[fg_console].d); } /** * set_con2fb_map - map console to frame buffer device * @unit: virtual console number to map * @newidx: frame buffer index to map virtual console to * @user: user request * * Maps a virtual console @unit to a frame buffer device * @newidx. * * This should be called with the console lock held. */ static int set_con2fb_map(int unit, int newidx, int user) { struct vc_data *vc = vc_cons[unit].d; int oldidx = con2fb_map[unit]; struct fb_info *info = fbcon_registered_fb[newidx]; struct fb_info *oldinfo = NULL; int err = 0, show_logo; WARN_CONSOLE_UNLOCKED(); if (oldidx == newidx) return 0; if (!info) return -EINVAL; if (!search_for_mapped_con() || !con_is_bound(&fb_con)) { info_idx = newidx; return do_fbcon_takeover(0); } if (oldidx != -1) oldinfo = fbcon_registered_fb[oldidx]; if (!search_fb_in_map(newidx)) { err = con2fb_acquire_newinfo(vc, info, unit); if (err) return err; fbcon_add_cursor_work(info); } con2fb_map[unit] = newidx; /* * If old fb is not mapped to any of the consoles, * fbcon should release it. */ if (oldinfo && !search_fb_in_map(oldidx)) con2fb_release_oldinfo(vc, oldinfo, info); show_logo = (fg_console == 0 && !user && logo_shown != FBCON_LOGO_DONTSHOW); con2fb_map_boot[unit] = newidx; con2fb_init_display(vc, info, unit, show_logo); if (!search_fb_in_map(info_idx)) info_idx = newidx; return err; } /* * Low Level Operations */ /* NOTE: fbcon cannot be __init: it may be called from do_take_over_console later */ static int var_to_display(struct fbcon_display *disp, struct fb_var_screeninfo *var, struct fb_info *info) { disp->xres_virtual = var->xres_virtual; disp->yres_virtual = var->yres_virtual; disp->bits_per_pixel = var->bits_per_pixel; disp->grayscale = var->grayscale; disp->nonstd = var->nonstd; disp->accel_flags = var->accel_flags; disp->height = var->height; disp->width = var->width; disp->red = var->red; disp->green = var->green; disp->blue = var->blue; disp->transp = var->transp; disp->rotate = var->rotate; disp->mode = fb_match_mode(var, &info->modelist); if (disp->mode == NULL) /* This should not happen */ return -EINVAL; return 0; } static void display_to_var(struct fb_var_screeninfo *var, struct fbcon_display *disp) { fb_videomode_to_var(var, disp->mode); var->xres_virtual = disp->xres_virtual; var->yres_virtual = disp->yres_virtual; var->bits_per_pixel = disp->bits_per_pixel; var->grayscale = disp->grayscale; var->nonstd = disp->nonstd; var->accel_flags = disp->accel_flags; var->height = disp->height; var->width = disp->width; var->red = disp->red; var->green = disp->green; var->blue = disp->blue; var->transp = disp->transp; var->rotate = disp->rotate; } static const char *fbcon_startup(void) { static const char display_desc[] = "frame buffer device"; struct fbcon_display *p = &fb_display[fg_console]; struct vc_data *vc = vc_cons[fg_console].d; const struct font_desc *font = NULL; struct fb_info *info = NULL; struct fbcon_ops *ops; int rows, cols; /* * If num_registered_fb is zero, this is a call for the dummy part. * The frame buffer devices weren't initialized yet. */ if (!fbcon_num_registered_fb || info_idx == -1) return display_desc; /* * Instead of blindly using registered_fb[0], we use info_idx, set by * fbcon_fb_registered(); */ info = fbcon_registered_fb[info_idx]; if (!info) return NULL; if (fbcon_open(info)) return NULL; ops = info->fbcon_par; ops->currcon = -1; ops->graphics = 1; ops->cur_rotate = -1; p->con_rotate = initial_rotation; if (p->con_rotate == -1) p->con_rotate = info->fbcon_rotate_hint; if (p->con_rotate == -1) p->con_rotate = FB_ROTATE_UR; set_blitting_type(vc, info); /* Setup default font */ if (!p->fontdata) { if (!fontname[0] || !(font = find_font(fontname))) font = get_default_font(info->var.xres, info->var.yres, info->pixmap.blit_x, info->pixmap.blit_y); vc->vc_font.width = font->width; vc->vc_font.height = font->height; vc->vc_font.data = (void *)(p->fontdata = font->data); vc->vc_font.charcount = font->charcount; } cols = FBCON_SWAP(ops->rotate, info->var.xres, info->var.yres); rows = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres); cols /= vc->vc_font.width; rows /= vc->vc_font.height; vc_resize(vc, cols, rows); pr_debug("mode: %s\n", info->fix.id); pr_debug("visual: %d\n", info->fix.visual); pr_debug("res: %dx%d-%d\n", info->var.xres, info->var.yres, info->var.bits_per_pixel); fbcon_add_cursor_work(info); return display_desc; } static void fbcon_init(struct vc_data *vc, bool init) { struct fb_info *info; struct fbcon_ops *ops; struct vc_data **default_mode = vc->vc_display_fg; struct vc_data *svc = *default_mode; struct fbcon_display *t, *p = &fb_display[vc->vc_num]; int logo = 1, new_rows, new_cols, rows, cols; int ret; if (WARN_ON(info_idx == -1)) return; if (con2fb_map[vc->vc_num] == -1) con2fb_map[vc->vc_num] = info_idx; info = fbcon_info_from_console(vc->vc_num); if (logo_shown < 0 && console_loglevel <= CONSOLE_LOGLEVEL_QUIET) logo_shown = FBCON_LOGO_DONTSHOW; if (vc != svc || logo_shown == FBCON_LOGO_DONTSHOW || (info->fix.type == FB_TYPE_TEXT)) logo = 0; if (var_to_display(p, &info->var, info)) return; if (!info->fbcon_par) con2fb_acquire_newinfo(vc, info, vc->vc_num); /* If we are not the first console on this fb, copy the font from that console */ t = &fb_display[fg_console]; if (!p->fontdata) { if (t->fontdata) { struct vc_data *fvc = vc_cons[fg_console].d; vc->vc_font.data = (void *)(p->fontdata = fvc->vc_font.data); vc->vc_font.width = fvc->vc_font.width; vc->vc_font.height = fvc->vc_font.height; vc->vc_font.charcount = fvc->vc_font.charcount; p->userfont = t->userfont; if (p->userfont) REFCOUNT(p->fontdata)++; } else { const struct font_desc *font = NULL; if (!fontname[0] || !(font = find_font(fontname))) font = get_default_font(info->var.xres, info->var.yres, info->pixmap.blit_x, info->pixmap.blit_y); vc->vc_font.width = font->width; vc->vc_font.height = font->height; vc->vc_font.data = (void *)(p->fontdata = font->data); vc->vc_font.charcount = font->charcount; } } vc->vc_can_do_color = (fb_get_color_depth(&info->var, &info->fix)!=1); vc->vc_complement_mask = vc->vc_can_do_color ? 0x7700 : 0x0800; if (vc->vc_font.charcount == 256) { vc->vc_hi_font_mask = 0; } else { vc->vc_hi_font_mask = 0x100; if (vc->vc_can_do_color) vc->vc_complement_mask <<= 1; } if (!*svc->uni_pagedict_loc) con_set_default_unimap(svc); if (!*vc->uni_pagedict_loc) con_copy_unimap(vc, svc); ops = info->fbcon_par; ops->cur_blink_jiffies = msecs_to_jiffies(vc->vc_cur_blink_ms); p->con_rotate = initial_rotation; if (p->con_rotate == -1) p->con_rotate = info->fbcon_rotate_hint; if (p->con_rotate == -1) p->con_rotate = FB_ROTATE_UR; set_blitting_type(vc, info); cols = vc->vc_cols; rows = vc->vc_rows; new_cols = FBCON_SWAP(ops->rotate, info->var.xres, info->var.yres); new_rows = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres); new_cols /= vc->vc_font.width; new_rows /= vc->vc_font.height; /* * We must always set the mode. The mode of the previous console * driver could be in the same resolution but we are using different * hardware so we have to initialize the hardware. * * We need to do it in fbcon_init() to prevent screen corruption. */ if (con_is_visible(vc) && vc->vc_mode == KD_TEXT) { if (info->fbops->fb_set_par && !ops->initialized) { ret = info->fbops->fb_set_par(info); if (ret) printk(KERN_ERR "fbcon_init: detected " "unhandled fb_set_par error, " "error code %d\n", ret); } ops->initialized = true; } ops->graphics = 0; #ifdef CONFIG_FRAMEBUFFER_CONSOLE_LEGACY_ACCELERATION if ((info->flags & FBINFO_HWACCEL_COPYAREA) && !(info->flags & FBINFO_HWACCEL_DISABLED)) p->scrollmode = SCROLL_MOVE; else /* default to something safe */ p->scrollmode = SCROLL_REDRAW; #endif /* * ++guenther: console.c:vc_allocate() relies on initializing * vc_{cols,rows}, but we must not set those if we are only * resizing the console. */ if (init) { vc->vc_cols = new_cols; vc->vc_rows = new_rows; } else vc_resize(vc, new_cols, new_rows); if (logo) fbcon_prepare_logo(vc, info, cols, rows, new_cols, new_rows); if (ops->rotate_font && ops->rotate_font(info, vc)) { ops->rotate = FB_ROTATE_UR; set_blitting_type(vc, info); } ops->p = &fb_display[fg_console]; } static void fbcon_free_font(struct fbcon_display *p) { if (p->userfont && p->fontdata && (--REFCOUNT(p->fontdata) == 0)) kfree(p->fontdata - FONT_EXTRA_WORDS * sizeof(int)); p->fontdata = NULL; p->userfont = 0; } static void set_vc_hi_font(struct vc_data *vc, bool set); static void fbcon_release_all(void) { struct fb_info *info; int i, j, mapped; fbcon_for_each_registered_fb(i) { mapped = 0; info = fbcon_registered_fb[i]; for (j = first_fb_vc; j <= last_fb_vc; j++) { if (con2fb_map[j] == i) { mapped = 1; con2fb_map[j] = -1; } } if (mapped) fbcon_release(info); } } static void fbcon_deinit(struct vc_data *vc) { struct fbcon_display *p = &fb_display[vc->vc_num]; struct fb_info *info; struct fbcon_ops *ops; int idx; fbcon_free_font(p); idx = con2fb_map[vc->vc_num]; if (idx == -1) goto finished; info = fbcon_registered_fb[idx]; if (!info) goto finished; ops = info->fbcon_par; if (!ops) goto finished; if (con_is_visible(vc)) fbcon_del_cursor_work(info); ops->initialized = false; finished: fbcon_free_font(p); vc->vc_font.data = NULL; if (vc->vc_hi_font_mask && vc->vc_screenbuf) set_vc_hi_font(vc, false); if (!con_is_bound(&fb_con)) fbcon_release_all(); if (vc->vc_num == logo_shown) logo_shown = FBCON_LOGO_CANSHOW; return; } /* ====================================================================== */ /* fbcon_XXX routines - interface used by the world * * This system is now divided into two levels because of complications * caused by hardware scrolling. Top level functions: * * fbcon_bmove(), fbcon_clear(), fbcon_putc(), fbcon_clear_margins() * * handles y values in range [0, scr_height-1] that correspond to real * screen positions. y_wrap shift means that first line of bitmap may be * anywhere on this display. These functions convert lineoffsets to * bitmap offsets and deal with the wrap-around case by splitting blits. * * fbcon_bmove_physical_8() -- These functions fast implementations * fbcon_clear_physical_8() -- of original fbcon_XXX fns. * fbcon_putc_physical_8() -- (font width != 8) may be added later * * WARNING: * * At the moment fbcon_putc() cannot blit across vertical wrap boundary * Implies should only really hardware scroll in rows. Only reason for * restriction is simplicity & efficiency at the moment. */ static void __fbcon_clear(struct vc_data *vc, unsigned int sy, unsigned int sx, unsigned int height, unsigned int width) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_ops *ops = info->fbcon_par; struct fbcon_display *p = &fb_display[vc->vc_num]; u_int y_break; if (fbcon_is_inactive(vc, info)) return; if (!height || !width) return; if (sy < vc->vc_top && vc->vc_top == logo_lines) { vc->vc_top = 0; /* * If the font dimensions are not an integral of the display * dimensions then the ops->clear below won't end up clearing * the margins. Call clear_margins here in case the logo * bitmap stretched into the margin area. */ fbcon_clear_margins(vc, 0); } /* Split blits that cross physical y_wrap boundary */ y_break = p->vrows - p->yscroll; if (sy < y_break && sy + height - 1 >= y_break) { u_int b = y_break - sy; ops->clear(vc, info, real_y(p, sy), sx, b, width); ops->clear(vc, info, real_y(p, sy + b), sx, height - b, width); } else ops->clear(vc, info, real_y(p, sy), sx, height, width); } static void fbcon_clear(struct vc_data *vc, unsigned int sy, unsigned int sx, unsigned int width) { __fbcon_clear(vc, sy, sx, 1, width); } static void fbcon_putcs(struct vc_data *vc, const u16 *s, unsigned int count, unsigned int ypos, unsigned int xpos) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_display *p = &fb_display[vc->vc_num]; struct fbcon_ops *ops = info->fbcon_par; if (!fbcon_is_inactive(vc, info)) ops->putcs(vc, info, s, count, real_y(p, ypos), xpos, get_color(vc, info, scr_readw(s), 1), get_color(vc, info, scr_readw(s), 0)); } static void fbcon_clear_margins(struct vc_data *vc, int bottom_only) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_ops *ops = info->fbcon_par; if (!fbcon_is_inactive(vc, info)) ops->clear_margins(vc, info, margin_color, bottom_only); } static void fbcon_cursor(struct vc_data *vc, bool enable) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_ops *ops = info->fbcon_par; int c = scr_readw((u16 *) vc->vc_pos); ops->cur_blink_jiffies = msecs_to_jiffies(vc->vc_cur_blink_ms); if (fbcon_is_inactive(vc, info) || vc->vc_deccm != 1) return; if (vc->vc_cursor_type & CUR_SW) fbcon_del_cursor_work(info); else fbcon_add_cursor_work(info); ops->cursor_flash = enable; if (!ops->cursor) return; ops->cursor(vc, info, enable, get_color(vc, info, c, 1), get_color(vc, info, c, 0)); } static int scrollback_phys_max = 0; static int scrollback_max = 0; static int scrollback_current = 0; static void fbcon_set_disp(struct fb_info *info, struct fb_var_screeninfo *var, int unit) { struct fbcon_display *p, *t; struct vc_data **default_mode, *vc; struct vc_data *svc; struct fbcon_ops *ops = info->fbcon_par; int rows, cols; p = &fb_display[unit]; if (var_to_display(p, var, info)) return; vc = vc_cons[unit].d; if (!vc) return; default_mode = vc->vc_display_fg; svc = *default_mode; t = &fb_display[svc->vc_num]; if (!vc->vc_font.data) { vc->vc_font.data = (void *)(p->fontdata = t->fontdata); vc->vc_font.width = (*default_mode)->vc_font.width; vc->vc_font.height = (*default_mode)->vc_font.height; vc->vc_font.charcount = (*default_mode)->vc_font.charcount; p->userfont = t->userfont; if (p->userfont) REFCOUNT(p->fontdata)++; } var->activate = FB_ACTIVATE_NOW; info->var.activate = var->activate; var->yoffset = info->var.yoffset; var->xoffset = info->var.xoffset; fb_set_var(info, var); ops->var = info->var; vc->vc_can_do_color = (fb_get_color_depth(&info->var, &info->fix)!=1); vc->vc_complement_mask = vc->vc_can_do_color ? 0x7700 : 0x0800; if (vc->vc_font.charcount == 256) { vc->vc_hi_font_mask = 0; } else { vc->vc_hi_font_mask = 0x100; if (vc->vc_can_do_color) vc->vc_complement_mask <<= 1; } if (!*svc->uni_pagedict_loc) con_set_default_unimap(svc); if (!*vc->uni_pagedict_loc) con_copy_unimap(vc, svc); cols = FBCON_SWAP(ops->rotate, info->var.xres, info->var.yres); rows = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres); cols /= vc->vc_font.width; rows /= vc->vc_font.height; vc_resize(vc, cols, rows); if (con_is_visible(vc)) { update_screen(vc); } } static __inline__ void ywrap_up(struct vc_data *vc, int count) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_ops *ops = info->fbcon_par; struct fbcon_display *p = &fb_display[vc->vc_num]; p->yscroll += count; if (p->yscroll >= p->vrows) /* Deal with wrap */ p->yscroll -= p->vrows; ops->var.xoffset = 0; ops->var.yoffset = p->yscroll * vc->vc_font.height; ops->var.vmode |= FB_VMODE_YWRAP; ops->update_start(info); scrollback_max += count; if (scrollback_max > scrollback_phys_max) scrollback_max = scrollback_phys_max; scrollback_current = 0; } static __inline__ void ywrap_down(struct vc_data *vc, int count) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_ops *ops = info->fbcon_par; struct fbcon_display *p = &fb_display[vc->vc_num]; p->yscroll -= count; if (p->yscroll < 0) /* Deal with wrap */ p->yscroll += p->vrows; ops->var.xoffset = 0; ops->var.yoffset = p->yscroll * vc->vc_font.height; ops->var.vmode |= FB_VMODE_YWRAP; ops->update_start(info); scrollback_max -= count; if (scrollback_max < 0) scrollback_max = 0; scrollback_current = 0; } static __inline__ void ypan_up(struct vc_data *vc, int count) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_display *p = &fb_display[vc->vc_num]; struct fbcon_ops *ops = info->fbcon_par; p->yscroll += count; if (p->yscroll > p->vrows - vc->vc_rows) { ops->bmove(vc, info, p->vrows - vc->vc_rows, 0, 0, 0, vc->vc_rows, vc->vc_cols); p->yscroll -= p->vrows - vc->vc_rows; } ops->var.xoffset = 0; ops->var.yoffset = p->yscroll * vc->vc_font.height; ops->var.vmode &= ~FB_VMODE_YWRAP; ops->update_start(info); fbcon_clear_margins(vc, 1); scrollback_max += count; if (scrollback_max > scrollback_phys_max) scrollback_max = scrollback_phys_max; scrollback_current = 0; } static __inline__ void ypan_up_redraw(struct vc_data *vc, int t, int count) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_ops *ops = info->fbcon_par; struct fbcon_display *p = &fb_display[vc->vc_num]; p->yscroll += count; if (p->yscroll > p->vrows - vc->vc_rows) { p->yscroll -= p->vrows - vc->vc_rows; fbcon_redraw_move(vc, p, t + count, vc->vc_rows - count, t); } ops->var.xoffset = 0; ops->var.yoffset = p->yscroll * vc->vc_font.height; ops->var.vmode &= ~FB_VMODE_YWRAP; ops->update_start(info); fbcon_clear_margins(vc, 1); scrollback_max += count; if (scrollback_max > scrollback_phys_max) scrollback_max = scrollback_phys_max; scrollback_current = 0; } static __inline__ void ypan_down(struct vc_data *vc, int count) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_display *p = &fb_display[vc->vc_num]; struct fbcon_ops *ops = info->fbcon_par; p->yscroll -= count; if (p->yscroll < 0) { ops->bmove(vc, info, 0, 0, p->vrows - vc->vc_rows, 0, vc->vc_rows, vc->vc_cols); p->yscroll += p->vrows - vc->vc_rows; } ops->var.xoffset = 0; ops->var.yoffset = p->yscroll * vc->vc_font.height; ops->var.vmode &= ~FB_VMODE_YWRAP; ops->update_start(info); fbcon_clear_margins(vc, 1); scrollback_max -= count; if (scrollback_max < 0) scrollback_max = 0; scrollback_current = 0; } static __inline__ void ypan_down_redraw(struct vc_data *vc, int t, int count) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_ops *ops = info->fbcon_par; struct fbcon_display *p = &fb_display[vc->vc_num]; p->yscroll -= count; if (p->yscroll < 0) { p->yscroll += p->vrows - vc->vc_rows; fbcon_redraw_move(vc, p, t, vc->vc_rows - count, t + count); } ops->var.xoffset = 0; ops->var.yoffset = p->yscroll * vc->vc_font.height; ops->var.vmode &= ~FB_VMODE_YWRAP; ops->update_start(info); fbcon_clear_margins(vc, 1); scrollback_max -= count; if (scrollback_max < 0) scrollback_max = 0; scrollback_current = 0; } static void fbcon_redraw_move(struct vc_data *vc, struct fbcon_display *p, int line, int count, int dy) { unsigned short *s = (unsigned short *) (vc->vc_origin + vc->vc_size_row * line); while (count--) { unsigned short *start = s; unsigned short *le = advance_row(s, 1); unsigned short c; int x = 0; unsigned short attr = 1; do { c = scr_readw(s); if (attr != (c & 0xff00)) { attr = c & 0xff00; if (s > start) { fbcon_putcs(vc, start, s - start, dy, x); x += s - start; start = s; } } console_conditional_schedule(); s++; } while (s < le); if (s > start) fbcon_putcs(vc, start, s - start, dy, x); console_conditional_schedule(); dy++; } } static void fbcon_redraw_blit(struct vc_data *vc, struct fb_info *info, struct fbcon_display *p, int line, int count, int ycount) { int offset = ycount * vc->vc_cols; unsigned short *d = (unsigned short *) (vc->vc_origin + vc->vc_size_row * line); unsigned short *s = d + offset; struct fbcon_ops *ops = info->fbcon_par; while (count--) { unsigned short *start = s; unsigned short *le = advance_row(s, 1); unsigned short c; int x = 0; do { c = scr_readw(s); if (c == scr_readw(d)) { if (s > start) { ops->bmove(vc, info, line + ycount, x, line, x, 1, s-start); x += s - start + 1; start = s + 1; } else { x++; start++; } } scr_writew(c, d); console_conditional_schedule(); s++; d++; } while (s < le); if (s > start) ops->bmove(vc, info, line + ycount, x, line, x, 1, s-start); console_conditional_schedule(); if (ycount > 0) line++; else { line--; /* NOTE: We subtract two lines from these pointers */ s -= vc->vc_size_row; d -= vc->vc_size_row; } } } static void fbcon_redraw(struct vc_data *vc, int line, int count, int offset) { unsigned short *d = (unsigned short *) (vc->vc_origin + vc->vc_size_row * line); unsigned short *s = d + offset; while (count--) { unsigned short *start = s; unsigned short *le = advance_row(s, 1); unsigned short c; int x = 0; unsigned short attr = 1; do { c = scr_readw(s); if (attr != (c & 0xff00)) { attr = c & 0xff00; if (s > start) { fbcon_putcs(vc, start, s - start, line, x); x += s - start; start = s; } } if (c == scr_readw(d)) { if (s > start) { fbcon_putcs(vc, start, s - start, line, x); x += s - start + 1; start = s + 1; } else { x++; start++; } } scr_writew(c, d); console_conditional_schedule(); s++; d++; } while (s < le); if (s > start) fbcon_putcs(vc, start, s - start, line, x); console_conditional_schedule(); if (offset > 0) line++; else { line--; /* NOTE: We subtract two lines from these pointers */ s -= vc->vc_size_row; d -= vc->vc_size_row; } } } static void fbcon_bmove_rec(struct vc_data *vc, struct fbcon_display *p, int sy, int sx, int dy, int dx, int height, int width, u_int y_break) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_ops *ops = info->fbcon_par; u_int b; if (sy < y_break && sy + height > y_break) { b = y_break - sy; if (dy < sy) { /* Avoid trashing self */ fbcon_bmove_rec(vc, p, sy, sx, dy, dx, b, width, y_break); fbcon_bmove_rec(vc, p, sy + b, sx, dy + b, dx, height - b, width, y_break); } else { fbcon_bmove_rec(vc, p, sy + b, sx, dy + b, dx, height - b, width, y_break); fbcon_bmove_rec(vc, p, sy, sx, dy, dx, b, width, y_break); } return; } if (dy < y_break && dy + height > y_break) { b = y_break - dy; if (dy < sy) { /* Avoid trashing self */ fbcon_bmove_rec(vc, p, sy, sx, dy, dx, b, width, y_break); fbcon_bmove_rec(vc, p, sy + b, sx, dy + b, dx, height - b, width, y_break); } else { fbcon_bmove_rec(vc, p, sy + b, sx, dy + b, dx, height - b, width, y_break); fbcon_bmove_rec(vc, p, sy, sx, dy, dx, b, width, y_break); } return; } ops->bmove(vc, info, real_y(p, sy), sx, real_y(p, dy), dx, height, width); } static void fbcon_bmove(struct vc_data *vc, int sy, int sx, int dy, int dx, int height, int width) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_display *p = &fb_display[vc->vc_num]; if (fbcon_is_inactive(vc, info)) return; if (!width || !height) return; /* Split blits that cross physical y_wrap case. * Pathological case involves 4 blits, better to use recursive * code rather than unrolled case * * Recursive invocations don't need to erase the cursor over and * over again, so we use fbcon_bmove_rec() */ fbcon_bmove_rec(vc, p, sy, sx, dy, dx, height, width, p->vrows - p->yscroll); } static bool fbcon_scroll(struct vc_data *vc, unsigned int t, unsigned int b, enum con_scroll dir, unsigned int count) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_display *p = &fb_display[vc->vc_num]; int scroll_partial = info->flags & FBINFO_PARTIAL_PAN_OK; if (fbcon_is_inactive(vc, info)) return true; fbcon_cursor(vc, false); /* * ++Geert: Only use ywrap/ypan if the console is in text mode * ++Andrew: Only use ypan on hardware text mode when scrolling the * whole screen (prevents flicker). */ switch (dir) { case SM_UP: if (count > vc->vc_rows) /* Maximum realistic size */ count = vc->vc_rows; switch (fb_scrollmode(p)) { case SCROLL_MOVE: fbcon_redraw_blit(vc, info, p, t, b - t - count, count); __fbcon_clear(vc, b - count, 0, count, vc->vc_cols); scr_memsetw((unsigned short *) (vc->vc_origin + vc->vc_size_row * (b - count)), vc->vc_video_erase_char, vc->vc_size_row * count); return true; case SCROLL_WRAP_MOVE: if (b - t - count > 3 * vc->vc_rows >> 2) { if (t > 0) fbcon_bmove(vc, 0, 0, count, 0, t, vc->vc_cols); ywrap_up(vc, count); if (vc->vc_rows - b > 0) fbcon_bmove(vc, b - count, 0, b, 0, vc->vc_rows - b, vc->vc_cols); } else if (info->flags & FBINFO_READS_FAST) fbcon_bmove(vc, t + count, 0, t, 0, b - t - count, vc->vc_cols); else goto redraw_up; __fbcon_clear(vc, b - count, 0, count, vc->vc_cols); break; case SCROLL_PAN_REDRAW: if ((p->yscroll + count <= 2 * (p->vrows - vc->vc_rows)) && ((!scroll_partial && (b - t == vc->vc_rows)) || (scroll_partial && (b - t - count > 3 * vc->vc_rows >> 2)))) { if (t > 0) fbcon_redraw_move(vc, p, 0, t, count); ypan_up_redraw(vc, t, count); if (vc->vc_rows - b > 0) fbcon_redraw_move(vc, p, b, vc->vc_rows - b, b); } else fbcon_redraw_move(vc, p, t + count, b - t - count, t); __fbcon_clear(vc, b - count, 0, count, vc->vc_cols); break; case SCROLL_PAN_MOVE: if ((p->yscroll + count <= 2 * (p->vrows - vc->vc_rows)) && ((!scroll_partial && (b - t == vc->vc_rows)) || (scroll_partial && (b - t - count > 3 * vc->vc_rows >> 2)))) { if (t > 0) fbcon_bmove(vc, 0, 0, count, 0, t, vc->vc_cols); ypan_up(vc, count); if (vc->vc_rows - b > 0) fbcon_bmove(vc, b - count, 0, b, 0, vc->vc_rows - b, vc->vc_cols); } else if (info->flags & FBINFO_READS_FAST) fbcon_bmove(vc, t + count, 0, t, 0, b - t - count, vc->vc_cols); else goto redraw_up; __fbcon_clear(vc, b - count, 0, count, vc->vc_cols); break; case SCROLL_REDRAW: redraw_up: fbcon_redraw(vc, t, b - t - count, count * vc->vc_cols); __fbcon_clear(vc, b - count, 0, count, vc->vc_cols); scr_memsetw((unsigned short *) (vc->vc_origin + vc->vc_size_row * (b - count)), vc->vc_video_erase_char, vc->vc_size_row * count); return true; } break; case SM_DOWN: if (count > vc->vc_rows) /* Maximum realistic size */ count = vc->vc_rows; switch (fb_scrollmode(p)) { case SCROLL_MOVE: fbcon_redraw_blit(vc, info, p, b - 1, b - t - count, -count); __fbcon_clear(vc, t, 0, count, vc->vc_cols); scr_memsetw((unsigned short *) (vc->vc_origin + vc->vc_size_row * t), vc->vc_video_erase_char, vc->vc_size_row * count); return true; case SCROLL_WRAP_MOVE: if (b - t - count > 3 * vc->vc_rows >> 2) { if (vc->vc_rows - b > 0) fbcon_bmove(vc, b, 0, b - count, 0, vc->vc_rows - b, vc->vc_cols); ywrap_down(vc, count); if (t > 0) fbcon_bmove(vc, count, 0, 0, 0, t, vc->vc_cols); } else if (info->flags & FBINFO_READS_FAST) fbcon_bmove(vc, t, 0, t + count, 0, b - t - count, vc->vc_cols); else goto redraw_down; __fbcon_clear(vc, t, 0, count, vc->vc_cols); break; case SCROLL_PAN_MOVE: if ((count - p->yscroll <= p->vrows - vc->vc_rows) && ((!scroll_partial && (b - t == vc->vc_rows)) || (scroll_partial && (b - t - count > 3 * vc->vc_rows >> 2)))) { if (vc->vc_rows - b > 0) fbcon_bmove(vc, b, 0, b - count, 0, vc->vc_rows - b, vc->vc_cols); ypan_down(vc, count); if (t > 0) fbcon_bmove(vc, count, 0, 0, 0, t, vc->vc_cols); } else if (info->flags & FBINFO_READS_FAST) fbcon_bmove(vc, t, 0, t + count, 0, b - t - count, vc->vc_cols); else goto redraw_down; __fbcon_clear(vc, t, 0, count, vc->vc_cols); break; case SCROLL_PAN_REDRAW: if ((count - p->yscroll <= p->vrows - vc->vc_rows) && ((!scroll_partial && (b - t == vc->vc_rows)) || (scroll_partial && (b - t - count > 3 * vc->vc_rows >> 2)))) { if (vc->vc_rows - b > 0) fbcon_redraw_move(vc, p, b, vc->vc_rows - b, b - count); ypan_down_redraw(vc, t, count); if (t > 0) fbcon_redraw_move(vc, p, count, t, 0); } else fbcon_redraw_move(vc, p, t, b - t - count, t + count); __fbcon_clear(vc, t, 0, count, vc->vc_cols); break; case SCROLL_REDRAW: redraw_down: fbcon_redraw(vc, b - 1, b - t - count, -count * vc->vc_cols); __fbcon_clear(vc, t, 0, count, vc->vc_cols); scr_memsetw((unsigned short *) (vc->vc_origin + vc->vc_size_row * t), vc->vc_video_erase_char, vc->vc_size_row * count); return true; } } return false; } static void updatescrollmode_accel(struct fbcon_display *p, struct fb_info *info, struct vc_data *vc) { #ifdef CONFIG_FRAMEBUFFER_CONSOLE_LEGACY_ACCELERATION struct fbcon_ops *ops = info->fbcon_par; int cap = info->flags; u16 t = 0; int ypan = FBCON_SWAP(ops->rotate, info->fix.ypanstep, info->fix.xpanstep); int ywrap = FBCON_SWAP(ops->rotate, info->fix.ywrapstep, t); int yres = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres); int vyres = FBCON_SWAP(ops->rotate, info->var.yres_virtual, info->var.xres_virtual); int good_pan = (cap & FBINFO_HWACCEL_YPAN) && divides(ypan, vc->vc_font.height) && vyres > yres; int good_wrap = (cap & FBINFO_HWACCEL_YWRAP) && divides(ywrap, vc->vc_font.height) && divides(vc->vc_font.height, vyres) && divides(vc->vc_font.height, yres); int reading_fast = cap & FBINFO_READS_FAST; int fast_copyarea = (cap & FBINFO_HWACCEL_COPYAREA) && !(cap & FBINFO_HWACCEL_DISABLED); int fast_imageblit = (cap & FBINFO_HWACCEL_IMAGEBLIT) && !(cap & FBINFO_HWACCEL_DISABLED); if (good_wrap || good_pan) { if (reading_fast || fast_copyarea) p->scrollmode = good_wrap ? SCROLL_WRAP_MOVE : SCROLL_PAN_MOVE; else p->scrollmode = good_wrap ? SCROLL_REDRAW : SCROLL_PAN_REDRAW; } else { if (reading_fast || (fast_copyarea && !fast_imageblit)) p->scrollmode = SCROLL_MOVE; else p->scrollmode = SCROLL_REDRAW; } #endif } static void updatescrollmode(struct fbcon_display *p, struct fb_info *info, struct vc_data *vc) { struct fbcon_ops *ops = info->fbcon_par; int fh = vc->vc_font.height; int yres = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres); int vyres = FBCON_SWAP(ops->rotate, info->var.yres_virtual, info->var.xres_virtual); p->vrows = vyres/fh; if (yres > (fh * (vc->vc_rows + 1))) p->vrows -= (yres - (fh * vc->vc_rows)) / fh; if ((yres % fh) && (vyres % fh < yres % fh)) p->vrows--; /* update scrollmode in case hardware acceleration is used */ updatescrollmode_accel(p, info, vc); } #define PITCH(w) (((w) + 7) >> 3) #define CALC_FONTSZ(h, p, c) ((h) * (p) * (c)) /* size = height * pitch * charcount */ static int fbcon_resize(struct vc_data *vc, unsigned int width, unsigned int height, bool from_user) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_ops *ops = info->fbcon_par; struct fbcon_display *p = &fb_display[vc->vc_num]; struct fb_var_screeninfo var = info->var; int x_diff, y_diff, virt_w, virt_h, virt_fw, virt_fh; if (p->userfont && FNTSIZE(vc->vc_font.data)) { int size; int pitch = PITCH(vc->vc_font.width); /* * If user font, ensure that a possible change to user font * height or width will not allow a font data out-of-bounds access. * NOTE: must use original charcount in calculation as font * charcount can change and cannot be used to determine the * font data allocated size. */ if (pitch <= 0) return -EINVAL; size = CALC_FONTSZ(vc->vc_font.height, pitch, vc->vc_font.charcount); if (size > FNTSIZE(vc->vc_font.data)) return -EINVAL; } virt_w = FBCON_SWAP(ops->rotate, width, height); virt_h = FBCON_SWAP(ops->rotate, height, width); virt_fw = FBCON_SWAP(ops->rotate, vc->vc_font.width, vc->vc_font.height); virt_fh = FBCON_SWAP(ops->rotate, vc->vc_font.height, vc->vc_font.width); var.xres = virt_w * virt_fw; var.yres = virt_h * virt_fh; x_diff = info->var.xres - var.xres; y_diff = info->var.yres - var.yres; if (x_diff < 0 || x_diff > virt_fw || y_diff < 0 || y_diff > virt_fh) { const struct fb_videomode *mode; pr_debug("attempting resize %ix%i\n", var.xres, var.yres); mode = fb_find_best_mode(&var, &info->modelist); if (mode == NULL) return -EINVAL; display_to_var(&var, p); fb_videomode_to_var(&var, mode); if (virt_w > var.xres/virt_fw || virt_h > var.yres/virt_fh) return -EINVAL; pr_debug("resize now %ix%i\n", var.xres, var.yres); if (con_is_visible(vc) && vc->vc_mode == KD_TEXT) { var.activate = FB_ACTIVATE_NOW | FB_ACTIVATE_FORCE; fb_set_var(info, &var); } var_to_display(p, &info->var, info); ops->var = info->var; } updatescrollmode(p, info, vc); return 0; } static bool fbcon_switch(struct vc_data *vc) { struct fb_info *info, *old_info = NULL; struct fbcon_ops *ops; struct fbcon_display *p = &fb_display[vc->vc_num]; struct fb_var_screeninfo var; int i, ret, prev_console; info = fbcon_info_from_console(vc->vc_num); ops = info->fbcon_par; if (logo_shown >= 0) { struct vc_data *conp2 = vc_cons[logo_shown].d; if (conp2->vc_top == logo_lines && conp2->vc_bottom == conp2->vc_rows) conp2->vc_top = 0; logo_shown = FBCON_LOGO_CANSHOW; } prev_console = ops->currcon; if (prev_console != -1) old_info = fbcon_info_from_console(prev_console); /* * FIXME: If we have multiple fbdev's loaded, we need to * update all info->currcon. Perhaps, we can place this * in a centralized structure, but this might break some * drivers. * * info->currcon = vc->vc_num; */ fbcon_for_each_registered_fb(i) { if (fbcon_registered_fb[i]->fbcon_par) { struct fbcon_ops *o = fbcon_registered_fb[i]->fbcon_par; o->currcon = vc->vc_num; } } memset(&var, 0, sizeof(struct fb_var_screeninfo)); display_to_var(&var, p); var.activate = FB_ACTIVATE_NOW; /* * make sure we don't unnecessarily trip the memcmp() * in fb_set_var() */ info->var.activate = var.activate; var.vmode |= info->var.vmode & ~FB_VMODE_MASK; fb_set_var(info, &var); ops->var = info->var; if (old_info != NULL && (old_info != info || info->flags & FBINFO_MISC_ALWAYS_SETPAR)) { if (info->fbops->fb_set_par) { ret = info->fbops->fb_set_par(info); if (ret) printk(KERN_ERR "fbcon_switch: detected " "unhandled fb_set_par error, " "error code %d\n", ret); } if (old_info != info) fbcon_del_cursor_work(old_info); } if (fbcon_is_inactive(vc, info) || ops->blank_state != FB_BLANK_UNBLANK) fbcon_del_cursor_work(info); else fbcon_add_cursor_work(info); set_blitting_type(vc, info); ops->cursor_reset = 1; if (ops->rotate_font && ops->rotate_font(info, vc)) { ops->rotate = FB_ROTATE_UR; set_blitting_type(vc, info); } vc->vc_can_do_color = (fb_get_color_depth(&info->var, &info->fix)!=1); vc->vc_complement_mask = vc->vc_can_do_color ? 0x7700 : 0x0800; if (vc->vc_font.charcount > 256) vc->vc_complement_mask <<= 1; updatescrollmode(p, info, vc); switch (fb_scrollmode(p)) { case SCROLL_WRAP_MOVE: scrollback_phys_max = p->vrows - vc->vc_rows; break; case SCROLL_PAN_MOVE: case SCROLL_PAN_REDRAW: scrollback_phys_max = p->vrows - 2 * vc->vc_rows; if (scrollback_phys_max < 0) scrollback_phys_max = 0; break; default: scrollback_phys_max = 0; break; } scrollback_max = 0; scrollback_current = 0; if (!fbcon_is_inactive(vc, info)) { ops->var.xoffset = ops->var.yoffset = p->yscroll = 0; ops->update_start(info); } fbcon_set_palette(vc, color_table); fbcon_clear_margins(vc, 0); if (logo_shown == FBCON_LOGO_DRAW) { logo_shown = fg_console; fb_show_logo(info, ops->rotate); update_region(vc, vc->vc_origin + vc->vc_size_row * vc->vc_top, vc->vc_size_row * (vc->vc_bottom - vc->vc_top) / 2); return false; } return true; } static void fbcon_generic_blank(struct vc_data *vc, struct fb_info *info, int blank) { if (blank) { unsigned short charmask = vc->vc_hi_font_mask ? 0x1ff : 0xff; unsigned short oldc; oldc = vc->vc_video_erase_char; vc->vc_video_erase_char &= charmask; __fbcon_clear(vc, 0, 0, vc->vc_rows, vc->vc_cols); vc->vc_video_erase_char = oldc; } } static bool fbcon_blank(struct vc_data *vc, enum vesa_blank_mode blank, bool mode_switch) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_ops *ops = info->fbcon_par; if (mode_switch) { struct fb_var_screeninfo var = info->var; ops->graphics = 1; if (!blank) { var.activate = FB_ACTIVATE_NOW | FB_ACTIVATE_FORCE | FB_ACTIVATE_KD_TEXT; fb_set_var(info, &var); ops->graphics = 0; ops->var = info->var; } } if (!fbcon_is_inactive(vc, info)) { if (ops->blank_state != blank) { ops->blank_state = blank; fbcon_cursor(vc, !blank); ops->cursor_flash = (!blank); if (fb_blank(info, blank)) fbcon_generic_blank(vc, info, blank); } if (!blank) update_screen(vc); } if (mode_switch || fbcon_is_inactive(vc, info) || ops->blank_state != FB_BLANK_UNBLANK) fbcon_del_cursor_work(info); else fbcon_add_cursor_work(info); return false; } static void fbcon_debug_enter(struct vc_data *vc) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_ops *ops = info->fbcon_par; ops->save_graphics = ops->graphics; ops->graphics = 0; if (info->fbops->fb_debug_enter) info->fbops->fb_debug_enter(info); fbcon_set_palette(vc, color_table); } static void fbcon_debug_leave(struct vc_data *vc) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_ops *ops = info->fbcon_par; ops->graphics = ops->save_graphics; if (info->fbops->fb_debug_leave) info->fbops->fb_debug_leave(info); } static int fbcon_get_font(struct vc_data *vc, struct console_font *font, unsigned int vpitch) { u8 *fontdata = vc->vc_font.data; u8 *data = font->data; int i, j; font->width = vc->vc_font.width; font->height = vc->vc_font.height; if (font->height > vpitch) return -ENOSPC; font->charcount = vc->vc_hi_font_mask ? 512 : 256; if (!font->data) return 0; if (font->width <= 8) { j = vc->vc_font.height; if (font->charcount * j > FNTSIZE(fontdata)) return -EINVAL; for (i = 0; i < font->charcount; i++) { memcpy(data, fontdata, j); memset(data + j, 0, vpitch - j); data += vpitch; fontdata += j; } } else if (font->width <= 16) { j = vc->vc_font.height * 2; if (font->charcount * j > FNTSIZE(fontdata)) return -EINVAL; for (i = 0; i < font->charcount; i++) { memcpy(data, fontdata, j); memset(data + j, 0, 2*vpitch - j); data += 2*vpitch; fontdata += j; } } else if (font->width <= 24) { if (font->charcount * (vc->vc_font.height * sizeof(u32)) > FNTSIZE(fontdata)) return -EINVAL; for (i = 0; i < font->charcount; i++) { for (j = 0; j < vc->vc_font.height; j++) { *data++ = fontdata[0]; *data++ = fontdata[1]; *data++ = fontdata[2]; fontdata += sizeof(u32); } memset(data, 0, 3 * (vpitch - j)); data += 3 * (vpitch - j); } } else { j = vc->vc_font.height * 4; if (font->charcount * j > FNTSIZE(fontdata)) return -EINVAL; for (i = 0; i < font->charcount; i++) { memcpy(data, fontdata, j); memset(data + j, 0, 4 * vpitch - j); data += 4 * vpitch; fontdata += j; } } return 0; } /* set/clear vc_hi_font_mask and update vc attrs accordingly */ static void set_vc_hi_font(struct vc_data *vc, bool set) { if (!set) { vc->vc_hi_font_mask = 0; if (vc->vc_can_do_color) { vc->vc_complement_mask >>= 1; vc->vc_s_complement_mask >>= 1; } /* ++Edmund: reorder the attribute bits */ if (vc->vc_can_do_color) { unsigned short *cp = (unsigned short *) vc->vc_origin; int count = vc->vc_screenbuf_size / 2; unsigned short c; for (; count > 0; count--, cp++) { c = scr_readw(cp); scr_writew(((c & 0xfe00) >> 1) | (c & 0xff), cp); } c = vc->vc_video_erase_char; vc->vc_video_erase_char = ((c & 0xfe00) >> 1) | (c & 0xff); vc->vc_attr >>= 1; } } else { vc->vc_hi_font_mask = 0x100; if (vc->vc_can_do_color) { vc->vc_complement_mask <<= 1; vc->vc_s_complement_mask <<= 1; } /* ++Edmund: reorder the attribute bits */ { unsigned short *cp = (unsigned short *) vc->vc_origin; int count = vc->vc_screenbuf_size / 2; unsigned short c; for (; count > 0; count--, cp++) { unsigned short newc; c = scr_readw(cp); if (vc->vc_can_do_color) newc = ((c & 0xff00) << 1) | (c & 0xff); else newc = c & ~0x100; scr_writew(newc, cp); } c = vc->vc_video_erase_char; if (vc->vc_can_do_color) { vc->vc_video_erase_char = ((c & 0xff00) << 1) | (c & 0xff); vc->vc_attr <<= 1; } else vc->vc_video_erase_char = c & ~0x100; } } } static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount, const u8 * data, int userfont) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_ops *ops = info->fbcon_par; struct fbcon_display *p = &fb_display[vc->vc_num]; int resize, ret, old_userfont, old_width, old_height, old_charcount; u8 *old_data = vc->vc_font.data; resize = (w != vc->vc_font.width) || (h != vc->vc_font.height); vc->vc_font.data = (void *)(p->fontdata = data); old_userfont = p->userfont; if ((p->userfont = userfont)) REFCOUNT(data)++; old_width = vc->vc_font.width; old_height = vc->vc_font.height; old_charcount = vc->vc_font.charcount; vc->vc_font.width = w; vc->vc_font.height = h; vc->vc_font.charcount = charcount; if (vc->vc_hi_font_mask && charcount == 256) set_vc_hi_font(vc, false); else if (!vc->vc_hi_font_mask && charcount == 512) set_vc_hi_font(vc, true); if (resize) { int cols, rows; cols = FBCON_SWAP(ops->rotate, info->var.xres, info->var.yres); rows = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres); cols /= w; rows /= h; ret = vc_resize(vc, cols, rows); if (ret) goto err_out; } else if (con_is_visible(vc) && vc->vc_mode == KD_TEXT) { fbcon_clear_margins(vc, 0); update_screen(vc); } if (old_userfont && (--REFCOUNT(old_data) == 0)) kfree(old_data - FONT_EXTRA_WORDS * sizeof(int)); return 0; err_out: p->fontdata = old_data; vc->vc_font.data = old_data; if (userfont) { p->userfont = old_userfont; if (--REFCOUNT(data) == 0) kfree(data - FONT_EXTRA_WORDS * sizeof(int)); } vc->vc_font.width = old_width; vc->vc_font.height = old_height; vc->vc_font.charcount = old_charcount; return ret; } /* * User asked to set font; we are guaranteed that charcount does not exceed 512 * but lets not assume that, since charcount of 512 is small for unicode support. */ static int fbcon_set_font(struct vc_data *vc, const struct console_font *font, unsigned int vpitch, unsigned int flags) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); unsigned charcount = font->charcount; int w = font->width; int h = font->height; int size; int i, csum; u8 *new_data, *data = font->data; int pitch = PITCH(font->width); /* Is there a reason why fbconsole couldn't handle any charcount >256? * If not this check should be changed to charcount < 256 */ if (charcount != 256 && charcount != 512) return -EINVAL; /* font bigger than screen resolution ? */ if (w > FBCON_SWAP(info->var.rotate, info->var.xres, info->var.yres) || h > FBCON_SWAP(info->var.rotate, info->var.yres, info->var.xres)) return -EINVAL; if (font->width > FB_MAX_BLIT_WIDTH || font->height > FB_MAX_BLIT_HEIGHT) return -EINVAL; /* Make sure drawing engine can handle the font */ if (!test_bit(font->width - 1, info->pixmap.blit_x) || !test_bit(font->height - 1, info->pixmap.blit_y)) return -EINVAL; /* Make sure driver can handle the font length */ if (fbcon_invalid_charcount(info, charcount)) return -EINVAL; size = CALC_FONTSZ(h, pitch, charcount); new_data = kmalloc(FONT_EXTRA_WORDS * sizeof(int) + size, GFP_USER); if (!new_data) return -ENOMEM; memset(new_data, 0, FONT_EXTRA_WORDS * sizeof(int)); new_data += FONT_EXTRA_WORDS * sizeof(int); FNTSIZE(new_data) = size; REFCOUNT(new_data) = 0; /* usage counter */ for (i=0; i< charcount; i++) { memcpy(new_data + i*h*pitch, data + i*vpitch*pitch, h*pitch); } /* Since linux has a nice crc32 function use it for counting font * checksums. */ csum = crc32(0, new_data, size); FNTSUM(new_data) = csum; /* Check if the same font is on some other console already */ for (i = first_fb_vc; i <= last_fb_vc; i++) { struct vc_data *tmp = vc_cons[i].d; if (fb_display[i].userfont && fb_display[i].fontdata && FNTSUM(fb_display[i].fontdata) == csum && FNTSIZE(fb_display[i].fontdata) == size && tmp->vc_font.width == w && !memcmp(fb_display[i].fontdata, new_data, size)) { kfree(new_data - FONT_EXTRA_WORDS * sizeof(int)); new_data = (u8 *)fb_display[i].fontdata; break; } } return fbcon_do_set_font(vc, font->width, font->height, charcount, new_data, 1); } static int fbcon_set_def_font(struct vc_data *vc, struct console_font *font, const char *name) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); const struct font_desc *f; if (!name) f = get_default_font(info->var.xres, info->var.yres, info->pixmap.blit_x, info->pixmap.blit_y); else if (!(f = find_font(name))) return -ENOENT; font->width = f->width; font->height = f->height; return fbcon_do_set_font(vc, f->width, f->height, f->charcount, f->data, 0); } static u16 palette_red[16]; static u16 palette_green[16]; static u16 palette_blue[16]; static struct fb_cmap palette_cmap = { 0, 16, palette_red, palette_green, palette_blue, NULL }; static void fbcon_set_palette(struct vc_data *vc, const unsigned char *table) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); int i, j, k, depth; u8 val; if (fbcon_is_inactive(vc, info)) return; if (!con_is_visible(vc)) return; depth = fb_get_color_depth(&info->var, &info->fix); if (depth > 3) { for (i = j = 0; i < 16; i++) { k = table[i]; val = vc->vc_palette[j++]; palette_red[k] = (val << 8) | val; val = vc->vc_palette[j++]; palette_green[k] = (val << 8) | val; val = vc->vc_palette[j++]; palette_blue[k] = (val << 8) | val; } palette_cmap.len = 16; palette_cmap.start = 0; /* * If framebuffer is capable of less than 16 colors, * use default palette of fbcon. */ } else fb_copy_cmap(fb_default_cmap(1 << depth), &palette_cmap); fb_set_cmap(&palette_cmap, info); } /* As we might be inside of softback, we may work with non-contiguous buffer, that's why we have to use a separate routine. */ static void fbcon_invert_region(struct vc_data *vc, u16 * p, int cnt) { while (cnt--) { u16 a = scr_readw(p); if (!vc->vc_can_do_color) a ^= 0x0800; else if (vc->vc_hi_font_mask == 0x100) a = ((a) & 0x11ff) | (((a) & 0xe000) >> 4) | (((a) & 0x0e00) << 4); else a = ((a) & 0x88ff) | (((a) & 0x7000) >> 4) | (((a) & 0x0700) << 4); scr_writew(a, p++); } } void fbcon_suspended(struct fb_info *info) { struct vc_data *vc = NULL; struct fbcon_ops *ops = info->fbcon_par; if (!ops || ops->currcon < 0) return; vc = vc_cons[ops->currcon].d; /* Clear cursor, restore saved data */ fbcon_cursor(vc, false); } void fbcon_resumed(struct fb_info *info) { struct vc_data *vc; struct fbcon_ops *ops = info->fbcon_par; if (!ops || ops->currcon < 0) return; vc = vc_cons[ops->currcon].d; update_screen(vc); } static void fbcon_modechanged(struct fb_info *info) { struct fbcon_ops *ops = info->fbcon_par; struct vc_data *vc; struct fbcon_display *p; int rows, cols; if (!ops || ops->currcon < 0) return; vc = vc_cons[ops->currcon].d; if (vc->vc_mode != KD_TEXT || fbcon_info_from_console(ops->currcon) != info) return; p = &fb_display[vc->vc_num]; set_blitting_type(vc, info); if (con_is_visible(vc)) { var_to_display(p, &info->var, info); cols = FBCON_SWAP(ops->rotate, info->var.xres, info->var.yres); rows = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres); cols /= vc->vc_font.width; rows /= vc->vc_font.height; vc_resize(vc, cols, rows); updatescrollmode(p, info, vc); scrollback_max = 0; scrollback_current = 0; if (!fbcon_is_inactive(vc, info)) { ops->var.xoffset = ops->var.yoffset = p->yscroll = 0; ops->update_start(info); } fbcon_set_palette(vc, color_table); update_screen(vc); } } static void fbcon_set_all_vcs(struct fb_info *info) { struct fbcon_ops *ops = info->fbcon_par; struct vc_data *vc; struct fbcon_display *p; int i, rows, cols, fg = -1; if (!ops || ops->currcon < 0) return; for (i = first_fb_vc; i <= last_fb_vc; i++) { vc = vc_cons[i].d; if (!vc || vc->vc_mode != KD_TEXT || fbcon_info_from_console(i) != info) continue; if (con_is_visible(vc)) { fg = i; continue; } p = &fb_display[vc->vc_num]; set_blitting_type(vc, info); var_to_display(p, &info->var, info); cols = FBCON_SWAP(ops->rotate, info->var.xres, info->var.yres); rows = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres); cols /= vc->vc_font.width; rows /= vc->vc_font.height; vc_resize(vc, cols, rows); } if (fg != -1) fbcon_modechanged(info); } void fbcon_update_vcs(struct fb_info *info, bool all) { if (all) fbcon_set_all_vcs(info); else fbcon_modechanged(info); } EXPORT_SYMBOL(fbcon_update_vcs); /* let fbcon check if it supports a new screen resolution */ int fbcon_modechange_possible(struct fb_info *info, struct fb_var_screeninfo *var) { struct fbcon_ops *ops = info->fbcon_par; struct vc_data *vc; unsigned int i; WARN_CONSOLE_UNLOCKED(); if (!ops) return 0; /* prevent setting a screen size which is smaller than font size */ for (i = first_fb_vc; i <= last_fb_vc; i++) { vc = vc_cons[i].d; if (!vc || vc->vc_mode != KD_TEXT || fbcon_info_from_console(i) != info) continue; if (vc->vc_font.width > FBCON_SWAP(var->rotate, var->xres, var->yres) || vc->vc_font.height > FBCON_SWAP(var->rotate, var->yres, var->xres)) return -EINVAL; } return 0; } EXPORT_SYMBOL_GPL(fbcon_modechange_possible); int fbcon_mode_deleted(struct fb_info *info, struct fb_videomode *mode) { struct fb_info *fb_info; struct fbcon_display *p; int i, j, found = 0; /* before deletion, ensure that mode is not in use */ for (i = first_fb_vc; i <= last_fb_vc; i++) { j = con2fb_map[i]; if (j == -1) continue; fb_info = fbcon_registered_fb[j]; if (fb_info != info) continue; p = &fb_display[i]; if (!p || !p->mode) continue; if (fb_mode_is_equal(p->mode, mode)) { found = 1; break; } } return found; } #ifdef CONFIG_VT_HW_CONSOLE_BINDING static void fbcon_unbind(void) { int ret; ret = do_unbind_con_driver(&fb_con, first_fb_vc, last_fb_vc, fbcon_is_default); if (!ret) fbcon_has_console_bind = 0; } #else static inline void fbcon_unbind(void) {} #endif /* CONFIG_VT_HW_CONSOLE_BINDING */ void fbcon_fb_unbind(struct fb_info *info) { int i, new_idx = -1; int idx = info->node; console_lock(); if (!fbcon_has_console_bind) { console_unlock(); return; } for (i = first_fb_vc; i <= last_fb_vc; i++) { if (con2fb_map[i] != idx && con2fb_map[i] != -1) { new_idx = con2fb_map[i]; break; } } if (new_idx != -1) { for (i = first_fb_vc; i <= last_fb_vc; i++) { if (con2fb_map[i] == idx) set_con2fb_map(i, new_idx, 0); } } else { struct fb_info *info = fbcon_registered_fb[idx]; /* This is sort of like set_con2fb_map, except it maps * the consoles to no device and then releases the * oldinfo to free memory and cancel the cursor blink * timer. I can imagine this just becoming part of * set_con2fb_map where new_idx is -1 */ for (i = first_fb_vc; i <= last_fb_vc; i++) { if (con2fb_map[i] == idx) { con2fb_map[i] = -1; if (!search_fb_in_map(idx)) { con2fb_release_oldinfo(vc_cons[i].d, info, NULL); } } } fbcon_unbind(); } console_unlock(); } void fbcon_fb_unregistered(struct fb_info *info) { int i, idx; console_lock(); fbcon_registered_fb[info->node] = NULL; fbcon_num_registered_fb--; if (deferred_takeover) { console_unlock(); return; } idx = info->node; for (i = first_fb_vc; i <= last_fb_vc; i++) { if (con2fb_map[i] == idx) con2fb_map[i] = -1; } if (idx == info_idx) { info_idx = -1; fbcon_for_each_registered_fb(i) { info_idx = i; break; } } if (info_idx != -1) { for (i = first_fb_vc; i <= last_fb_vc; i++) { if (con2fb_map[i] == -1) con2fb_map[i] = info_idx; } } if (primary_device == idx) primary_device = -1; if (!fbcon_num_registered_fb) do_unregister_con_driver(&fb_con); console_unlock(); } void fbcon_remap_all(struct fb_info *info) { int i, idx = info->node; console_lock(); if (deferred_takeover) { for (i = first_fb_vc; i <= last_fb_vc; i++) con2fb_map_boot[i] = idx; fbcon_map_override(); console_unlock(); return; } for (i = first_fb_vc; i <= last_fb_vc; i++) set_con2fb_map(i, idx, 0); if (con_is_bound(&fb_con)) { printk(KERN_INFO "fbcon: Remapping primary device, " "fb%i, to tty %i-%i\n", idx, first_fb_vc + 1, last_fb_vc + 1); info_idx = idx; } console_unlock(); } #ifdef CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY static void fbcon_select_primary(struct fb_info *info) { if (!map_override && primary_device == -1 && video_is_primary_device(info->device)) { int i; printk(KERN_INFO "fbcon: %s (fb%i) is primary device\n", info->fix.id, info->node); primary_device = info->node; for (i = first_fb_vc; i <= last_fb_vc; i++) con2fb_map_boot[i] = primary_device; if (con_is_bound(&fb_con)) { printk(KERN_INFO "fbcon: Remapping primary device, " "fb%i, to tty %i-%i\n", info->node, first_fb_vc + 1, last_fb_vc + 1); info_idx = primary_device; } } } #else static inline void fbcon_select_primary(struct fb_info *info) { return; } #endif /* CONFIG_FRAMEBUFFER_DETECT_PRIMARY */ static bool lockless_register_fb; module_param_named_unsafe(lockless_register_fb, lockless_register_fb, bool, 0400); MODULE_PARM_DESC(lockless_register_fb, "Lockless framebuffer registration for debugging [default=off]"); /* called with console_lock held */ static int do_fb_registered(struct fb_info *info) { int ret = 0, i, idx; WARN_CONSOLE_UNLOCKED(); fbcon_registered_fb[info->node] = info; fbcon_num_registered_fb++; idx = info->node; fbcon_select_primary(info); if (deferred_takeover) { pr_info("fbcon: Deferring console take-over\n"); return 0; } if (info_idx == -1) { for (i = first_fb_vc; i <= last_fb_vc; i++) { if (con2fb_map_boot[i] == idx) { info_idx = idx; break; } } if (info_idx != -1) ret = do_fbcon_takeover(1); } else { for (i = first_fb_vc; i <= last_fb_vc; i++) { if (con2fb_map_boot[i] == idx) set_con2fb_map(i, idx, 0); } } return ret; } int fbcon_fb_registered(struct fb_info *info) { int ret; if (!lockless_register_fb) console_lock(); else atomic_inc(&ignore_console_lock_warning); ret = do_fb_registered(info); if (!lockless_register_fb) console_unlock(); else atomic_dec(&ignore_console_lock_warning); return ret; } void fbcon_fb_blanked(struct fb_info *info, int blank) { struct fbcon_ops *ops = info->fbcon_par; struct vc_data *vc; if (!ops || ops->currcon < 0) return; vc = vc_cons[ops->currcon].d; if (vc->vc_mode != KD_TEXT || fbcon_info_from_console(ops->currcon) != info) return; if (con_is_visible(vc)) { if (blank) do_blank_screen(0); else do_unblank_screen(0); } ops->blank_state = blank; } void fbcon_new_modelist(struct fb_info *info) { int i; struct vc_data *vc; struct fb_var_screeninfo var; const struct fb_videomode *mode; for (i = first_fb_vc; i <= last_fb_vc; i++) { if (fbcon_info_from_console(i) != info) continue; if (!fb_display[i].mode) continue; vc = vc_cons[i].d; display_to_var(&var, &fb_display[i]); mode = fb_find_nearest_mode(fb_display[i].mode, &info->modelist); fb_videomode_to_var(&var, mode); fbcon_set_disp(info, &var, vc->vc_num); } } void fbcon_get_requirement(struct fb_info *info, struct fb_blit_caps *caps) { struct vc_data *vc; if (caps->flags) { int i, charcnt; for (i = first_fb_vc; i <= last_fb_vc; i++) { vc = vc_cons[i].d; if (vc && vc->vc_mode == KD_TEXT && info->node == con2fb_map[i]) { set_bit(vc->vc_font.width - 1, caps->x); set_bit(vc->vc_font.height - 1, caps->y); charcnt = vc->vc_font.charcount; if (caps->len < charcnt) caps->len = charcnt; } } } else { vc = vc_cons[fg_console].d; if (vc && vc->vc_mode == KD_TEXT && info->node == con2fb_map[fg_console]) { bitmap_zero(caps->x, FB_MAX_BLIT_WIDTH); set_bit(vc->vc_font.width - 1, caps->x); bitmap_zero(caps->y, FB_MAX_BLIT_HEIGHT); set_bit(vc->vc_font.height - 1, caps->y); caps->len = vc->vc_font.charcount; } } } int fbcon_set_con2fb_map_ioctl(void __user *argp) { struct fb_con2fbmap con2fb; int ret; if (copy_from_user(&con2fb, argp, sizeof(con2fb))) return -EFAULT; if (con2fb.console < 1 || con2fb.console > MAX_NR_CONSOLES) return -EINVAL; if (con2fb.framebuffer >= FB_MAX) return -EINVAL; if (!fbcon_registered_fb[con2fb.framebuffer]) request_module("fb%d", con2fb.framebuffer); if (!fbcon_registered_fb[con2fb.framebuffer]) { return -EINVAL; } console_lock(); ret = set_con2fb_map(con2fb.console - 1, con2fb.framebuffer, 1); console_unlock(); return ret; } int fbcon_get_con2fb_map_ioctl(void __user *argp) { struct fb_con2fbmap con2fb; if (copy_from_user(&con2fb, argp, sizeof(con2fb))) return -EFAULT; if (con2fb.console < 1 || con2fb.console > MAX_NR_CONSOLES) return -EINVAL; console_lock(); con2fb.framebuffer = con2fb_map[con2fb.console - 1]; console_unlock(); return copy_to_user(argp, &con2fb, sizeof(con2fb)) ? -EFAULT : 0; } /* * The console `switch' structure for the frame buffer based console */ static const struct consw fb_con = { .owner = THIS_MODULE, .con_startup = fbcon_startup, .con_init = fbcon_init, .con_deinit = fbcon_deinit, .con_clear = fbcon_clear, .con_putcs = fbcon_putcs, .con_cursor = fbcon_cursor, .con_scroll = fbcon_scroll, .con_switch = fbcon_switch, .con_blank = fbcon_blank, .con_font_set = fbcon_set_font, .con_font_get = fbcon_get_font, .con_font_default = fbcon_set_def_font, .con_set_palette = fbcon_set_palette, .con_invert_region = fbcon_invert_region, .con_resize = fbcon_resize, .con_debug_enter = fbcon_debug_enter, .con_debug_leave = fbcon_debug_leave, }; static ssize_t store_rotate(struct device *device, struct device_attribute *attr, const char *buf, size_t count) { struct fb_info *info; int rotate, idx; char **last = NULL; console_lock(); idx = con2fb_map[fg_console]; if (idx == -1 || fbcon_registered_fb[idx] == NULL) goto err; info = fbcon_registered_fb[idx]; rotate = simple_strtoul(buf, last, 0); fbcon_rotate(info, rotate); err: console_unlock(); return count; } static ssize_t store_rotate_all(struct device *device, struct device_attribute *attr,const char *buf, size_t count) { struct fb_info *info; int rotate, idx; char **last = NULL; console_lock(); idx = con2fb_map[fg_console]; if (idx == -1 || fbcon_registered_fb[idx] == NULL) goto err; info = fbcon_registered_fb[idx]; rotate = simple_strtoul(buf, last, 0); fbcon_rotate_all(info, rotate); err: console_unlock(); return count; } static ssize_t show_rotate(struct device *device, struct device_attribute *attr,char *buf) { struct fb_info *info; int rotate = 0, idx; console_lock(); idx = con2fb_map[fg_console]; if (idx == -1 || fbcon_registered_fb[idx] == NULL) goto err; info = fbcon_registered_fb[idx]; rotate = fbcon_get_rotate(info); err: console_unlock(); return sysfs_emit(buf, "%d\n", rotate); } static ssize_t show_cursor_blink(struct device *device, struct device_attribute *attr, char *buf) { struct fb_info *info; struct fbcon_ops *ops; int idx, blink = -1; console_lock(); idx = con2fb_map[fg_console]; if (idx == -1 || fbcon_registered_fb[idx] == NULL) goto err; info = fbcon_registered_fb[idx]; ops = info->fbcon_par; if (!ops) goto err; blink = delayed_work_pending(&ops->cursor_work); err: console_unlock(); return sysfs_emit(buf, "%d\n", blink); } static ssize_t store_cursor_blink(struct device *device, struct device_attribute *attr, const char *buf, size_t count) { struct fb_info *info; int blink, idx; char **last = NULL; console_lock(); idx = con2fb_map[fg_console]; if (idx == -1 || fbcon_registered_fb[idx] == NULL) goto err; info = fbcon_registered_fb[idx]; if (!info->fbcon_par) goto err; blink = simple_strtoul(buf, last, 0); if (blink) { fbcon_cursor_noblink = 0; fbcon_add_cursor_work(info); } else { fbcon_cursor_noblink = 1; fbcon_del_cursor_work(info); } err: console_unlock(); return count; } static struct device_attribute device_attrs[] = { __ATTR(rotate, S_IRUGO|S_IWUSR, show_rotate, store_rotate), __ATTR(rotate_all, S_IWUSR, NULL, store_rotate_all), __ATTR(cursor_blink, S_IRUGO|S_IWUSR, show_cursor_blink, store_cursor_blink), }; static int fbcon_init_device(void) { int i, error = 0; fbcon_has_sysfs = 1; for (i = 0; i < ARRAY_SIZE(device_attrs); i++) { error = device_create_file(fbcon_device, &device_attrs[i]); if (error) break; } if (error) { while (--i >= 0) device_remove_file(fbcon_device, &device_attrs[i]); fbcon_has_sysfs = 0; } return 0; } #ifdef CONFIG_FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER static void fbcon_register_existing_fbs(struct work_struct *work) { int i; console_lock(); deferred_takeover = false; logo_shown = FBCON_LOGO_DONTSHOW; fbcon_for_each_registered_fb(i) do_fb_registered(fbcon_registered_fb[i]); console_unlock(); } static struct notifier_block fbcon_output_nb; static DECLARE_WORK(fbcon_deferred_takeover_work, fbcon_register_existing_fbs); static int fbcon_output_notifier(struct notifier_block *nb, unsigned long action, void *data) { WARN_CONSOLE_UNLOCKED(); pr_info("fbcon: Taking over console\n"); dummycon_unregister_output_notifier(&fbcon_output_nb); /* We may get called in atomic context */ schedule_work(&fbcon_deferred_takeover_work); return NOTIFY_OK; } #endif static void fbcon_start(void) { WARN_CONSOLE_UNLOCKED(); #ifdef CONFIG_FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER if (conswitchp != &dummy_con) deferred_takeover = false; if (deferred_takeover) { fbcon_output_nb.notifier_call = fbcon_output_notifier; dummycon_register_output_notifier(&fbcon_output_nb); return; } #endif } void __init fb_console_init(void) { int i; console_lock(); fbcon_device = device_create(fb_class, NULL, MKDEV(0, 0), NULL, "fbcon"); if (IS_ERR(fbcon_device)) { printk(KERN_WARNING "Unable to create device " "for fbcon; errno = %ld\n", PTR_ERR(fbcon_device)); fbcon_device = NULL; } else fbcon_init_device(); for (i = 0; i < MAX_NR_CONSOLES; i++) con2fb_map[i] = -1; fbcon_start(); console_unlock(); } #ifdef MODULE static void __exit fbcon_deinit_device(void) { int i; if (fbcon_has_sysfs) { for (i = 0; i < ARRAY_SIZE(device_attrs); i++) device_remove_file(fbcon_device, &device_attrs[i]); fbcon_has_sysfs = 0; } } void __exit fb_console_exit(void) { #ifdef CONFIG_FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER console_lock(); if (deferred_takeover) dummycon_unregister_output_notifier(&fbcon_output_nb); console_unlock(); cancel_work_sync(&fbcon_deferred_takeover_work); #endif console_lock(); fbcon_deinit_device(); device_destroy(fb_class, MKDEV(0, 0)); do_unregister_con_driver(&fb_con); console_unlock(); } #endif |
| 3 39 39 2552 2 3 399 1 2491 297 692 194 161 292 45 695 189 114 6172 5813 1027 1763 5357 6083 9 58 641 1142 5482 5695 934 58 34 1171 114 114 4577 2 4578 2319 438 1660 1 20 8 4 63 541 136 15 826 357 332 1894 342 331 1806 15 25 25 21 512 902 33 1231 1089 1171 1 255 166 1 7 327 1 2 148 36 182 1 1 179 986 3 307 1072 237 89 521 51 502 20 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FS_H #define _LINUX_FS_H #include <linux/linkage.h> #include <linux/wait_bit.h> #include <linux/kdev_t.h> #include <linux/dcache.h> #include <linux/path.h> #include <linux/stat.h> #include <linux/cache.h> #include <linux/list.h> #include <linux/list_lru.h> #include <linux/llist.h> #include <linux/radix-tree.h> #include <linux/xarray.h> #include <linux/rbtree.h> #include <linux/init.h> #include <linux/pid.h> #include <linux/bug.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/mm_types.h> #include <linux/capability.h> #include <linux/semaphore.h> #include <linux/fcntl.h> #include <linux/rculist_bl.h> #include <linux/atomic.h> #include <linux/shrinker.h> #include <linux/migrate_mode.h> #include <linux/uidgid.h> #include <linux/lockdep.h> #include <linux/percpu-rwsem.h> #include <linux/workqueue.h> #include <linux/delayed_call.h> #include <linux/uuid.h> #include <linux/errseq.h> #include <linux/ioprio.h> #include <linux/fs_types.h> #include <linux/build_bug.h> #include <linux/stddef.h> #include <linux/mount.h> #include <linux/cred.h> #include <linux/mnt_idmapping.h> #include <linux/slab.h> #include <linux/maple_tree.h> #include <linux/rw_hint.h> #include <asm/byteorder.h> #include <uapi/linux/fs.h> struct backing_dev_info; struct bdi_writeback; struct bio; struct io_comp_batch; struct export_operations; struct fiemap_extent_info; struct hd_geometry; struct iovec; struct kiocb; struct kobject; struct pipe_inode_info; struct poll_table_struct; struct kstatfs; struct vm_area_struct; struct vfsmount; struct cred; struct swap_info_struct; struct seq_file; struct workqueue_struct; struct iov_iter; struct fscrypt_inode_info; struct fscrypt_operations; struct fsverity_info; struct fsverity_operations; struct fsnotify_mark_connector; struct fsnotify_sb_info; struct fs_context; struct fs_parameter_spec; struct fileattr; struct iomap_ops; extern void __init inode_init(void); extern void __init inode_init_early(void); extern void __init files_init(void); extern void __init files_maxfiles_init(void); extern unsigned long get_max_files(void); extern unsigned int sysctl_nr_open; typedef __kernel_rwf_t rwf_t; struct buffer_head; typedef int (get_block_t)(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, ssize_t bytes, void *private); #define MAY_EXEC 0x00000001 #define MAY_WRITE 0x00000002 #define MAY_READ 0x00000004 #define MAY_APPEND 0x00000008 #define MAY_ACCESS 0x00000010 #define MAY_OPEN 0x00000020 #define MAY_CHDIR 0x00000040 /* called from RCU mode, don't block */ #define MAY_NOT_BLOCK 0x00000080 /* * flags in file.f_mode. Note that FMODE_READ and FMODE_WRITE must correspond * to O_WRONLY and O_RDWR via the strange trick in do_dentry_open() */ /* file is open for reading */ #define FMODE_READ ((__force fmode_t)(1 << 0)) /* file is open for writing */ #define FMODE_WRITE ((__force fmode_t)(1 << 1)) /* file is seekable */ #define FMODE_LSEEK ((__force fmode_t)(1 << 2)) /* file can be accessed using pread */ #define FMODE_PREAD ((__force fmode_t)(1 << 3)) /* file can be accessed using pwrite */ #define FMODE_PWRITE ((__force fmode_t)(1 << 4)) /* File is opened for execution with sys_execve / sys_uselib */ #define FMODE_EXEC ((__force fmode_t)(1 << 5)) /* File writes are restricted (block device specific) */ #define FMODE_WRITE_RESTRICTED ((__force fmode_t)(1 << 6)) /* File supports atomic writes */ #define FMODE_CAN_ATOMIC_WRITE ((__force fmode_t)(1 << 7)) /* FMODE_* bit 8 */ /* 32bit hashes as llseek() offset (for directories) */ #define FMODE_32BITHASH ((__force fmode_t)(1 << 9)) /* 64bit hashes as llseek() offset (for directories) */ #define FMODE_64BITHASH ((__force fmode_t)(1 << 10)) /* * Don't update ctime and mtime. * * Currently a special hack for the XFS open_by_handle ioctl, but we'll * hopefully graduate it to a proper O_CMTIME flag supported by open(2) soon. */ #define FMODE_NOCMTIME ((__force fmode_t)(1 << 11)) /* Expect random access pattern */ #define FMODE_RANDOM ((__force fmode_t)(1 << 12)) /* File is huge (eg. /dev/mem): treat loff_t as unsigned */ #define FMODE_UNSIGNED_OFFSET ((__force fmode_t)(1 << 13)) /* File is opened with O_PATH; almost nothing can be done with it */ #define FMODE_PATH ((__force fmode_t)(1 << 14)) /* File needs atomic accesses to f_pos */ #define FMODE_ATOMIC_POS ((__force fmode_t)(1 << 15)) /* Write access to underlying fs */ #define FMODE_WRITER ((__force fmode_t)(1 << 16)) /* Has read method(s) */ #define FMODE_CAN_READ ((__force fmode_t)(1 << 17)) /* Has write method(s) */ #define FMODE_CAN_WRITE ((__force fmode_t)(1 << 18)) #define FMODE_OPENED ((__force fmode_t)(1 << 19)) #define FMODE_CREATED ((__force fmode_t)(1 << 20)) /* File is stream-like */ #define FMODE_STREAM ((__force fmode_t)(1 << 21)) /* File supports DIRECT IO */ #define FMODE_CAN_ODIRECT ((__force fmode_t)(1 << 22)) #define FMODE_NOREUSE ((__force fmode_t)(1 << 23)) /* FMODE_* bit 24 */ /* File is embedded in backing_file object */ #define FMODE_BACKING ((__force fmode_t)(1 << 25)) /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)(1 << 26)) /* File is capable of returning -EAGAIN if I/O will block */ #define FMODE_NOWAIT ((__force fmode_t)(1 << 27)) /* File represents mount that needs unmounting */ #define FMODE_NEED_UNMOUNT ((__force fmode_t)(1 << 28)) /* File does not contribute to nr_files count */ #define FMODE_NOACCOUNT ((__force fmode_t)(1 << 29)) /* * Attribute flags. These should be or-ed together to figure out what * has been changed! */ #define ATTR_MODE (1 << 0) #define ATTR_UID (1 << 1) #define ATTR_GID (1 << 2) #define ATTR_SIZE (1 << 3) #define ATTR_ATIME (1 << 4) #define ATTR_MTIME (1 << 5) #define ATTR_CTIME (1 << 6) #define ATTR_ATIME_SET (1 << 7) #define ATTR_MTIME_SET (1 << 8) #define ATTR_FORCE (1 << 9) /* Not a change, but a change it */ #define ATTR_KILL_SUID (1 << 11) #define ATTR_KILL_SGID (1 << 12) #define ATTR_FILE (1 << 13) #define ATTR_KILL_PRIV (1 << 14) #define ATTR_OPEN (1 << 15) /* Truncating from open(O_TRUNC) */ #define ATTR_TIMES_SET (1 << 16) #define ATTR_TOUCH (1 << 17) /* * Whiteout is represented by a char device. The following constants define the * mode and device number to use. */ #define WHITEOUT_MODE 0 #define WHITEOUT_DEV 0 /* * This is the Inode Attributes structure, used for notify_change(). It * uses the above definitions as flags, to know which values have changed. * Also, in this manner, a Filesystem can look at only the values it cares * about. Basically, these are the attributes that the VFS layer can * request to change from the FS layer. * * Derek Atkins <warlord@MIT.EDU> 94-10-20 */ struct iattr { unsigned int ia_valid; umode_t ia_mode; /* * The two anonymous unions wrap structures with the same member. * * Filesystems raising FS_ALLOW_IDMAP need to use ia_vfs{g,u}id which * are a dedicated type requiring the filesystem to use the dedicated * helpers. Other filesystem can continue to use ia_{g,u}id until they * have been ported. * * They always contain the same value. In other words FS_ALLOW_IDMAP * pass down the same value on idmapped mounts as they would on regular * mounts. */ union { kuid_t ia_uid; vfsuid_t ia_vfsuid; }; union { kgid_t ia_gid; vfsgid_t ia_vfsgid; }; loff_t ia_size; struct timespec64 ia_atime; struct timespec64 ia_mtime; struct timespec64 ia_ctime; /* * Not an attribute, but an auxiliary info for filesystems wanting to * implement an ftruncate() like method. NOTE: filesystem should * check for (ia_valid & ATTR_FILE), and not for (ia_file != NULL). */ struct file *ia_file; }; /* * Includes for diskquotas. */ #include <linux/quota.h> /* * Maximum number of layers of fs stack. Needs to be limited to * prevent kernel stack overflow */ #define FILESYSTEM_MAX_STACK_DEPTH 2 /** * enum positive_aop_returns - aop return codes with specific semantics * * @AOP_WRITEPAGE_ACTIVATE: Informs the caller that page writeback has * completed, that the page is still locked, and * should be considered active. The VM uses this hint * to return the page to the active list -- it won't * be a candidate for writeback again in the near * future. Other callers must be careful to unlock * the page if they get this return. Returned by * writepage(); * * @AOP_TRUNCATED_PAGE: The AOP method that was handed a locked page has * unlocked it and the page might have been truncated. * The caller should back up to acquiring a new page and * trying again. The aop will be taking reasonable * precautions not to livelock. If the caller held a page * reference, it should drop it before retrying. Returned * by read_folio(). * * address_space_operation functions return these large constants to indicate * special semantics to the caller. These are much larger than the bytes in a * page to allow for functions that return the number of bytes operated on in a * given page. */ enum positive_aop_returns { AOP_WRITEPAGE_ACTIVATE = 0x80000, AOP_TRUNCATED_PAGE = 0x80001, }; /* * oh the beauties of C type declarations. */ struct page; struct address_space; struct writeback_control; struct readahead_control; /* Match RWF_* bits to IOCB bits */ #define IOCB_HIPRI (__force int) RWF_HIPRI #define IOCB_DSYNC (__force int) RWF_DSYNC #define IOCB_SYNC (__force int) RWF_SYNC #define IOCB_NOWAIT (__force int) RWF_NOWAIT #define IOCB_APPEND (__force int) RWF_APPEND #define IOCB_ATOMIC (__force int) RWF_ATOMIC /* non-RWF related bits - start at 16 */ #define IOCB_EVENTFD (1 << 16) #define IOCB_DIRECT (1 << 17) #define IOCB_WRITE (1 << 18) /* iocb->ki_waitq is valid */ #define IOCB_WAITQ (1 << 19) #define IOCB_NOIO (1 << 20) /* can use bio alloc cache */ #define IOCB_ALLOC_CACHE (1 << 21) /* * IOCB_DIO_CALLER_COMP can be set by the iocb owner, to indicate that the * iocb completion can be passed back to the owner for execution from a safe * context rather than needing to be punted through a workqueue. If this * flag is set, the bio completion handling may set iocb->dio_complete to a * handler function and iocb->private to context information for that handler. * The issuer should call the handler with that context information from task * context to complete the processing of the iocb. Note that while this * provides a task context for the dio_complete() callback, it should only be * used on the completion side for non-IO generating completions. It's fine to * call blocking functions from this callback, but they should not wait for * unrelated IO (like cache flushing, new IO generation, etc). */ #define IOCB_DIO_CALLER_COMP (1 << 22) /* kiocb is a read or write operation submitted by fs/aio.c. */ #define IOCB_AIO_RW (1 << 23) /* for use in trace events */ #define TRACE_IOCB_STRINGS \ { IOCB_HIPRI, "HIPRI" }, \ { IOCB_DSYNC, "DSYNC" }, \ { IOCB_SYNC, "SYNC" }, \ { IOCB_NOWAIT, "NOWAIT" }, \ { IOCB_APPEND, "APPEND" }, \ { IOCB_ATOMIC, "ATOMIC"}, \ { IOCB_EVENTFD, "EVENTFD"}, \ { IOCB_DIRECT, "DIRECT" }, \ { IOCB_WRITE, "WRITE" }, \ { IOCB_WAITQ, "WAITQ" }, \ { IOCB_NOIO, "NOIO" }, \ { IOCB_ALLOC_CACHE, "ALLOC_CACHE" }, \ { IOCB_DIO_CALLER_COMP, "CALLER_COMP" } struct kiocb { struct file *ki_filp; loff_t ki_pos; void (*ki_complete)(struct kiocb *iocb, long ret); void *private; int ki_flags; u16 ki_ioprio; /* See linux/ioprio.h */ union { /* * Only used for async buffered reads, where it denotes the * page waitqueue associated with completing the read. Valid * IFF IOCB_WAITQ is set. */ struct wait_page_queue *ki_waitq; /* * Can be used for O_DIRECT IO, where the completion handling * is punted back to the issuer of the IO. May only be set * if IOCB_DIO_CALLER_COMP is set by the issuer, and the issuer * must then check for presence of this handler when ki_complete * is invoked. The data passed in to this handler must be * assigned to ->private when dio_complete is assigned. */ ssize_t (*dio_complete)(void *data); }; }; static inline bool is_sync_kiocb(struct kiocb *kiocb) { return kiocb->ki_complete == NULL; } struct address_space_operations { int (*writepage)(struct page *page, struct writeback_control *wbc); int (*read_folio)(struct file *, struct folio *); /* Write back some dirty pages from this mapping. */ int (*writepages)(struct address_space *, struct writeback_control *); /* Mark a folio dirty. Return true if this dirtied it */ bool (*dirty_folio)(struct address_space *, struct folio *); void (*readahead)(struct readahead_control *); int (*write_begin)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, struct page **pagep, void **fsdata); int (*write_end)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata); /* Unfortunately this kludge is needed for FIBMAP. Don't use it */ sector_t (*bmap)(struct address_space *, sector_t); void (*invalidate_folio) (struct folio *, size_t offset, size_t len); bool (*release_folio)(struct folio *, gfp_t); void (*free_folio)(struct folio *folio); ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter); /* * migrate the contents of a folio to the specified target. If * migrate_mode is MIGRATE_ASYNC, it must not block. */ int (*migrate_folio)(struct address_space *, struct folio *dst, struct folio *src, enum migrate_mode); int (*launder_folio)(struct folio *); bool (*is_partially_uptodate) (struct folio *, size_t from, size_t count); void (*is_dirty_writeback) (struct folio *, bool *dirty, bool *wb); int (*error_remove_folio)(struct address_space *, struct folio *); /* swapfile support */ int (*swap_activate)(struct swap_info_struct *sis, struct file *file, sector_t *span); void (*swap_deactivate)(struct file *file); int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter); }; extern const struct address_space_operations empty_aops; /** * struct address_space - Contents of a cacheable, mappable object. * @host: Owner, either the inode or the block_device. * @i_pages: Cached pages. * @invalidate_lock: Guards coherency between page cache contents and * file offset->disk block mappings in the filesystem during invalidates. * It is also used to block modification of page cache contents through * memory mappings. * @gfp_mask: Memory allocation flags to use for allocating pages. * @i_mmap_writable: Number of VM_SHARED, VM_MAYWRITE mappings. * @nr_thps: Number of THPs in the pagecache (non-shmem only). * @i_mmap: Tree of private and shared mappings. * @i_mmap_rwsem: Protects @i_mmap and @i_mmap_writable. * @nrpages: Number of page entries, protected by the i_pages lock. * @writeback_index: Writeback starts here. * @a_ops: Methods. * @flags: Error bits and flags (AS_*). * @wb_err: The most recent error which has occurred. * @i_private_lock: For use by the owner of the address_space. * @i_private_list: For use by the owner of the address_space. * @i_private_data: For use by the owner of the address_space. */ struct address_space { struct inode *host; struct xarray i_pages; struct rw_semaphore invalidate_lock; gfp_t gfp_mask; atomic_t i_mmap_writable; #ifdef CONFIG_READ_ONLY_THP_FOR_FS /* number of thp, only for non-shmem files */ atomic_t nr_thps; #endif struct rb_root_cached i_mmap; unsigned long nrpages; pgoff_t writeback_index; const struct address_space_operations *a_ops; unsigned long flags; errseq_t wb_err; spinlock_t i_private_lock; struct list_head i_private_list; struct rw_semaphore i_mmap_rwsem; void * i_private_data; } __attribute__((aligned(sizeof(long)))) __randomize_layout; /* * On most architectures that alignment is already the case; but * must be enforced here for CRIS, to let the least significant bit * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON. */ /* XArray tags, for tagging dirty and writeback pages in the pagecache. */ #define PAGECACHE_TAG_DIRTY XA_MARK_0 #define PAGECACHE_TAG_WRITEBACK XA_MARK_1 #define PAGECACHE_TAG_TOWRITE XA_MARK_2 /* * Returns true if any of the pages in the mapping are marked with the tag. */ static inline bool mapping_tagged(struct address_space *mapping, xa_mark_t tag) { return xa_marked(&mapping->i_pages, tag); } static inline void i_mmap_lock_write(struct address_space *mapping) { down_write(&mapping->i_mmap_rwsem); } static inline int i_mmap_trylock_write(struct address_space *mapping) { return down_write_trylock(&mapping->i_mmap_rwsem); } static inline void i_mmap_unlock_write(struct address_space *mapping) { up_write(&mapping->i_mmap_rwsem); } static inline int i_mmap_trylock_read(struct address_space *mapping) { return down_read_trylock(&mapping->i_mmap_rwsem); } static inline void i_mmap_lock_read(struct address_space *mapping) { down_read(&mapping->i_mmap_rwsem); } static inline void i_mmap_unlock_read(struct address_space *mapping) { up_read(&mapping->i_mmap_rwsem); } static inline void i_mmap_assert_locked(struct address_space *mapping) { lockdep_assert_held(&mapping->i_mmap_rwsem); } static inline void i_mmap_assert_write_locked(struct address_space *mapping) { lockdep_assert_held_write(&mapping->i_mmap_rwsem); } /* * Might pages of this file be mapped into userspace? */ static inline int mapping_mapped(struct address_space *mapping) { return !RB_EMPTY_ROOT(&mapping->i_mmap.rb_root); } /* * Might pages of this file have been modified in userspace? * Note that i_mmap_writable counts all VM_SHARED, VM_MAYWRITE vmas: do_mmap * marks vma as VM_SHARED if it is shared, and the file was opened for * writing i.e. vma may be mprotected writable even if now readonly. * * If i_mmap_writable is negative, no new writable mappings are allowed. You * can only deny writable mappings, if none exists right now. */ static inline int mapping_writably_mapped(struct address_space *mapping) { return atomic_read(&mapping->i_mmap_writable) > 0; } static inline int mapping_map_writable(struct address_space *mapping) { return atomic_inc_unless_negative(&mapping->i_mmap_writable) ? 0 : -EPERM; } static inline void mapping_unmap_writable(struct address_space *mapping) { atomic_dec(&mapping->i_mmap_writable); } static inline int mapping_deny_writable(struct address_space *mapping) { return atomic_dec_unless_positive(&mapping->i_mmap_writable) ? 0 : -EBUSY; } static inline void mapping_allow_writable(struct address_space *mapping) { atomic_inc(&mapping->i_mmap_writable); } /* * Use sequence counter to get consistent i_size on 32-bit processors. */ #if BITS_PER_LONG==32 && defined(CONFIG_SMP) #include <linux/seqlock.h> #define __NEED_I_SIZE_ORDERED #define i_size_ordered_init(inode) seqcount_init(&inode->i_size_seqcount) #else #define i_size_ordered_init(inode) do { } while (0) #endif struct posix_acl; #define ACL_NOT_CACHED ((void *)(-1)) /* * ACL_DONT_CACHE is for stacked filesystems, that rely on underlying fs to * cache the ACL. This also means that ->get_inode_acl() can be called in RCU * mode with the LOOKUP_RCU flag. */ #define ACL_DONT_CACHE ((void *)(-3)) static inline struct posix_acl * uncached_acl_sentinel(struct task_struct *task) { return (void *)task + 1; } static inline bool is_uncached_acl(struct posix_acl *acl) { return (long)acl & 1; } #define IOP_FASTPERM 0x0001 #define IOP_LOOKUP 0x0002 #define IOP_NOFOLLOW 0x0004 #define IOP_XATTR 0x0008 #define IOP_DEFAULT_READLINK 0x0010 /* * Keep mostly read-only and often accessed (especially for * the RCU path lookup and 'stat' data) fields at the beginning * of the 'struct inode' */ struct inode { umode_t i_mode; unsigned short i_opflags; kuid_t i_uid; kgid_t i_gid; unsigned int i_flags; #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *i_acl; struct posix_acl *i_default_acl; #endif const struct inode_operations *i_op; struct super_block *i_sb; struct address_space *i_mapping; #ifdef CONFIG_SECURITY void *i_security; #endif /* Stat data, not accessed from path walking */ unsigned long i_ino; /* * Filesystems may only read i_nlink directly. They shall use the * following functions for modification: * * (set|clear|inc|drop)_nlink * inode_(inc|dec)_link_count */ union { const unsigned int i_nlink; unsigned int __i_nlink; }; dev_t i_rdev; loff_t i_size; time64_t i_atime_sec; time64_t i_mtime_sec; time64_t i_ctime_sec; u32 i_atime_nsec; u32 i_mtime_nsec; u32 i_ctime_nsec; u32 i_generation; spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned short i_bytes; u8 i_blkbits; enum rw_hint i_write_hint; blkcnt_t i_blocks; #ifdef __NEED_I_SIZE_ORDERED seqcount_t i_size_seqcount; #endif /* Misc */ unsigned long i_state; struct rw_semaphore i_rwsem; unsigned long dirtied_when; /* jiffies of first dirtying */ unsigned long dirtied_time_when; struct hlist_node i_hash; struct list_head i_io_list; /* backing dev IO list */ #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *i_wb; /* the associated cgroup wb */ /* foreign inode detection, see wbc_detach_inode() */ int i_wb_frn_winner; u16 i_wb_frn_avg_time; u16 i_wb_frn_history; #endif struct list_head i_lru; /* inode LRU list */ struct list_head i_sb_list; struct list_head i_wb_list; /* backing dev writeback list */ union { struct hlist_head i_dentry; struct rcu_head i_rcu; }; atomic64_t i_version; atomic64_t i_sequence; /* see futex */ atomic_t i_count; atomic_t i_dio_count; atomic_t i_writecount; #if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING) atomic_t i_readcount; /* struct files open RO */ #endif union { const struct file_operations *i_fop; /* former ->i_op->default_file_ops */ void (*free_inode)(struct inode *); }; struct file_lock_context *i_flctx; struct address_space i_data; struct list_head i_devices; union { struct pipe_inode_info *i_pipe; struct cdev *i_cdev; char *i_link; unsigned i_dir_seq; }; #ifdef CONFIG_FSNOTIFY __u32 i_fsnotify_mask; /* all events this inode cares about */ /* 32-bit hole reserved for expanding i_fsnotify_mask */ struct fsnotify_mark_connector __rcu *i_fsnotify_marks; #endif #ifdef CONFIG_FS_ENCRYPTION struct fscrypt_inode_info *i_crypt_info; #endif #ifdef CONFIG_FS_VERITY struct fsverity_info *i_verity_info; #endif void *i_private; /* fs or device private pointer */ } __randomize_layout; struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode); static inline unsigned int i_blocksize(const struct inode *node) { return (1 << node->i_blkbits); } static inline int inode_unhashed(struct inode *inode) { return hlist_unhashed(&inode->i_hash); } /* * __mark_inode_dirty expects inodes to be hashed. Since we don't * want special inodes in the fileset inode space, we make them * appear hashed, but do not put on any lists. hlist_del() * will work fine and require no locking. */ static inline void inode_fake_hash(struct inode *inode) { hlist_add_fake(&inode->i_hash); } /* * inode->i_mutex nesting subclasses for the lock validator: * * 0: the object of the current VFS operation * 1: parent * 2: child/target * 3: xattr * 4: second non-directory * 5: second parent (when locking independent directories in rename) * * I_MUTEX_NONDIR2 is for certain operations (such as rename) which lock two * non-directories at once. * * The locking order between these classes is * parent[2] -> child -> grandchild -> normal -> xattr -> second non-directory */ enum inode_i_mutex_lock_class { I_MUTEX_NORMAL, I_MUTEX_PARENT, I_MUTEX_CHILD, I_MUTEX_XATTR, I_MUTEX_NONDIR2, I_MUTEX_PARENT2, }; static inline void inode_lock(struct inode *inode) { down_write(&inode->i_rwsem); } static inline void inode_unlock(struct inode *inode) { up_write(&inode->i_rwsem); } static inline void inode_lock_shared(struct inode *inode) { down_read(&inode->i_rwsem); } static inline void inode_unlock_shared(struct inode *inode) { up_read(&inode->i_rwsem); } static inline int inode_trylock(struct inode *inode) { return down_write_trylock(&inode->i_rwsem); } static inline int inode_trylock_shared(struct inode *inode) { return down_read_trylock(&inode->i_rwsem); } static inline int inode_is_locked(struct inode *inode) { return rwsem_is_locked(&inode->i_rwsem); } static inline void inode_lock_nested(struct inode *inode, unsigned subclass) { down_write_nested(&inode->i_rwsem, subclass); } static inline void inode_lock_shared_nested(struct inode *inode, unsigned subclass) { down_read_nested(&inode->i_rwsem, subclass); } static inline void filemap_invalidate_lock(struct address_space *mapping) { down_write(&mapping->invalidate_lock); } static inline void filemap_invalidate_unlock(struct address_space *mapping) { up_write(&mapping->invalidate_lock); } static inline void filemap_invalidate_lock_shared(struct address_space *mapping) { down_read(&mapping->invalidate_lock); } static inline int filemap_invalidate_trylock_shared( struct address_space *mapping) { return down_read_trylock(&mapping->invalidate_lock); } static inline void filemap_invalidate_unlock_shared( struct address_space *mapping) { up_read(&mapping->invalidate_lock); } void lock_two_nondirectories(struct inode *, struct inode*); void unlock_two_nondirectories(struct inode *, struct inode*); void filemap_invalidate_lock_two(struct address_space *mapping1, struct address_space *mapping2); void filemap_invalidate_unlock_two(struct address_space *mapping1, struct address_space *mapping2); /* * NOTE: in a 32bit arch with a preemptable kernel and * an UP compile the i_size_read/write must be atomic * with respect to the local cpu (unlike with preempt disabled), * but they don't need to be atomic with respect to other cpus like in * true SMP (so they need either to either locally disable irq around * the read or for example on x86 they can be still implemented as a * cmpxchg8b without the need of the lock prefix). For SMP compiles * and 64bit archs it makes no difference if preempt is enabled or not. */ static inline loff_t i_size_read(const struct inode *inode) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) loff_t i_size; unsigned int seq; do { seq = read_seqcount_begin(&inode->i_size_seqcount); i_size = inode->i_size; } while (read_seqcount_retry(&inode->i_size_seqcount, seq)); return i_size; #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) loff_t i_size; preempt_disable(); i_size = inode->i_size; preempt_enable(); return i_size; #else /* Pairs with smp_store_release() in i_size_write() */ return smp_load_acquire(&inode->i_size); #endif } /* * NOTE: unlike i_size_read(), i_size_write() does need locking around it * (normally i_mutex), otherwise on 32bit/SMP an update of i_size_seqcount * can be lost, resulting in subsequent i_size_read() calls spinning forever. */ static inline void i_size_write(struct inode *inode, loff_t i_size) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) preempt_disable(); write_seqcount_begin(&inode->i_size_seqcount); inode->i_size = i_size; write_seqcount_end(&inode->i_size_seqcount); preempt_enable(); #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) preempt_disable(); inode->i_size = i_size; preempt_enable(); #else /* * Pairs with smp_load_acquire() in i_size_read() to ensure * changes related to inode size (such as page contents) are * visible before we see the changed inode size. */ smp_store_release(&inode->i_size, i_size); #endif } static inline unsigned iminor(const struct inode *inode) { return MINOR(inode->i_rdev); } static inline unsigned imajor(const struct inode *inode) { return MAJOR(inode->i_rdev); } struct fown_struct { rwlock_t lock; /* protects pid, uid, euid fields */ struct pid *pid; /* pid or -pgrp where SIGIO should be sent */ enum pid_type pid_type; /* Kind of process group SIGIO should be sent to */ kuid_t uid, euid; /* uid/euid of process setting the owner */ int signum; /* posix.1b rt signal to be delivered on IO */ }; /** * struct file_ra_state - Track a file's readahead state. * @start: Where the most recent readahead started. * @size: Number of pages read in the most recent readahead. * @async_size: Numer of pages that were/are not needed immediately * and so were/are genuinely "ahead". Start next readahead when * the first of these pages is accessed. * @ra_pages: Maximum size of a readahead request, copied from the bdi. * @mmap_miss: How many mmap accesses missed in the page cache. * @prev_pos: The last byte in the most recent read request. * * When this structure is passed to ->readahead(), the "most recent" * readahead means the current readahead. */ struct file_ra_state { pgoff_t start; unsigned int size; unsigned int async_size; unsigned int ra_pages; unsigned int mmap_miss; loff_t prev_pos; }; /* * Check if @index falls in the readahead windows. */ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) { return (index >= ra->start && index < ra->start + ra->size); } /* * f_{lock,count,pos_lock} members can be highly contended and share * the same cacheline. f_{lock,mode} are very frequently used together * and so share the same cacheline as well. The read-mostly * f_{path,inode,op} are kept on a separate cacheline. */ struct file { union { /* fput() uses task work when closing and freeing file (default). */ struct callback_head f_task_work; /* fput() must use workqueue (most kernel threads). */ struct llist_node f_llist; unsigned int f_iocb_flags; }; /* * Protects f_ep, f_flags. * Must not be taken from IRQ context. */ spinlock_t f_lock; fmode_t f_mode; atomic_long_t f_count; struct mutex f_pos_lock; loff_t f_pos; unsigned int f_flags; struct fown_struct f_owner; const struct cred *f_cred; struct file_ra_state f_ra; struct path f_path; struct inode *f_inode; /* cached value */ const struct file_operations *f_op; u64 f_version; #ifdef CONFIG_SECURITY void *f_security; #endif /* needed for tty driver, and maybe others */ void *private_data; #ifdef CONFIG_EPOLL /* Used by fs/eventpoll.c to link all the hooks to this file */ struct hlist_head *f_ep; #endif /* #ifdef CONFIG_EPOLL */ struct address_space *f_mapping; errseq_t f_wb_err; errseq_t f_sb_err; /* for syncfs */ } __randomize_layout __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ struct file_handle { __u32 handle_bytes; int handle_type; /* file identifier */ unsigned char f_handle[] __counted_by(handle_bytes); }; static inline struct file *get_file(struct file *f) { long prior = atomic_long_fetch_inc_relaxed(&f->f_count); WARN_ONCE(!prior, "struct file::f_count incremented from zero; use-after-free condition present!\n"); return f; } struct file *get_file_rcu(struct file __rcu **f); struct file *get_file_active(struct file **f); #define file_count(x) atomic_long_read(&(x)->f_count) #define MAX_NON_LFS ((1UL<<31) - 1) /* Page cache limit. The filesystems should put that into their s_maxbytes limits, otherwise bad things can happen in VM. */ #if BITS_PER_LONG==32 #define MAX_LFS_FILESIZE ((loff_t)ULONG_MAX << PAGE_SHIFT) #elif BITS_PER_LONG==64 #define MAX_LFS_FILESIZE ((loff_t)LLONG_MAX) #endif /* legacy typedef, should eventually be removed */ typedef void *fl_owner_t; struct file_lock; struct file_lease; /* The following constant reflects the upper bound of the file/locking space */ #ifndef OFFSET_MAX #define OFFSET_MAX type_max(loff_t) #define OFFT_OFFSET_MAX type_max(off_t) #endif extern void send_sigio(struct fown_struct *fown, int fd, int band); static inline struct inode *file_inode(const struct file *f) { return f->f_inode; } /* * file_dentry() is a relic from the days that overlayfs was using files with a * "fake" path, meaning, f_path on overlayfs and f_inode on underlying fs. * In those days, file_dentry() was needed to get the underlying fs dentry that * matches f_inode. * Files with "fake" path should not exist nowadays, so use an assertion to make * sure that file_dentry() was not papering over filesystem bugs. */ static inline struct dentry *file_dentry(const struct file *file) { struct dentry *dentry = file->f_path.dentry; WARN_ON_ONCE(d_inode(dentry) != file_inode(file)); return dentry; } struct fasync_struct { rwlock_t fa_lock; int magic; int fa_fd; struct fasync_struct *fa_next; /* singly linked list */ struct file *fa_file; struct rcu_head fa_rcu; }; #define FASYNC_MAGIC 0x4601 /* SMP safe fasync helpers: */ extern int fasync_helper(int, struct file *, int, struct fasync_struct **); extern struct fasync_struct *fasync_insert_entry(int, struct file *, struct fasync_struct **, struct fasync_struct *); extern int fasync_remove_entry(struct file *, struct fasync_struct **); extern struct fasync_struct *fasync_alloc(void); extern void fasync_free(struct fasync_struct *); /* can be called from interrupts */ extern void kill_fasync(struct fasync_struct **, int, int); extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force); extern int f_setown(struct file *filp, int who, int force); extern void f_delown(struct file *filp); extern pid_t f_getown(struct file *filp); extern int send_sigurg(struct fown_struct *fown); /* * sb->s_flags. Note that these mirror the equivalent MS_* flags where * represented in both. */ #define SB_RDONLY BIT(0) /* Mount read-only */ #define SB_NOSUID BIT(1) /* Ignore suid and sgid bits */ #define SB_NODEV BIT(2) /* Disallow access to device special files */ #define SB_NOEXEC BIT(3) /* Disallow program execution */ #define SB_SYNCHRONOUS BIT(4) /* Writes are synced at once */ #define SB_MANDLOCK BIT(6) /* Allow mandatory locks on an FS */ #define SB_DIRSYNC BIT(7) /* Directory modifications are synchronous */ #define SB_NOATIME BIT(10) /* Do not update access times. */ #define SB_NODIRATIME BIT(11) /* Do not update directory access times */ #define SB_SILENT BIT(15) #define SB_POSIXACL BIT(16) /* Supports POSIX ACLs */ #define SB_INLINECRYPT BIT(17) /* Use blk-crypto for encrypted files */ #define SB_KERNMOUNT BIT(22) /* this is a kern_mount call */ #define SB_I_VERSION BIT(23) /* Update inode I_version field */ #define SB_LAZYTIME BIT(25) /* Update the on-disk [acm]times lazily */ /* These sb flags are internal to the kernel */ #define SB_DEAD BIT(21) #define SB_DYING BIT(24) #define SB_SUBMOUNT BIT(26) #define SB_FORCE BIT(27) #define SB_NOSEC BIT(28) #define SB_BORN BIT(29) #define SB_ACTIVE BIT(30) #define SB_NOUSER BIT(31) /* These flags relate to encoding and casefolding */ #define SB_ENC_STRICT_MODE_FL (1 << 0) #define sb_has_strict_encoding(sb) \ (sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL) /* * Umount options */ #define MNT_FORCE 0x00000001 /* Attempt to forcibily umount */ #define MNT_DETACH 0x00000002 /* Just detach from the tree */ #define MNT_EXPIRE 0x00000004 /* Mark for expiry */ #define UMOUNT_NOFOLLOW 0x00000008 /* Don't follow symlink on umount */ #define UMOUNT_UNUSED 0x80000000 /* Flag guaranteed to be unused */ /* sb->s_iflags */ #define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */ #define SB_I_NOEXEC 0x00000002 /* Ignore executables on this fs */ #define SB_I_NODEV 0x00000004 /* Ignore devices on this fs */ #define SB_I_STABLE_WRITES 0x00000008 /* don't modify blks until WB is done */ /* sb->s_iflags to limit user namespace mounts */ #define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ #define SB_I_IMA_UNVERIFIABLE_SIGNATURE 0x00000020 #define SB_I_UNTRUSTED_MOUNTER 0x00000040 #define SB_I_EVM_HMAC_UNSUPPORTED 0x00000080 #define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */ #define SB_I_PERSB_BDI 0x00000200 /* has a per-sb bdi */ #define SB_I_TS_EXPIRY_WARNED 0x00000400 /* warned about timestamp range expiry */ #define SB_I_RETIRED 0x00000800 /* superblock shouldn't be reused */ #define SB_I_NOUMASK 0x00001000 /* VFS does not apply umask */ /* Possible states of 'frozen' field */ enum { SB_UNFROZEN = 0, /* FS is unfrozen */ SB_FREEZE_WRITE = 1, /* Writes, dir ops, ioctls frozen */ SB_FREEZE_PAGEFAULT = 2, /* Page faults stopped as well */ SB_FREEZE_FS = 3, /* For internal FS use (e.g. to stop * internal threads if needed) */ SB_FREEZE_COMPLETE = 4, /* ->freeze_fs finished successfully */ }; #define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1) struct sb_writers { unsigned short frozen; /* Is sb frozen? */ int freeze_kcount; /* How many kernel freeze requests? */ int freeze_ucount; /* How many userspace freeze requests? */ struct percpu_rw_semaphore rw_sem[SB_FREEZE_LEVELS]; }; struct super_block { struct list_head s_list; /* Keep this first */ dev_t s_dev; /* search index; _not_ kdev_t */ unsigned char s_blocksize_bits; unsigned long s_blocksize; loff_t s_maxbytes; /* Max file size */ struct file_system_type *s_type; const struct super_operations *s_op; const struct dquot_operations *dq_op; const struct quotactl_ops *s_qcop; const struct export_operations *s_export_op; unsigned long s_flags; unsigned long s_iflags; /* internal SB_I_* flags */ unsigned long s_magic; struct dentry *s_root; struct rw_semaphore s_umount; int s_count; atomic_t s_active; #ifdef CONFIG_SECURITY void *s_security; #endif const struct xattr_handler * const *s_xattr; #ifdef CONFIG_FS_ENCRYPTION const struct fscrypt_operations *s_cop; struct fscrypt_keyring *s_master_keys; /* master crypto keys in use */ #endif #ifdef CONFIG_FS_VERITY const struct fsverity_operations *s_vop; #endif #if IS_ENABLED(CONFIG_UNICODE) struct unicode_map *s_encoding; __u16 s_encoding_flags; #endif struct hlist_bl_head s_roots; /* alternate root dentries for NFS */ struct list_head s_mounts; /* list of mounts; _not_ for fs use */ struct block_device *s_bdev; /* can go away once we use an accessor for @s_bdev_file */ struct file *s_bdev_file; struct backing_dev_info *s_bdi; struct mtd_info *s_mtd; struct hlist_node s_instances; unsigned int s_quota_types; /* Bitmask of supported quota types */ struct quota_info s_dquot; /* Diskquota specific options */ struct sb_writers s_writers; /* * Keep s_fs_info, s_time_gran, s_fsnotify_mask, and * s_fsnotify_info together for cache efficiency. They are frequently * accessed and rarely modified. */ void *s_fs_info; /* Filesystem private info */ /* Granularity of c/m/atime in ns (cannot be worse than a second) */ u32 s_time_gran; /* Time limits for c/m/atime in seconds */ time64_t s_time_min; time64_t s_time_max; #ifdef CONFIG_FSNOTIFY __u32 s_fsnotify_mask; struct fsnotify_sb_info *s_fsnotify_info; #endif /* * q: why are s_id and s_sysfs_name not the same? both are human * readable strings that identify the filesystem * a: s_id is allowed to change at runtime; it's used in log messages, * and we want to when a device starts out as single device (s_id is dev * name) but then a device is hot added and we have to switch to * identifying it by UUID * but s_sysfs_name is a handle for programmatic access, and can't * change at runtime */ char s_id[32]; /* Informational name */ uuid_t s_uuid; /* UUID */ u8 s_uuid_len; /* Default 16, possibly smaller for weird filesystems */ /* if set, fs shows up under sysfs at /sys/fs/$FSTYP/s_sysfs_name */ char s_sysfs_name[UUID_STRING_LEN + 1]; unsigned int s_max_links; /* * The next field is for VFS *only*. No filesystems have any business * even looking at it. You had been warned. */ struct mutex s_vfs_rename_mutex; /* Kludge */ /* * Filesystem subtype. If non-empty the filesystem type field * in /proc/mounts will be "type.subtype" */ const char *s_subtype; const struct dentry_operations *s_d_op; /* default d_op for dentries */ struct shrinker *s_shrink; /* per-sb shrinker handle */ /* Number of inodes with nlink == 0 but still referenced */ atomic_long_t s_remove_count; /* Read-only state of the superblock is being changed */ int s_readonly_remount; /* per-sb errseq_t for reporting writeback errors via syncfs */ errseq_t s_wb_err; /* AIO completions deferred from interrupt context */ struct workqueue_struct *s_dio_done_wq; struct hlist_head s_pins; /* * Owning user namespace and default context in which to * interpret filesystem uids, gids, quotas, device nodes, * xattrs and security labels. */ struct user_namespace *s_user_ns; /* * The list_lru structure is essentially just a pointer to a table * of per-node lru lists, each of which has its own spinlock. * There is no need to put them into separate cachelines. */ struct list_lru s_dentry_lru; struct list_lru s_inode_lru; struct rcu_head rcu; struct work_struct destroy_work; struct mutex s_sync_lock; /* sync serialisation lock */ /* * Indicates how deep in a filesystem stack this SB is */ int s_stack_depth; /* s_inode_list_lock protects s_inodes */ spinlock_t s_inode_list_lock ____cacheline_aligned_in_smp; struct list_head s_inodes; /* all inodes */ spinlock_t s_inode_wblist_lock; struct list_head s_inodes_wb; /* writeback inodes */ } __randomize_layout; static inline struct user_namespace *i_user_ns(const struct inode *inode) { return inode->i_sb->s_user_ns; } /* Helper functions so that in most cases filesystems will * not need to deal directly with kuid_t and kgid_t and can * instead deal with the raw numeric values that are stored * in the filesystem. */ static inline uid_t i_uid_read(const struct inode *inode) { return from_kuid(i_user_ns(inode), inode->i_uid); } static inline gid_t i_gid_read(const struct inode *inode) { return from_kgid(i_user_ns(inode), inode->i_gid); } static inline void i_uid_write(struct inode *inode, uid_t uid) { inode->i_uid = make_kuid(i_user_ns(inode), uid); } static inline void i_gid_write(struct inode *inode, gid_t gid) { inode->i_gid = make_kgid(i_user_ns(inode), gid); } /** * i_uid_into_vfsuid - map an inode's i_uid down according to an idmapping * @idmap: idmap of the mount the inode was found from * @inode: inode to map * * Return: whe inode's i_uid mapped down according to @idmap. * If the inode's i_uid has no mapping INVALID_VFSUID is returned. */ static inline vfsuid_t i_uid_into_vfsuid(struct mnt_idmap *idmap, const struct inode *inode) { return make_vfsuid(idmap, i_user_ns(inode), inode->i_uid); } /** * i_uid_needs_update - check whether inode's i_uid needs to be updated * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Check whether the $inode's i_uid field needs to be updated taking idmapped * mounts into account if the filesystem supports it. * * Return: true if @inode's i_uid field needs to be updated, false if not. */ static inline bool i_uid_needs_update(struct mnt_idmap *idmap, const struct iattr *attr, const struct inode *inode) { return ((attr->ia_valid & ATTR_UID) && !vfsuid_eq(attr->ia_vfsuid, i_uid_into_vfsuid(idmap, inode))); } /** * i_uid_update - update @inode's i_uid field * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Safely update @inode's i_uid field translating the vfsuid of any idmapped * mount into the filesystem kuid. */ static inline void i_uid_update(struct mnt_idmap *idmap, const struct iattr *attr, struct inode *inode) { if (attr->ia_valid & ATTR_UID) inode->i_uid = from_vfsuid(idmap, i_user_ns(inode), attr->ia_vfsuid); } /** * i_gid_into_vfsgid - map an inode's i_gid down according to an idmapping * @idmap: idmap of the mount the inode was found from * @inode: inode to map * * Return: the inode's i_gid mapped down according to @idmap. * If the inode's i_gid has no mapping INVALID_VFSGID is returned. */ static inline vfsgid_t i_gid_into_vfsgid(struct mnt_idmap *idmap, const struct inode *inode) { return make_vfsgid(idmap, i_user_ns(inode), inode->i_gid); } /** * i_gid_needs_update - check whether inode's i_gid needs to be updated * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Check whether the $inode's i_gid field needs to be updated taking idmapped * mounts into account if the filesystem supports it. * * Return: true if @inode's i_gid field needs to be updated, false if not. */ static inline bool i_gid_needs_update(struct mnt_idmap *idmap, const struct iattr *attr, const struct inode *inode) { return ((attr->ia_valid & ATTR_GID) && !vfsgid_eq(attr->ia_vfsgid, i_gid_into_vfsgid(idmap, inode))); } /** * i_gid_update - update @inode's i_gid field * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Safely update @inode's i_gid field translating the vfsgid of any idmapped * mount into the filesystem kgid. */ static inline void i_gid_update(struct mnt_idmap *idmap, const struct iattr *attr, struct inode *inode) { if (attr->ia_valid & ATTR_GID) inode->i_gid = from_vfsgid(idmap, i_user_ns(inode), attr->ia_vfsgid); } /** * inode_fsuid_set - initialize inode's i_uid field with callers fsuid * @inode: inode to initialize * @idmap: idmap of the mount the inode was found from * * Initialize the i_uid field of @inode. If the inode was found/created via * an idmapped mount map the caller's fsuid according to @idmap. */ static inline void inode_fsuid_set(struct inode *inode, struct mnt_idmap *idmap) { inode->i_uid = mapped_fsuid(idmap, i_user_ns(inode)); } /** * inode_fsgid_set - initialize inode's i_gid field with callers fsgid * @inode: inode to initialize * @idmap: idmap of the mount the inode was found from * * Initialize the i_gid field of @inode. If the inode was found/created via * an idmapped mount map the caller's fsgid according to @idmap. */ static inline void inode_fsgid_set(struct inode *inode, struct mnt_idmap *idmap) { inode->i_gid = mapped_fsgid(idmap, i_user_ns(inode)); } /** * fsuidgid_has_mapping() - check whether caller's fsuid/fsgid is mapped * @sb: the superblock we want a mapping in * @idmap: idmap of the relevant mount * * Check whether the caller's fsuid and fsgid have a valid mapping in the * s_user_ns of the superblock @sb. If the caller is on an idmapped mount map * the caller's fsuid and fsgid according to the @idmap first. * * Return: true if fsuid and fsgid is mapped, false if not. */ static inline bool fsuidgid_has_mapping(struct super_block *sb, struct mnt_idmap *idmap) { struct user_namespace *fs_userns = sb->s_user_ns; kuid_t kuid; kgid_t kgid; kuid = mapped_fsuid(idmap, fs_userns); if (!uid_valid(kuid)) return false; kgid = mapped_fsgid(idmap, fs_userns); if (!gid_valid(kgid)) return false; return kuid_has_mapping(fs_userns, kuid) && kgid_has_mapping(fs_userns, kgid); } struct timespec64 current_time(struct inode *inode); struct timespec64 inode_set_ctime_current(struct inode *inode); static inline time64_t inode_get_atime_sec(const struct inode *inode) { return inode->i_atime_sec; } static inline long inode_get_atime_nsec(const struct inode *inode) { return inode->i_atime_nsec; } static inline struct timespec64 inode_get_atime(const struct inode *inode) { struct timespec64 ts = { .tv_sec = inode_get_atime_sec(inode), .tv_nsec = inode_get_atime_nsec(inode) }; return ts; } static inline struct timespec64 inode_set_atime_to_ts(struct inode *inode, struct timespec64 ts) { inode->i_atime_sec = ts.tv_sec; inode->i_atime_nsec = ts.tv_nsec; return ts; } static inline struct timespec64 inode_set_atime(struct inode *inode, time64_t sec, long nsec) { struct timespec64 ts = { .tv_sec = sec, .tv_nsec = nsec }; return inode_set_atime_to_ts(inode, ts); } static inline time64_t inode_get_mtime_sec(const struct inode *inode) { return inode->i_mtime_sec; } static inline long inode_get_mtime_nsec(const struct inode *inode) { return inode->i_mtime_nsec; } static inline struct timespec64 inode_get_mtime(const struct inode *inode) { struct timespec64 ts = { .tv_sec = inode_get_mtime_sec(inode), .tv_nsec = inode_get_mtime_nsec(inode) }; return ts; } static inline struct timespec64 inode_set_mtime_to_ts(struct inode *inode, struct timespec64 ts) { inode->i_mtime_sec = ts.tv_sec; inode->i_mtime_nsec = ts.tv_nsec; return ts; } static inline struct timespec64 inode_set_mtime(struct inode *inode, time64_t sec, long nsec) { struct timespec64 ts = { .tv_sec = sec, .tv_nsec = nsec }; return inode_set_mtime_to_ts(inode, ts); } static inline time64_t inode_get_ctime_sec(const struct inode *inode) { return inode->i_ctime_sec; } static inline long inode_get_ctime_nsec(const struct inode *inode) { return inode->i_ctime_nsec; } static inline struct timespec64 inode_get_ctime(const struct inode *inode) { struct timespec64 ts = { .tv_sec = inode_get_ctime_sec(inode), .tv_nsec = inode_get_ctime_nsec(inode) }; return ts; } static inline struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts) { inode->i_ctime_sec = ts.tv_sec; inode->i_ctime_nsec = ts.tv_nsec; return ts; } /** * inode_set_ctime - set the ctime in the inode * @inode: inode in which to set the ctime * @sec: tv_sec value to set * @nsec: tv_nsec value to set * * Set the ctime in @inode to { @sec, @nsec } */ static inline struct timespec64 inode_set_ctime(struct inode *inode, time64_t sec, long nsec) { struct timespec64 ts = { .tv_sec = sec, .tv_nsec = nsec }; return inode_set_ctime_to_ts(inode, ts); } struct timespec64 simple_inode_init_ts(struct inode *inode); /* * Snapshotting support. */ /* * These are internal functions, please use sb_start_{write,pagefault,intwrite} * instead. */ static inline void __sb_end_write(struct super_block *sb, int level) { percpu_up_read(sb->s_writers.rw_sem + level-1); } static inline void __sb_start_write(struct super_block *sb, int level) { percpu_down_read(sb->s_writers.rw_sem + level - 1); } static inline bool __sb_start_write_trylock(struct super_block *sb, int level) { return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1); } #define __sb_writers_acquired(sb, lev) \ percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) #define __sb_writers_release(sb, lev) \ percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) /** * __sb_write_started - check if sb freeze level is held * @sb: the super we write to * @level: the freeze level * * * > 0 - sb freeze level is held * * 0 - sb freeze level is not held * * < 0 - !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN */ static inline int __sb_write_started(const struct super_block *sb, int level) { return lockdep_is_held_type(sb->s_writers.rw_sem + level - 1, 1); } /** * sb_write_started - check if SB_FREEZE_WRITE is held * @sb: the super we write to * * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. */ static inline bool sb_write_started(const struct super_block *sb) { return __sb_write_started(sb, SB_FREEZE_WRITE); } /** * sb_write_not_started - check if SB_FREEZE_WRITE is not held * @sb: the super we write to * * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. */ static inline bool sb_write_not_started(const struct super_block *sb) { return __sb_write_started(sb, SB_FREEZE_WRITE) <= 0; } /** * file_write_started - check if SB_FREEZE_WRITE is held * @file: the file we write to * * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. * May be false positive with !S_ISREG, because file_start_write() has * no effect on !S_ISREG. */ static inline bool file_write_started(const struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; return sb_write_started(file_inode(file)->i_sb); } /** * file_write_not_started - check if SB_FREEZE_WRITE is not held * @file: the file we write to * * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. * May be false positive with !S_ISREG, because file_start_write() has * no effect on !S_ISREG. */ static inline bool file_write_not_started(const struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; return sb_write_not_started(file_inode(file)->i_sb); } /** * sb_end_write - drop write access to a superblock * @sb: the super we wrote to * * Decrement number of writers to the filesystem. Wake up possible waiters * wanting to freeze the filesystem. */ static inline void sb_end_write(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_WRITE); } /** * sb_end_pagefault - drop write access to a superblock from a page fault * @sb: the super we wrote to * * Decrement number of processes handling write page fault to the filesystem. * Wake up possible waiters wanting to freeze the filesystem. */ static inline void sb_end_pagefault(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_PAGEFAULT); } /** * sb_end_intwrite - drop write access to a superblock for internal fs purposes * @sb: the super we wrote to * * Decrement fs-internal number of writers to the filesystem. Wake up possible * waiters wanting to freeze the filesystem. */ static inline void sb_end_intwrite(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_FS); } /** * sb_start_write - get write access to a superblock * @sb: the super we write to * * When a process wants to write data or metadata to a file system (i.e. dirty * a page or an inode), it should embed the operation in a sb_start_write() - * sb_end_write() pair to get exclusion against file system freezing. This * function increments number of writers preventing freezing. If the file * system is already frozen, the function waits until the file system is * thawed. * * Since freeze protection behaves as a lock, users have to preserve * ordering of freeze protection and other filesystem locks. Generally, * freeze protection should be the outermost lock. In particular, we have: * * sb_start_write * -> i_mutex (write path, truncate, directory ops, ...) * -> s_umount (freeze_super, thaw_super) */ static inline void sb_start_write(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_WRITE); } static inline bool sb_start_write_trylock(struct super_block *sb) { return __sb_start_write_trylock(sb, SB_FREEZE_WRITE); } /** * sb_start_pagefault - get write access to a superblock from a page fault * @sb: the super we write to * * When a process starts handling write page fault, it should embed the * operation into sb_start_pagefault() - sb_end_pagefault() pair to get * exclusion against file system freezing. This is needed since the page fault * is going to dirty a page. This function increments number of running page * faults preventing freezing. If the file system is already frozen, the * function waits until the file system is thawed. * * Since page fault freeze protection behaves as a lock, users have to preserve * ordering of freeze protection and other filesystem locks. It is advised to * put sb_start_pagefault() close to mmap_lock in lock ordering. Page fault * handling code implies lock dependency: * * mmap_lock * -> sb_start_pagefault */ static inline void sb_start_pagefault(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_PAGEFAULT); } /** * sb_start_intwrite - get write access to a superblock for internal fs purposes * @sb: the super we write to * * This is the third level of protection against filesystem freezing. It is * free for use by a filesystem. The only requirement is that it must rank * below sb_start_pagefault. * * For example filesystem can call sb_start_intwrite() when starting a * transaction which somewhat eases handling of freezing for internal sources * of filesystem changes (internal fs threads, discarding preallocation on file * close, etc.). */ static inline void sb_start_intwrite(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_FS); } static inline bool sb_start_intwrite_trylock(struct super_block *sb) { return __sb_start_write_trylock(sb, SB_FREEZE_FS); } bool inode_owner_or_capable(struct mnt_idmap *idmap, const struct inode *inode); /* * VFS helper functions.. */ int vfs_create(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, bool); int vfs_mkdir(struct mnt_idmap *, struct inode *, struct dentry *, umode_t); int vfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, dev_t); int vfs_symlink(struct mnt_idmap *, struct inode *, struct dentry *, const char *); int vfs_link(struct dentry *, struct mnt_idmap *, struct inode *, struct dentry *, struct inode **); int vfs_rmdir(struct mnt_idmap *, struct inode *, struct dentry *); int vfs_unlink(struct mnt_idmap *, struct inode *, struct dentry *, struct inode **); /** * struct renamedata - contains all information required for renaming * @old_mnt_idmap: idmap of the old mount the inode was found from * @old_dir: parent of source * @old_dentry: source * @new_mnt_idmap: idmap of the new mount the inode was found from * @new_dir: parent of destination * @new_dentry: destination * @delegated_inode: returns an inode needing a delegation break * @flags: rename flags */ struct renamedata { struct mnt_idmap *old_mnt_idmap; struct inode *old_dir; struct dentry *old_dentry; struct mnt_idmap *new_mnt_idmap; struct inode *new_dir; struct dentry *new_dentry; struct inode **delegated_inode; unsigned int flags; } __randomize_layout; int vfs_rename(struct renamedata *); static inline int vfs_whiteout(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry) { return vfs_mknod(idmap, dir, dentry, S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV); } struct file *kernel_tmpfile_open(struct mnt_idmap *idmap, const struct path *parentpath, umode_t mode, int open_flag, const struct cred *cred); struct file *kernel_file_open(const struct path *path, int flags, const struct cred *cred); int vfs_mkobj(struct dentry *, umode_t, int (*f)(struct dentry *, umode_t, void *), void *); int vfs_fchown(struct file *file, uid_t user, gid_t group); int vfs_fchmod(struct file *file, umode_t mode); int vfs_utimes(const struct path *path, struct timespec64 *times); extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #ifdef CONFIG_COMPAT extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #else #define compat_ptr_ioctl NULL #endif /* * VFS file helper functions. */ void inode_init_owner(struct mnt_idmap *idmap, struct inode *inode, const struct inode *dir, umode_t mode); extern bool may_open_dev(const struct path *path); umode_t mode_strip_sgid(struct mnt_idmap *idmap, const struct inode *dir, umode_t mode); bool in_group_or_capable(struct mnt_idmap *idmap, const struct inode *inode, vfsgid_t vfsgid); /* * This is the "filldir" function type, used by readdir() to let * the kernel specify what kind of dirent layout it wants to have. * This allows the kernel to read directories into kernel space or * to have different dirent layouts depending on the binary type. * Return 'true' to keep going and 'false' if there are no more entries. */ struct dir_context; typedef bool (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64, unsigned); struct dir_context { filldir_t actor; loff_t pos; }; /* * These flags let !MMU mmap() govern direct device mapping vs immediate * copying more easily for MAP_PRIVATE, especially for ROM filesystems. * * NOMMU_MAP_COPY: Copy can be mapped (MAP_PRIVATE) * NOMMU_MAP_DIRECT: Can be mapped directly (MAP_SHARED) * NOMMU_MAP_READ: Can be mapped for reading * NOMMU_MAP_WRITE: Can be mapped for writing * NOMMU_MAP_EXEC: Can be mapped for execution */ #define NOMMU_MAP_COPY 0x00000001 #define NOMMU_MAP_DIRECT 0x00000008 #define NOMMU_MAP_READ VM_MAYREAD #define NOMMU_MAP_WRITE VM_MAYWRITE #define NOMMU_MAP_EXEC VM_MAYEXEC #define NOMMU_VMFLAGS \ (NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC) /* * These flags control the behavior of the remap_file_range function pointer. * If it is called with len == 0 that means "remap to end of source file". * See Documentation/filesystems/vfs.rst for more details about this call. * * REMAP_FILE_DEDUP: only remap if contents identical (i.e. deduplicate) * REMAP_FILE_CAN_SHORTEN: caller can handle a shortened request */ #define REMAP_FILE_DEDUP (1 << 0) #define REMAP_FILE_CAN_SHORTEN (1 << 1) /* * These flags signal that the caller is ok with altering various aspects of * the behavior of the remap operation. The changes must be made by the * implementation; the vfs remap helper functions can take advantage of them. * Flags in this category exist to preserve the quirky behavior of the hoisted * btrfs clone/dedupe ioctls. */ #define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN) /* * These flags control the behavior of vfs_copy_file_range(). * They are not available to the user via syscall. * * COPY_FILE_SPLICE: call splice direct instead of fs clone/copy ops */ #define COPY_FILE_SPLICE (1 << 0) struct iov_iter; struct io_uring_cmd; struct offset_ctx; typedef unsigned int __bitwise fop_flags_t; struct file_operations { struct module *owner; fop_flags_t fop_flags; loff_t (*llseek) (struct file *, loff_t, int); ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); ssize_t (*read_iter) (struct kiocb *, struct iov_iter *); ssize_t (*write_iter) (struct kiocb *, struct iov_iter *); int (*iopoll)(struct kiocb *kiocb, struct io_comp_batch *, unsigned int flags); int (*iterate_shared) (struct file *, struct dir_context *); __poll_t (*poll) (struct file *, struct poll_table_struct *); long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*mmap) (struct file *, struct vm_area_struct *); int (*open) (struct inode *, struct file *); int (*flush) (struct file *, fl_owner_t id); int (*release) (struct inode *, struct file *); int (*fsync) (struct file *, loff_t, loff_t, int datasync); int (*fasync) (int, struct file *, int); int (*lock) (struct file *, int, struct file_lock *); unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); int (*check_flags)(int); int (*flock) (struct file *, int, struct file_lock *); ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); void (*splice_eof)(struct file *file); int (*setlease)(struct file *, int, struct file_lease **, void **); long (*fallocate)(struct file *file, int mode, loff_t offset, loff_t len); void (*show_fdinfo)(struct seq_file *m, struct file *f); #ifndef CONFIG_MMU unsigned (*mmap_capabilities)(struct file *); #endif ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); int (*uring_cmd)(struct io_uring_cmd *ioucmd, unsigned int issue_flags); int (*uring_cmd_iopoll)(struct io_uring_cmd *, struct io_comp_batch *, unsigned int poll_flags); } __randomize_layout; /* Supports async buffered reads */ #define FOP_BUFFER_RASYNC ((__force fop_flags_t)(1 << 0)) /* Supports async buffered writes */ #define FOP_BUFFER_WASYNC ((__force fop_flags_t)(1 << 1)) /* Supports synchronous page faults for mappings */ #define FOP_MMAP_SYNC ((__force fop_flags_t)(1 << 2)) /* Supports non-exclusive O_DIRECT writes from multiple threads */ #define FOP_DIO_PARALLEL_WRITE ((__force fop_flags_t)(1 << 3)) /* Contains huge pages */ #define FOP_HUGE_PAGES ((__force fop_flags_t)(1 << 4)) /* Wrap a directory iterator that needs exclusive inode access */ int wrap_directory_iterator(struct file *, struct dir_context *, int (*) (struct file *, struct dir_context *)); #define WRAP_DIR_ITER(x) \ static int shared_##x(struct file *file , struct dir_context *ctx) \ { return wrap_directory_iterator(file, ctx, x); } struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *); int (*permission) (struct mnt_idmap *, struct inode *, int); struct posix_acl * (*get_inode_acl)(struct inode *, int, bool); int (*readlink) (struct dentry *, char __user *,int); int (*create) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t, bool); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *, const char *); int (*mkdir) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t); int (*rmdir) (struct inode *,struct dentry *); int (*mknod) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t,dev_t); int (*rename) (struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); int (*setattr) (struct mnt_idmap *, struct dentry *, struct iattr *); int (*getattr) (struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); int (*update_time)(struct inode *, int); int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, umode_t create_mode); int (*tmpfile) (struct mnt_idmap *, struct inode *, struct file *, umode_t); struct posix_acl *(*get_acl)(struct mnt_idmap *, struct dentry *, int); int (*set_acl)(struct mnt_idmap *, struct dentry *, struct posix_acl *, int); int (*fileattr_set)(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); int (*fileattr_get)(struct dentry *dentry, struct fileattr *fa); struct offset_ctx *(*get_offset_ctx)(struct inode *inode); } ____cacheline_aligned; static inline int call_mmap(struct file *file, struct vm_area_struct *vma) { return file->f_op->mmap(file, vma); } extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); int remap_verify_area(struct file *file, loff_t pos, loff_t len, bool write); int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *len, unsigned int remap_flags, const struct iomap_ops *dax_read_ops); int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *count, unsigned int remap_flags); extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, struct file *dst_file, loff_t dst_pos, loff_t len, unsigned int remap_flags); /** * enum freeze_holder - holder of the freeze * @FREEZE_HOLDER_KERNEL: kernel wants to freeze or thaw filesystem * @FREEZE_HOLDER_USERSPACE: userspace wants to freeze or thaw filesystem * @FREEZE_MAY_NEST: whether nesting freeze and thaw requests is allowed * * Indicate who the owner of the freeze or thaw request is and whether * the freeze needs to be exclusive or can nest. * Without @FREEZE_MAY_NEST, multiple freeze and thaw requests from the * same holder aren't allowed. It is however allowed to hold a single * @FREEZE_HOLDER_USERSPACE and a single @FREEZE_HOLDER_KERNEL freeze at * the same time. This is relied upon by some filesystems during online * repair or similar. */ enum freeze_holder { FREEZE_HOLDER_KERNEL = (1U << 0), FREEZE_HOLDER_USERSPACE = (1U << 1), FREEZE_MAY_NEST = (1U << 2), }; struct super_operations { struct inode *(*alloc_inode)(struct super_block *sb); void (*destroy_inode)(struct inode *); void (*free_inode)(struct inode *); void (*dirty_inode) (struct inode *, int flags); int (*write_inode) (struct inode *, struct writeback_control *wbc); int (*drop_inode) (struct inode *); void (*evict_inode) (struct inode *); void (*put_super) (struct super_block *); int (*sync_fs)(struct super_block *sb, int wait); int (*freeze_super) (struct super_block *, enum freeze_holder who); int (*freeze_fs) (struct super_block *); int (*thaw_super) (struct super_block *, enum freeze_holder who); int (*unfreeze_fs) (struct super_block *); int (*statfs) (struct dentry *, struct kstatfs *); int (*remount_fs) (struct super_block *, int *, char *); void (*umount_begin) (struct super_block *); int (*show_options)(struct seq_file *, struct dentry *); int (*show_devname)(struct seq_file *, struct dentry *); int (*show_path)(struct seq_file *, struct dentry *); int (*show_stats)(struct seq_file *, struct dentry *); #ifdef CONFIG_QUOTA ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t); ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); struct dquot __rcu **(*get_dquots)(struct inode *); #endif long (*nr_cached_objects)(struct super_block *, struct shrink_control *); long (*free_cached_objects)(struct super_block *, struct shrink_control *); void (*shutdown)(struct super_block *sb); }; /* * Inode flags - they have no relation to superblock flags now */ #define S_SYNC (1 << 0) /* Writes are synced at once */ #define S_NOATIME (1 << 1) /* Do not update access times */ #define S_APPEND (1 << 2) /* Append-only file */ #define S_IMMUTABLE (1 << 3) /* Immutable file */ #define S_DEAD (1 << 4) /* removed, but still open directory */ #define S_NOQUOTA (1 << 5) /* Inode is not counted to quota */ #define S_DIRSYNC (1 << 6) /* Directory modifications are synchronous */ #define S_NOCMTIME (1 << 7) /* Do not update file c/mtime */ #define S_SWAPFILE (1 << 8) /* Do not truncate: swapon got its bmaps */ #define S_PRIVATE (1 << 9) /* Inode is fs-internal */ #define S_IMA (1 << 10) /* Inode has an associated IMA struct */ #define S_AUTOMOUNT (1 << 11) /* Automount/referral quasi-directory */ #define S_NOSEC (1 << 12) /* no suid or xattr security attributes */ #ifdef CONFIG_FS_DAX #define S_DAX (1 << 13) /* Direct Access, avoiding the page cache */ #else #define S_DAX 0 /* Make all the DAX code disappear */ #endif #define S_ENCRYPTED (1 << 14) /* Encrypted file (using fs/crypto/) */ #define S_CASEFOLD (1 << 15) /* Casefolded file */ #define S_VERITY (1 << 16) /* Verity file (using fs/verity/) */ #define S_KERNEL_FILE (1 << 17) /* File is in use by the kernel (eg. fs/cachefiles) */ /* * Note that nosuid etc flags are inode-specific: setting some file-system * flags just means all the inodes inherit those flags by default. It might be * possible to override it selectively if you really wanted to with some * ioctl() that is not currently implemented. * * Exception: SB_RDONLY is always applied to the entire file system. * * Unfortunately, it is possible to change a filesystems flags with it mounted * with files in use. This means that all of the inodes will not have their * i_flags updated. Hence, i_flags no longer inherit the superblock mount * flags, so these have to be checked separately. -- rmk@arm.uk.linux.org */ #define __IS_FLG(inode, flg) ((inode)->i_sb->s_flags & (flg)) static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags & SB_RDONLY; } #define IS_RDONLY(inode) sb_rdonly((inode)->i_sb) #define IS_SYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS) || \ ((inode)->i_flags & S_SYNC)) #define IS_DIRSYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS|SB_DIRSYNC) || \ ((inode)->i_flags & (S_SYNC|S_DIRSYNC))) #define IS_MANDLOCK(inode) __IS_FLG(inode, SB_MANDLOCK) #define IS_NOATIME(inode) __IS_FLG(inode, SB_RDONLY|SB_NOATIME) #define IS_I_VERSION(inode) __IS_FLG(inode, SB_I_VERSION) #define IS_NOQUOTA(inode) ((inode)->i_flags & S_NOQUOTA) #define IS_APPEND(inode) ((inode)->i_flags & S_APPEND) #define IS_IMMUTABLE(inode) ((inode)->i_flags & S_IMMUTABLE) #ifdef CONFIG_FS_POSIX_ACL #define IS_POSIXACL(inode) __IS_FLG(inode, SB_POSIXACL) #else #define IS_POSIXACL(inode) 0 #endif #define IS_DEADDIR(inode) ((inode)->i_flags & S_DEAD) #define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME) #ifdef CONFIG_SWAP #define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE) #else #define IS_SWAPFILE(inode) ((void)(inode), 0U) #endif #define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE) #define IS_IMA(inode) ((inode)->i_flags & S_IMA) #define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT) #define IS_NOSEC(inode) ((inode)->i_flags & S_NOSEC) #define IS_DAX(inode) ((inode)->i_flags & S_DAX) #define IS_ENCRYPTED(inode) ((inode)->i_flags & S_ENCRYPTED) #define IS_CASEFOLDED(inode) ((inode)->i_flags & S_CASEFOLD) #define IS_VERITY(inode) ((inode)->i_flags & S_VERITY) #define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \ (inode)->i_rdev == WHITEOUT_DEV) static inline bool HAS_UNMAPPED_ID(struct mnt_idmap *idmap, struct inode *inode) { return !vfsuid_valid(i_uid_into_vfsuid(idmap, inode)) || !vfsgid_valid(i_gid_into_vfsgid(idmap, inode)); } static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) { *kiocb = (struct kiocb) { .ki_filp = filp, .ki_flags = filp->f_iocb_flags, .ki_ioprio = get_current_ioprio(), }; } static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, struct file *filp) { *kiocb = (struct kiocb) { .ki_filp = filp, .ki_flags = kiocb_src->ki_flags, .ki_ioprio = kiocb_src->ki_ioprio, .ki_pos = kiocb_src->ki_pos, }; } /* * Inode state bits. Protected by inode->i_lock * * Four bits determine the dirty state of the inode: I_DIRTY_SYNC, * I_DIRTY_DATASYNC, I_DIRTY_PAGES, and I_DIRTY_TIME. * * Four bits define the lifetime of an inode. Initially, inodes are I_NEW, * until that flag is cleared. I_WILL_FREE, I_FREEING and I_CLEAR are set at * various stages of removing an inode. * * Two bits are used for locking and completion notification, I_NEW and I_SYNC. * * I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on * fdatasync() (unless I_DIRTY_DATASYNC is also set). * Timestamp updates are the usual cause. * I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of * these changes separately from I_DIRTY_SYNC so that we * don't have to write inode on fdatasync() when only * e.g. the timestamps have changed. * I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean. * I_DIRTY_TIME The inode itself has dirty timestamps, and the * lazytime mount option is enabled. We keep track of this * separately from I_DIRTY_SYNC in order to implement * lazytime. This gets cleared if I_DIRTY_INODE * (I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set. But * I_DIRTY_TIME can still be set if I_DIRTY_SYNC is already * in place because writeback might already be in progress * and we don't want to lose the time update * I_NEW Serves as both a mutex and completion notification. * New inodes set I_NEW. If two processes both create * the same inode, one of them will release its inode and * wait for I_NEW to be released before returning. * Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can * also cause waiting on I_NEW, without I_NEW actually * being set. find_inode() uses this to prevent returning * nearly-dead inodes. * I_WILL_FREE Must be set when calling write_inode_now() if i_count * is zero. I_FREEING must be set when I_WILL_FREE is * cleared. * I_FREEING Set when inode is about to be freed but still has dirty * pages or buffers attached or the inode itself is still * dirty. * I_CLEAR Added by clear_inode(). In this state the inode is * clean and can be destroyed. Inode keeps I_FREEING. * * Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are * prohibited for many purposes. iget() must wait for * the inode to be completely released, then create it * anew. Other functions will just ignore such inodes, * if appropriate. I_NEW is used for waiting. * * I_SYNC Writeback of inode is running. The bit is set during * data writeback, and cleared with a wakeup on the bit * address once it is done. The bit is also used to pin * the inode in memory for flusher thread. * * I_REFERENCED Marks the inode as recently references on the LRU list. * * I_DIO_WAKEUP Never set. Only used as a key for wait_on_bit(). * * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to * synchronize competing switching instances and to tell * wb stat updates to grab the i_pages lock. See * inode_switch_wbs_work_fn() for details. * * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper * and work dirs among overlayfs mounts. * * I_CREATING New object's inode in the middle of setting up. * * I_DONTCACHE Evict inode as soon as it is not used anymore. * * I_SYNC_QUEUED Inode is queued in b_io or b_more_io writeback lists. * Used to detect that mark_inode_dirty() should not move * inode between dirty lists. * * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback. * * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding * i_count. * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) #define I_DIRTY_DATASYNC (1 << 1) #define I_DIRTY_PAGES (1 << 2) #define __I_NEW 3 #define I_NEW (1 << __I_NEW) #define I_WILL_FREE (1 << 4) #define I_FREEING (1 << 5) #define I_CLEAR (1 << 6) #define __I_SYNC 7 #define I_SYNC (1 << __I_SYNC) #define I_REFERENCED (1 << 8) #define __I_DIO_WAKEUP 9 #define I_DIO_WAKEUP (1 << __I_DIO_WAKEUP) #define I_LINKABLE (1 << 10) #define I_DIRTY_TIME (1 << 11) #define I_WB_SWITCH (1 << 13) #define I_OVL_INUSE (1 << 14) #define I_CREATING (1 << 15) #define I_DONTCACHE (1 << 16) #define I_SYNC_QUEUED (1 << 17) #define I_PINNING_NETFS_WB (1 << 18) #define __I_LRU_ISOLATING 19 #define I_LRU_ISOLATING (1 << __I_LRU_ISOLATING) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) #define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) extern void __mark_inode_dirty(struct inode *, int); static inline void mark_inode_dirty(struct inode *inode) { __mark_inode_dirty(inode, I_DIRTY); } static inline void mark_inode_dirty_sync(struct inode *inode) { __mark_inode_dirty(inode, I_DIRTY_SYNC); } /* * Returns true if the given inode itself only has dirty timestamps (its pages * may still be dirty) and isn't currently being allocated or freed. * Filesystems should call this if when writing an inode when lazytime is * enabled, they want to opportunistically write the timestamps of other inodes * located very nearby on-disk, e.g. in the same inode block. This returns true * if the given inode is in need of such an opportunistic update. Requires * i_lock, or at least later re-checking under i_lock. */ static inline bool inode_is_dirtytime_only(struct inode *inode) { return (inode->i_state & (I_DIRTY_TIME | I_NEW | I_FREEING | I_WILL_FREE)) == I_DIRTY_TIME; } extern void inc_nlink(struct inode *inode); extern void drop_nlink(struct inode *inode); extern void clear_nlink(struct inode *inode); extern void set_nlink(struct inode *inode, unsigned int nlink); static inline void inode_inc_link_count(struct inode *inode) { inc_nlink(inode); mark_inode_dirty(inode); } static inline void inode_dec_link_count(struct inode *inode) { drop_nlink(inode); mark_inode_dirty(inode); } enum file_time_flags { S_ATIME = 1, S_MTIME = 2, S_CTIME = 4, S_VERSION = 8, }; extern bool atime_needs_update(const struct path *, struct inode *); extern void touch_atime(const struct path *); int inode_update_time(struct inode *inode, int flags); static inline void file_accessed(struct file *file) { if (!(file->f_flags & O_NOATIME)) touch_atime(&file->f_path); } extern int file_modified(struct file *file); int kiocb_modified(struct kiocb *iocb); int sync_inode_metadata(struct inode *inode, int wait); struct file_system_type { const char *name; int fs_flags; #define FS_REQUIRES_DEV 1 #define FS_BINARY_MOUNTDATA 2 #define FS_HAS_SUBTYPE 4 #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */ #define FS_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ int (*init_fs_context)(struct fs_context *); const struct fs_parameter_spec *parameters; struct dentry *(*mount) (struct file_system_type *, int, const char *, void *); void (*kill_sb) (struct super_block *); struct module *owner; struct file_system_type * next; struct hlist_head fs_supers; struct lock_class_key s_lock_key; struct lock_class_key s_umount_key; struct lock_class_key s_vfs_rename_key; struct lock_class_key s_writers_key[SB_FREEZE_LEVELS]; struct lock_class_key i_lock_key; struct lock_class_key i_mutex_key; struct lock_class_key invalidate_lock_key; struct lock_class_key i_mutex_dir_key; }; #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME) extern struct dentry *mount_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_single(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_nodev(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path); void retire_super(struct super_block *sb); void generic_shutdown_super(struct super_block *sb); void kill_block_super(struct super_block *sb); void kill_anon_super(struct super_block *sb); void kill_litter_super(struct super_block *sb); void deactivate_super(struct super_block *sb); void deactivate_locked_super(struct super_block *sb); int set_anon_super(struct super_block *s, void *data); int set_anon_super_fc(struct super_block *s, struct fs_context *fc); int get_anon_bdev(dev_t *); void free_anon_bdev(dev_t); struct super_block *sget_fc(struct fs_context *fc, int (*test)(struct super_block *, struct fs_context *), int (*set)(struct super_block *, struct fs_context *)); struct super_block *sget(struct file_system_type *type, int (*test)(struct super_block *,void *), int (*set)(struct super_block *,void *), int flags, void *data); struct super_block *sget_dev(struct fs_context *fc, dev_t dev); /* Alas, no aliases. Too much hassle with bringing module.h everywhere */ #define fops_get(fops) \ (((fops) && try_module_get((fops)->owner) ? (fops) : NULL)) #define fops_put(fops) \ do { if (fops) module_put((fops)->owner); } while(0) /* * This one is to be used *ONLY* from ->open() instances. * fops must be non-NULL, pinned down *and* module dependencies * should be sufficient to pin the caller down as well. */ #define replace_fops(f, fops) \ do { \ struct file *__file = (f); \ fops_put(__file->f_op); \ BUG_ON(!(__file->f_op = (fops))); \ } while(0) extern int register_filesystem(struct file_system_type *); extern int unregister_filesystem(struct file_system_type *); extern int vfs_statfs(const struct path *, struct kstatfs *); extern int user_statfs(const char __user *, struct kstatfs *); extern int fd_statfs(int, struct kstatfs *); int freeze_super(struct super_block *super, enum freeze_holder who); int thaw_super(struct super_block *super, enum freeze_holder who); extern __printf(2, 3) int super_setup_bdi_name(struct super_block *sb, char *fmt, ...); extern int super_setup_bdi(struct super_block *sb); static inline void super_set_uuid(struct super_block *sb, const u8 *uuid, unsigned len) { if (WARN_ON(len > sizeof(sb->s_uuid))) len = sizeof(sb->s_uuid); sb->s_uuid_len = len; memcpy(&sb->s_uuid, uuid, len); } /* set sb sysfs name based on sb->s_bdev */ static inline void super_set_sysfs_name_bdev(struct super_block *sb) { snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pg", sb->s_bdev); } /* set sb sysfs name based on sb->s_uuid */ static inline void super_set_sysfs_name_uuid(struct super_block *sb) { WARN_ON(sb->s_uuid_len != sizeof(sb->s_uuid)); snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pU", sb->s_uuid.b); } /* set sb sysfs name based on sb->s_id */ static inline void super_set_sysfs_name_id(struct super_block *sb) { strscpy(sb->s_sysfs_name, sb->s_id, sizeof(sb->s_sysfs_name)); } /* try to use something standard before you use this */ __printf(2, 3) static inline void super_set_sysfs_name_generic(struct super_block *sb, const char *fmt, ...) { va_list args; va_start(args, fmt); vsnprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), fmt, args); va_end(args); } extern int current_umask(void); extern void ihold(struct inode * inode); extern void iput(struct inode *); int inode_update_timestamps(struct inode *inode, int flags); int generic_update_time(struct inode *, int); /* /sys/fs */ extern struct kobject *fs_kobj; #define MAX_RW_COUNT (INT_MAX & PAGE_MASK) /* fs/open.c */ struct audit_names; struct filename { const char *name; /* pointer to actual string */ const __user char *uptr; /* original userland pointer */ atomic_t refcnt; struct audit_names *aname; const char iname[]; }; static_assert(offsetof(struct filename, iname) % sizeof(long) == 0); static inline struct mnt_idmap *file_mnt_idmap(const struct file *file) { return mnt_idmap(file->f_path.mnt); } /** * is_idmapped_mnt - check whether a mount is mapped * @mnt: the mount to check * * If @mnt has an non @nop_mnt_idmap attached to it then @mnt is mapped. * * Return: true if mount is mapped, false if not. */ static inline bool is_idmapped_mnt(const struct vfsmount *mnt) { return mnt_idmap(mnt) != &nop_mnt_idmap; } extern long vfs_truncate(const struct path *, loff_t); int do_truncate(struct mnt_idmap *, struct dentry *, loff_t start, unsigned int time_attrs, struct file *filp); extern int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len); extern long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode); extern struct file *file_open_name(struct filename *, int, umode_t); extern struct file *filp_open(const char *, int, umode_t); extern struct file *file_open_root(const struct path *, const char *, int, umode_t); static inline struct file *file_open_root_mnt(struct vfsmount *mnt, const char *name, int flags, umode_t mode) { return file_open_root(&(struct path){.mnt = mnt, .dentry = mnt->mnt_root}, name, flags, mode); } struct file *dentry_open(const struct path *path, int flags, const struct cred *creds); struct file *dentry_create(const struct path *path, int flags, umode_t mode, const struct cred *cred); struct path *backing_file_user_path(struct file *f); /* * When mmapping a file on a stackable filesystem (e.g., overlayfs), the file * stored in ->vm_file is a backing file whose f_inode is on the underlying * filesystem. When the mapped file path and inode number are displayed to * user (e.g. via /proc/<pid>/maps), these helpers should be used to get the * path and inode number to display to the user, which is the path of the fd * that user has requested to map and the inode number that would be returned * by fstat() on that same fd. */ /* Get the path to display in /proc/<pid>/maps */ static inline const struct path *file_user_path(struct file *f) { if (unlikely(f->f_mode & FMODE_BACKING)) return backing_file_user_path(f); return &f->f_path; } /* Get the inode whose inode number to display in /proc/<pid>/maps */ static inline const struct inode *file_user_inode(struct file *f) { if (unlikely(f->f_mode & FMODE_BACKING)) return d_inode(backing_file_user_path(f)->dentry); return file_inode(f); } static inline struct file *file_clone_open(struct file *file) { return dentry_open(&file->f_path, file->f_flags, file->f_cred); } extern int filp_close(struct file *, fl_owner_t id); extern struct filename *getname_flags(const char __user *, int); extern struct filename *getname_uflags(const char __user *, int); extern struct filename *getname(const char __user *); extern struct filename *getname_kernel(const char *); extern void putname(struct filename *name); extern int finish_open(struct file *file, struct dentry *dentry, int (*open)(struct inode *, struct file *)); extern int finish_no_open(struct file *file, struct dentry *dentry); /* Helper for the simple case when original dentry is used */ static inline int finish_open_simple(struct file *file, int error) { if (error) return error; return finish_open(file, file->f_path.dentry, NULL); } /* fs/dcache.c */ extern void __init vfs_caches_init_early(void); extern void __init vfs_caches_init(void); extern struct kmem_cache *names_cachep; #define __getname() kmem_cache_alloc(names_cachep, GFP_KERNEL) #define __putname(name) kmem_cache_free(names_cachep, (void *)(name)) extern struct super_block *blockdev_superblock; static inline bool sb_is_blkdev_sb(struct super_block *sb) { return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock; } void emergency_thaw_all(void); extern int sync_filesystem(struct super_block *); extern const struct file_operations def_blk_fops; extern const struct file_operations def_chr_fops; /* fs/char_dev.c */ #define CHRDEV_MAJOR_MAX 512 /* Marks the bottom of the first segment of free char majors */ #define CHRDEV_MAJOR_DYN_END 234 /* Marks the top and bottom of the second segment of free char majors */ #define CHRDEV_MAJOR_DYN_EXT_START 511 #define CHRDEV_MAJOR_DYN_EXT_END 384 extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *); extern int register_chrdev_region(dev_t, unsigned, const char *); extern int __register_chrdev(unsigned int major, unsigned int baseminor, unsigned int count, const char *name, const struct file_operations *fops); extern void __unregister_chrdev(unsigned int major, unsigned int baseminor, unsigned int count, const char *name); extern void unregister_chrdev_region(dev_t, unsigned); extern void chrdev_show(struct seq_file *,off_t); static inline int register_chrdev(unsigned int major, const char *name, const struct file_operations *fops) { return __register_chrdev(major, 0, 256, name, fops); } static inline void unregister_chrdev(unsigned int major, const char *name) { __unregister_chrdev(major, 0, 256, name); } extern void init_special_inode(struct inode *, umode_t, dev_t); /* Invalid inode operations -- fs/bad_inode.c */ extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, loff_t lend); extern int __must_check file_check_and_advance_wb_err(struct file *file); extern int __must_check file_write_and_wait_range(struct file *file, loff_t start, loff_t end); static inline int file_write_and_wait(struct file *file) { return file_write_and_wait_range(file, 0, LLONG_MAX); } extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync); extern int vfs_fsync(struct file *file, int datasync); extern int sync_file_range(struct file *file, loff_t offset, loff_t nbytes, unsigned int flags); static inline bool iocb_is_dsync(const struct kiocb *iocb) { return (iocb->ki_flags & IOCB_DSYNC) || IS_SYNC(iocb->ki_filp->f_mapping->host); } /* * Sync the bytes written if this was a synchronous write. Expect ki_pos * to already be updated for the write, and will return either the amount * of bytes passed in, or an error if syncing the file failed. */ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count) { if (iocb_is_dsync(iocb)) { int ret = vfs_fsync_range(iocb->ki_filp, iocb->ki_pos - count, iocb->ki_pos - 1, (iocb->ki_flags & IOCB_SYNC) ? 0 : 1); if (ret) return ret; } return count; } extern void emergency_sync(void); extern void emergency_remount(void); #ifdef CONFIG_BLOCK extern int bmap(struct inode *inode, sector_t *block); #else static inline int bmap(struct inode *inode, sector_t *block) { return -EINVAL; } #endif int notify_change(struct mnt_idmap *, struct dentry *, struct iattr *, struct inode **); int inode_permission(struct mnt_idmap *, struct inode *, int); int generic_permission(struct mnt_idmap *, struct inode *, int); static inline int file_permission(struct file *file, int mask) { return inode_permission(file_mnt_idmap(file), file_inode(file), mask); } static inline int path_permission(const struct path *path, int mask) { return inode_permission(mnt_idmap(path->mnt), d_inode(path->dentry), mask); } int __check_sticky(struct mnt_idmap *idmap, struct inode *dir, struct inode *inode); static inline bool execute_ok(struct inode *inode) { return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode); } static inline bool inode_wrong_type(const struct inode *inode, umode_t mode) { return (inode->i_mode ^ mode) & S_IFMT; } /** * file_start_write - get write access to a superblock for regular file io * @file: the file we want to write to * * This is a variant of sb_start_write() which is a noop on non-regualr file. * Should be matched with a call to file_end_write(). */ static inline void file_start_write(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return; sb_start_write(file_inode(file)->i_sb); } static inline bool file_start_write_trylock(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; return sb_start_write_trylock(file_inode(file)->i_sb); } /** * file_end_write - drop write access to a superblock of a regular file * @file: the file we wrote to * * Should be matched with a call to file_start_write(). */ static inline void file_end_write(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return; sb_end_write(file_inode(file)->i_sb); } /** * kiocb_start_write - get write access to a superblock for async file io * @iocb: the io context we want to submit the write with * * This is a variant of sb_start_write() for async io submission. * Should be matched with a call to kiocb_end_write(). */ static inline void kiocb_start_write(struct kiocb *iocb) { struct inode *inode = file_inode(iocb->ki_filp); sb_start_write(inode->i_sb); /* * Fool lockdep by telling it the lock got released so that it * doesn't complain about the held lock when we return to userspace. */ __sb_writers_release(inode->i_sb, SB_FREEZE_WRITE); } /** * kiocb_end_write - drop write access to a superblock after async file io * @iocb: the io context we sumbitted the write with * * Should be matched with a call to kiocb_start_write(). */ static inline void kiocb_end_write(struct kiocb *iocb) { struct inode *inode = file_inode(iocb->ki_filp); /* * Tell lockdep we inherited freeze protection from submission thread. */ __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE); sb_end_write(inode->i_sb); } /* * This is used for regular files where some users -- especially the * currently executed binary in a process, previously handled via * VM_DENYWRITE -- cannot handle concurrent write (and maybe mmap * read-write shared) accesses. * * get_write_access() gets write permission for a file. * put_write_access() releases this write permission. * deny_write_access() denies write access to a file. * allow_write_access() re-enables write access to a file. * * The i_writecount field of an inode can have the following values: * 0: no write access, no denied write access * < 0: (-i_writecount) users that denied write access to the file. * > 0: (i_writecount) users that have write access to the file. * * Normally we operate on that counter with atomic_{inc,dec} and it's safe * except for the cases where we don't hold i_writecount yet. Then we need to * use {get,deny}_write_access() - these functions check the sign and refuse * to do the change if sign is wrong. */ static inline int get_write_access(struct inode *inode) { return atomic_inc_unless_negative(&inode->i_writecount) ? 0 : -ETXTBSY; } static inline int deny_write_access(struct file *file) { struct inode *inode = file_inode(file); return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY; } static inline void put_write_access(struct inode * inode) { atomic_dec(&inode->i_writecount); } static inline void allow_write_access(struct file *file) { if (file) atomic_inc(&file_inode(file)->i_writecount); } static inline bool inode_is_open_for_write(const struct inode *inode) { return atomic_read(&inode->i_writecount) > 0; } #if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING) static inline void i_readcount_dec(struct inode *inode) { BUG_ON(atomic_dec_return(&inode->i_readcount) < 0); } static inline void i_readcount_inc(struct inode *inode) { atomic_inc(&inode->i_readcount); } #else static inline void i_readcount_dec(struct inode *inode) { return; } static inline void i_readcount_inc(struct inode *inode) { return; } #endif extern int do_pipe_flags(int *, int); extern ssize_t kernel_read(struct file *, void *, size_t, loff_t *); ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos); extern ssize_t kernel_write(struct file *, const void *, size_t, loff_t *); extern ssize_t __kernel_write(struct file *, const void *, size_t, loff_t *); extern struct file * open_exec(const char *); /* fs/dcache.c -- generic fs support functions */ extern bool is_subdir(struct dentry *, struct dentry *); extern bool path_is_under(const struct path *, const struct path *); extern char *file_path(struct file *, char *, int); /** * is_dot_dotdot - returns true only if @name is "." or ".." * @name: file name to check * @len: length of file name, in bytes */ static inline bool is_dot_dotdot(const char *name, size_t len) { return len && unlikely(name[0] == '.') && (len == 1 || (len == 2 && name[1] == '.')); } #include <linux/err.h> /* needed for stackable file system support */ extern loff_t default_llseek(struct file *file, loff_t offset, int whence); extern loff_t vfs_llseek(struct file *file, loff_t offset, int whence); extern int inode_init_always(struct super_block *, struct inode *); extern void inode_init_once(struct inode *); extern void address_space_init_once(struct address_space *mapping); extern struct inode * igrab(struct inode *); extern ino_t iunique(struct super_block *, ino_t); extern int inode_needs_sync(struct inode *inode); extern int generic_delete_inode(struct inode *inode); static inline int generic_drop_inode(struct inode *inode) { return !inode->i_nlink || inode_unhashed(inode); } extern void d_mark_dontcache(struct inode *inode); extern struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data); extern struct inode *ilookup5(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data); extern struct inode *ilookup(struct super_block *sb, unsigned long ino); extern struct inode *inode_insert5(struct inode *inode, unsigned long hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data); struct inode *iget5_locked(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *); struct inode *iget5_locked_rcu(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *); extern struct inode * iget_locked(struct super_block *, unsigned long); extern struct inode *find_inode_nowait(struct super_block *, unsigned long, int (*match)(struct inode *, unsigned long, void *), void *data); extern struct inode *find_inode_rcu(struct super_block *, unsigned long, int (*)(struct inode *, void *), void *); extern struct inode *find_inode_by_ino_rcu(struct super_block *, unsigned long); extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *); extern int insert_inode_locked(struct inode *); #ifdef CONFIG_DEBUG_LOCK_ALLOC extern void lockdep_annotate_inode_mutex_key(struct inode *inode); #else static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { }; #endif extern void unlock_new_inode(struct inode *); extern void discard_new_inode(struct inode *); extern unsigned int get_next_ino(void); extern void evict_inodes(struct super_block *sb); void dump_mapping(const struct address_space *); /* * Userspace may rely on the inode number being non-zero. For example, glibc * simply ignores files with zero i_ino in unlink() and other places. * * As an additional complication, if userspace was compiled with * _FILE_OFFSET_BITS=32 on a 64-bit kernel we'll only end up reading out the * lower 32 bits, so we need to check that those aren't zero explicitly. With * _FILE_OFFSET_BITS=64, this may cause some harmless false-negatives, but * better safe than sorry. */ static inline bool is_zero_ino(ino_t ino) { return (u32)ino == 0; } extern void __iget(struct inode * inode); extern void iget_failed(struct inode *); extern void clear_inode(struct inode *); extern void __destroy_inode(struct inode *); extern struct inode *new_inode_pseudo(struct super_block *sb); extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); extern int setattr_should_drop_suidgid(struct mnt_idmap *, struct inode *); extern int file_remove_privs_flags(struct file *file, unsigned int flags); extern int file_remove_privs(struct file *); int setattr_should_drop_sgid(struct mnt_idmap *idmap, const struct inode *inode); /* * This must be used for allocating filesystems specific inodes to set * up the inode reclaim context correctly. */ #define alloc_inode_sb(_sb, _cache, _gfp) kmem_cache_alloc_lru(_cache, &_sb->s_inode_lru, _gfp) extern void __insert_inode_hash(struct inode *, unsigned long hashval); static inline void insert_inode_hash(struct inode *inode) { __insert_inode_hash(inode, inode->i_ino); } extern void __remove_inode_hash(struct inode *); static inline void remove_inode_hash(struct inode *inode) { if (!inode_unhashed(inode) && !hlist_fake(&inode->i_hash)) __remove_inode_hash(inode); } extern void inode_sb_list_add(struct inode *inode); extern void inode_add_lru(struct inode *inode); extern int sb_set_blocksize(struct super_block *, int); extern int sb_min_blocksize(struct super_block *, int); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); int generic_write_checks_count(struct kiocb *iocb, loff_t *count); extern int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count); extern int generic_file_rw_checks(struct file *file_in, struct file *file_out); ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *to, ssize_t already_read); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *); ssize_t generic_perform_write(struct kiocb *, struct iov_iter *); ssize_t direct_write_fallback(struct kiocb *iocb, struct iov_iter *iter, ssize_t direct_written, ssize_t buffered_written); ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags); ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags); ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb, struct iov_iter *iter); ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, struct iov_iter *iter); /* fs/splice.c */ ssize_t filemap_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); ssize_t copy_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); extern ssize_t iter_file_splice_write(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); extern void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); extern loff_t noop_llseek(struct file *file, loff_t offset, int whence); #define no_llseek NULL extern loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize); extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence); extern loff_t generic_file_llseek_size(struct file *file, loff_t offset, int whence, loff_t maxsize, loff_t eof); extern loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size); extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t); extern loff_t no_seek_end_llseek(struct file *, loff_t, int); int rw_verify_area(int, struct file *, const loff_t *, size_t); extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); extern int stream_open(struct inode * inode, struct file * filp); #ifdef CONFIG_BLOCK typedef void (dio_submit_t)(struct bio *bio, struct inode *inode, loff_t file_offset); enum { /* need locking between buffered and direct access */ DIO_LOCKING = 0x01, /* filesystem does not support filling holes */ DIO_SKIP_HOLES = 0x02, }; ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, get_block_t get_block, dio_iodone_t end_io, int flags); static inline ssize_t blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct iov_iter *iter, get_block_t get_block) { return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, get_block, NULL, DIO_LOCKING | DIO_SKIP_HOLES); } #endif void inode_dio_wait(struct inode *inode); /** * inode_dio_begin - signal start of a direct I/O requests * @inode: inode the direct I/O happens on * * This is called once we've finished processing a direct I/O request, * and is used to wake up callers waiting for direct I/O to be quiesced. */ static inline void inode_dio_begin(struct inode *inode) { atomic_inc(&inode->i_dio_count); } /** * inode_dio_end - signal finish of a direct I/O requests * @inode: inode the direct I/O happens on * * This is called once we've finished processing a direct I/O request, * and is used to wake up callers waiting for direct I/O to be quiesced. */ static inline void inode_dio_end(struct inode *inode) { if (atomic_dec_and_test(&inode->i_dio_count)) wake_up_bit(&inode->i_state, __I_DIO_WAKEUP); } extern void inode_set_flags(struct inode *inode, unsigned int flags, unsigned int mask); extern const struct file_operations generic_ro_fops; #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m)) extern int readlink_copy(char __user *, int, const char *); extern int page_readlink(struct dentry *, char __user *, int); extern const char *page_get_link(struct dentry *, struct inode *, struct delayed_call *); extern void page_put_link(void *); extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *); void generic_fill_statx_attr(struct inode *inode, struct kstat *stat); void generic_fill_statx_atomic_writes(struct kstat *stat, unsigned int unit_min, unsigned int unit_max); extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int); extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int); void __inode_add_bytes(struct inode *inode, loff_t bytes); void inode_add_bytes(struct inode *inode, loff_t bytes); void __inode_sub_bytes(struct inode *inode, loff_t bytes); void inode_sub_bytes(struct inode *inode, loff_t bytes); static inline loff_t __inode_get_bytes(struct inode *inode) { return (((loff_t)inode->i_blocks) << 9) + inode->i_bytes; } loff_t inode_get_bytes(struct inode *inode); void inode_set_bytes(struct inode *inode, loff_t bytes); const char *simple_get_link(struct dentry *, struct inode *, struct delayed_call *); extern const struct inode_operations simple_symlink_inode_operations; extern int iterate_dir(struct file *, struct dir_context *); int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat, int flags); int vfs_fstat(int fd, struct kstat *stat); static inline int vfs_stat(const char __user *filename, struct kstat *stat) { return vfs_fstatat(AT_FDCWD, filename, stat, 0); } static inline int vfs_lstat(const char __user *name, struct kstat *stat) { return vfs_fstatat(AT_FDCWD, name, stat, AT_SYMLINK_NOFOLLOW); } extern const char *vfs_get_link(struct dentry *, struct delayed_call *); extern int vfs_readlink(struct dentry *, char __user *, int); extern struct file_system_type *get_filesystem(struct file_system_type *fs); extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); extern void drop_super(struct super_block *sb); extern void drop_super_exclusive(struct super_block *sb); extern void iterate_supers(void (*)(struct super_block *, void *), void *); extern void iterate_supers_type(struct file_system_type *, void (*)(struct super_block *, void *), void *); extern int dcache_dir_open(struct inode *, struct file *); extern int dcache_dir_close(struct inode *, struct file *); extern loff_t dcache_dir_lseek(struct file *, loff_t, int); extern int dcache_readdir(struct file *, struct dir_context *); extern int simple_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); extern int simple_getattr(struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); extern int simple_statfs(struct dentry *, struct kstatfs *); extern int simple_open(struct inode *inode, struct file *file); extern int simple_link(struct dentry *, struct inode *, struct dentry *); extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); void simple_rename_timestamp(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); extern int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); extern int simple_rename(struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); extern void simple_recursive_removal(struct dentry *, void (*callback)(struct dentry *)); extern int noop_fsync(struct file *, loff_t, loff_t, int); extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int simple_empty(struct dentry *); extern int simple_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, struct page **pagep, void **fsdata); extern const struct address_space_operations ram_aops; extern int always_delete_dentry(const struct dentry *); extern struct inode *alloc_anon_inode(struct super_block *); extern int simple_nosetlease(struct file *, int, struct file_lease **, void **); extern const struct dentry_operations simple_dentry_operations; extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags); extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *); extern const struct file_operations simple_dir_operations; extern const struct inode_operations simple_dir_inode_operations; extern void make_empty_dir_inode(struct inode *inode); extern bool is_empty_dir_inode(struct inode *inode); struct tree_descr { const char *name; const struct file_operations *ops; int mode; }; struct dentry *d_alloc_name(struct dentry *, const char *); extern int simple_fill_super(struct super_block *, unsigned long, const struct tree_descr *); extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count); extern void simple_release_fs(struct vfsmount **mount, int *count); extern ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos, const void *from, size_t available); extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos, const void __user *from, size_t count); struct offset_ctx { struct maple_tree mt; unsigned long next_offset; }; void simple_offset_init(struct offset_ctx *octx); int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry); void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry); int simple_offset_empty(struct dentry *dentry); int simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); int simple_offset_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); void simple_offset_destroy(struct offset_ctx *octx); extern const struct file_operations simple_offset_dir_operations; extern int __generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_check_addressable(unsigned, u64); extern void generic_set_sb_d_ops(struct super_block *sb); extern int generic_ci_match(const struct inode *parent, const struct qstr *name, const struct qstr *folded_name, const u8 *de_name, u32 de_name_len); static inline bool sb_has_encoding(const struct super_block *sb) { #if IS_ENABLED(CONFIG_UNICODE) return !!sb->s_encoding; #else return false; #endif } int may_setattr(struct mnt_idmap *idmap, struct inode *inode, unsigned int ia_valid); int setattr_prepare(struct mnt_idmap *, struct dentry *, struct iattr *); extern int inode_newsize_ok(const struct inode *, loff_t offset); void setattr_copy(struct mnt_idmap *, struct inode *inode, const struct iattr *attr); extern int file_update_time(struct file *file); static inline bool vma_is_dax(const struct vm_area_struct *vma) { return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); } static inline bool vma_is_fsdax(struct vm_area_struct *vma) { struct inode *inode; if (!IS_ENABLED(CONFIG_FS_DAX) || !vma->vm_file) return false; if (!vma_is_dax(vma)) return false; inode = file_inode(vma->vm_file); if (S_ISCHR(inode->i_mode)) return false; /* device-dax */ return true; } static inline int iocb_flags(struct file *file) { int res = 0; if (file->f_flags & O_APPEND) res |= IOCB_APPEND; if (file->f_flags & O_DIRECT) res |= IOCB_DIRECT; if (file->f_flags & O_DSYNC) res |= IOCB_DSYNC; if (file->f_flags & __O_SYNC) res |= IOCB_SYNC; return res; } static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags, int rw_type) { int kiocb_flags = 0; /* make sure there's no overlap between RWF and private IOCB flags */ BUILD_BUG_ON((__force int) RWF_SUPPORTED & IOCB_EVENTFD); if (!flags) return 0; if (unlikely(flags & ~RWF_SUPPORTED)) return -EOPNOTSUPP; if (unlikely((flags & RWF_APPEND) && (flags & RWF_NOAPPEND))) return -EINVAL; if (flags & RWF_NOWAIT) { if (!(ki->ki_filp->f_mode & FMODE_NOWAIT)) return -EOPNOTSUPP; kiocb_flags |= IOCB_NOIO; } if (flags & RWF_ATOMIC) { if (rw_type != WRITE) return -EOPNOTSUPP; if (!(ki->ki_filp->f_mode & FMODE_CAN_ATOMIC_WRITE)) return -EOPNOTSUPP; } kiocb_flags |= (__force int) (flags & RWF_SUPPORTED); if (flags & RWF_SYNC) kiocb_flags |= IOCB_DSYNC; if ((flags & RWF_NOAPPEND) && (ki->ki_flags & IOCB_APPEND)) { if (IS_APPEND(file_inode(ki->ki_filp))) return -EPERM; ki->ki_flags &= ~IOCB_APPEND; } ki->ki_flags |= kiocb_flags; return 0; } /* Transaction based IO helpers */ /* * An argresp is stored in an allocated page and holds the * size of the argument or response, along with its content */ struct simple_transaction_argresp { ssize_t size; char data[]; }; #define SIMPLE_TRANSACTION_LIMIT (PAGE_SIZE - sizeof(struct simple_transaction_argresp)) char *simple_transaction_get(struct file *file, const char __user *buf, size_t size); ssize_t simple_transaction_read(struct file *file, char __user *buf, size_t size, loff_t *pos); int simple_transaction_release(struct inode *inode, struct file *file); void simple_transaction_set(struct file *file, size_t n); /* * simple attribute files * * These attributes behave similar to those in sysfs: * * Writing to an attribute immediately sets a value, an open file can be * written to multiple times. * * Reading from an attribute creates a buffer from the value that might get * read with multiple read calls. When the attribute has been read * completely, no further read calls are possible until the file is opened * again. * * All attributes contain a text representation of a numeric value * that are accessed with the get() and set() functions. */ #define DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, __is_signed) \ static int __fops ## _open(struct inode *inode, struct file *file) \ { \ __simple_attr_check_format(__fmt, 0ull); \ return simple_attr_open(inode, file, __get, __set, __fmt); \ } \ static const struct file_operations __fops = { \ .owner = THIS_MODULE, \ .open = __fops ## _open, \ .release = simple_attr_release, \ .read = simple_attr_read, \ .write = (__is_signed) ? simple_attr_write_signed : simple_attr_write, \ .llseek = generic_file_llseek, \ } #define DEFINE_SIMPLE_ATTRIBUTE(__fops, __get, __set, __fmt) \ DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, false) #define DEFINE_SIMPLE_ATTRIBUTE_SIGNED(__fops, __get, __set, __fmt) \ DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, true) static inline __printf(1, 2) void __simple_attr_check_format(const char *fmt, ...) { /* don't do anything, just let the compiler check the arguments; */ } int simple_attr_open(struct inode *inode, struct file *file, int (*get)(void *, u64 *), int (*set)(void *, u64), const char *fmt); int simple_attr_release(struct inode *inode, struct file *file); ssize_t simple_attr_read(struct file *file, char __user *buf, size_t len, loff_t *ppos); ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos); ssize_t simple_attr_write_signed(struct file *file, const char __user *buf, size_t len, loff_t *ppos); struct ctl_table; int __init list_bdev_fs_names(char *buf, size_t size); #define __FMODE_EXEC ((__force int) FMODE_EXEC) #define __FMODE_NONOTIFY ((__force int) FMODE_NONOTIFY) #define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE]) #define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \ (flag & __FMODE_NONOTIFY))) static inline bool is_sxid(umode_t mode) { return mode & (S_ISUID | S_ISGID); } static inline int check_sticky(struct mnt_idmap *idmap, struct inode *dir, struct inode *inode) { if (!(dir->i_mode & S_ISVTX)) return 0; return __check_sticky(idmap, dir, inode); } static inline void inode_has_no_xattr(struct inode *inode) { if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & SB_NOSEC)) inode->i_flags |= S_NOSEC; } static inline bool is_root_inode(struct inode *inode) { return inode == inode->i_sb->s_root->d_inode; } static inline bool dir_emit(struct dir_context *ctx, const char *name, int namelen, u64 ino, unsigned type) { return ctx->actor(ctx, name, namelen, ctx->pos, ino, type); } static inline bool dir_emit_dot(struct file *file, struct dir_context *ctx) { return ctx->actor(ctx, ".", 1, ctx->pos, file->f_path.dentry->d_inode->i_ino, DT_DIR); } static inline bool dir_emit_dotdot(struct file *file, struct dir_context *ctx) { return ctx->actor(ctx, "..", 2, ctx->pos, d_parent_ino(file->f_path.dentry), DT_DIR); } static inline bool dir_emit_dots(struct file *file, struct dir_context *ctx) { if (ctx->pos == 0) { if (!dir_emit_dot(file, ctx)) return false; ctx->pos = 1; } if (ctx->pos == 1) { if (!dir_emit_dotdot(file, ctx)) return false; ctx->pos = 2; } return true; } static inline bool dir_relax(struct inode *inode) { inode_unlock(inode); inode_lock(inode); return !IS_DEADDIR(inode); } static inline bool dir_relax_shared(struct inode *inode) { inode_unlock_shared(inode); inode_lock_shared(inode); return !IS_DEADDIR(inode); } extern bool path_noexec(const struct path *path); extern void inode_nohighmem(struct inode *inode); /* mm/fadvise.c */ extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len, int advice); extern int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice); static inline bool vfs_empty_path(int dfd, const char __user *path) { char c; if (dfd < 0) return false; /* We now allow NULL to be used for empty path. */ if (!path) return true; if (unlikely(get_user(c, path))) return false; return !c; } bool generic_atomic_write_valid(struct iov_iter *iter, loff_t pos); #endif /* _LINUX_FS_H */ |
| 17 2431 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 | /* SPDX-License-Identifier: GPL-2.0 */ /* File: linux/xattr.h Extended attributes handling. Copyright (C) 2001 by Andreas Gruenbacher <a.gruenbacher@computer.org> Copyright (c) 2001-2002 Silicon Graphics, Inc. All Rights Reserved. Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com> */ #ifndef _LINUX_XATTR_H #define _LINUX_XATTR_H #include <linux/slab.h> #include <linux/types.h> #include <linux/spinlock.h> #include <linux/mm.h> #include <linux/user_namespace.h> #include <uapi/linux/xattr.h> struct inode; struct dentry; static inline bool is_posix_acl_xattr(const char *name) { return (strcmp(name, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || (strcmp(name, XATTR_NAME_POSIX_ACL_DEFAULT) == 0); } /* * struct xattr_handler: When @name is set, match attributes with exactly that * name. When @prefix is set instead, match attributes with that prefix and * with a non-empty suffix. */ struct xattr_handler { const char *name; const char *prefix; int flags; /* fs private flags */ bool (*list)(struct dentry *dentry); int (*get)(const struct xattr_handler *, struct dentry *dentry, struct inode *inode, const char *name, void *buffer, size_t size); int (*set)(const struct xattr_handler *, struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, const char *name, const void *buffer, size_t size, int flags); }; /** * xattr_handler_can_list - check whether xattr can be listed * @handler: handler for this type of xattr * @dentry: dentry whose inode xattr to list * * Determine whether the xattr associated with @dentry can be listed given * @handler. * * Return: true if xattr can be listed, false if not. */ static inline bool xattr_handler_can_list(const struct xattr_handler *handler, struct dentry *dentry) { return handler && (!handler->list || handler->list(dentry)); } const char *xattr_full_name(const struct xattr_handler *, const char *); struct xattr { const char *name; void *value; size_t value_len; }; ssize_t __vfs_getxattr(struct dentry *, struct inode *, const char *, void *, size_t); ssize_t vfs_getxattr(struct mnt_idmap *, struct dentry *, const char *, void *, size_t); ssize_t vfs_listxattr(struct dentry *d, char *list, size_t size); int __vfs_setxattr(struct mnt_idmap *, struct dentry *, struct inode *, const char *, const void *, size_t, int); int __vfs_setxattr_noperm(struct mnt_idmap *, struct dentry *, const char *, const void *, size_t, int); int __vfs_setxattr_locked(struct mnt_idmap *, struct dentry *, const char *, const void *, size_t, int, struct inode **); int vfs_setxattr(struct mnt_idmap *, struct dentry *, const char *, const void *, size_t, int); int __vfs_removexattr(struct mnt_idmap *, struct dentry *, const char *); int __vfs_removexattr_locked(struct mnt_idmap *, struct dentry *, const char *, struct inode **); int vfs_removexattr(struct mnt_idmap *, struct dentry *, const char *); ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size); int vfs_getxattr_alloc(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, char **xattr_value, size_t size, gfp_t flags); int xattr_supports_user_prefix(struct inode *inode); static inline const char *xattr_prefix(const struct xattr_handler *handler) { return handler->prefix ?: handler->name; } struct simple_xattrs { struct rb_root rb_root; rwlock_t lock; }; struct simple_xattr { struct rb_node rb_node; char *name; size_t size; char value[]; }; void simple_xattrs_init(struct simple_xattrs *xattrs); void simple_xattrs_free(struct simple_xattrs *xattrs, size_t *freed_space); size_t simple_xattr_space(const char *name, size_t size); struct simple_xattr *simple_xattr_alloc(const void *value, size_t size); void simple_xattr_free(struct simple_xattr *xattr); int simple_xattr_get(struct simple_xattrs *xattrs, const char *name, void *buffer, size_t size); struct simple_xattr *simple_xattr_set(struct simple_xattrs *xattrs, const char *name, const void *value, size_t size, int flags); ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, char *buffer, size_t size); void simple_xattr_add(struct simple_xattrs *xattrs, struct simple_xattr *new_xattr); int xattr_list_one(char **buffer, ssize_t *remaining_size, const char *name); #endif /* _LINUX_XATTR_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 | /* SPDX-License-Identifier: GPL-2.0 */ /* interrupt.h */ #ifndef _LINUX_INTERRUPT_H #define _LINUX_INTERRUPT_H #include <linux/kernel.h> #include <linux/bitops.h> #include <linux/cleanup.h> #include <linux/irqreturn.h> #include <linux/irqnr.h> #include <linux/hardirq.h> #include <linux/irqflags.h> #include <linux/hrtimer.h> #include <linux/kref.h> #include <linux/cpumask_types.h> #include <linux/workqueue.h> #include <linux/jump_label.h> #include <linux/atomic.h> #include <asm/ptrace.h> #include <asm/irq.h> #include <asm/sections.h> /* * These correspond to the IORESOURCE_IRQ_* defines in * linux/ioport.h to select the interrupt line behaviour. When * requesting an interrupt without specifying a IRQF_TRIGGER, the * setting should be assumed to be "as already configured", which * may be as per machine or firmware initialisation. */ #define IRQF_TRIGGER_NONE 0x00000000 #define IRQF_TRIGGER_RISING 0x00000001 #define IRQF_TRIGGER_FALLING 0x00000002 #define IRQF_TRIGGER_HIGH 0x00000004 #define IRQF_TRIGGER_LOW 0x00000008 #define IRQF_TRIGGER_MASK (IRQF_TRIGGER_HIGH | IRQF_TRIGGER_LOW | \ IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING) #define IRQF_TRIGGER_PROBE 0x00000010 /* * These flags used only by the kernel as part of the * irq handling routines. * * IRQF_SHARED - allow sharing the irq among several devices * IRQF_PROBE_SHARED - set by callers when they expect sharing mismatches to occur * IRQF_TIMER - Flag to mark this interrupt as timer interrupt * IRQF_PERCPU - Interrupt is per cpu * IRQF_NOBALANCING - Flag to exclude this interrupt from irq balancing * IRQF_IRQPOLL - Interrupt is used for polling (only the interrupt that is * registered first in a shared interrupt is considered for * performance reasons) * IRQF_ONESHOT - Interrupt is not reenabled after the hardirq handler finished. * Used by threaded interrupts which need to keep the * irq line disabled until the threaded handler has been run. * IRQF_NO_SUSPEND - Do not disable this IRQ during suspend. Does not guarantee * that this interrupt will wake the system from a suspended * state. See Documentation/power/suspend-and-interrupts.rst * IRQF_FORCE_RESUME - Force enable it on resume even if IRQF_NO_SUSPEND is set * IRQF_NO_THREAD - Interrupt cannot be threaded * IRQF_EARLY_RESUME - Resume IRQ early during syscore instead of at device * resume time. * IRQF_COND_SUSPEND - If the IRQ is shared with a NO_SUSPEND user, execute this * interrupt handler after suspending interrupts. For system * wakeup devices users need to implement wakeup detection in * their interrupt handlers. * IRQF_NO_AUTOEN - Don't enable IRQ or NMI automatically when users request it. * Users will enable it explicitly by enable_irq() or enable_nmi() * later. * IRQF_NO_DEBUG - Exclude from runnaway detection for IPI and similar handlers, * depends on IRQF_PERCPU. * IRQF_COND_ONESHOT - Agree to do IRQF_ONESHOT if already set for a shared * interrupt. */ #define IRQF_SHARED 0x00000080 #define IRQF_PROBE_SHARED 0x00000100 #define __IRQF_TIMER 0x00000200 #define IRQF_PERCPU 0x00000400 #define IRQF_NOBALANCING 0x00000800 #define IRQF_IRQPOLL 0x00001000 #define IRQF_ONESHOT 0x00002000 #define IRQF_NO_SUSPEND 0x00004000 #define IRQF_FORCE_RESUME 0x00008000 #define IRQF_NO_THREAD 0x00010000 #define IRQF_EARLY_RESUME 0x00020000 #define IRQF_COND_SUSPEND 0x00040000 #define IRQF_NO_AUTOEN 0x00080000 #define IRQF_NO_DEBUG 0x00100000 #define IRQF_COND_ONESHOT 0x00200000 #define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD) /* * These values can be returned by request_any_context_irq() and * describe the context the interrupt will be run in. * * IRQC_IS_HARDIRQ - interrupt runs in hardirq context * IRQC_IS_NESTED - interrupt runs in a nested threaded context */ enum { IRQC_IS_HARDIRQ = 0, IRQC_IS_NESTED, }; typedef irqreturn_t (*irq_handler_t)(int, void *); /** * struct irqaction - per interrupt action descriptor * @handler: interrupt handler function * @name: name of the device * @dev_id: cookie to identify the device * @percpu_dev_id: cookie to identify the device * @next: pointer to the next irqaction for shared interrupts * @irq: interrupt number * @flags: flags (see IRQF_* above) * @thread_fn: interrupt handler function for threaded interrupts * @thread: thread pointer for threaded interrupts * @secondary: pointer to secondary irqaction (force threading) * @thread_flags: flags related to @thread * @thread_mask: bitmask for keeping track of @thread activity * @dir: pointer to the proc/irq/NN/name entry */ struct irqaction { irq_handler_t handler; void *dev_id; void __percpu *percpu_dev_id; struct irqaction *next; irq_handler_t thread_fn; struct task_struct *thread; struct irqaction *secondary; unsigned int irq; unsigned int flags; unsigned long thread_flags; unsigned long thread_mask; const char *name; struct proc_dir_entry *dir; } ____cacheline_internodealigned_in_smp; extern irqreturn_t no_action(int cpl, void *dev_id); /* * If a (PCI) device interrupt is not connected we set dev->irq to * IRQ_NOTCONNECTED. This causes request_irq() to fail with -ENOTCONN, so we * can distingiush that case from other error returns. * * 0x80000000 is guaranteed to be outside the available range of interrupts * and easy to distinguish from other possible incorrect values. */ #define IRQ_NOTCONNECTED (1U << 31) extern int __must_check request_threaded_irq(unsigned int irq, irq_handler_t handler, irq_handler_t thread_fn, unsigned long flags, const char *name, void *dev); /** * request_irq - Add a handler for an interrupt line * @irq: The interrupt line to allocate * @handler: Function to be called when the IRQ occurs. * Primary handler for threaded interrupts * If NULL, the default primary handler is installed * @flags: Handling flags * @name: Name of the device generating this interrupt * @dev: A cookie passed to the handler function * * This call allocates an interrupt and establishes a handler; see * the documentation for request_threaded_irq() for details. */ static inline int __must_check request_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, const char *name, void *dev) { return request_threaded_irq(irq, handler, NULL, flags | IRQF_COND_ONESHOT, name, dev); } extern int __must_check request_any_context_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, const char *name, void *dev_id); extern int __must_check __request_percpu_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, const char *devname, void __percpu *percpu_dev_id); extern int __must_check request_nmi(unsigned int irq, irq_handler_t handler, unsigned long flags, const char *name, void *dev); static inline int __must_check request_percpu_irq(unsigned int irq, irq_handler_t handler, const char *devname, void __percpu *percpu_dev_id) { return __request_percpu_irq(irq, handler, 0, devname, percpu_dev_id); } extern int __must_check request_percpu_nmi(unsigned int irq, irq_handler_t handler, const char *devname, void __percpu *dev); extern const void *free_irq(unsigned int, void *); extern void free_percpu_irq(unsigned int, void __percpu *); extern const void *free_nmi(unsigned int irq, void *dev_id); extern void free_percpu_nmi(unsigned int irq, void __percpu *percpu_dev_id); struct device; extern int __must_check devm_request_threaded_irq(struct device *dev, unsigned int irq, irq_handler_t handler, irq_handler_t thread_fn, unsigned long irqflags, const char *devname, void *dev_id); static inline int __must_check devm_request_irq(struct device *dev, unsigned int irq, irq_handler_t handler, unsigned long irqflags, const char *devname, void *dev_id) { return devm_request_threaded_irq(dev, irq, handler, NULL, irqflags, devname, dev_id); } extern int __must_check devm_request_any_context_irq(struct device *dev, unsigned int irq, irq_handler_t handler, unsigned long irqflags, const char *devname, void *dev_id); extern void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id); bool irq_has_action(unsigned int irq); extern void disable_irq_nosync(unsigned int irq); extern bool disable_hardirq(unsigned int irq); extern void disable_irq(unsigned int irq); extern void disable_percpu_irq(unsigned int irq); extern void enable_irq(unsigned int irq); extern void enable_percpu_irq(unsigned int irq, unsigned int type); extern bool irq_percpu_is_enabled(unsigned int irq); extern void irq_wake_thread(unsigned int irq, void *dev_id); DEFINE_LOCK_GUARD_1(disable_irq, int, disable_irq(*_T->lock), enable_irq(*_T->lock)) extern void disable_nmi_nosync(unsigned int irq); extern void disable_percpu_nmi(unsigned int irq); extern void enable_nmi(unsigned int irq); extern void enable_percpu_nmi(unsigned int irq, unsigned int type); extern int prepare_percpu_nmi(unsigned int irq); extern void teardown_percpu_nmi(unsigned int irq); extern int irq_inject_interrupt(unsigned int irq); /* The following three functions are for the core kernel use only. */ extern void suspend_device_irqs(void); extern void resume_device_irqs(void); extern void rearm_wake_irq(unsigned int irq); /** * struct irq_affinity_notify - context for notification of IRQ affinity changes * @irq: Interrupt to which notification applies * @kref: Reference count, for internal use * @work: Work item, for internal use * @notify: Function to be called on change. This will be * called in process context. * @release: Function to be called on release. This will be * called in process context. Once registered, the * structure must only be freed when this function is * called or later. */ struct irq_affinity_notify { unsigned int irq; struct kref kref; struct work_struct work; void (*notify)(struct irq_affinity_notify *, const cpumask_t *mask); void (*release)(struct kref *ref); }; #define IRQ_AFFINITY_MAX_SETS 4 /** * struct irq_affinity - Description for automatic irq affinity assignements * @pre_vectors: Don't apply affinity to @pre_vectors at beginning of * the MSI(-X) vector space * @post_vectors: Don't apply affinity to @post_vectors at end of * the MSI(-X) vector space * @nr_sets: The number of interrupt sets for which affinity * spreading is required * @set_size: Array holding the size of each interrupt set * @calc_sets: Callback for calculating the number and size * of interrupt sets * @priv: Private data for usage by @calc_sets, usually a * pointer to driver/device specific data. */ struct irq_affinity { unsigned int pre_vectors; unsigned int post_vectors; unsigned int nr_sets; unsigned int set_size[IRQ_AFFINITY_MAX_SETS]; void (*calc_sets)(struct irq_affinity *, unsigned int nvecs); void *priv; }; /** * struct irq_affinity_desc - Interrupt affinity descriptor * @mask: cpumask to hold the affinity assignment * @is_managed: 1 if the interrupt is managed internally */ struct irq_affinity_desc { struct cpumask mask; unsigned int is_managed : 1; }; #if defined(CONFIG_SMP) extern cpumask_var_t irq_default_affinity; extern int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask); extern int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask); extern int irq_can_set_affinity(unsigned int irq); extern int irq_select_affinity(unsigned int irq); extern int __irq_apply_affinity_hint(unsigned int irq, const struct cpumask *m, bool setaffinity); /** * irq_update_affinity_hint - Update the affinity hint * @irq: Interrupt to update * @m: cpumask pointer (NULL to clear the hint) * * Updates the affinity hint, but does not change the affinity of the interrupt. */ static inline int irq_update_affinity_hint(unsigned int irq, const struct cpumask *m) { return __irq_apply_affinity_hint(irq, m, false); } /** * irq_set_affinity_and_hint - Update the affinity hint and apply the provided * cpumask to the interrupt * @irq: Interrupt to update * @m: cpumask pointer (NULL to clear the hint) * * Updates the affinity hint and if @m is not NULL it applies it as the * affinity of that interrupt. */ static inline int irq_set_affinity_and_hint(unsigned int irq, const struct cpumask *m) { return __irq_apply_affinity_hint(irq, m, true); } /* * Deprecated. Use irq_update_affinity_hint() or irq_set_affinity_and_hint() * instead. */ static inline int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m) { return irq_set_affinity_and_hint(irq, m); } extern int irq_update_affinity_desc(unsigned int irq, struct irq_affinity_desc *affinity); extern int irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify); struct irq_affinity_desc * irq_create_affinity_masks(unsigned int nvec, struct irq_affinity *affd); unsigned int irq_calc_affinity_vectors(unsigned int minvec, unsigned int maxvec, const struct irq_affinity *affd); #else /* CONFIG_SMP */ static inline int irq_set_affinity(unsigned int irq, const struct cpumask *m) { return -EINVAL; } static inline int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask) { return 0; } static inline int irq_can_set_affinity(unsigned int irq) { return 0; } static inline int irq_select_affinity(unsigned int irq) { return 0; } static inline int irq_update_affinity_hint(unsigned int irq, const struct cpumask *m) { return -EINVAL; } static inline int irq_set_affinity_and_hint(unsigned int irq, const struct cpumask *m) { return -EINVAL; } static inline int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m) { return -EINVAL; } static inline int irq_update_affinity_desc(unsigned int irq, struct irq_affinity_desc *affinity) { return -EINVAL; } static inline int irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify) { return 0; } static inline struct irq_affinity_desc * irq_create_affinity_masks(unsigned int nvec, struct irq_affinity *affd) { return NULL; } static inline unsigned int irq_calc_affinity_vectors(unsigned int minvec, unsigned int maxvec, const struct irq_affinity *affd) { return maxvec; } #endif /* CONFIG_SMP */ /* * Special lockdep variants of irq disabling/enabling. * These should be used for locking constructs that * know that a particular irq context which is disabled, * and which is the only irq-context user of a lock, * that it's safe to take the lock in the irq-disabled * section without disabling hardirqs. * * On !CONFIG_LOCKDEP they are equivalent to the normal * irq disable/enable methods. */ static inline void disable_irq_nosync_lockdep(unsigned int irq) { disable_irq_nosync(irq); #ifdef CONFIG_LOCKDEP local_irq_disable(); #endif } static inline void disable_irq_nosync_lockdep_irqsave(unsigned int irq, unsigned long *flags) { disable_irq_nosync(irq); #ifdef CONFIG_LOCKDEP local_irq_save(*flags); #endif } static inline void disable_irq_lockdep(unsigned int irq) { disable_irq(irq); #ifdef CONFIG_LOCKDEP local_irq_disable(); #endif } static inline void enable_irq_lockdep(unsigned int irq) { #ifdef CONFIG_LOCKDEP local_irq_enable(); #endif enable_irq(irq); } static inline void enable_irq_lockdep_irqrestore(unsigned int irq, unsigned long *flags) { #ifdef CONFIG_LOCKDEP local_irq_restore(*flags); #endif enable_irq(irq); } /* IRQ wakeup (PM) control: */ extern int irq_set_irq_wake(unsigned int irq, unsigned int on); static inline int enable_irq_wake(unsigned int irq) { return irq_set_irq_wake(irq, 1); } static inline int disable_irq_wake(unsigned int irq) { return irq_set_irq_wake(irq, 0); } /* * irq_get_irqchip_state/irq_set_irqchip_state specific flags */ enum irqchip_irq_state { IRQCHIP_STATE_PENDING, /* Is interrupt pending? */ IRQCHIP_STATE_ACTIVE, /* Is interrupt in progress? */ IRQCHIP_STATE_MASKED, /* Is interrupt masked? */ IRQCHIP_STATE_LINE_LEVEL, /* Is IRQ line high? */ }; extern int irq_get_irqchip_state(unsigned int irq, enum irqchip_irq_state which, bool *state); extern int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which, bool state); #ifdef CONFIG_IRQ_FORCED_THREADING # ifdef CONFIG_PREEMPT_RT # define force_irqthreads() (true) # else DECLARE_STATIC_KEY_FALSE(force_irqthreads_key); # define force_irqthreads() (static_branch_unlikely(&force_irqthreads_key)) # endif #else #define force_irqthreads() (false) #endif #ifndef local_softirq_pending #ifndef local_softirq_pending_ref #define local_softirq_pending_ref irq_stat.__softirq_pending #endif #define local_softirq_pending() (__this_cpu_read(local_softirq_pending_ref)) #define set_softirq_pending(x) (__this_cpu_write(local_softirq_pending_ref, (x))) #define or_softirq_pending(x) (__this_cpu_or(local_softirq_pending_ref, (x))) #endif /* local_softirq_pending */ /* Some architectures might implement lazy enabling/disabling of * interrupts. In some cases, such as stop_machine, we might want * to ensure that after a local_irq_disable(), interrupts have * really been disabled in hardware. Such architectures need to * implement the following hook. */ #ifndef hard_irq_disable #define hard_irq_disable() do { } while(0) #endif /* PLEASE, avoid to allocate new softirqs, if you need not _really_ high frequency threaded job scheduling. For almost all the purposes tasklets are more than enough. F.e. all serial device BHs et al. should be converted to tasklets, not to softirqs. */ enum { HI_SOFTIRQ=0, TIMER_SOFTIRQ, NET_TX_SOFTIRQ, NET_RX_SOFTIRQ, BLOCK_SOFTIRQ, IRQ_POLL_SOFTIRQ, TASKLET_SOFTIRQ, SCHED_SOFTIRQ, HRTIMER_SOFTIRQ, RCU_SOFTIRQ, /* Preferable RCU should always be the last softirq */ NR_SOFTIRQS }; /* * The following vectors can be safely ignored after ksoftirqd is parked: * * _ RCU: * 1) rcutree_migrate_callbacks() migrates the queue. * 2) rcutree_report_cpu_dead() reports the final quiescent states. * * _ IRQ_POLL: irq_poll_cpu_dead() migrates the queue * * _ (HR)TIMER_SOFTIRQ: (hr)timers_dead_cpu() migrates the queue */ #define SOFTIRQ_HOTPLUG_SAFE_MASK (BIT(TIMER_SOFTIRQ) | BIT(IRQ_POLL_SOFTIRQ) |\ BIT(HRTIMER_SOFTIRQ) | BIT(RCU_SOFTIRQ)) /* map softirq index to softirq name. update 'softirq_to_name' in * kernel/softirq.c when adding a new softirq. */ extern const char * const softirq_to_name[NR_SOFTIRQS]; /* softirq mask and active fields moved to irq_cpustat_t in * asm/hardirq.h to get better cache usage. KAO */ struct softirq_action { void (*action)(struct softirq_action *); }; asmlinkage void do_softirq(void); asmlinkage void __do_softirq(void); #ifdef CONFIG_PREEMPT_RT extern void do_softirq_post_smp_call_flush(unsigned int was_pending); #else static inline void do_softirq_post_smp_call_flush(unsigned int unused) { do_softirq(); } #endif extern void open_softirq(int nr, void (*action)(struct softirq_action *)); extern void softirq_init(void); extern void __raise_softirq_irqoff(unsigned int nr); extern void raise_softirq_irqoff(unsigned int nr); extern void raise_softirq(unsigned int nr); DECLARE_PER_CPU(struct task_struct *, ksoftirqd); static inline struct task_struct *this_cpu_ksoftirqd(void) { return this_cpu_read(ksoftirqd); } /* Tasklets --- multithreaded analogue of BHs. This API is deprecated. Please consider using threaded IRQs instead: https://lore.kernel.org/lkml/20200716081538.2sivhkj4hcyrusem@linutronix.de Main feature differing them of generic softirqs: tasklet is running only on one CPU simultaneously. Main feature differing them of BHs: different tasklets may be run simultaneously on different CPUs. Properties: * If tasklet_schedule() is called, then tasklet is guaranteed to be executed on some cpu at least once after this. * If the tasklet is already scheduled, but its execution is still not started, it will be executed only once. * If this tasklet is already running on another CPU (or schedule is called from tasklet itself), it is rescheduled for later. * Tasklet is strictly serialized wrt itself, but not wrt another tasklets. If client needs some intertask synchronization, he makes it with spinlocks. */ struct tasklet_struct { struct tasklet_struct *next; unsigned long state; atomic_t count; bool use_callback; union { void (*func)(unsigned long data); void (*callback)(struct tasklet_struct *t); }; unsigned long data; }; #define DECLARE_TASKLET(name, _callback) \ struct tasklet_struct name = { \ .count = ATOMIC_INIT(0), \ .callback = _callback, \ .use_callback = true, \ } #define DECLARE_TASKLET_DISABLED(name, _callback) \ struct tasklet_struct name = { \ .count = ATOMIC_INIT(1), \ .callback = _callback, \ .use_callback = true, \ } #define from_tasklet(var, callback_tasklet, tasklet_fieldname) \ container_of(callback_tasklet, typeof(*var), tasklet_fieldname) #define DECLARE_TASKLET_OLD(name, _func) \ struct tasklet_struct name = { \ .count = ATOMIC_INIT(0), \ .func = _func, \ } #define DECLARE_TASKLET_DISABLED_OLD(name, _func) \ struct tasklet_struct name = { \ .count = ATOMIC_INIT(1), \ .func = _func, \ } enum { TASKLET_STATE_SCHED, /* Tasklet is scheduled for execution */ TASKLET_STATE_RUN /* Tasklet is running (SMP only) */ }; #if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT) static inline int tasklet_trylock(struct tasklet_struct *t) { return !test_and_set_bit(TASKLET_STATE_RUN, &(t)->state); } void tasklet_unlock(struct tasklet_struct *t); void tasklet_unlock_wait(struct tasklet_struct *t); void tasklet_unlock_spin_wait(struct tasklet_struct *t); #else static inline int tasklet_trylock(struct tasklet_struct *t) { return 1; } static inline void tasklet_unlock(struct tasklet_struct *t) { } static inline void tasklet_unlock_wait(struct tasklet_struct *t) { } static inline void tasklet_unlock_spin_wait(struct tasklet_struct *t) { } #endif extern void __tasklet_schedule(struct tasklet_struct *t); static inline void tasklet_schedule(struct tasklet_struct *t) { if (!test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) __tasklet_schedule(t); } extern void __tasklet_hi_schedule(struct tasklet_struct *t); static inline void tasklet_hi_schedule(struct tasklet_struct *t) { if (!test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) __tasklet_hi_schedule(t); } static inline void tasklet_disable_nosync(struct tasklet_struct *t) { atomic_inc(&t->count); smp_mb__after_atomic(); } /* * Do not use in new code. Disabling tasklets from atomic contexts is * error prone and should be avoided. */ static inline void tasklet_disable_in_atomic(struct tasklet_struct *t) { tasklet_disable_nosync(t); tasklet_unlock_spin_wait(t); smp_mb(); } static inline void tasklet_disable(struct tasklet_struct *t) { tasklet_disable_nosync(t); tasklet_unlock_wait(t); smp_mb(); } static inline void tasklet_enable(struct tasklet_struct *t) { smp_mb__before_atomic(); atomic_dec(&t->count); } extern void tasklet_kill(struct tasklet_struct *t); extern void tasklet_init(struct tasklet_struct *t, void (*func)(unsigned long), unsigned long data); extern void tasklet_setup(struct tasklet_struct *t, void (*callback)(struct tasklet_struct *)); /* * Autoprobing for irqs: * * probe_irq_on() and probe_irq_off() provide robust primitives * for accurate IRQ probing during kernel initialization. They are * reasonably simple to use, are not "fooled" by spurious interrupts, * and, unlike other attempts at IRQ probing, they do not get hung on * stuck interrupts (such as unused PS2 mouse interfaces on ASUS boards). * * For reasonably foolproof probing, use them as follows: * * 1. clear and/or mask the device's internal interrupt. * 2. sti(); * 3. irqs = probe_irq_on(); // "take over" all unassigned idle IRQs * 4. enable the device and cause it to trigger an interrupt. * 5. wait for the device to interrupt, using non-intrusive polling or a delay. * 6. irq = probe_irq_off(irqs); // get IRQ number, 0=none, negative=multiple * 7. service the device to clear its pending interrupt. * 8. loop again if paranoia is required. * * probe_irq_on() returns a mask of allocated irq's. * * probe_irq_off() takes the mask as a parameter, * and returns the irq number which occurred, * or zero if none occurred, or a negative irq number * if more than one irq occurred. */ #if !defined(CONFIG_GENERIC_IRQ_PROBE) static inline unsigned long probe_irq_on(void) { return 0; } static inline int probe_irq_off(unsigned long val) { return 0; } static inline unsigned int probe_irq_mask(unsigned long val) { return 0; } #else extern unsigned long probe_irq_on(void); /* returns 0 on failure */ extern int probe_irq_off(unsigned long); /* returns 0 or negative on failure */ extern unsigned int probe_irq_mask(unsigned long); /* returns mask of ISA interrupts */ #endif #ifdef CONFIG_PROC_FS /* Initialize /proc/irq/ */ extern void init_irq_proc(void); #else static inline void init_irq_proc(void) { } #endif #ifdef CONFIG_IRQ_TIMINGS void irq_timings_enable(void); void irq_timings_disable(void); u64 irq_timings_next_event(u64 now); #endif struct seq_file; int show_interrupts(struct seq_file *p, void *v); int arch_show_interrupts(struct seq_file *p, int prec); extern int early_irq_init(void); extern int arch_probe_nr_irqs(void); extern int arch_early_irq_init(void); /* * We want to know which function is an entrypoint of a hardirq or a softirq. */ #ifndef __irq_entry # define __irq_entry __section(".irqentry.text") #endif #define __softirq_entry __section(".softirqentry.text") #endif |
| 2 4754 4758 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 | // SPDX-License-Identifier: GPL-2.0 /* * bio-integrity.c - bio data integrity extensions * * Copyright (C) 2007, 2008, 2009 Oracle Corporation * Written by: Martin K. Petersen <martin.petersen@oracle.com> */ #include <linux/blk-integrity.h> #include <linux/mempool.h> #include <linux/export.h> #include <linux/bio.h> #include <linux/workqueue.h> #include <linux/slab.h> #include "blk.h" static struct kmem_cache *bip_slab; static struct workqueue_struct *kintegrityd_wq; void blk_flush_integrity(void) { flush_workqueue(kintegrityd_wq); } /** * bio_integrity_free - Free bio integrity payload * @bio: bio containing bip to be freed * * Description: Free the integrity portion of a bio. */ void bio_integrity_free(struct bio *bio) { struct bio_integrity_payload *bip = bio_integrity(bio); struct bio_set *bs = bio->bi_pool; if (bs && mempool_initialized(&bs->bio_integrity_pool)) { if (bip->bip_vec) bvec_free(&bs->bvec_integrity_pool, bip->bip_vec, bip->bip_max_vcnt); mempool_free(bip, &bs->bio_integrity_pool); } else { kfree(bip); } bio->bi_integrity = NULL; bio->bi_opf &= ~REQ_INTEGRITY; } /** * bio_integrity_alloc - Allocate integrity payload and attach it to bio * @bio: bio to attach integrity metadata to * @gfp_mask: Memory allocation mask * @nr_vecs: Number of integrity metadata scatter-gather elements * * Description: This function prepares a bio for attaching integrity * metadata. nr_vecs specifies the maximum number of pages containing * integrity metadata that can be attached. */ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, gfp_t gfp_mask, unsigned int nr_vecs) { struct bio_integrity_payload *bip; struct bio_set *bs = bio->bi_pool; unsigned inline_vecs; if (WARN_ON_ONCE(bio_has_crypt_ctx(bio))) return ERR_PTR(-EOPNOTSUPP); if (!bs || !mempool_initialized(&bs->bio_integrity_pool)) { bip = kmalloc(struct_size(bip, bip_inline_vecs, nr_vecs), gfp_mask); inline_vecs = nr_vecs; } else { bip = mempool_alloc(&bs->bio_integrity_pool, gfp_mask); inline_vecs = BIO_INLINE_VECS; } if (unlikely(!bip)) return ERR_PTR(-ENOMEM); memset(bip, 0, sizeof(*bip)); /* always report as many vecs as asked explicitly, not inline vecs */ bip->bip_max_vcnt = nr_vecs; if (nr_vecs > inline_vecs) { bip->bip_vec = bvec_alloc(&bs->bvec_integrity_pool, &bip->bip_max_vcnt, gfp_mask); if (!bip->bip_vec) goto err; } else if (nr_vecs) { bip->bip_vec = bip->bip_inline_vecs; } bip->bip_bio = bio; bio->bi_integrity = bip; bio->bi_opf |= REQ_INTEGRITY; return bip; err: if (bs && mempool_initialized(&bs->bio_integrity_pool)) mempool_free(bip, &bs->bio_integrity_pool); else kfree(bip); return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL(bio_integrity_alloc); static void bio_integrity_unpin_bvec(struct bio_vec *bv, int nr_vecs, bool dirty) { int i; for (i = 0; i < nr_vecs; i++) { if (dirty && !PageCompound(bv[i].bv_page)) set_page_dirty_lock(bv[i].bv_page); unpin_user_page(bv[i].bv_page); } } static void bio_integrity_uncopy_user(struct bio_integrity_payload *bip) { unsigned short nr_vecs = bip->bip_max_vcnt - 1; struct bio_vec *copy = &bip->bip_vec[1]; size_t bytes = bip->bip_iter.bi_size; struct iov_iter iter; int ret; iov_iter_bvec(&iter, ITER_DEST, copy, nr_vecs, bytes); ret = copy_to_iter(bvec_virt(bip->bip_vec), bytes, &iter); WARN_ON_ONCE(ret != bytes); bio_integrity_unpin_bvec(copy, nr_vecs, true); } /** * bio_integrity_unmap_user - Unmap user integrity payload * @bio: bio containing bip to be unmapped * * Unmap the user mapped integrity portion of a bio. */ void bio_integrity_unmap_user(struct bio *bio) { struct bio_integrity_payload *bip = bio_integrity(bio); if (bip->bip_flags & BIP_COPY_USER) { if (bio_data_dir(bio) == READ) bio_integrity_uncopy_user(bip); kfree(bvec_virt(bip->bip_vec)); return; } bio_integrity_unpin_bvec(bip->bip_vec, bip->bip_max_vcnt, bio_data_dir(bio) == READ); } /** * bio_integrity_add_page - Attach integrity metadata * @bio: bio to update * @page: page containing integrity metadata * @len: number of bytes of integrity metadata in page * @offset: start offset within page * * Description: Attach a page containing integrity metadata to bio. */ int bio_integrity_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int offset) { struct request_queue *q = bdev_get_queue(bio->bi_bdev); struct bio_integrity_payload *bip = bio_integrity(bio); if (((bip->bip_iter.bi_size + len) >> SECTOR_SHIFT) > queue_max_hw_sectors(q)) return 0; if (bip->bip_vcnt > 0) { struct bio_vec *bv = &bip->bip_vec[bip->bip_vcnt - 1]; bool same_page = false; if (bvec_try_merge_hw_page(q, bv, page, len, offset, &same_page)) { bip->bip_iter.bi_size += len; return len; } if (bip->bip_vcnt >= min(bip->bip_max_vcnt, queue_max_integrity_segments(q))) return 0; /* * If the queue doesn't support SG gaps and adding this segment * would create a gap, disallow it. */ if (bvec_gap_to_prev(&q->limits, bv, offset)) return 0; } bvec_set_page(&bip->bip_vec[bip->bip_vcnt], page, len, offset); bip->bip_vcnt++; bip->bip_iter.bi_size += len; return len; } EXPORT_SYMBOL(bio_integrity_add_page); static int bio_integrity_copy_user(struct bio *bio, struct bio_vec *bvec, int nr_vecs, unsigned int len, unsigned int direction, u32 seed) { bool write = direction == ITER_SOURCE; struct bio_integrity_payload *bip; struct iov_iter iter; void *buf; int ret; buf = kmalloc(len, GFP_KERNEL); if (!buf) return -ENOMEM; if (write) { iov_iter_bvec(&iter, direction, bvec, nr_vecs, len); if (!copy_from_iter_full(buf, len, &iter)) { ret = -EFAULT; goto free_buf; } bip = bio_integrity_alloc(bio, GFP_KERNEL, 1); } else { memset(buf, 0, len); /* * We need to preserve the original bvec and the number of vecs * in it for completion handling */ bip = bio_integrity_alloc(bio, GFP_KERNEL, nr_vecs + 1); } if (IS_ERR(bip)) { ret = PTR_ERR(bip); goto free_buf; } if (write) bio_integrity_unpin_bvec(bvec, nr_vecs, false); else memcpy(&bip->bip_vec[1], bvec, nr_vecs * sizeof(*bvec)); ret = bio_integrity_add_page(bio, virt_to_page(buf), len, offset_in_page(buf)); if (ret != len) { ret = -ENOMEM; goto free_bip; } bip->bip_flags |= BIP_COPY_USER; bip->bip_iter.bi_sector = seed; bip->bip_vcnt = nr_vecs; return 0; free_bip: bio_integrity_free(bio); free_buf: kfree(buf); return ret; } static int bio_integrity_init_user(struct bio *bio, struct bio_vec *bvec, int nr_vecs, unsigned int len, u32 seed) { struct bio_integrity_payload *bip; bip = bio_integrity_alloc(bio, GFP_KERNEL, nr_vecs); if (IS_ERR(bip)) return PTR_ERR(bip); memcpy(bip->bip_vec, bvec, nr_vecs * sizeof(*bvec)); bip->bip_iter.bi_sector = seed; bip->bip_iter.bi_size = len; bip->bip_vcnt = nr_vecs; return 0; } static unsigned int bvec_from_pages(struct bio_vec *bvec, struct page **pages, int nr_vecs, ssize_t bytes, ssize_t offset) { unsigned int nr_bvecs = 0; int i, j; for (i = 0; i < nr_vecs; i = j) { size_t size = min_t(size_t, bytes, PAGE_SIZE - offset); struct folio *folio = page_folio(pages[i]); bytes -= size; for (j = i + 1; j < nr_vecs; j++) { size_t next = min_t(size_t, PAGE_SIZE, bytes); if (page_folio(pages[j]) != folio || pages[j] != pages[j - 1] + 1) break; unpin_user_page(pages[j]); size += next; bytes -= next; } bvec_set_page(&bvec[nr_bvecs], pages[i], size, offset); offset = 0; nr_bvecs++; } return nr_bvecs; } int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t bytes, u32 seed) { struct request_queue *q = bdev_get_queue(bio->bi_bdev); unsigned int align = blk_lim_dma_alignment_and_pad(&q->limits); struct page *stack_pages[UIO_FASTIOV], **pages = stack_pages; struct bio_vec stack_vec[UIO_FASTIOV], *bvec = stack_vec; unsigned int direction, nr_bvecs; struct iov_iter iter; int ret, nr_vecs; size_t offset; bool copy; if (bio_integrity(bio)) return -EINVAL; if (bytes >> SECTOR_SHIFT > queue_max_hw_sectors(q)) return -E2BIG; if (bio_data_dir(bio) == READ) direction = ITER_DEST; else direction = ITER_SOURCE; iov_iter_ubuf(&iter, direction, ubuf, bytes); nr_vecs = iov_iter_npages(&iter, BIO_MAX_VECS + 1); if (nr_vecs > BIO_MAX_VECS) return -E2BIG; if (nr_vecs > UIO_FASTIOV) { bvec = kcalloc(nr_vecs, sizeof(*bvec), GFP_KERNEL); if (!bvec) return -ENOMEM; pages = NULL; } copy = !iov_iter_is_aligned(&iter, align, align); ret = iov_iter_extract_pages(&iter, &pages, bytes, nr_vecs, 0, &offset); if (unlikely(ret < 0)) goto free_bvec; nr_bvecs = bvec_from_pages(bvec, pages, nr_vecs, bytes, offset); if (pages != stack_pages) kvfree(pages); if (nr_bvecs > queue_max_integrity_segments(q)) copy = true; if (copy) ret = bio_integrity_copy_user(bio, bvec, nr_bvecs, bytes, direction, seed); else ret = bio_integrity_init_user(bio, bvec, nr_bvecs, bytes, seed); if (ret) goto release_pages; if (bvec != stack_vec) kfree(bvec); return 0; release_pages: bio_integrity_unpin_bvec(bvec, nr_bvecs, false); free_bvec: if (bvec != stack_vec) kfree(bvec); return ret; } EXPORT_SYMBOL_GPL(bio_integrity_map_user); /** * bio_integrity_prep - Prepare bio for integrity I/O * @bio: bio to prepare * * Description: Checks if the bio already has an integrity payload attached. * If it does, the payload has been generated by another kernel subsystem, * and we just pass it through. Otherwise allocates integrity payload. * The bio must have data direction, target device and start sector set priot * to calling. In the WRITE case, integrity metadata will be generated using * the block device's integrity function. In the READ case, the buffer * will be prepared for DMA and a suitable end_io handler set up. */ bool bio_integrity_prep(struct bio *bio) { struct bio_integrity_payload *bip; struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk); unsigned int len; void *buf; gfp_t gfp = GFP_NOIO; if (!bi) return true; if (!bio_sectors(bio)) return true; /* Already protected? */ if (bio_integrity(bio)) return true; switch (bio_op(bio)) { case REQ_OP_READ: if (bi->flags & BLK_INTEGRITY_NOVERIFY) return true; break; case REQ_OP_WRITE: if (bi->flags & BLK_INTEGRITY_NOGENERATE) return true; /* * Zero the memory allocated to not leak uninitialized kernel * memory to disk for non-integrity metadata where nothing else * initializes the memory. */ if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE) gfp |= __GFP_ZERO; break; default: return true; } /* Allocate kernel buffer for protection data */ len = bio_integrity_bytes(bi, bio_sectors(bio)); buf = kmalloc(len, gfp); if (unlikely(buf == NULL)) { goto err_end_io; } bip = bio_integrity_alloc(bio, GFP_NOIO, 1); if (IS_ERR(bip)) { kfree(buf); goto err_end_io; } bip->bip_flags |= BIP_BLOCK_INTEGRITY; bip_set_seed(bip, bio->bi_iter.bi_sector); if (bi->csum_type == BLK_INTEGRITY_CSUM_IP) bip->bip_flags |= BIP_IP_CHECKSUM; if (bio_integrity_add_page(bio, virt_to_page(buf), len, offset_in_page(buf)) < len) { printk(KERN_ERR "could not attach integrity payload\n"); goto err_end_io; } /* Auto-generate integrity metadata if this is a write */ if (bio_data_dir(bio) == WRITE) blk_integrity_generate(bio); else bip->bio_iter = bio->bi_iter; return true; err_end_io: bio->bi_status = BLK_STS_RESOURCE; bio_endio(bio); return false; } EXPORT_SYMBOL(bio_integrity_prep); /** * bio_integrity_verify_fn - Integrity I/O completion worker * @work: Work struct stored in bio to be verified * * Description: This workqueue function is called to complete a READ * request. The function verifies the transferred integrity metadata * and then calls the original bio end_io function. */ static void bio_integrity_verify_fn(struct work_struct *work) { struct bio_integrity_payload *bip = container_of(work, struct bio_integrity_payload, bip_work); struct bio *bio = bip->bip_bio; blk_integrity_verify(bio); kfree(bvec_virt(bip->bip_vec)); bio_integrity_free(bio); bio_endio(bio); } /** * __bio_integrity_endio - Integrity I/O completion function * @bio: Protected bio * * Description: Completion for integrity I/O * * Normally I/O completion is done in interrupt context. However, * verifying I/O integrity is a time-consuming task which must be run * in process context. This function postpones completion * accordingly. */ bool __bio_integrity_endio(struct bio *bio) { struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk); struct bio_integrity_payload *bip = bio_integrity(bio); if (bio_op(bio) == REQ_OP_READ && !bio->bi_status && bi->csum_type) { INIT_WORK(&bip->bip_work, bio_integrity_verify_fn); queue_work(kintegrityd_wq, &bip->bip_work); return false; } kfree(bvec_virt(bip->bip_vec)); bio_integrity_free(bio); return true; } /** * bio_integrity_advance - Advance integrity vector * @bio: bio whose integrity vector to update * @bytes_done: number of data bytes that have been completed * * Description: This function calculates how many integrity bytes the * number of completed data bytes correspond to and advances the * integrity vector accordingly. */ void bio_integrity_advance(struct bio *bio, unsigned int bytes_done) { struct bio_integrity_payload *bip = bio_integrity(bio); struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk); unsigned bytes = bio_integrity_bytes(bi, bytes_done >> 9); bip->bip_iter.bi_sector += bio_integrity_intervals(bi, bytes_done >> 9); bvec_iter_advance(bip->bip_vec, &bip->bip_iter, bytes); } /** * bio_integrity_trim - Trim integrity vector * @bio: bio whose integrity vector to update * * Description: Used to trim the integrity vector in a cloned bio. */ void bio_integrity_trim(struct bio *bio) { struct bio_integrity_payload *bip = bio_integrity(bio); struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk); bip->bip_iter.bi_size = bio_integrity_bytes(bi, bio_sectors(bio)); } EXPORT_SYMBOL(bio_integrity_trim); /** * bio_integrity_clone - Callback for cloning bios with integrity metadata * @bio: New bio * @bio_src: Original bio * @gfp_mask: Memory allocation mask * * Description: Called to allocate a bip when cloning a bio */ int bio_integrity_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp_mask) { struct bio_integrity_payload *bip_src = bio_integrity(bio_src); struct bio_integrity_payload *bip; BUG_ON(bip_src == NULL); bip = bio_integrity_alloc(bio, gfp_mask, 0); if (IS_ERR(bip)) return PTR_ERR(bip); bip->bip_vec = bip_src->bip_vec; bip->bip_iter = bip_src->bip_iter; bip->bip_flags = bip_src->bip_flags & ~BIP_BLOCK_INTEGRITY; return 0; } int bioset_integrity_create(struct bio_set *bs, int pool_size) { if (mempool_initialized(&bs->bio_integrity_pool)) return 0; if (mempool_init_slab_pool(&bs->bio_integrity_pool, pool_size, bip_slab)) return -1; if (biovec_init_pool(&bs->bvec_integrity_pool, pool_size)) { mempool_exit(&bs->bio_integrity_pool); return -1; } return 0; } EXPORT_SYMBOL(bioset_integrity_create); void bioset_integrity_free(struct bio_set *bs) { mempool_exit(&bs->bio_integrity_pool); mempool_exit(&bs->bvec_integrity_pool); } void __init bio_integrity_init(void) { /* * kintegrityd won't block much but may burn a lot of CPU cycles. * Make it highpri CPU intensive wq with max concurrency of 1. */ kintegrityd_wq = alloc_workqueue("kintegrityd", WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_CPU_INTENSIVE, 1); if (!kintegrityd_wq) panic("Failed to create kintegrityd\n"); bip_slab = kmem_cache_create("bio_integrity_payload", sizeof(struct bio_integrity_payload) + sizeof(struct bio_vec) * BIO_INLINE_VECS, 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2023 Isovalent */ #ifndef __NET_TCX_H #define __NET_TCX_H #include <linux/bpf.h> #include <linux/bpf_mprog.h> #include <net/sch_generic.h> struct mini_Qdisc; struct tcx_entry { struct mini_Qdisc __rcu *miniq; struct bpf_mprog_bundle bundle; u32 miniq_active; struct rcu_head rcu; }; struct tcx_link { struct bpf_link link; struct net_device *dev; u32 location; }; static inline void tcx_set_ingress(struct sk_buff *skb, bool ingress) { #ifdef CONFIG_NET_XGRESS skb->tc_at_ingress = ingress; #endif } #ifdef CONFIG_NET_XGRESS static inline struct tcx_entry *tcx_entry(struct bpf_mprog_entry *entry) { struct bpf_mprog_bundle *bundle = entry->parent; return container_of(bundle, struct tcx_entry, bundle); } static inline struct tcx_link *tcx_link(const struct bpf_link *link) { return container_of(link, struct tcx_link, link); } void tcx_inc(void); void tcx_dec(void); static inline void tcx_entry_sync(void) { /* bpf_mprog_entry got a/b swapped, therefore ensure that * there are no inflight users on the old one anymore. */ synchronize_rcu(); } static inline void tcx_entry_update(struct net_device *dev, struct bpf_mprog_entry *entry, bool ingress) { ASSERT_RTNL(); if (ingress) rcu_assign_pointer(dev->tcx_ingress, entry); else rcu_assign_pointer(dev->tcx_egress, entry); } static inline struct bpf_mprog_entry * tcx_entry_fetch(struct net_device *dev, bool ingress) { ASSERT_RTNL(); if (ingress) return rcu_dereference_rtnl(dev->tcx_ingress); else return rcu_dereference_rtnl(dev->tcx_egress); } static inline struct bpf_mprog_entry *tcx_entry_create_noprof(void) { struct tcx_entry *tcx = kzalloc_noprof(sizeof(*tcx), GFP_KERNEL); if (tcx) { bpf_mprog_bundle_init(&tcx->bundle); return &tcx->bundle.a; } return NULL; } #define tcx_entry_create(...) alloc_hooks(tcx_entry_create_noprof(__VA_ARGS__)) static inline void tcx_entry_free(struct bpf_mprog_entry *entry) { kfree_rcu(tcx_entry(entry), rcu); } static inline struct bpf_mprog_entry * tcx_entry_fetch_or_create(struct net_device *dev, bool ingress, bool *created) { struct bpf_mprog_entry *entry = tcx_entry_fetch(dev, ingress); *created = false; if (!entry) { entry = tcx_entry_create(); if (!entry) return NULL; *created = true; } return entry; } static inline void tcx_skeys_inc(bool ingress) { tcx_inc(); if (ingress) net_inc_ingress_queue(); else net_inc_egress_queue(); } static inline void tcx_skeys_dec(bool ingress) { if (ingress) net_dec_ingress_queue(); else net_dec_egress_queue(); tcx_dec(); } static inline void tcx_miniq_inc(struct bpf_mprog_entry *entry) { ASSERT_RTNL(); tcx_entry(entry)->miniq_active++; } static inline void tcx_miniq_dec(struct bpf_mprog_entry *entry) { ASSERT_RTNL(); tcx_entry(entry)->miniq_active--; } static inline bool tcx_entry_is_active(struct bpf_mprog_entry *entry) { ASSERT_RTNL(); return bpf_mprog_total(entry) || tcx_entry(entry)->miniq_active; } static inline enum tcx_action_base tcx_action_code(struct sk_buff *skb, int code) { switch (code) { case TCX_PASS: skb->tc_index = qdisc_skb_cb(skb)->tc_classid; fallthrough; case TCX_DROP: case TCX_REDIRECT: return code; case TCX_NEXT: default: return TCX_NEXT; } } #endif /* CONFIG_NET_XGRESS */ #if defined(CONFIG_NET_XGRESS) && defined(CONFIG_BPF_SYSCALL) int tcx_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); int tcx_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int tcx_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog); void tcx_uninstall(struct net_device *dev, bool ingress); int tcx_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); static inline void dev_tcx_uninstall(struct net_device *dev) { ASSERT_RTNL(); tcx_uninstall(dev, true); tcx_uninstall(dev, false); } #else static inline int tcx_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EINVAL; } static inline int tcx_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EINVAL; } static inline int tcx_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EINVAL; } static inline int tcx_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { return -EINVAL; } static inline void dev_tcx_uninstall(struct net_device *dev) { } #endif /* CONFIG_NET_XGRESS && CONFIG_BPF_SYSCALL */ #endif /* __NET_TCX_H */ |
| 9 207 9 190 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef LINUX_EXPORTFS_H #define LINUX_EXPORTFS_H 1 #include <linux/types.h> struct dentry; struct iattr; struct inode; struct iomap; struct super_block; struct vfsmount; /* limit the handle size to NFSv4 handle size now */ #define MAX_HANDLE_SZ 128 /* * The fileid_type identifies how the file within the filesystem is encoded. * In theory this is freely set and parsed by the filesystem, but we try to * stick to conventions so we can share some generic code and don't confuse * sniffers like ethereal/wireshark. * * The filesystem must not use the value '0' or '0xff'. */ enum fid_type { /* * The root, or export point, of the filesystem. * (Never actually passed down to the filesystem. */ FILEID_ROOT = 0, /* * 32bit inode number, 32 bit generation number. */ FILEID_INO32_GEN = 1, /* * 32bit inode number, 32 bit generation number, * 32 bit parent directory inode number. */ FILEID_INO32_GEN_PARENT = 2, /* * 64 bit object ID, 64 bit root object ID, * 32 bit generation number. */ FILEID_BTRFS_WITHOUT_PARENT = 0x4d, /* * 64 bit object ID, 64 bit root object ID, * 32 bit generation number, * 64 bit parent object ID, 32 bit parent generation. */ FILEID_BTRFS_WITH_PARENT = 0x4e, /* * 64 bit object ID, 64 bit root object ID, * 32 bit generation number, * 64 bit parent object ID, 32 bit parent generation, * 64 bit parent root object ID. */ FILEID_BTRFS_WITH_PARENT_ROOT = 0x4f, /* * 32 bit block number, 16 bit partition reference, * 16 bit unused, 32 bit generation number. */ FILEID_UDF_WITHOUT_PARENT = 0x51, /* * 32 bit block number, 16 bit partition reference, * 16 bit unused, 32 bit generation number, * 32 bit parent block number, 32 bit parent generation number */ FILEID_UDF_WITH_PARENT = 0x52, /* * 64 bit checkpoint number, 64 bit inode number, * 32 bit generation number. */ FILEID_NILFS_WITHOUT_PARENT = 0x61, /* * 64 bit checkpoint number, 64 bit inode number, * 32 bit generation number, 32 bit parent generation. * 64 bit parent inode number. */ FILEID_NILFS_WITH_PARENT = 0x62, /* * 32 bit generation number, 40 bit i_pos. */ FILEID_FAT_WITHOUT_PARENT = 0x71, /* * 32 bit generation number, 40 bit i_pos, * 32 bit parent generation number, 40 bit parent i_pos */ FILEID_FAT_WITH_PARENT = 0x72, /* * 64 bit inode number, 32 bit generation number. */ FILEID_INO64_GEN = 0x81, /* * 64 bit inode number, 32 bit generation number, * 64 bit parent inode number, 32 bit parent generation. */ FILEID_INO64_GEN_PARENT = 0x82, /* * 128 bit child FID (struct lu_fid) * 128 bit parent FID (struct lu_fid) */ FILEID_LUSTRE = 0x97, /* * 64 bit inode number, 32 bit subvolume, 32 bit generation number: */ FILEID_BCACHEFS_WITHOUT_PARENT = 0xb1, FILEID_BCACHEFS_WITH_PARENT = 0xb2, /* * 64 bit unique kernfs id */ FILEID_KERNFS = 0xfe, /* * Filesystems must not use 0xff file ID. */ FILEID_INVALID = 0xff, }; struct fid { union { struct { u32 ino; u32 gen; u32 parent_ino; u32 parent_gen; } i32; struct { u64 ino; u32 gen; } __packed i64; struct { u32 block; u16 partref; u16 parent_partref; u32 generation; u32 parent_block; u32 parent_generation; } udf; DECLARE_FLEX_ARRAY(__u32, raw); }; }; #define EXPORT_FH_CONNECTABLE 0x1 /* Encode file handle with parent */ #define EXPORT_FH_FID 0x2 /* File handle may be non-decodeable */ #define EXPORT_FH_DIR_ONLY 0x4 /* Only decode file handle for a directory */ /** * struct export_operations - for nfsd to communicate with file systems * @encode_fh: encode a file handle fragment from a dentry * @fh_to_dentry: find the implied object and get a dentry for it * @fh_to_parent: find the implied object's parent and get a dentry for it * @get_name: find the name for a given inode in a given directory * @get_parent: find the parent of a given directory * @commit_metadata: commit metadata changes to stable storage * * See Documentation/filesystems/nfs/exporting.rst for details on how to use * this interface correctly. * * encode_fh: * @encode_fh should store in the file handle fragment @fh (using at most * @max_len bytes) information that can be used by @decode_fh to recover the * file referred to by the &struct dentry @de. If @flag has CONNECTABLE bit * set, the encode_fh() should store sufficient information so that a good * attempt can be made to find not only the file but also it's place in the * filesystem. This typically means storing a reference to de->d_parent in * the filehandle fragment. encode_fh() should return the fileid_type on * success and on error returns 255 (if the space needed to encode fh is * greater than @max_len*4 bytes). On error @max_len contains the minimum * size(in 4 byte unit) needed to encode the file handle. * * fh_to_dentry: * @fh_to_dentry is given a &struct super_block (@sb) and a file handle * fragment (@fh, @fh_len). It should return a &struct dentry which refers * to the same file that the file handle fragment refers to. If it cannot, * it should return a %NULL pointer if the file cannot be found, or an * %ERR_PTR error code of %ENOMEM if a memory allocation failure occurred. * Any other error code is treated like %NULL, and will cause an %ESTALE error * for callers of exportfs_decode_fh(). * Any suitable dentry can be returned including, if necessary, a new dentry * created with d_alloc_root. The caller can then find any other extant * dentries by following the d_alias links. * * fh_to_parent: * Same as @fh_to_dentry, except that it returns a pointer to the parent * dentry if it was encoded into the filehandle fragment by @encode_fh. * * get_name: * @get_name should find a name for the given @child in the given @parent * directory. The name should be stored in the @name (with the * understanding that it is already pointing to a %NAME_MAX+1 sized * buffer. get_name() should return %0 on success, a negative error code * or error. @get_name will be called without @parent->i_mutex held. * * get_parent: * @get_parent should find the parent directory for the given @child which * is also a directory. In the event that it cannot be found, or storage * space cannot be allocated, a %ERR_PTR should be returned. * * commit_metadata: * @commit_metadata should commit metadata changes to stable storage. * * Locking rules: * get_parent is called with child->d_inode->i_mutex down * get_name is not (which is possibly inconsistent) */ struct export_operations { int (*encode_fh)(struct inode *inode, __u32 *fh, int *max_len, struct inode *parent); struct dentry * (*fh_to_dentry)(struct super_block *sb, struct fid *fid, int fh_len, int fh_type); struct dentry * (*fh_to_parent)(struct super_block *sb, struct fid *fid, int fh_len, int fh_type); int (*get_name)(struct dentry *parent, char *name, struct dentry *child); struct dentry * (*get_parent)(struct dentry *child); int (*commit_metadata)(struct inode *inode); int (*get_uuid)(struct super_block *sb, u8 *buf, u32 *len, u64 *offset); int (*map_blocks)(struct inode *inode, loff_t offset, u64 len, struct iomap *iomap, bool write, u32 *device_generation); int (*commit_blocks)(struct inode *inode, struct iomap *iomaps, int nr_iomaps, struct iattr *iattr); #define EXPORT_OP_NOWCC (0x1) /* don't collect v3 wcc data */ #define EXPORT_OP_NOSUBTREECHK (0x2) /* no subtree checking */ #define EXPORT_OP_CLOSE_BEFORE_UNLINK (0x4) /* close files before unlink */ #define EXPORT_OP_REMOTE_FS (0x8) /* Filesystem is remote */ #define EXPORT_OP_NOATOMIC_ATTR (0x10) /* Filesystem cannot supply atomic attribute updates */ #define EXPORT_OP_FLUSH_ON_CLOSE (0x20) /* fs flushes file data on close */ #define EXPORT_OP_ASYNC_LOCK (0x40) /* fs can do async lock request */ unsigned long flags; }; /** * exportfs_lock_op_is_async() - export op supports async lock operation * @export_ops: the nfs export operations to check * * Returns true if the nfs export_operations structure has * EXPORT_OP_ASYNC_LOCK in their flags set */ static inline bool exportfs_lock_op_is_async(const struct export_operations *export_ops) { return export_ops->flags & EXPORT_OP_ASYNC_LOCK; } extern int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid, int *max_len, struct inode *parent, int flags); extern int exportfs_encode_fh(struct dentry *dentry, struct fid *fid, int *max_len, int flags); static inline bool exportfs_can_encode_fid(const struct export_operations *nop) { return !nop || nop->encode_fh; } static inline bool exportfs_can_decode_fh(const struct export_operations *nop) { return nop && nop->fh_to_dentry; } static inline bool exportfs_can_encode_fh(const struct export_operations *nop, int fh_flags) { /* * If a non-decodeable file handle was requested, we only need to make * sure that filesystem did not opt-out of encoding fid. */ if (fh_flags & EXPORT_FH_FID) return exportfs_can_encode_fid(nop); /* * If a decodeable file handle was requested, we need to make sure that * filesystem can also decode file handles. */ return exportfs_can_decode_fh(nop); } static inline int exportfs_encode_fid(struct inode *inode, struct fid *fid, int *max_len) { return exportfs_encode_inode_fh(inode, fid, max_len, NULL, EXPORT_FH_FID); } extern struct dentry *exportfs_decode_fh_raw(struct vfsmount *mnt, struct fid *fid, int fh_len, int fileid_type, unsigned int flags, int (*acceptable)(void *, struct dentry *), void *context); extern struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid, int fh_len, int fileid_type, int (*acceptable)(void *, struct dentry *), void *context); /* * Generic helpers for filesystems. */ int generic_encode_ino32_fh(struct inode *inode, __u32 *fh, int *max_len, struct inode *parent); struct dentry *generic_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type, struct inode *(*get_inode) (struct super_block *sb, u64 ino, u32 gen)); struct dentry *generic_fh_to_parent(struct super_block *sb, struct fid *fid, int fh_len, int fh_type, struct inode *(*get_inode) (struct super_block *sb, u64 ino, u32 gen)); #endif /* LINUX_EXPORTFS_H */ |
| 244 244 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * crc16.c */ #include <linux/types.h> #include <linux/module.h> #include <linux/crc16.h> /** CRC table for the CRC-16. The poly is 0x8005 (x^16 + x^15 + x^2 + 1) */ u16 const crc16_table[256] = { 0x0000, 0xC0C1, 0xC181, 0x0140, 0xC301, 0x03C0, 0x0280, 0xC241, 0xC601, 0x06C0, 0x0780, 0xC741, 0x0500, 0xC5C1, 0xC481, 0x0440, 0xCC01, 0x0CC0, 0x0D80, 0xCD41, 0x0F00, 0xCFC1, 0xCE81, 0x0E40, 0x0A00, 0xCAC1, 0xCB81, 0x0B40, 0xC901, 0x09C0, 0x0880, 0xC841, 0xD801, 0x18C0, 0x1980, 0xD941, 0x1B00, 0xDBC1, 0xDA81, 0x1A40, 0x1E00, 0xDEC1, 0xDF81, 0x1F40, 0xDD01, 0x1DC0, 0x1C80, 0xDC41, 0x1400, 0xD4C1, 0xD581, 0x1540, 0xD701, 0x17C0, 0x1680, 0xD641, 0xD201, 0x12C0, 0x1380, 0xD341, 0x1100, 0xD1C1, 0xD081, 0x1040, 0xF001, 0x30C0, 0x3180, 0xF141, 0x3300, 0xF3C1, 0xF281, 0x3240, 0x3600, 0xF6C1, 0xF781, 0x3740, 0xF501, 0x35C0, 0x3480, 0xF441, 0x3C00, 0xFCC1, 0xFD81, 0x3D40, 0xFF01, 0x3FC0, 0x3E80, 0xFE41, 0xFA01, 0x3AC0, 0x3B80, 0xFB41, 0x3900, 0xF9C1, 0xF881, 0x3840, 0x2800, 0xE8C1, 0xE981, 0x2940, 0xEB01, 0x2BC0, 0x2A80, 0xEA41, 0xEE01, 0x2EC0, 0x2F80, 0xEF41, 0x2D00, 0xEDC1, 0xEC81, 0x2C40, 0xE401, 0x24C0, 0x2580, 0xE541, 0x2700, 0xE7C1, 0xE681, 0x2640, 0x2200, 0xE2C1, 0xE381, 0x2340, 0xE101, 0x21C0, 0x2080, 0xE041, 0xA001, 0x60C0, 0x6180, 0xA141, 0x6300, 0xA3C1, 0xA281, 0x6240, 0x6600, 0xA6C1, 0xA781, 0x6740, 0xA501, 0x65C0, 0x6480, 0xA441, 0x6C00, 0xACC1, 0xAD81, 0x6D40, 0xAF01, 0x6FC0, 0x6E80, 0xAE41, 0xAA01, 0x6AC0, 0x6B80, 0xAB41, 0x6900, 0xA9C1, 0xA881, 0x6840, 0x7800, 0xB8C1, 0xB981, 0x7940, 0xBB01, 0x7BC0, 0x7A80, 0xBA41, 0xBE01, 0x7EC0, 0x7F80, 0xBF41, 0x7D00, 0xBDC1, 0xBC81, 0x7C40, 0xB401, 0x74C0, 0x7580, 0xB541, 0x7700, 0xB7C1, 0xB681, 0x7640, 0x7200, 0xB2C1, 0xB381, 0x7340, 0xB101, 0x71C0, 0x7080, 0xB041, 0x5000, 0x90C1, 0x9181, 0x5140, 0x9301, 0x53C0, 0x5280, 0x9241, 0x9601, 0x56C0, 0x5780, 0x9741, 0x5500, 0x95C1, 0x9481, 0x5440, 0x9C01, 0x5CC0, 0x5D80, 0x9D41, 0x5F00, 0x9FC1, 0x9E81, 0x5E40, 0x5A00, 0x9AC1, 0x9B81, 0x5B40, 0x9901, 0x59C0, 0x5880, 0x9841, 0x8801, 0x48C0, 0x4980, 0x8941, 0x4B00, 0x8BC1, 0x8A81, 0x4A40, 0x4E00, 0x8EC1, 0x8F81, 0x4F40, 0x8D01, 0x4DC0, 0x4C80, 0x8C41, 0x4400, 0x84C1, 0x8581, 0x4540, 0x8701, 0x47C0, 0x4680, 0x8641, 0x8201, 0x42C0, 0x4380, 0x8341, 0x4100, 0x81C1, 0x8081, 0x4040 }; EXPORT_SYMBOL(crc16_table); /** * crc16 - compute the CRC-16 for the data buffer * @crc: previous CRC value * @buffer: data pointer * @len: number of bytes in the buffer * * Returns the updated CRC value. */ u16 crc16(u16 crc, u8 const *buffer, size_t len) { while (len--) crc = crc16_byte(crc, *buffer++); return crc; } EXPORT_SYMBOL(crc16); MODULE_DESCRIPTION("CRC16 calculations"); MODULE_LICENSE("GPL"); |
| 91 1 1 1 89 1 67 19 78 2 4 5 87 23 23 23 11 23 10 3 8 211 40 196 5 17 16 17 53 15 3 3 38 3 8 1 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/hfsplus/btree.c * * Copyright (C) 2001 * Brad Boyer (flar@allandria.com) * (C) 2003 Ardis Technologies <roman@ardistech.com> * * Handle opening/closing btree */ #include <linux/slab.h> #include <linux/pagemap.h> #include <linux/log2.h> #include "hfsplus_fs.h" #include "hfsplus_raw.h" /* * Initial source code of clump size calculation is gotten * from http://opensource.apple.com/tarballs/diskdev_cmds/ */ #define CLUMP_ENTRIES 15 static short clumptbl[CLUMP_ENTRIES * 3] = { /* * Volume Attributes Catalog Extents * Size Clump (MB) Clump (MB) Clump (MB) */ /* 1GB */ 4, 4, 4, /* 2GB */ 6, 6, 4, /* 4GB */ 8, 8, 4, /* 8GB */ 11, 11, 5, /* * For volumes 16GB and larger, we want to make sure that a full OS * install won't require fragmentation of the Catalog or Attributes * B-trees. We do this by making the clump sizes sufficiently large, * and by leaving a gap after the B-trees for them to grow into. * * For SnowLeopard 10A298, a FullNetInstall with all packages selected * results in: * Catalog B-tree Header * nodeSize: 8192 * totalNodes: 31616 * freeNodes: 1978 * (used = 231.55 MB) * Attributes B-tree Header * nodeSize: 8192 * totalNodes: 63232 * freeNodes: 958 * (used = 486.52 MB) * * We also want Time Machine backup volumes to have a sufficiently * large clump size to reduce fragmentation. * * The series of numbers for Catalog and Attribute form a geometric * series. For Catalog (16GB to 512GB), each term is 8**(1/5) times * the previous term. For Attributes (16GB to 512GB), each term is * 4**(1/5) times the previous term. For 1TB to 16TB, each term is * 2**(1/5) times the previous term. */ /* 16GB */ 64, 32, 5, /* 32GB */ 84, 49, 6, /* 64GB */ 111, 74, 7, /* 128GB */ 147, 111, 8, /* 256GB */ 194, 169, 9, /* 512GB */ 256, 256, 11, /* 1TB */ 294, 294, 14, /* 2TB */ 338, 338, 16, /* 4TB */ 388, 388, 20, /* 8TB */ 446, 446, 25, /* 16TB */ 512, 512, 32 }; u32 hfsplus_calc_btree_clump_size(u32 block_size, u32 node_size, u64 sectors, int file_id) { u32 mod = max(node_size, block_size); u32 clump_size; int column; int i; /* Figure out which column of the above table to use for this file. */ switch (file_id) { case HFSPLUS_ATTR_CNID: column = 0; break; case HFSPLUS_CAT_CNID: column = 1; break; default: column = 2; break; } /* * The default clump size is 0.8% of the volume size. And * it must also be a multiple of the node and block size. */ if (sectors < 0x200000) { clump_size = sectors << 2; /* 0.8 % */ if (clump_size < (8 * node_size)) clump_size = 8 * node_size; } else { /* turn exponent into table index... */ for (i = 0, sectors = sectors >> 22; sectors && (i < CLUMP_ENTRIES - 1); ++i, sectors = sectors >> 1) { /* empty body */ } clump_size = clumptbl[column + (i) * 3] * 1024 * 1024; } /* * Round the clump size to a multiple of node and block size. * NOTE: This rounds down. */ clump_size /= mod; clump_size *= mod; /* * Rounding down could have rounded down to 0 if the block size was * greater than the clump size. If so, just use one block or node. */ if (clump_size == 0) clump_size = mod; return clump_size; } /* Get a reference to a B*Tree and do some initial checks */ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id) { struct hfs_btree *tree; struct hfs_btree_header_rec *head; struct address_space *mapping; struct inode *inode; struct page *page; unsigned int size; tree = kzalloc(sizeof(*tree), GFP_KERNEL); if (!tree) return NULL; mutex_init(&tree->tree_lock); spin_lock_init(&tree->hash_lock); tree->sb = sb; tree->cnid = id; inode = hfsplus_iget(sb, id); if (IS_ERR(inode)) goto free_tree; tree->inode = inode; if (!HFSPLUS_I(tree->inode)->first_blocks) { pr_err("invalid btree extent records (0 size)\n"); goto free_inode; } mapping = tree->inode->i_mapping; page = read_mapping_page(mapping, 0, NULL); if (IS_ERR(page)) goto free_inode; /* Load the header */ head = (struct hfs_btree_header_rec *)(kmap_local_page(page) + sizeof(struct hfs_bnode_desc)); tree->root = be32_to_cpu(head->root); tree->leaf_count = be32_to_cpu(head->leaf_count); tree->leaf_head = be32_to_cpu(head->leaf_head); tree->leaf_tail = be32_to_cpu(head->leaf_tail); tree->node_count = be32_to_cpu(head->node_count); tree->free_nodes = be32_to_cpu(head->free_nodes); tree->attributes = be32_to_cpu(head->attributes); tree->node_size = be16_to_cpu(head->node_size); tree->max_key_len = be16_to_cpu(head->max_key_len); tree->depth = be16_to_cpu(head->depth); /* Verify the tree and set the correct compare function */ switch (id) { case HFSPLUS_EXT_CNID: if (tree->max_key_len != HFSPLUS_EXT_KEYLEN - sizeof(u16)) { pr_err("invalid extent max_key_len %d\n", tree->max_key_len); goto fail_page; } if (tree->attributes & HFS_TREE_VARIDXKEYS) { pr_err("invalid extent btree flag\n"); goto fail_page; } tree->keycmp = hfsplus_ext_cmp_key; break; case HFSPLUS_CAT_CNID: if (tree->max_key_len != HFSPLUS_CAT_KEYLEN - sizeof(u16)) { pr_err("invalid catalog max_key_len %d\n", tree->max_key_len); goto fail_page; } if (!(tree->attributes & HFS_TREE_VARIDXKEYS)) { pr_err("invalid catalog btree flag\n"); goto fail_page; } if (test_bit(HFSPLUS_SB_HFSX, &HFSPLUS_SB(sb)->flags) && (head->key_type == HFSPLUS_KEY_BINARY)) tree->keycmp = hfsplus_cat_bin_cmp_key; else { tree->keycmp = hfsplus_cat_case_cmp_key; set_bit(HFSPLUS_SB_CASEFOLD, &HFSPLUS_SB(sb)->flags); } break; case HFSPLUS_ATTR_CNID: if (tree->max_key_len != HFSPLUS_ATTR_KEYLEN - sizeof(u16)) { pr_err("invalid attributes max_key_len %d\n", tree->max_key_len); goto fail_page; } tree->keycmp = hfsplus_attr_bin_cmp_key; break; default: pr_err("unknown B*Tree requested\n"); goto fail_page; } if (!(tree->attributes & HFS_TREE_BIGKEYS)) { pr_err("invalid btree flag\n"); goto fail_page; } size = tree->node_size; if (!is_power_of_2(size)) goto fail_page; if (!tree->node_count) goto fail_page; tree->node_size_shift = ffs(size) - 1; tree->pages_per_bnode = (tree->node_size + PAGE_SIZE - 1) >> PAGE_SHIFT; kunmap_local(head); put_page(page); return tree; fail_page: kunmap_local(head); put_page(page); free_inode: tree->inode->i_mapping->a_ops = &hfsplus_aops; iput(tree->inode); free_tree: kfree(tree); return NULL; } /* Release resources used by a btree */ void hfs_btree_close(struct hfs_btree *tree) { struct hfs_bnode *node; int i; if (!tree) return; for (i = 0; i < NODE_HASH_SIZE; i++) { while ((node = tree->node_hash[i])) { tree->node_hash[i] = node->next_hash; if (atomic_read(&node->refcnt)) pr_crit("node %d:%d " "still has %d user(s)!\n", node->tree->cnid, node->this, atomic_read(&node->refcnt)); hfs_bnode_free(node); tree->node_hash_cnt--; } } iput(tree->inode); kfree(tree); } int hfs_btree_write(struct hfs_btree *tree) { struct hfs_btree_header_rec *head; struct hfs_bnode *node; struct page *page; node = hfs_bnode_find(tree, 0); if (IS_ERR(node)) /* panic? */ return -EIO; /* Load the header */ page = node->page[0]; head = (struct hfs_btree_header_rec *)(kmap_local_page(page) + sizeof(struct hfs_bnode_desc)); head->root = cpu_to_be32(tree->root); head->leaf_count = cpu_to_be32(tree->leaf_count); head->leaf_head = cpu_to_be32(tree->leaf_head); head->leaf_tail = cpu_to_be32(tree->leaf_tail); head->node_count = cpu_to_be32(tree->node_count); head->free_nodes = cpu_to_be32(tree->free_nodes); head->attributes = cpu_to_be32(tree->attributes); head->depth = cpu_to_be16(tree->depth); kunmap_local(head); set_page_dirty(page); hfs_bnode_put(node); return 0; } static struct hfs_bnode *hfs_bmap_new_bmap(struct hfs_bnode *prev, u32 idx) { struct hfs_btree *tree = prev->tree; struct hfs_bnode *node; struct hfs_bnode_desc desc; __be32 cnid; node = hfs_bnode_create(tree, idx); if (IS_ERR(node)) return node; tree->free_nodes--; prev->next = idx; cnid = cpu_to_be32(idx); hfs_bnode_write(prev, &cnid, offsetof(struct hfs_bnode_desc, next), 4); node->type = HFS_NODE_MAP; node->num_recs = 1; hfs_bnode_clear(node, 0, tree->node_size); desc.next = 0; desc.prev = 0; desc.type = HFS_NODE_MAP; desc.height = 0; desc.num_recs = cpu_to_be16(1); desc.reserved = 0; hfs_bnode_write(node, &desc, 0, sizeof(desc)); hfs_bnode_write_u16(node, 14, 0x8000); hfs_bnode_write_u16(node, tree->node_size - 2, 14); hfs_bnode_write_u16(node, tree->node_size - 4, tree->node_size - 6); return node; } /* Make sure @tree has enough space for the @rsvd_nodes */ int hfs_bmap_reserve(struct hfs_btree *tree, int rsvd_nodes) { struct inode *inode = tree->inode; struct hfsplus_inode_info *hip = HFSPLUS_I(inode); u32 count; int res; if (rsvd_nodes <= 0) return 0; while (tree->free_nodes < rsvd_nodes) { res = hfsplus_file_extend(inode, hfs_bnode_need_zeroout(tree)); if (res) return res; hip->phys_size = inode->i_size = (loff_t)hip->alloc_blocks << HFSPLUS_SB(tree->sb)->alloc_blksz_shift; hip->fs_blocks = hip->alloc_blocks << HFSPLUS_SB(tree->sb)->fs_shift; inode_set_bytes(inode, inode->i_size); count = inode->i_size >> tree->node_size_shift; tree->free_nodes += count - tree->node_count; tree->node_count = count; } return 0; } struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree) { struct hfs_bnode *node, *next_node; struct page **pagep; u32 nidx, idx; unsigned off; u16 off16; u16 len; u8 *data, byte, m; int i, res; res = hfs_bmap_reserve(tree, 1); if (res) return ERR_PTR(res); nidx = 0; node = hfs_bnode_find(tree, nidx); if (IS_ERR(node)) return node; len = hfs_brec_lenoff(node, 2, &off16); off = off16; off += node->page_offset; pagep = node->page + (off >> PAGE_SHIFT); data = kmap_local_page(*pagep); off &= ~PAGE_MASK; idx = 0; for (;;) { while (len) { byte = data[off]; if (byte != 0xff) { for (m = 0x80, i = 0; i < 8; m >>= 1, i++) { if (!(byte & m)) { idx += i; data[off] |= m; set_page_dirty(*pagep); kunmap_local(data); tree->free_nodes--; mark_inode_dirty(tree->inode); hfs_bnode_put(node); return hfs_bnode_create(tree, idx); } } } if (++off >= PAGE_SIZE) { kunmap_local(data); data = kmap_local_page(*++pagep); off = 0; } idx += 8; len--; } kunmap_local(data); nidx = node->next; if (!nidx) { hfs_dbg(BNODE_MOD, "create new bmap node\n"); next_node = hfs_bmap_new_bmap(node, idx); } else next_node = hfs_bnode_find(tree, nidx); hfs_bnode_put(node); if (IS_ERR(next_node)) return next_node; node = next_node; len = hfs_brec_lenoff(node, 0, &off16); off = off16; off += node->page_offset; pagep = node->page + (off >> PAGE_SHIFT); data = kmap_local_page(*pagep); off &= ~PAGE_MASK; } } void hfs_bmap_free(struct hfs_bnode *node) { struct hfs_btree *tree; struct page *page; u16 off, len; u32 nidx; u8 *data, byte, m; hfs_dbg(BNODE_MOD, "btree_free_node: %u\n", node->this); BUG_ON(!node->this); tree = node->tree; nidx = node->this; node = hfs_bnode_find(tree, 0); if (IS_ERR(node)) return; len = hfs_brec_lenoff(node, 2, &off); while (nidx >= len * 8) { u32 i; nidx -= len * 8; i = node->next; if (!i) { /* panic */; pr_crit("unable to free bnode %u. " "bmap not found!\n", node->this); hfs_bnode_put(node); return; } hfs_bnode_put(node); node = hfs_bnode_find(tree, i); if (IS_ERR(node)) return; if (node->type != HFS_NODE_MAP) { /* panic */; pr_crit("invalid bmap found! " "(%u,%d)\n", node->this, node->type); hfs_bnode_put(node); return; } len = hfs_brec_lenoff(node, 0, &off); } off += node->page_offset + nidx / 8; page = node->page[off >> PAGE_SHIFT]; data = kmap_local_page(page); off &= ~PAGE_MASK; m = 1 << (~nidx & 7); byte = data[off]; if (!(byte & m)) { pr_crit("trying to free free bnode " "%u(%d)\n", node->this, node->type); kunmap_local(data); hfs_bnode_put(node); return; } data[off] = byte & ~m; set_page_dirty(page); kunmap_local(data); hfs_bnode_put(node); tree->free_nodes++; mark_inode_dirty(tree->inode); } |
| 1 4 1 3 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Sound core. This file is composed of two parts. sound_class * which is common to both OSS and ALSA and OSS sound core which * is used OSS or emulation of it. */ /* * First, the common part. */ #include <linux/module.h> #include <linux/device.h> #include <linux/err.h> #include <linux/kdev_t.h> #include <linux/major.h> #include <sound/core.h> #ifdef CONFIG_SOUND_OSS_CORE static int __init init_oss_soundcore(void); static void cleanup_oss_soundcore(void); #else static inline int init_oss_soundcore(void) { return 0; } static inline void cleanup_oss_soundcore(void) { } #endif MODULE_DESCRIPTION("Core sound module"); MODULE_AUTHOR("Alan Cox"); MODULE_LICENSE("GPL"); static char *sound_devnode(const struct device *dev, umode_t *mode) { if (MAJOR(dev->devt) == SOUND_MAJOR) return NULL; return kasprintf(GFP_KERNEL, "snd/%s", dev_name(dev)); } const struct class sound_class = { .name = "sound", .devnode = sound_devnode, }; EXPORT_SYMBOL(sound_class); static int __init init_soundcore(void) { int rc; rc = init_oss_soundcore(); if (rc) return rc; rc = class_register(&sound_class); if (rc) { cleanup_oss_soundcore(); return rc; } return 0; } static void __exit cleanup_soundcore(void) { cleanup_oss_soundcore(); class_unregister(&sound_class); } subsys_initcall(init_soundcore); module_exit(cleanup_soundcore); #ifdef CONFIG_SOUND_OSS_CORE /* * OSS sound core handling. Breaks out sound functions to submodules * * Author: Alan Cox <alan@lxorguk.ukuu.org.uk> * * Fixes: * * -------------------- * * Top level handler for the sound subsystem. Various devices can * plug into this. The fact they don't all go via OSS doesn't mean * they don't have to implement the OSS API. There is a lot of logic * to keeping much of the OSS weight out of the code in a compatibility * module, but it's up to the driver to rember to load it... * * The code provides a set of functions for registration of devices * by type. This is done rather than providing a single call so that * we can hide any future changes in the internals (eg when we go to * 32bit dev_t) from the modules and their interface. * * Secondly we need to allocate the dsp, dsp16 and audio devices as * one. Thus we misuse the chains a bit to simplify this. * * Thirdly to make it more fun and for 2.3.x and above we do all * of this using fine grained locking. * * FIXME: we have to resolve modules and fine grained load/unload * locking at some point in 2.3.x. */ #include <linux/init.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/sound.h> #include <linux/kmod.h> #define SOUND_STEP 16 struct sound_unit { int unit_minor; const struct file_operations *unit_fops; struct sound_unit *next; char name[32]; }; /* * By default, OSS sound_core claims full legacy minor range (0-255) * of SOUND_MAJOR to trap open attempts to any sound minor and * requests modules using custom sound-slot/service-* module aliases. * The only benefit of doing this is allowing use of custom module * aliases instead of the standard char-major-* ones. This behavior * prevents alternative OSS implementation and is scheduled to be * removed. * * CONFIG_SOUND_OSS_CORE_PRECLAIM and soundcore.preclaim_oss kernel * parameter are added to allow distros and developers to try and * switch to alternative implementations without needing to rebuild * the kernel in the meantime. If preclaim_oss is non-zero, the * kernel will behave the same as before. All SOUND_MAJOR minors are * preclaimed and the custom module aliases along with standard chrdev * ones are emitted if a missing device is opened. If preclaim_oss is * zero, sound_core only grabs what's actually in use and for missing * devices only the standard chrdev aliases are requested. * * All these clutters are scheduled to be removed along with * sound-slot/service-* module aliases. */ static int preclaim_oss = IS_ENABLED(CONFIG_SOUND_OSS_CORE_PRECLAIM); module_param(preclaim_oss, int, 0444); static int soundcore_open(struct inode *, struct file *); static const struct file_operations soundcore_fops = { /* We must have an owner or the module locking fails */ .owner = THIS_MODULE, .open = soundcore_open, .llseek = noop_llseek, }; /* * Low level list operator. Scan the ordered list, find a hole and * join into it. Called with the lock asserted */ static int __sound_insert_unit(struct sound_unit * s, struct sound_unit **list, const struct file_operations *fops, int index, int low, int top) { int n=low; if (index < 0) { /* first free */ while (*list && (*list)->unit_minor<n) list=&((*list)->next); while(n<top) { /* Found a hole ? */ if(*list==NULL || (*list)->unit_minor>n) break; list=&((*list)->next); n+=SOUND_STEP; } if(n>=top) return -ENOENT; } else { n = low+(index*16); while (*list) { if ((*list)->unit_minor==n) return -EBUSY; if ((*list)->unit_minor>n) break; list=&((*list)->next); } } /* * Fill it in */ s->unit_minor=n; s->unit_fops=fops; /* * Link it */ s->next=*list; *list=s; return n; } /* * Remove a node from the chain. Called with the lock asserted */ static struct sound_unit *__sound_remove_unit(struct sound_unit **list, int unit) { while(*list) { struct sound_unit *p=*list; if(p->unit_minor==unit) { *list=p->next; return p; } list=&(p->next); } printk(KERN_ERR "Sound device %d went missing!\n", unit); return NULL; } /* * This lock guards the sound loader list. */ static DEFINE_SPINLOCK(sound_loader_lock); /* * Allocate the controlling structure and add it to the sound driver * list. Acquires locks as needed */ static int sound_insert_unit(struct sound_unit **list, const struct file_operations *fops, int index, int low, int top, const char *name, umode_t mode, struct device *dev) { struct sound_unit *s = kmalloc(sizeof(*s), GFP_KERNEL); int r; if (!s) return -ENOMEM; spin_lock(&sound_loader_lock); retry: r = __sound_insert_unit(s, list, fops, index, low, top); spin_unlock(&sound_loader_lock); if (r < 0) goto fail; else if (r < SOUND_STEP) sprintf(s->name, "sound/%s", name); else sprintf(s->name, "sound/%s%d", name, r / SOUND_STEP); if (!preclaim_oss) { /* * Something else might have grabbed the minor. If * first free slot is requested, rescan with @low set * to the next unit; otherwise, -EBUSY. */ r = __register_chrdev(SOUND_MAJOR, s->unit_minor, 1, s->name, &soundcore_fops); if (r < 0) { spin_lock(&sound_loader_lock); __sound_remove_unit(list, s->unit_minor); if (index < 0) { low = s->unit_minor + SOUND_STEP; goto retry; } spin_unlock(&sound_loader_lock); r = -EBUSY; goto fail; } } device_create(&sound_class, dev, MKDEV(SOUND_MAJOR, s->unit_minor), NULL, "%s", s->name+6); return s->unit_minor; fail: kfree(s); return r; } /* * Remove a unit. Acquires locks as needed. The drivers MUST have * completed the removal before their file operations become * invalid. */ static void sound_remove_unit(struct sound_unit **list, int unit) { struct sound_unit *p; spin_lock(&sound_loader_lock); p = __sound_remove_unit(list, unit); spin_unlock(&sound_loader_lock); if (p) { if (!preclaim_oss) __unregister_chrdev(SOUND_MAJOR, p->unit_minor, 1, p->name); device_destroy(&sound_class, MKDEV(SOUND_MAJOR, p->unit_minor)); kfree(p); } } /* * Allocations * * 0 *16 Mixers * 1 *8 Sequencers * 2 *16 Midi * 3 *16 DSP * 4 *16 SunDSP * 5 *16 DSP16 * 6 -- sndstat (obsolete) * 7 *16 unused * 8 -- alternate sequencer (see above) * 9 *16 raw synthesizer access * 10 *16 unused * 11 *16 unused * 12 *16 unused * 13 *16 unused * 14 *16 unused * 15 *16 unused */ static struct sound_unit *chains[SOUND_STEP]; /** * register_sound_special_device - register a special sound node * @fops: File operations for the driver * @unit: Unit number to allocate * @dev: device pointer * * Allocate a special sound device by minor number from the sound * subsystem. * * Return: The allocated number is returned on success. On failure, * a negative error code is returned. */ int register_sound_special_device(const struct file_operations *fops, int unit, struct device *dev) { const int chain = unit % SOUND_STEP; int max_unit = 256; const char *name; char _name[16]; switch (chain) { case 0: name = "mixer"; break; case 1: name = "sequencer"; if (unit >= SOUND_STEP) goto __unknown; max_unit = unit + 1; break; case 2: name = "midi"; break; case 3: name = "dsp"; break; case 4: name = "audio"; break; case 5: name = "dspW"; break; case 8: name = "sequencer2"; if (unit >= SOUND_STEP) goto __unknown; max_unit = unit + 1; break; case 9: name = "dmmidi"; break; case 10: name = "dmfm"; break; case 12: name = "adsp"; break; case 13: name = "amidi"; break; case 14: name = "admmidi"; break; default: { __unknown: sprintf(_name, "unknown%d", chain); if (unit >= SOUND_STEP) strcat(_name, "-"); name = _name; } break; } return sound_insert_unit(&chains[chain], fops, -1, unit, max_unit, name, 0600, dev); } EXPORT_SYMBOL(register_sound_special_device); int register_sound_special(const struct file_operations *fops, int unit) { return register_sound_special_device(fops, unit, NULL); } EXPORT_SYMBOL(register_sound_special); /** * register_sound_mixer - register a mixer device * @fops: File operations for the driver * @dev: Unit number to allocate * * Allocate a mixer device. Unit is the number of the mixer requested. * Pass -1 to request the next free mixer unit. * * Return: On success, the allocated number is returned. On failure, * a negative error code is returned. */ int register_sound_mixer(const struct file_operations *fops, int dev) { return sound_insert_unit(&chains[0], fops, dev, 0, 128, "mixer", 0600, NULL); } EXPORT_SYMBOL(register_sound_mixer); /* * DSP's are registered as a triple. Register only one and cheat * in open - see below. */ /** * register_sound_dsp - register a DSP device * @fops: File operations for the driver * @dev: Unit number to allocate * * Allocate a DSP device. Unit is the number of the DSP requested. * Pass -1 to request the next free DSP unit. * * This function allocates both the audio and dsp device entries together * and will always allocate them as a matching pair - eg dsp3/audio3 * * Return: On success, the allocated number is returned. On failure, * a negative error code is returned. */ int register_sound_dsp(const struct file_operations *fops, int dev) { return sound_insert_unit(&chains[3], fops, dev, 3, 131, "dsp", 0600, NULL); } EXPORT_SYMBOL(register_sound_dsp); /** * unregister_sound_special - unregister a special sound device * @unit: unit number to allocate * * Release a sound device that was allocated with * register_sound_special(). The unit passed is the return value from * the register function. */ void unregister_sound_special(int unit) { sound_remove_unit(&chains[unit % SOUND_STEP], unit); } EXPORT_SYMBOL(unregister_sound_special); /** * unregister_sound_mixer - unregister a mixer * @unit: unit number to allocate * * Release a sound device that was allocated with register_sound_mixer(). * The unit passed is the return value from the register function. */ void unregister_sound_mixer(int unit) { sound_remove_unit(&chains[0], unit); } EXPORT_SYMBOL(unregister_sound_mixer); /** * unregister_sound_dsp - unregister a DSP device * @unit: unit number to allocate * * Release a sound device that was allocated with register_sound_dsp(). * The unit passed is the return value from the register function. * * Both of the allocated units are released together automatically. */ void unregister_sound_dsp(int unit) { sound_remove_unit(&chains[3], unit); } EXPORT_SYMBOL(unregister_sound_dsp); static struct sound_unit *__look_for_unit(int chain, int unit) { struct sound_unit *s; s=chains[chain]; while(s && s->unit_minor <= unit) { if(s->unit_minor==unit) return s; s=s->next; } return NULL; } static int soundcore_open(struct inode *inode, struct file *file) { int chain; int unit = iminor(inode); struct sound_unit *s; const struct file_operations *new_fops = NULL; chain=unit&0x0F; if(chain==4 || chain==5) /* dsp/audio/dsp16 */ { unit&=0xF0; unit|=3; chain=3; } spin_lock(&sound_loader_lock); s = __look_for_unit(chain, unit); if (s) new_fops = fops_get(s->unit_fops); if (preclaim_oss && !new_fops) { spin_unlock(&sound_loader_lock); /* * Please, don't change this order or code. * For ALSA slot means soundcard and OSS emulation code * comes as add-on modules which aren't depend on * ALSA toplevel modules for soundcards, thus we need * load them at first. [Jaroslav Kysela <perex@jcu.cz>] */ request_module("sound-slot-%i", unit>>4); request_module("sound-service-%i-%i", unit>>4, chain); /* * sound-slot/service-* module aliases are scheduled * for removal in favor of the standard char-major-* * module aliases. For the time being, generate both * the legacy and standard module aliases to ease * transition. */ if (request_module("char-major-%d-%d", SOUND_MAJOR, unit) > 0) request_module("char-major-%d", SOUND_MAJOR); spin_lock(&sound_loader_lock); s = __look_for_unit(chain, unit); if (s) new_fops = fops_get(s->unit_fops); } spin_unlock(&sound_loader_lock); if (!new_fops) return -ENODEV; /* * We rely upon the fact that we can't be unloaded while the * subdriver is there. */ replace_fops(file, new_fops); if (!file->f_op->open) return -ENODEV; return file->f_op->open(inode, file); } MODULE_ALIAS_CHARDEV_MAJOR(SOUND_MAJOR); static void cleanup_oss_soundcore(void) { /* We have nothing to really do here - we know the lists must be empty */ unregister_chrdev(SOUND_MAJOR, "sound"); } static int __init init_oss_soundcore(void) { if (preclaim_oss && register_chrdev(SOUND_MAJOR, "sound", &soundcore_fops) < 0) { printk(KERN_ERR "soundcore: sound device already in use.\n"); return -EBUSY; } return 0; } #endif /* CONFIG_SOUND_OSS_CORE */ |
| 25 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_GENERIC_BITOPS_LE_H_ #define _ASM_GENERIC_BITOPS_LE_H_ #include <asm/types.h> #include <asm/byteorder.h> #if defined(__LITTLE_ENDIAN) #define BITOP_LE_SWIZZLE 0 #elif defined(__BIG_ENDIAN) #define BITOP_LE_SWIZZLE ((BITS_PER_LONG-1) & ~0x7) #endif static inline int test_bit_le(int nr, const void *addr) { return test_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline void set_bit_le(int nr, void *addr) { set_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline void clear_bit_le(int nr, void *addr) { clear_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline void __set_bit_le(int nr, void *addr) { __set_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline void __clear_bit_le(int nr, void *addr) { __clear_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline int test_and_set_bit_le(int nr, void *addr) { return test_and_set_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline int test_and_clear_bit_le(int nr, void *addr) { return test_and_clear_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline int __test_and_set_bit_le(int nr, void *addr) { return __test_and_set_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline int __test_and_clear_bit_le(int nr, void *addr) { return __test_and_clear_bit(nr ^ BITOP_LE_SWIZZLE, addr); } #endif /* _ASM_GENERIC_BITOPS_LE_H_ */ |
| 2 14 16 16 16 3 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 | // SPDX-License-Identifier: GPL-2.0-only /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation. * * Authors: Artem Bityutskiy (Битюцкий Артём) * Adrian Hunter */ /* * This file implements UBIFS initialization and VFS superblock operations. Some * initialization stuff which is rather large and complex is placed at * corresponding subsystems, but most of it is here. */ #include <linux/init.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/ctype.h> #include <linux/kthread.h> #include <linux/parser.h> #include <linux/seq_file.h> #include <linux/mount.h> #include <linux/math64.h> #include <linux/writeback.h> #include "ubifs.h" static int ubifs_default_version_set(const char *val, const struct kernel_param *kp) { int n = 0, ret; ret = kstrtoint(val, 10, &n); if (ret != 0 || n < 4 || n > UBIFS_FORMAT_VERSION) return -EINVAL; return param_set_int(val, kp); } static const struct kernel_param_ops ubifs_default_version_ops = { .set = ubifs_default_version_set, .get = param_get_int, }; int ubifs_default_version = UBIFS_FORMAT_VERSION; module_param_cb(default_version, &ubifs_default_version_ops, &ubifs_default_version, 0600); /* * Maximum amount of memory we may 'kmalloc()' without worrying that we are * allocating too much. */ #define UBIFS_KMALLOC_OK (128*1024) /* Slab cache for UBIFS inodes */ static struct kmem_cache *ubifs_inode_slab; /* UBIFS TNC shrinker description */ static struct shrinker *ubifs_shrinker_info; /** * validate_inode - validate inode. * @c: UBIFS file-system description object * @inode: the inode to validate * * This is a helper function for 'ubifs_iget()' which validates various fields * of a newly built inode to make sure they contain sane values and prevent * possible vulnerabilities. Returns zero if the inode is all right and * a non-zero error code if not. */ static int validate_inode(struct ubifs_info *c, const struct inode *inode) { int err; const struct ubifs_inode *ui = ubifs_inode(inode); if (inode->i_size > c->max_inode_sz) { ubifs_err(c, "inode is too large (%lld)", (long long)inode->i_size); return 1; } if (ui->compr_type >= UBIFS_COMPR_TYPES_CNT) { ubifs_err(c, "unknown compression type %d", ui->compr_type); return 2; } if (ui->xattr_names + ui->xattr_cnt > XATTR_LIST_MAX) return 3; if (ui->data_len < 0 || ui->data_len > UBIFS_MAX_INO_DATA) return 4; if (ui->xattr && !S_ISREG(inode->i_mode)) return 5; if (!ubifs_compr_present(c, ui->compr_type)) { ubifs_warn(c, "inode %lu uses '%s' compression, but it was not compiled in", inode->i_ino, ubifs_compr_name(c, ui->compr_type)); } err = dbg_check_dir(c, inode); return err; } struct inode *ubifs_iget(struct super_block *sb, unsigned long inum) { int err; union ubifs_key key; struct ubifs_ino_node *ino; struct ubifs_info *c = sb->s_fs_info; struct inode *inode; struct ubifs_inode *ui; dbg_gen("inode %lu", inum); inode = iget_locked(sb, inum); if (!inode) return ERR_PTR(-ENOMEM); if (!(inode->i_state & I_NEW)) return inode; ui = ubifs_inode(inode); ino = kmalloc(UBIFS_MAX_INO_NODE_SZ, GFP_NOFS); if (!ino) { err = -ENOMEM; goto out; } ino_key_init(c, &key, inode->i_ino); err = ubifs_tnc_lookup(c, &key, ino); if (err) goto out_ino; inode->i_flags |= S_NOCMTIME; if (!IS_ENABLED(CONFIG_UBIFS_ATIME_SUPPORT)) inode->i_flags |= S_NOATIME; set_nlink(inode, le32_to_cpu(ino->nlink)); i_uid_write(inode, le32_to_cpu(ino->uid)); i_gid_write(inode, le32_to_cpu(ino->gid)); inode_set_atime(inode, (int64_t)le64_to_cpu(ino->atime_sec), le32_to_cpu(ino->atime_nsec)); inode_set_mtime(inode, (int64_t)le64_to_cpu(ino->mtime_sec), le32_to_cpu(ino->mtime_nsec)); inode_set_ctime(inode, (int64_t)le64_to_cpu(ino->ctime_sec), le32_to_cpu(ino->ctime_nsec)); inode->i_mode = le32_to_cpu(ino->mode); inode->i_size = le64_to_cpu(ino->size); ui->data_len = le32_to_cpu(ino->data_len); ui->flags = le32_to_cpu(ino->flags); ui->compr_type = le16_to_cpu(ino->compr_type); ui->creat_sqnum = le64_to_cpu(ino->creat_sqnum); ui->xattr_cnt = le32_to_cpu(ino->xattr_cnt); ui->xattr_size = le32_to_cpu(ino->xattr_size); ui->xattr_names = le32_to_cpu(ino->xattr_names); ui->synced_i_size = ui->ui_size = inode->i_size; ui->xattr = (ui->flags & UBIFS_XATTR_FL) ? 1 : 0; err = validate_inode(c, inode); if (err) goto out_invalid; switch (inode->i_mode & S_IFMT) { case S_IFREG: inode->i_mapping->a_ops = &ubifs_file_address_operations; inode->i_op = &ubifs_file_inode_operations; inode->i_fop = &ubifs_file_operations; if (ui->xattr) { ui->data = kmalloc(ui->data_len + 1, GFP_NOFS); if (!ui->data) { err = -ENOMEM; goto out_ino; } memcpy(ui->data, ino->data, ui->data_len); ((char *)ui->data)[ui->data_len] = '\0'; } else if (ui->data_len != 0) { err = 10; goto out_invalid; } break; case S_IFDIR: inode->i_op = &ubifs_dir_inode_operations; inode->i_fop = &ubifs_dir_operations; if (ui->data_len != 0) { err = 11; goto out_invalid; } break; case S_IFLNK: inode->i_op = &ubifs_symlink_inode_operations; if (ui->data_len <= 0 || ui->data_len > UBIFS_MAX_INO_DATA) { err = 12; goto out_invalid; } ui->data = kmalloc(ui->data_len + 1, GFP_NOFS); if (!ui->data) { err = -ENOMEM; goto out_ino; } memcpy(ui->data, ino->data, ui->data_len); ((char *)ui->data)[ui->data_len] = '\0'; break; case S_IFBLK: case S_IFCHR: { dev_t rdev; union ubifs_dev_desc *dev; ui->data = kmalloc(sizeof(union ubifs_dev_desc), GFP_NOFS); if (!ui->data) { err = -ENOMEM; goto out_ino; } dev = (union ubifs_dev_desc *)ino->data; if (ui->data_len == sizeof(dev->new)) rdev = new_decode_dev(le32_to_cpu(dev->new)); else if (ui->data_len == sizeof(dev->huge)) rdev = huge_decode_dev(le64_to_cpu(dev->huge)); else { err = 13; goto out_invalid; } memcpy(ui->data, ino->data, ui->data_len); inode->i_op = &ubifs_file_inode_operations; init_special_inode(inode, inode->i_mode, rdev); break; } case S_IFSOCK: case S_IFIFO: inode->i_op = &ubifs_file_inode_operations; init_special_inode(inode, inode->i_mode, 0); if (ui->data_len != 0) { err = 14; goto out_invalid; } break; default: err = 15; goto out_invalid; } kfree(ino); ubifs_set_inode_flags(inode); unlock_new_inode(inode); return inode; out_invalid: ubifs_err(c, "inode %lu validation failed, error %d", inode->i_ino, err); ubifs_dump_node(c, ino, UBIFS_MAX_INO_NODE_SZ); ubifs_dump_inode(c, inode); err = -EINVAL; out_ino: kfree(ino); out: ubifs_err(c, "failed to read inode %lu, error %d", inode->i_ino, err); iget_failed(inode); return ERR_PTR(err); } static struct inode *ubifs_alloc_inode(struct super_block *sb) { struct ubifs_inode *ui; ui = alloc_inode_sb(sb, ubifs_inode_slab, GFP_NOFS); if (!ui) return NULL; memset((void *)ui + sizeof(struct inode), 0, sizeof(struct ubifs_inode) - sizeof(struct inode)); mutex_init(&ui->ui_mutex); init_rwsem(&ui->xattr_sem); spin_lock_init(&ui->ui_lock); return &ui->vfs_inode; }; static void ubifs_free_inode(struct inode *inode) { struct ubifs_inode *ui = ubifs_inode(inode); kfree(ui->data); fscrypt_free_inode(inode); kmem_cache_free(ubifs_inode_slab, ui); } /* * Note, Linux write-back code calls this without 'i_mutex'. */ static int ubifs_write_inode(struct inode *inode, struct writeback_control *wbc) { int err = 0; struct ubifs_info *c = inode->i_sb->s_fs_info; struct ubifs_inode *ui = ubifs_inode(inode); ubifs_assert(c, !ui->xattr); if (is_bad_inode(inode)) return 0; mutex_lock(&ui->ui_mutex); /* * Due to races between write-back forced by budgeting * (see 'sync_some_inodes()') and background write-back, the inode may * have already been synchronized, do not do this again. This might * also happen if it was synchronized in an VFS operation, e.g. * 'ubifs_link()'. */ if (!ui->dirty) { mutex_unlock(&ui->ui_mutex); return 0; } /* * As an optimization, do not write orphan inodes to the media just * because this is not needed. */ dbg_gen("inode %lu, mode %#x, nlink %u", inode->i_ino, (int)inode->i_mode, inode->i_nlink); if (inode->i_nlink) { err = ubifs_jnl_write_inode(c, inode); if (err) ubifs_err(c, "can't write inode %lu, error %d", inode->i_ino, err); else err = dbg_check_inode_size(c, inode, ui->ui_size); } ui->dirty = 0; mutex_unlock(&ui->ui_mutex); ubifs_release_dirty_inode_budget(c, ui); return err; } static int ubifs_drop_inode(struct inode *inode) { int drop = generic_drop_inode(inode); if (!drop) drop = fscrypt_drop_inode(inode); return drop; } static void ubifs_evict_inode(struct inode *inode) { int err; struct ubifs_info *c = inode->i_sb->s_fs_info; struct ubifs_inode *ui = ubifs_inode(inode); if (ui->xattr) /* * Extended attribute inode deletions are fully handled in * 'ubifs_removexattr()'. These inodes are special and have * limited usage, so there is nothing to do here. */ goto out; dbg_gen("inode %lu, mode %#x", inode->i_ino, (int)inode->i_mode); ubifs_assert(c, !atomic_read(&inode->i_count)); truncate_inode_pages_final(&inode->i_data); if (inode->i_nlink) goto done; if (is_bad_inode(inode)) goto out; ui->ui_size = inode->i_size = 0; err = ubifs_jnl_delete_inode(c, inode); if (err) /* * Worst case we have a lost orphan inode wasting space, so a * simple error message is OK here. */ ubifs_err(c, "can't delete inode %lu, error %d", inode->i_ino, err); out: if (ui->dirty) ubifs_release_dirty_inode_budget(c, ui); else { /* We've deleted something - clean the "no space" flags */ c->bi.nospace = c->bi.nospace_rp = 0; smp_wmb(); } done: clear_inode(inode); fscrypt_put_encryption_info(inode); } static void ubifs_dirty_inode(struct inode *inode, int flags) { struct ubifs_info *c = inode->i_sb->s_fs_info; struct ubifs_inode *ui = ubifs_inode(inode); ubifs_assert(c, mutex_is_locked(&ui->ui_mutex)); if (!ui->dirty) { ui->dirty = 1; dbg_gen("inode %lu", inode->i_ino); } } static int ubifs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct ubifs_info *c = dentry->d_sb->s_fs_info; unsigned long long free; __le32 *uuid = (__le32 *)c->uuid; free = ubifs_get_free_space(c); dbg_gen("free space %lld bytes (%lld blocks)", free, free >> UBIFS_BLOCK_SHIFT); buf->f_type = UBIFS_SUPER_MAGIC; buf->f_bsize = UBIFS_BLOCK_SIZE; buf->f_blocks = c->block_cnt; buf->f_bfree = free >> UBIFS_BLOCK_SHIFT; if (free > c->report_rp_size) buf->f_bavail = (free - c->report_rp_size) >> UBIFS_BLOCK_SHIFT; else buf->f_bavail = 0; buf->f_files = 0; buf->f_ffree = 0; buf->f_namelen = UBIFS_MAX_NLEN; buf->f_fsid.val[0] = le32_to_cpu(uuid[0]) ^ le32_to_cpu(uuid[2]); buf->f_fsid.val[1] = le32_to_cpu(uuid[1]) ^ le32_to_cpu(uuid[3]); ubifs_assert(c, buf->f_bfree <= c->block_cnt); return 0; } static int ubifs_show_options(struct seq_file *s, struct dentry *root) { struct ubifs_info *c = root->d_sb->s_fs_info; if (c->mount_opts.unmount_mode == 2) seq_puts(s, ",fast_unmount"); else if (c->mount_opts.unmount_mode == 1) seq_puts(s, ",norm_unmount"); if (c->mount_opts.bulk_read == 2) seq_puts(s, ",bulk_read"); else if (c->mount_opts.bulk_read == 1) seq_puts(s, ",no_bulk_read"); if (c->mount_opts.chk_data_crc == 2) seq_puts(s, ",chk_data_crc"); else if (c->mount_opts.chk_data_crc == 1) seq_puts(s, ",no_chk_data_crc"); if (c->mount_opts.override_compr) { seq_printf(s, ",compr=%s", ubifs_compr_name(c, c->mount_opts.compr_type)); } seq_printf(s, ",assert=%s", ubifs_assert_action_name(c)); seq_printf(s, ",ubi=%d,vol=%d", c->vi.ubi_num, c->vi.vol_id); return 0; } static int ubifs_sync_fs(struct super_block *sb, int wait) { int i, err; struct ubifs_info *c = sb->s_fs_info; /* * Zero @wait is just an advisory thing to help the file system shove * lots of data into the queues, and there will be the second * '->sync_fs()' call, with non-zero @wait. */ if (!wait) return 0; /* * Synchronize write buffers, because 'ubifs_run_commit()' does not * do this if it waits for an already running commit. */ for (i = 0; i < c->jhead_cnt; i++) { err = ubifs_wbuf_sync(&c->jheads[i].wbuf); if (err) return err; } /* * Strictly speaking, it is not necessary to commit the journal here, * synchronizing write-buffers would be enough. But committing makes * UBIFS free space predictions much more accurate, so we want to let * the user be able to get more accurate results of 'statfs()' after * they synchronize the file system. */ err = ubifs_run_commit(c); if (err) return err; return ubi_sync(c->vi.ubi_num); } /** * init_constants_early - initialize UBIFS constants. * @c: UBIFS file-system description object * * This function initialize UBIFS constants which do not need the superblock to * be read. It also checks that the UBI volume satisfies basic UBIFS * requirements. Returns zero in case of success and a negative error code in * case of failure. */ static int init_constants_early(struct ubifs_info *c) { if (c->vi.corrupted) { ubifs_warn(c, "UBI volume is corrupted - read-only mode"); c->ro_media = 1; } if (c->di.ro_mode) { ubifs_msg(c, "read-only UBI device"); c->ro_media = 1; } if (c->vi.vol_type == UBI_STATIC_VOLUME) { ubifs_msg(c, "static UBI volume - read-only mode"); c->ro_media = 1; } c->leb_cnt = c->vi.size; c->leb_size = c->vi.usable_leb_size; c->leb_start = c->di.leb_start; c->half_leb_size = c->leb_size / 2; c->min_io_size = c->di.min_io_size; c->min_io_shift = fls(c->min_io_size) - 1; c->max_write_size = c->di.max_write_size; c->max_write_shift = fls(c->max_write_size) - 1; if (c->leb_size < UBIFS_MIN_LEB_SZ) { ubifs_errc(c, "too small LEBs (%d bytes), min. is %d bytes", c->leb_size, UBIFS_MIN_LEB_SZ); return -EINVAL; } if (c->leb_cnt < UBIFS_MIN_LEB_CNT) { ubifs_errc(c, "too few LEBs (%d), min. is %d", c->leb_cnt, UBIFS_MIN_LEB_CNT); return -EINVAL; } if (!is_power_of_2(c->min_io_size)) { ubifs_errc(c, "bad min. I/O size %d", c->min_io_size); return -EINVAL; } /* * Maximum write size has to be greater or equivalent to min. I/O * size, and be multiple of min. I/O size. */ if (c->max_write_size < c->min_io_size || c->max_write_size % c->min_io_size || !is_power_of_2(c->max_write_size)) { ubifs_errc(c, "bad write buffer size %d for %d min. I/O unit", c->max_write_size, c->min_io_size); return -EINVAL; } /* * UBIFS aligns all node to 8-byte boundary, so to make function in * io.c simpler, assume minimum I/O unit size to be 8 bytes if it is * less than 8. */ if (c->min_io_size < 8) { c->min_io_size = 8; c->min_io_shift = 3; if (c->max_write_size < c->min_io_size) { c->max_write_size = c->min_io_size; c->max_write_shift = c->min_io_shift; } } c->ref_node_alsz = ALIGN(UBIFS_REF_NODE_SZ, c->min_io_size); c->mst_node_alsz = ALIGN(UBIFS_MST_NODE_SZ, c->min_io_size); /* * Initialize node length ranges which are mostly needed for node * length validation. */ c->ranges[UBIFS_PAD_NODE].len = UBIFS_PAD_NODE_SZ; c->ranges[UBIFS_SB_NODE].len = UBIFS_SB_NODE_SZ; c->ranges[UBIFS_MST_NODE].len = UBIFS_MST_NODE_SZ; c->ranges[UBIFS_REF_NODE].len = UBIFS_REF_NODE_SZ; c->ranges[UBIFS_TRUN_NODE].len = UBIFS_TRUN_NODE_SZ; c->ranges[UBIFS_CS_NODE].len = UBIFS_CS_NODE_SZ; c->ranges[UBIFS_AUTH_NODE].min_len = UBIFS_AUTH_NODE_SZ; c->ranges[UBIFS_AUTH_NODE].max_len = UBIFS_AUTH_NODE_SZ + UBIFS_MAX_HMAC_LEN; c->ranges[UBIFS_SIG_NODE].min_len = UBIFS_SIG_NODE_SZ; c->ranges[UBIFS_SIG_NODE].max_len = c->leb_size - UBIFS_SB_NODE_SZ; c->ranges[UBIFS_INO_NODE].min_len = UBIFS_INO_NODE_SZ; c->ranges[UBIFS_INO_NODE].max_len = UBIFS_MAX_INO_NODE_SZ; c->ranges[UBIFS_ORPH_NODE].min_len = UBIFS_ORPH_NODE_SZ + sizeof(__le64); c->ranges[UBIFS_ORPH_NODE].max_len = c->leb_size; c->ranges[UBIFS_DENT_NODE].min_len = UBIFS_DENT_NODE_SZ; c->ranges[UBIFS_DENT_NODE].max_len = UBIFS_MAX_DENT_NODE_SZ; c->ranges[UBIFS_XENT_NODE].min_len = UBIFS_XENT_NODE_SZ; c->ranges[UBIFS_XENT_NODE].max_len = UBIFS_MAX_XENT_NODE_SZ; c->ranges[UBIFS_DATA_NODE].min_len = UBIFS_DATA_NODE_SZ; c->ranges[UBIFS_DATA_NODE].max_len = UBIFS_MAX_DATA_NODE_SZ; /* * Minimum indexing node size is amended later when superblock is * read and the key length is known. */ c->ranges[UBIFS_IDX_NODE].min_len = UBIFS_IDX_NODE_SZ + UBIFS_BRANCH_SZ; /* * Maximum indexing node size is amended later when superblock is * read and the fanout is known. */ c->ranges[UBIFS_IDX_NODE].max_len = INT_MAX; /* * Initialize dead and dark LEB space watermarks. See gc.c for comments * about these values. */ c->dead_wm = ALIGN(MIN_WRITE_SZ, c->min_io_size); c->dark_wm = ALIGN(UBIFS_MAX_NODE_SZ, c->min_io_size); /* * Calculate how many bytes would be wasted at the end of LEB if it was * fully filled with data nodes of maximum size. This is used in * calculations when reporting free space. */ c->leb_overhead = c->leb_size % UBIFS_MAX_DATA_NODE_SZ; /* Buffer size for bulk-reads */ c->max_bu_buf_len = UBIFS_MAX_BULK_READ * UBIFS_MAX_DATA_NODE_SZ; if (c->max_bu_buf_len > c->leb_size) c->max_bu_buf_len = c->leb_size; /* Log is ready, preserve one LEB for commits. */ c->min_log_bytes = c->leb_size; return 0; } /** * bud_wbuf_callback - bud LEB write-buffer synchronization call-back. * @c: UBIFS file-system description object * @lnum: LEB the write-buffer was synchronized to * @free: how many free bytes left in this LEB * @pad: how many bytes were padded * * This is a callback function which is called by the I/O unit when the * write-buffer is synchronized. We need this to correctly maintain space * accounting in bud logical eraseblocks. This function returns zero in case of * success and a negative error code in case of failure. * * This function actually belongs to the journal, but we keep it here because * we want to keep it static. */ static int bud_wbuf_callback(struct ubifs_info *c, int lnum, int free, int pad) { return ubifs_update_one_lp(c, lnum, free, pad, 0, 0); } /* * init_constants_sb - initialize UBIFS constants. * @c: UBIFS file-system description object * * This is a helper function which initializes various UBIFS constants after * the superblock has been read. It also checks various UBIFS parameters and * makes sure they are all right. Returns zero in case of success and a * negative error code in case of failure. */ static int init_constants_sb(struct ubifs_info *c) { int tmp, err; long long tmp64; c->main_bytes = (long long)c->main_lebs * c->leb_size; c->max_znode_sz = sizeof(struct ubifs_znode) + c->fanout * sizeof(struct ubifs_zbranch); tmp = ubifs_idx_node_sz(c, 1); c->ranges[UBIFS_IDX_NODE].min_len = tmp; c->min_idx_node_sz = ALIGN(tmp, 8); tmp = ubifs_idx_node_sz(c, c->fanout); c->ranges[UBIFS_IDX_NODE].max_len = tmp; c->max_idx_node_sz = ALIGN(tmp, 8); /* Make sure LEB size is large enough to fit full commit */ tmp = UBIFS_CS_NODE_SZ + UBIFS_REF_NODE_SZ * c->jhead_cnt; tmp = ALIGN(tmp, c->min_io_size); if (tmp > c->leb_size) { ubifs_err(c, "too small LEB size %d, at least %d needed", c->leb_size, tmp); return -EINVAL; } /* * Make sure that the log is large enough to fit reference nodes for * all buds plus one reserved LEB. */ tmp64 = c->max_bud_bytes + c->leb_size - 1; c->max_bud_cnt = div_u64(tmp64, c->leb_size); tmp = (c->ref_node_alsz * c->max_bud_cnt + c->leb_size - 1); tmp /= c->leb_size; tmp += 1; if (c->log_lebs < tmp) { ubifs_err(c, "too small log %d LEBs, required min. %d LEBs", c->log_lebs, tmp); return -EINVAL; } /* * When budgeting we assume worst-case scenarios when the pages are not * be compressed and direntries are of the maximum size. * * Note, data, which may be stored in inodes is budgeted separately, so * it is not included into 'c->bi.inode_budget'. */ c->bi.page_budget = UBIFS_MAX_DATA_NODE_SZ * UBIFS_BLOCKS_PER_PAGE; c->bi.inode_budget = UBIFS_INO_NODE_SZ; c->bi.dent_budget = UBIFS_MAX_DENT_NODE_SZ; /* * When the amount of flash space used by buds becomes * 'c->max_bud_bytes', UBIFS just blocks all writers and starts commit. * The writers are unblocked when the commit is finished. To avoid * writers to be blocked UBIFS initiates background commit in advance, * when number of bud bytes becomes above the limit defined below. */ c->bg_bud_bytes = (c->max_bud_bytes * 13) >> 4; /* * Ensure minimum journal size. All the bytes in the journal heads are * considered to be used, when calculating the current journal usage. * Consequently, if the journal is too small, UBIFS will treat it as * always full. */ tmp64 = (long long)(c->jhead_cnt + 1) * c->leb_size + 1; if (c->bg_bud_bytes < tmp64) c->bg_bud_bytes = tmp64; if (c->max_bud_bytes < tmp64 + c->leb_size) c->max_bud_bytes = tmp64 + c->leb_size; err = ubifs_calc_lpt_geom(c); if (err) return err; /* Initialize effective LEB size used in budgeting calculations */ c->idx_leb_size = c->leb_size - c->max_idx_node_sz; return 0; } /* * init_constants_master - initialize UBIFS constants. * @c: UBIFS file-system description object * * This is a helper function which initializes various UBIFS constants after * the master node has been read. It also checks various UBIFS parameters and * makes sure they are all right. */ static void init_constants_master(struct ubifs_info *c) { long long tmp64; c->bi.min_idx_lebs = ubifs_calc_min_idx_lebs(c); c->report_rp_size = ubifs_reported_space(c, c->rp_size); /* * Calculate total amount of FS blocks. This number is not used * internally because it does not make much sense for UBIFS, but it is * necessary to report something for the 'statfs()' call. * * Subtract the LEB reserved for GC, the LEB which is reserved for * deletions, minimum LEBs for the index, and assume only one journal * head is available. */ tmp64 = c->main_lebs - 1 - 1 - MIN_INDEX_LEBS - c->jhead_cnt + 1; tmp64 *= (long long)c->leb_size - c->leb_overhead; tmp64 = ubifs_reported_space(c, tmp64); c->block_cnt = tmp64 >> UBIFS_BLOCK_SHIFT; } /** * take_gc_lnum - reserve GC LEB. * @c: UBIFS file-system description object * * This function ensures that the LEB reserved for garbage collection is marked * as "taken" in lprops. We also have to set free space to LEB size and dirty * space to zero, because lprops may contain out-of-date information if the * file-system was un-mounted before it has been committed. This function * returns zero in case of success and a negative error code in case of * failure. */ static int take_gc_lnum(struct ubifs_info *c) { int err; if (c->gc_lnum == -1) { ubifs_err(c, "no LEB for GC"); return -EINVAL; } /* And we have to tell lprops that this LEB is taken */ err = ubifs_change_one_lp(c, c->gc_lnum, c->leb_size, 0, LPROPS_TAKEN, 0, 0); return err; } /** * alloc_wbufs - allocate write-buffers. * @c: UBIFS file-system description object * * This helper function allocates and initializes UBIFS write-buffers. Returns * zero in case of success and %-ENOMEM in case of failure. */ static int alloc_wbufs(struct ubifs_info *c) { int i, err; c->jheads = kcalloc(c->jhead_cnt, sizeof(struct ubifs_jhead), GFP_KERNEL); if (!c->jheads) return -ENOMEM; /* Initialize journal heads */ for (i = 0; i < c->jhead_cnt; i++) { INIT_LIST_HEAD(&c->jheads[i].buds_list); err = ubifs_wbuf_init(c, &c->jheads[i].wbuf); if (err) goto out_wbuf; c->jheads[i].wbuf.sync_callback = &bud_wbuf_callback; c->jheads[i].wbuf.jhead = i; c->jheads[i].grouped = 1; c->jheads[i].log_hash = ubifs_hash_get_desc(c); if (IS_ERR(c->jheads[i].log_hash)) { err = PTR_ERR(c->jheads[i].log_hash); goto out_log_hash; } } /* * Garbage Collector head does not need to be synchronized by timer. * Also GC head nodes are not grouped. */ c->jheads[GCHD].wbuf.no_timer = 1; c->jheads[GCHD].grouped = 0; return 0; out_log_hash: kfree(c->jheads[i].wbuf.buf); kfree(c->jheads[i].wbuf.inodes); out_wbuf: while (i--) { kfree(c->jheads[i].wbuf.buf); kfree(c->jheads[i].wbuf.inodes); kfree(c->jheads[i].log_hash); } kfree(c->jheads); c->jheads = NULL; return err; } /** * free_wbufs - free write-buffers. * @c: UBIFS file-system description object */ static void free_wbufs(struct ubifs_info *c) { int i; if (c->jheads) { for (i = 0; i < c->jhead_cnt; i++) { kfree(c->jheads[i].wbuf.buf); kfree(c->jheads[i].wbuf.inodes); kfree(c->jheads[i].log_hash); } kfree(c->jheads); c->jheads = NULL; } } /** * free_orphans - free orphans. * @c: UBIFS file-system description object */ static void free_orphans(struct ubifs_info *c) { struct ubifs_orphan *orph; while (c->orph_dnext) { orph = c->orph_dnext; c->orph_dnext = orph->dnext; list_del(&orph->list); kfree(orph); } while (!list_empty(&c->orph_list)) { orph = list_entry(c->orph_list.next, struct ubifs_orphan, list); list_del(&orph->list); kfree(orph); ubifs_err(c, "orphan list not empty at unmount"); } vfree(c->orph_buf); c->orph_buf = NULL; } /** * free_buds - free per-bud objects. * @c: UBIFS file-system description object */ static void free_buds(struct ubifs_info *c) { struct ubifs_bud *bud, *n; rbtree_postorder_for_each_entry_safe(bud, n, &c->buds, rb) { kfree(bud->log_hash); kfree(bud); } } /** * check_volume_empty - check if the UBI volume is empty. * @c: UBIFS file-system description object * * This function checks if the UBIFS volume is empty by looking if its LEBs are * mapped or not. The result of checking is stored in the @c->empty variable. * Returns zero in case of success and a negative error code in case of * failure. */ static int check_volume_empty(struct ubifs_info *c) { int lnum, err; c->empty = 1; for (lnum = 0; lnum < c->leb_cnt; lnum++) { err = ubifs_is_mapped(c, lnum); if (unlikely(err < 0)) return err; if (err == 1) { c->empty = 0; break; } cond_resched(); } return 0; } /* * UBIFS mount options. * * Opt_fast_unmount: do not run a journal commit before un-mounting * Opt_norm_unmount: run a journal commit before un-mounting * Opt_bulk_read: enable bulk-reads * Opt_no_bulk_read: disable bulk-reads * Opt_chk_data_crc: check CRCs when reading data nodes * Opt_no_chk_data_crc: do not check CRCs when reading data nodes * Opt_override_compr: override default compressor * Opt_assert: set ubifs_assert() action * Opt_auth_key: The key name used for authentication * Opt_auth_hash_name: The hash type used for authentication * Opt_err: just end of array marker */ enum { Opt_fast_unmount, Opt_norm_unmount, Opt_bulk_read, Opt_no_bulk_read, Opt_chk_data_crc, Opt_no_chk_data_crc, Opt_override_compr, Opt_assert, Opt_auth_key, Opt_auth_hash_name, Opt_ignore, Opt_err, }; static const match_table_t tokens = { {Opt_fast_unmount, "fast_unmount"}, {Opt_norm_unmount, "norm_unmount"}, {Opt_bulk_read, "bulk_read"}, {Opt_no_bulk_read, "no_bulk_read"}, {Opt_chk_data_crc, "chk_data_crc"}, {Opt_no_chk_data_crc, "no_chk_data_crc"}, {Opt_override_compr, "compr=%s"}, {Opt_auth_key, "auth_key=%s"}, {Opt_auth_hash_name, "auth_hash_name=%s"}, {Opt_ignore, "ubi=%s"}, {Opt_ignore, "vol=%s"}, {Opt_assert, "assert=%s"}, {Opt_err, NULL}, }; /** * parse_standard_option - parse a standard mount option. * @option: the option to parse * * Normally, standard mount options like "sync" are passed to file-systems as * flags. However, when a "rootflags=" kernel boot parameter is used, they may * be present in the options string. This function tries to deal with this * situation and parse standard options. Returns 0 if the option was not * recognized, and the corresponding integer flag if it was. * * UBIFS is only interested in the "sync" option, so do not check for anything * else. */ static int parse_standard_option(const char *option) { pr_notice("UBIFS: parse %s\n", option); if (!strcmp(option, "sync")) return SB_SYNCHRONOUS; return 0; } /** * ubifs_parse_options - parse mount parameters. * @c: UBIFS file-system description object * @options: parameters to parse * @is_remount: non-zero if this is FS re-mount * * This function parses UBIFS mount options and returns zero in case success * and a negative error code in case of failure. */ static int ubifs_parse_options(struct ubifs_info *c, char *options, int is_remount) { char *p; substring_t args[MAX_OPT_ARGS]; if (!options) return 0; while ((p = strsep(&options, ","))) { int token; if (!*p) continue; token = match_token(p, tokens, args); switch (token) { /* * %Opt_fast_unmount and %Opt_norm_unmount options are ignored. * We accept them in order to be backward-compatible. But this * should be removed at some point. */ case Opt_fast_unmount: c->mount_opts.unmount_mode = 2; break; case Opt_norm_unmount: c->mount_opts.unmount_mode = 1; break; case Opt_bulk_read: c->mount_opts.bulk_read = 2; c->bulk_read = 1; break; case Opt_no_bulk_read: c->mount_opts.bulk_read = 1; c->bulk_read = 0; break; case Opt_chk_data_crc: c->mount_opts.chk_data_crc = 2; c->no_chk_data_crc = 0; break; case Opt_no_chk_data_crc: c->mount_opts.chk_data_crc = 1; c->no_chk_data_crc = 1; break; case Opt_override_compr: { char *name = match_strdup(&args[0]); if (!name) return -ENOMEM; if (!strcmp(name, "none")) c->mount_opts.compr_type = UBIFS_COMPR_NONE; else if (!strcmp(name, "lzo")) c->mount_opts.compr_type = UBIFS_COMPR_LZO; else if (!strcmp(name, "zlib")) c->mount_opts.compr_type = UBIFS_COMPR_ZLIB; else if (!strcmp(name, "zstd")) c->mount_opts.compr_type = UBIFS_COMPR_ZSTD; else { ubifs_err(c, "unknown compressor \"%s\"", name); //FIXME: is c ready? kfree(name); return -EINVAL; } kfree(name); c->mount_opts.override_compr = 1; c->default_compr = c->mount_opts.compr_type; break; } case Opt_assert: { char *act = match_strdup(&args[0]); if (!act) return -ENOMEM; if (!strcmp(act, "report")) c->assert_action = ASSACT_REPORT; else if (!strcmp(act, "read-only")) c->assert_action = ASSACT_RO; else if (!strcmp(act, "panic")) c->assert_action = ASSACT_PANIC; else { ubifs_err(c, "unknown assert action \"%s\"", act); kfree(act); return -EINVAL; } kfree(act); break; } case Opt_auth_key: if (!is_remount) { c->auth_key_name = kstrdup(args[0].from, GFP_KERNEL); if (!c->auth_key_name) return -ENOMEM; } break; case Opt_auth_hash_name: if (!is_remount) { c->auth_hash_name = kstrdup(args[0].from, GFP_KERNEL); if (!c->auth_hash_name) return -ENOMEM; } break; case Opt_ignore: break; default: { unsigned long flag; struct super_block *sb = c->vfs_sb; flag = parse_standard_option(p); if (!flag) { ubifs_err(c, "unrecognized mount option \"%s\" or missing value", p); return -EINVAL; } sb->s_flags |= flag; break; } } } return 0; } /* * ubifs_release_options - release mount parameters which have been dumped. * @c: UBIFS file-system description object */ static void ubifs_release_options(struct ubifs_info *c) { kfree(c->auth_key_name); c->auth_key_name = NULL; kfree(c->auth_hash_name); c->auth_hash_name = NULL; } /** * destroy_journal - destroy journal data structures. * @c: UBIFS file-system description object * * This function destroys journal data structures including those that may have * been created by recovery functions. */ static void destroy_journal(struct ubifs_info *c) { while (!list_empty(&c->unclean_leb_list)) { struct ubifs_unclean_leb *ucleb; ucleb = list_entry(c->unclean_leb_list.next, struct ubifs_unclean_leb, list); list_del(&ucleb->list); kfree(ucleb); } while (!list_empty(&c->old_buds)) { struct ubifs_bud *bud; bud = list_entry(c->old_buds.next, struct ubifs_bud, list); list_del(&bud->list); kfree(bud->log_hash); kfree(bud); } ubifs_destroy_idx_gc(c); ubifs_destroy_size_tree(c); ubifs_tnc_close(c); free_buds(c); } /** * bu_init - initialize bulk-read information. * @c: UBIFS file-system description object */ static void bu_init(struct ubifs_info *c) { ubifs_assert(c, c->bulk_read == 1); if (c->bu.buf) return; /* Already initialized */ again: c->bu.buf = kmalloc(c->max_bu_buf_len, GFP_KERNEL | __GFP_NOWARN); if (!c->bu.buf) { if (c->max_bu_buf_len > UBIFS_KMALLOC_OK) { c->max_bu_buf_len = UBIFS_KMALLOC_OK; goto again; } /* Just disable bulk-read */ ubifs_warn(c, "cannot allocate %d bytes of memory for bulk-read, disabling it", c->max_bu_buf_len); c->mount_opts.bulk_read = 1; c->bulk_read = 0; return; } } /** * check_free_space - check if there is enough free space to mount. * @c: UBIFS file-system description object * * This function makes sure UBIFS has enough free space to be mounted in * read/write mode. UBIFS must always have some free space to allow deletions. */ static int check_free_space(struct ubifs_info *c) { ubifs_assert(c, c->dark_wm > 0); if (c->lst.total_free + c->lst.total_dirty < c->dark_wm) { ubifs_err(c, "insufficient free space to mount in R/W mode"); ubifs_dump_budg(c, &c->bi); ubifs_dump_lprops(c); return -ENOSPC; } return 0; } /** * mount_ubifs - mount UBIFS file-system. * @c: UBIFS file-system description object * * This function mounts UBIFS file system. Returns zero in case of success and * a negative error code in case of failure. */ static int mount_ubifs(struct ubifs_info *c) { int err; long long x, y; size_t sz; c->ro_mount = !!sb_rdonly(c->vfs_sb); /* Suppress error messages while probing if SB_SILENT is set */ c->probing = !!(c->vfs_sb->s_flags & SB_SILENT); err = init_constants_early(c); if (err) return err; err = ubifs_debugging_init(c); if (err) return err; err = ubifs_sysfs_register(c); if (err) goto out_debugging; err = check_volume_empty(c); if (err) goto out_free; if (c->empty && (c->ro_mount || c->ro_media)) { /* * This UBI volume is empty, and read-only, or the file system * is mounted read-only - we cannot format it. */ ubifs_err(c, "can't format empty UBI volume: read-only %s", c->ro_media ? "UBI volume" : "mount"); err = -EROFS; goto out_free; } if (c->ro_media && !c->ro_mount) { ubifs_err(c, "cannot mount read-write - read-only media"); err = -EROFS; goto out_free; } /* * The requirement for the buffer is that it should fit indexing B-tree * height amount of integers. We assume the height if the TNC tree will * never exceed 64. */ err = -ENOMEM; c->bottom_up_buf = kmalloc_array(BOTTOM_UP_HEIGHT, sizeof(int), GFP_KERNEL); if (!c->bottom_up_buf) goto out_free; c->sbuf = vmalloc(c->leb_size); if (!c->sbuf) goto out_free; if (!c->ro_mount) { c->ileb_buf = vmalloc(c->leb_size); if (!c->ileb_buf) goto out_free; } if (c->bulk_read == 1) bu_init(c); if (!c->ro_mount) { c->write_reserve_buf = kmalloc(COMPRESSED_DATA_NODE_BUF_SZ + \ UBIFS_CIPHER_BLOCK_SIZE, GFP_KERNEL); if (!c->write_reserve_buf) goto out_free; } c->mounting = 1; if (c->auth_key_name) { if (IS_ENABLED(CONFIG_UBIFS_FS_AUTHENTICATION)) { err = ubifs_init_authentication(c); if (err) goto out_free; } else { ubifs_err(c, "auth_key_name, but UBIFS is built without" " authentication support"); err = -EINVAL; goto out_free; } } err = ubifs_read_superblock(c); if (err) goto out_auth; c->probing = 0; /* * Make sure the compressor which is set as default in the superblock * or overridden by mount options is actually compiled in. */ if (!ubifs_compr_present(c, c->default_compr)) { ubifs_err(c, "'compressor \"%s\" is not compiled in", ubifs_compr_name(c, c->default_compr)); err = -ENOTSUPP; goto out_auth; } err = init_constants_sb(c); if (err) goto out_auth; sz = ALIGN(c->max_idx_node_sz, c->min_io_size) * 2; c->cbuf = kmalloc(sz, GFP_NOFS); if (!c->cbuf) { err = -ENOMEM; goto out_auth; } err = alloc_wbufs(c); if (err) goto out_cbuf; sprintf(c->bgt_name, BGT_NAME_PATTERN, c->vi.ubi_num, c->vi.vol_id); if (!c->ro_mount) { /* Create background thread */ c->bgt = kthread_run(ubifs_bg_thread, c, "%s", c->bgt_name); if (IS_ERR(c->bgt)) { err = PTR_ERR(c->bgt); c->bgt = NULL; ubifs_err(c, "cannot spawn \"%s\", error %d", c->bgt_name, err); goto out_wbufs; } } err = ubifs_read_master(c); if (err) goto out_master; init_constants_master(c); if ((c->mst_node->flags & cpu_to_le32(UBIFS_MST_DIRTY)) != 0) { ubifs_msg(c, "recovery needed"); c->need_recovery = 1; } if (c->need_recovery && !c->ro_mount) { err = ubifs_recover_inl_heads(c, c->sbuf); if (err) goto out_master; } err = ubifs_lpt_init(c, 1, !c->ro_mount); if (err) goto out_master; if (!c->ro_mount && c->space_fixup) { err = ubifs_fixup_free_space(c); if (err) goto out_lpt; } if (!c->ro_mount && !c->need_recovery) { /* * Set the "dirty" flag so that if we reboot uncleanly we * will notice this immediately on the next mount. */ c->mst_node->flags |= cpu_to_le32(UBIFS_MST_DIRTY); err = ubifs_write_master(c); if (err) goto out_lpt; } /* * Handle offline signed images: Now that the master node is * written and its validation no longer depends on the hash * in the superblock, we can update the offline signed * superblock with a HMAC version, */ if (ubifs_authenticated(c) && ubifs_hmac_zero(c, c->sup_node->hmac)) { err = ubifs_hmac_wkm(c, c->sup_node->hmac_wkm); if (err) goto out_lpt; c->superblock_need_write = 1; } if (!c->ro_mount && c->superblock_need_write) { err = ubifs_write_sb_node(c, c->sup_node); if (err) goto out_lpt; c->superblock_need_write = 0; } err = dbg_check_idx_size(c, c->bi.old_idx_sz); if (err) goto out_lpt; err = ubifs_replay_journal(c); if (err) goto out_journal; /* Calculate 'min_idx_lebs' after journal replay */ c->bi.min_idx_lebs = ubifs_calc_min_idx_lebs(c); err = ubifs_mount_orphans(c, c->need_recovery, c->ro_mount); if (err) goto out_orphans; if (!c->ro_mount) { int lnum; err = check_free_space(c); if (err) goto out_orphans; /* Check for enough log space */ lnum = c->lhead_lnum + 1; if (lnum >= UBIFS_LOG_LNUM + c->log_lebs) lnum = UBIFS_LOG_LNUM; if (lnum == c->ltail_lnum) { err = ubifs_consolidate_log(c); if (err) goto out_orphans; } if (c->need_recovery) { if (!ubifs_authenticated(c)) { err = ubifs_recover_size(c, true); if (err) goto out_orphans; } err = ubifs_rcvry_gc_commit(c); if (err) goto out_orphans; if (ubifs_authenticated(c)) { err = ubifs_recover_size(c, false); if (err) goto out_orphans; } } else { err = take_gc_lnum(c); if (err) goto out_orphans; /* * GC LEB may contain garbage if there was an unclean * reboot, and it should be un-mapped. */ err = ubifs_leb_unmap(c, c->gc_lnum); if (err) goto out_orphans; } err = dbg_check_lprops(c); if (err) goto out_orphans; } else if (c->need_recovery) { err = ubifs_recover_size(c, false); if (err) goto out_orphans; } else { /* * Even if we mount read-only, we have to set space in GC LEB * to proper value because this affects UBIFS free space * reporting. We do not want to have a situation when * re-mounting from R/O to R/W changes amount of free space. */ err = take_gc_lnum(c); if (err) goto out_orphans; } spin_lock(&ubifs_infos_lock); list_add_tail(&c->infos_list, &ubifs_infos); spin_unlock(&ubifs_infos_lock); if (c->need_recovery) { if (c->ro_mount) ubifs_msg(c, "recovery deferred"); else { c->need_recovery = 0; ubifs_msg(c, "recovery completed"); /* * GC LEB has to be empty and taken at this point. But * the journal head LEBs may also be accounted as * "empty taken" if they are empty. */ ubifs_assert(c, c->lst.taken_empty_lebs > 0); } } else ubifs_assert(c, c->lst.taken_empty_lebs > 0); err = dbg_check_filesystem(c); if (err) goto out_infos; dbg_debugfs_init_fs(c); c->mounting = 0; ubifs_msg(c, "UBIFS: mounted UBI device %d, volume %d, name \"%s\"%s", c->vi.ubi_num, c->vi.vol_id, c->vi.name, c->ro_mount ? ", R/O mode" : ""); x = (long long)c->main_lebs * c->leb_size; y = (long long)c->log_lebs * c->leb_size + c->max_bud_bytes; ubifs_msg(c, "LEB size: %d bytes (%d KiB), min./max. I/O unit sizes: %d bytes/%d bytes", c->leb_size, c->leb_size >> 10, c->min_io_size, c->max_write_size); ubifs_msg(c, "FS size: %lld bytes (%lld MiB, %d LEBs), max %d LEBs, journal size %lld bytes (%lld MiB, %d LEBs)", x, x >> 20, c->main_lebs, c->max_leb_cnt, y, y >> 20, c->log_lebs + c->max_bud_cnt); ubifs_msg(c, "reserved for root: %llu bytes (%llu KiB)", c->report_rp_size, c->report_rp_size >> 10); ubifs_msg(c, "media format: w%d/r%d (latest is w%d/r%d), UUID %pUB%s", c->fmt_version, c->ro_compat_version, UBIFS_FORMAT_VERSION, UBIFS_RO_COMPAT_VERSION, c->uuid, c->big_lpt ? ", big LPT model" : ", small LPT model"); dbg_gen("default compressor: %s", ubifs_compr_name(c, c->default_compr)); dbg_gen("data journal heads: %d", c->jhead_cnt - NONDATA_JHEADS_CNT); dbg_gen("log LEBs: %d (%d - %d)", c->log_lebs, UBIFS_LOG_LNUM, c->log_last); dbg_gen("LPT area LEBs: %d (%d - %d)", c->lpt_lebs, c->lpt_first, c->lpt_last); dbg_gen("orphan area LEBs: %d (%d - %d)", c->orph_lebs, c->orph_first, c->orph_last); dbg_gen("main area LEBs: %d (%d - %d)", c->main_lebs, c->main_first, c->leb_cnt - 1); dbg_gen("index LEBs: %d", c->lst.idx_lebs); dbg_gen("total index bytes: %llu (%llu KiB, %llu MiB)", c->bi.old_idx_sz, c->bi.old_idx_sz >> 10, c->bi.old_idx_sz >> 20); dbg_gen("key hash type: %d", c->key_hash_type); dbg_gen("tree fanout: %d", c->fanout); dbg_gen("reserved GC LEB: %d", c->gc_lnum); dbg_gen("max. znode size %d", c->max_znode_sz); dbg_gen("max. index node size %d", c->max_idx_node_sz); dbg_gen("node sizes: data %zu, inode %zu, dentry %zu", UBIFS_DATA_NODE_SZ, UBIFS_INO_NODE_SZ, UBIFS_DENT_NODE_SZ); dbg_gen("node sizes: trun %zu, sb %zu, master %zu", UBIFS_TRUN_NODE_SZ, UBIFS_SB_NODE_SZ, UBIFS_MST_NODE_SZ); dbg_gen("node sizes: ref %zu, cmt. start %zu, orph %zu", UBIFS_REF_NODE_SZ, UBIFS_CS_NODE_SZ, UBIFS_ORPH_NODE_SZ); dbg_gen("max. node sizes: data %zu, inode %zu dentry %zu, idx %d", UBIFS_MAX_DATA_NODE_SZ, UBIFS_MAX_INO_NODE_SZ, UBIFS_MAX_DENT_NODE_SZ, ubifs_idx_node_sz(c, c->fanout)); dbg_gen("dead watermark: %d", c->dead_wm); dbg_gen("dark watermark: %d", c->dark_wm); dbg_gen("LEB overhead: %d", c->leb_overhead); x = (long long)c->main_lebs * c->dark_wm; dbg_gen("max. dark space: %lld (%lld KiB, %lld MiB)", x, x >> 10, x >> 20); dbg_gen("maximum bud bytes: %lld (%lld KiB, %lld MiB)", c->max_bud_bytes, c->max_bud_bytes >> 10, c->max_bud_bytes >> 20); dbg_gen("BG commit bud bytes: %lld (%lld KiB, %lld MiB)", c->bg_bud_bytes, c->bg_bud_bytes >> 10, c->bg_bud_bytes >> 20); dbg_gen("current bud bytes %lld (%lld KiB, %lld MiB)", c->bud_bytes, c->bud_bytes >> 10, c->bud_bytes >> 20); dbg_gen("max. seq. number: %llu", c->max_sqnum); dbg_gen("commit number: %llu", c->cmt_no); dbg_gen("max. xattrs per inode: %d", ubifs_xattr_max_cnt(c)); dbg_gen("max orphans: %d", c->max_orphans); return 0; out_infos: spin_lock(&ubifs_infos_lock); list_del(&c->infos_list); spin_unlock(&ubifs_infos_lock); out_orphans: free_orphans(c); out_journal: destroy_journal(c); out_lpt: ubifs_lpt_free(c, 0); out_master: kfree(c->mst_node); kfree(c->rcvrd_mst_node); if (c->bgt) kthread_stop(c->bgt); out_wbufs: free_wbufs(c); out_cbuf: kfree(c->cbuf); out_auth: ubifs_exit_authentication(c); out_free: kfree(c->write_reserve_buf); kfree(c->bu.buf); vfree(c->ileb_buf); vfree(c->sbuf); kfree(c->bottom_up_buf); kfree(c->sup_node); ubifs_sysfs_unregister(c); out_debugging: ubifs_debugging_exit(c); return err; } /** * ubifs_umount - un-mount UBIFS file-system. * @c: UBIFS file-system description object * * Note, this function is called to free allocated resourced when un-mounting, * as well as free resources when an error occurred while we were half way * through mounting (error path cleanup function). So it has to make sure the * resource was actually allocated before freeing it. */ static void ubifs_umount(struct ubifs_info *c) { dbg_gen("un-mounting UBI device %d, volume %d", c->vi.ubi_num, c->vi.vol_id); dbg_debugfs_exit_fs(c); spin_lock(&ubifs_infos_lock); list_del(&c->infos_list); spin_unlock(&ubifs_infos_lock); if (c->bgt) kthread_stop(c->bgt); destroy_journal(c); free_wbufs(c); free_orphans(c); ubifs_lpt_free(c, 0); ubifs_exit_authentication(c); ubifs_release_options(c); kfree(c->cbuf); kfree(c->rcvrd_mst_node); kfree(c->mst_node); kfree(c->write_reserve_buf); kfree(c->bu.buf); vfree(c->ileb_buf); vfree(c->sbuf); kfree(c->bottom_up_buf); kfree(c->sup_node); ubifs_debugging_exit(c); ubifs_sysfs_unregister(c); } /** * ubifs_remount_rw - re-mount in read-write mode. * @c: UBIFS file-system description object * * UBIFS avoids allocating many unnecessary resources when mounted in read-only * mode. This function allocates the needed resources and re-mounts UBIFS in * read-write mode. */ static int ubifs_remount_rw(struct ubifs_info *c) { int err, lnum; if (c->rw_incompat) { ubifs_err(c, "the file-system is not R/W-compatible"); ubifs_msg(c, "on-flash format version is w%d/r%d, but software only supports up to version w%d/r%d", c->fmt_version, c->ro_compat_version, UBIFS_FORMAT_VERSION, UBIFS_RO_COMPAT_VERSION); return -EROFS; } mutex_lock(&c->umount_mutex); dbg_save_space_info(c); c->remounting_rw = 1; c->ro_mount = 0; if (c->space_fixup) { err = ubifs_fixup_free_space(c); if (err) goto out; } err = check_free_space(c); if (err) goto out; if (c->need_recovery) { ubifs_msg(c, "completing deferred recovery"); err = ubifs_write_rcvrd_mst_node(c); if (err) goto out; if (!ubifs_authenticated(c)) { err = ubifs_recover_size(c, true); if (err) goto out; } err = ubifs_clean_lebs(c, c->sbuf); if (err) goto out; err = ubifs_recover_inl_heads(c, c->sbuf); if (err) goto out; } else { /* A readonly mount is not allowed to have orphans */ ubifs_assert(c, c->tot_orphans == 0); err = ubifs_clear_orphans(c); if (err) goto out; } if (!(c->mst_node->flags & cpu_to_le32(UBIFS_MST_DIRTY))) { c->mst_node->flags |= cpu_to_le32(UBIFS_MST_DIRTY); err = ubifs_write_master(c); if (err) goto out; } if (c->superblock_need_write) { struct ubifs_sb_node *sup = c->sup_node; err = ubifs_write_sb_node(c, sup); if (err) goto out; c->superblock_need_write = 0; } c->ileb_buf = vmalloc(c->leb_size); if (!c->ileb_buf) { err = -ENOMEM; goto out; } c->write_reserve_buf = kmalloc(COMPRESSED_DATA_NODE_BUF_SZ + \ UBIFS_CIPHER_BLOCK_SIZE, GFP_KERNEL); if (!c->write_reserve_buf) { err = -ENOMEM; goto out; } err = ubifs_lpt_init(c, 0, 1); if (err) goto out; /* Create background thread */ c->bgt = kthread_run(ubifs_bg_thread, c, "%s", c->bgt_name); if (IS_ERR(c->bgt)) { err = PTR_ERR(c->bgt); c->bgt = NULL; ubifs_err(c, "cannot spawn \"%s\", error %d", c->bgt_name, err); goto out; } c->orph_buf = vmalloc(c->leb_size); if (!c->orph_buf) { err = -ENOMEM; goto out; } /* Check for enough log space */ lnum = c->lhead_lnum + 1; if (lnum >= UBIFS_LOG_LNUM + c->log_lebs) lnum = UBIFS_LOG_LNUM; if (lnum == c->ltail_lnum) { err = ubifs_consolidate_log(c); if (err) goto out; } if (c->need_recovery) { err = ubifs_rcvry_gc_commit(c); if (err) goto out; if (ubifs_authenticated(c)) { err = ubifs_recover_size(c, false); if (err) goto out; } } else { err = ubifs_leb_unmap(c, c->gc_lnum); } if (err) goto out; dbg_gen("re-mounted read-write"); c->remounting_rw = 0; if (c->need_recovery) { c->need_recovery = 0; ubifs_msg(c, "deferred recovery completed"); } else { /* * Do not run the debugging space check if the were doing * recovery, because when we saved the information we had the * file-system in a state where the TNC and lprops has been * modified in memory, but all the I/O operations (including a * commit) were deferred. So the file-system was in * "non-committed" state. Now the file-system is in committed * state, and of course the amount of free space will change * because, for example, the old index size was imprecise. */ err = dbg_check_space_info(c); } mutex_unlock(&c->umount_mutex); return err; out: c->ro_mount = 1; vfree(c->orph_buf); c->orph_buf = NULL; if (c->bgt) { kthread_stop(c->bgt); c->bgt = NULL; } kfree(c->write_reserve_buf); c->write_reserve_buf = NULL; vfree(c->ileb_buf); c->ileb_buf = NULL; ubifs_lpt_free(c, 1); c->remounting_rw = 0; mutex_unlock(&c->umount_mutex); return err; } /** * ubifs_remount_ro - re-mount in read-only mode. * @c: UBIFS file-system description object * * We assume VFS has stopped writing. Possibly the background thread could be * running a commit, however kthread_stop will wait in that case. */ static void ubifs_remount_ro(struct ubifs_info *c) { int i, err; ubifs_assert(c, !c->need_recovery); ubifs_assert(c, !c->ro_mount); mutex_lock(&c->umount_mutex); if (c->bgt) { kthread_stop(c->bgt); c->bgt = NULL; } dbg_save_space_info(c); for (i = 0; i < c->jhead_cnt; i++) { err = ubifs_wbuf_sync(&c->jheads[i].wbuf); if (err) ubifs_ro_mode(c, err); } c->mst_node->flags &= ~cpu_to_le32(UBIFS_MST_DIRTY); c->mst_node->flags |= cpu_to_le32(UBIFS_MST_NO_ORPHS); c->mst_node->gc_lnum = cpu_to_le32(c->gc_lnum); err = ubifs_write_master(c); if (err) ubifs_ro_mode(c, err); vfree(c->orph_buf); c->orph_buf = NULL; kfree(c->write_reserve_buf); c->write_reserve_buf = NULL; vfree(c->ileb_buf); c->ileb_buf = NULL; ubifs_lpt_free(c, 1); c->ro_mount = 1; err = dbg_check_space_info(c); if (err) ubifs_ro_mode(c, err); mutex_unlock(&c->umount_mutex); } static void ubifs_put_super(struct super_block *sb) { int i; struct ubifs_info *c = sb->s_fs_info; ubifs_msg(c, "un-mount UBI device %d", c->vi.ubi_num); /* * The following asserts are only valid if there has not been a failure * of the media. For example, there will be dirty inodes if we failed * to write them back because of I/O errors. */ if (!c->ro_error) { ubifs_assert(c, c->bi.idx_growth == 0); ubifs_assert(c, c->bi.dd_growth == 0); ubifs_assert(c, c->bi.data_growth == 0); } /* * The 'c->umount_lock' prevents races between UBIFS memory shrinker * and file system un-mount. Namely, it prevents the shrinker from * picking this superblock for shrinking - it will be just skipped if * the mutex is locked. */ mutex_lock(&c->umount_mutex); if (!c->ro_mount) { /* * First of all kill the background thread to make sure it does * not interfere with un-mounting and freeing resources. */ if (c->bgt) { kthread_stop(c->bgt); c->bgt = NULL; } /* * On fatal errors c->ro_error is set to 1, in which case we do * not write the master node. */ if (!c->ro_error) { int err; /* Synchronize write-buffers */ for (i = 0; i < c->jhead_cnt; i++) { err = ubifs_wbuf_sync(&c->jheads[i].wbuf); if (err) ubifs_ro_mode(c, err); } /* * We are being cleanly unmounted which means the * orphans were killed - indicate this in the master * node. Also save the reserved GC LEB number. */ c->mst_node->flags &= ~cpu_to_le32(UBIFS_MST_DIRTY); c->mst_node->flags |= cpu_to_le32(UBIFS_MST_NO_ORPHS); c->mst_node->gc_lnum = cpu_to_le32(c->gc_lnum); err = ubifs_write_master(c); if (err) /* * Recovery will attempt to fix the master area * next mount, so we just print a message and * continue to unmount normally. */ ubifs_err(c, "failed to write master node, error %d", err); } else { for (i = 0; i < c->jhead_cnt; i++) /* Make sure write-buffer timers are canceled */ hrtimer_cancel(&c->jheads[i].wbuf.timer); } } ubifs_umount(c); ubi_close_volume(c->ubi); mutex_unlock(&c->umount_mutex); } static int ubifs_remount_fs(struct super_block *sb, int *flags, char *data) { int err; struct ubifs_info *c = sb->s_fs_info; sync_filesystem(sb); dbg_gen("old flags %#lx, new flags %#x", sb->s_flags, *flags); err = ubifs_parse_options(c, data, 1); if (err) { ubifs_err(c, "invalid or unknown remount parameter"); return err; } if (c->ro_mount && !(*flags & SB_RDONLY)) { if (c->ro_error) { ubifs_msg(c, "cannot re-mount R/W due to prior errors"); return -EROFS; } if (c->ro_media) { ubifs_msg(c, "cannot re-mount R/W - UBI volume is R/O"); return -EROFS; } err = ubifs_remount_rw(c); if (err) return err; } else if (!c->ro_mount && (*flags & SB_RDONLY)) { if (c->ro_error) { ubifs_msg(c, "cannot re-mount R/O due to prior errors"); return -EROFS; } ubifs_remount_ro(c); } if (c->bulk_read == 1) bu_init(c); else { dbg_gen("disable bulk-read"); mutex_lock(&c->bu_mutex); kfree(c->bu.buf); c->bu.buf = NULL; mutex_unlock(&c->bu_mutex); } if (!c->need_recovery) ubifs_assert(c, c->lst.taken_empty_lebs > 0); return 0; } const struct super_operations ubifs_super_operations = { .alloc_inode = ubifs_alloc_inode, .free_inode = ubifs_free_inode, .put_super = ubifs_put_super, .write_inode = ubifs_write_inode, .drop_inode = ubifs_drop_inode, .evict_inode = ubifs_evict_inode, .statfs = ubifs_statfs, .dirty_inode = ubifs_dirty_inode, .remount_fs = ubifs_remount_fs, .show_options = ubifs_show_options, .sync_fs = ubifs_sync_fs, }; /** * open_ubi - parse UBI device name string and open the UBI device. * @name: UBI volume name * @mode: UBI volume open mode * * The primary method of mounting UBIFS is by specifying the UBI volume * character device node path. However, UBIFS may also be mounted without any * character device node using one of the following methods: * * o ubiX_Y - mount UBI device number X, volume Y; * o ubiY - mount UBI device number 0, volume Y; * o ubiX:NAME - mount UBI device X, volume with name NAME; * o ubi:NAME - mount UBI device 0, volume with name NAME. * * Alternative '!' separator may be used instead of ':' (because some shells * like busybox may interpret ':' as an NFS host name separator). This function * returns UBI volume description object in case of success and a negative * error code in case of failure. */ static struct ubi_volume_desc *open_ubi(const char *name, int mode) { struct ubi_volume_desc *ubi; int dev, vol; char *endptr; if (!name || !*name) return ERR_PTR(-EINVAL); /* First, try to open using the device node path method */ ubi = ubi_open_volume_path(name, mode); if (!IS_ERR(ubi)) return ubi; /* Try the "nodev" method */ if (name[0] != 'u' || name[1] != 'b' || name[2] != 'i') return ERR_PTR(-EINVAL); /* ubi:NAME method */ if ((name[3] == ':' || name[3] == '!') && name[4] != '\0') return ubi_open_volume_nm(0, name + 4, mode); if (!isdigit(name[3])) return ERR_PTR(-EINVAL); dev = simple_strtoul(name + 3, &endptr, 0); /* ubiY method */ if (*endptr == '\0') return ubi_open_volume(0, dev, mode); /* ubiX_Y method */ if (*endptr == '_' && isdigit(endptr[1])) { vol = simple_strtoul(endptr + 1, &endptr, 0); if (*endptr != '\0') return ERR_PTR(-EINVAL); return ubi_open_volume(dev, vol, mode); } /* ubiX:NAME method */ if ((*endptr == ':' || *endptr == '!') && endptr[1] != '\0') return ubi_open_volume_nm(dev, ++endptr, mode); return ERR_PTR(-EINVAL); } static struct ubifs_info *alloc_ubifs_info(struct ubi_volume_desc *ubi) { struct ubifs_info *c; c = kzalloc(sizeof(struct ubifs_info), GFP_KERNEL); if (c) { spin_lock_init(&c->cnt_lock); spin_lock_init(&c->cs_lock); spin_lock_init(&c->buds_lock); spin_lock_init(&c->space_lock); spin_lock_init(&c->orphan_lock); init_rwsem(&c->commit_sem); mutex_init(&c->lp_mutex); mutex_init(&c->tnc_mutex); mutex_init(&c->log_mutex); mutex_init(&c->umount_mutex); mutex_init(&c->bu_mutex); mutex_init(&c->write_reserve_mutex); init_waitqueue_head(&c->cmt_wq); init_waitqueue_head(&c->reserve_space_wq); atomic_set(&c->need_wait_space, 0); c->buds = RB_ROOT; c->old_idx = RB_ROOT; c->size_tree = RB_ROOT; c->orph_tree = RB_ROOT; INIT_LIST_HEAD(&c->infos_list); INIT_LIST_HEAD(&c->idx_gc); INIT_LIST_HEAD(&c->replay_list); INIT_LIST_HEAD(&c->replay_buds); INIT_LIST_HEAD(&c->uncat_list); INIT_LIST_HEAD(&c->empty_list); INIT_LIST_HEAD(&c->freeable_list); INIT_LIST_HEAD(&c->frdi_idx_list); INIT_LIST_HEAD(&c->unclean_leb_list); INIT_LIST_HEAD(&c->old_buds); INIT_LIST_HEAD(&c->orph_list); INIT_LIST_HEAD(&c->orph_new); c->no_chk_data_crc = 1; c->assert_action = ASSACT_RO; c->highest_inum = UBIFS_FIRST_INO; c->lhead_lnum = c->ltail_lnum = UBIFS_LOG_LNUM; ubi_get_volume_info(ubi, &c->vi); ubi_get_device_info(c->vi.ubi_num, &c->di); } return c; } static int ubifs_fill_super(struct super_block *sb, void *data, int silent) { struct ubifs_info *c = sb->s_fs_info; struct inode *root; int err; c->vfs_sb = sb; /* Re-open the UBI device in read-write mode */ c->ubi = ubi_open_volume(c->vi.ubi_num, c->vi.vol_id, UBI_READWRITE); if (IS_ERR(c->ubi)) { err = PTR_ERR(c->ubi); goto out; } err = ubifs_parse_options(c, data, 0); if (err) goto out_close; /* * UBIFS provides 'backing_dev_info' in order to disable read-ahead. For * UBIFS, I/O is not deferred, it is done immediately in read_folio, * which means the user would have to wait not just for their own I/O * but the read-ahead I/O as well i.e. completely pointless. * * Read-ahead will be disabled because @sb->s_bdi->ra_pages is 0. Also * @sb->s_bdi->capabilities are initialized to 0 so there won't be any * writeback happening. */ err = super_setup_bdi_name(sb, "ubifs_%d_%d", c->vi.ubi_num, c->vi.vol_id); if (err) goto out_close; sb->s_bdi->ra_pages = 0; sb->s_bdi->io_pages = 0; sb->s_fs_info = c; sb->s_magic = UBIFS_SUPER_MAGIC; sb->s_blocksize = UBIFS_BLOCK_SIZE; sb->s_blocksize_bits = UBIFS_BLOCK_SHIFT; sb->s_maxbytes = c->max_inode_sz = key_max_inode_size(c); if (c->max_inode_sz > MAX_LFS_FILESIZE) sb->s_maxbytes = c->max_inode_sz = MAX_LFS_FILESIZE; sb->s_op = &ubifs_super_operations; sb->s_xattr = ubifs_xattr_handlers; fscrypt_set_ops(sb, &ubifs_crypt_operations); mutex_lock(&c->umount_mutex); err = mount_ubifs(c); if (err) { ubifs_assert(c, err < 0); goto out_unlock; } /* Read the root inode */ root = ubifs_iget(sb, UBIFS_ROOT_INO); if (IS_ERR(root)) { err = PTR_ERR(root); goto out_umount; } generic_set_sb_d_ops(sb); sb->s_root = d_make_root(root); if (!sb->s_root) { err = -ENOMEM; goto out_umount; } super_set_uuid(sb, c->uuid, sizeof(c->uuid)); mutex_unlock(&c->umount_mutex); return 0; out_umount: ubifs_umount(c); out_unlock: mutex_unlock(&c->umount_mutex); out_close: ubifs_release_options(c); ubi_close_volume(c->ubi); out: return err; } static int sb_test(struct super_block *sb, void *data) { struct ubifs_info *c1 = data; struct ubifs_info *c = sb->s_fs_info; return c->vi.cdev == c1->vi.cdev; } static int sb_set(struct super_block *sb, void *data) { sb->s_fs_info = data; return set_anon_super(sb, NULL); } static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags, const char *name, void *data) { struct ubi_volume_desc *ubi; struct ubifs_info *c; struct super_block *sb; int err; dbg_gen("name %s, flags %#x", name, flags); /* * Get UBI device number and volume ID. Mount it read-only so far * because this might be a new mount point, and UBI allows only one * read-write user at a time. */ ubi = open_ubi(name, UBI_READONLY); if (IS_ERR(ubi)) { if (!(flags & SB_SILENT)) pr_err("UBIFS error (pid: %d): cannot open \"%s\", error %d", current->pid, name, (int)PTR_ERR(ubi)); return ERR_CAST(ubi); } c = alloc_ubifs_info(ubi); if (!c) { err = -ENOMEM; goto out_close; } dbg_gen("opened ubi%d_%d", c->vi.ubi_num, c->vi.vol_id); sb = sget(fs_type, sb_test, sb_set, flags, c); if (IS_ERR(sb)) { err = PTR_ERR(sb); kfree(c); goto out_close; } if (sb->s_root) { struct ubifs_info *c1 = sb->s_fs_info; kfree(c); /* A new mount point for already mounted UBIFS */ dbg_gen("this ubi volume is already mounted"); if (!!(flags & SB_RDONLY) != c1->ro_mount) { err = -EBUSY; goto out_deact; } } else { err = ubifs_fill_super(sb, data, flags & SB_SILENT ? 1 : 0); if (err) goto out_deact; /* We do not support atime */ sb->s_flags |= SB_ACTIVE; if (IS_ENABLED(CONFIG_UBIFS_ATIME_SUPPORT)) ubifs_msg(c, "full atime support is enabled."); else sb->s_flags |= SB_NOATIME; } /* 'fill_super()' opens ubi again so we must close it here */ ubi_close_volume(ubi); return dget(sb->s_root); out_deact: deactivate_locked_super(sb); out_close: ubi_close_volume(ubi); return ERR_PTR(err); } static void kill_ubifs_super(struct super_block *s) { struct ubifs_info *c = s->s_fs_info; kill_anon_super(s); kfree(c); } static struct file_system_type ubifs_fs_type = { .name = "ubifs", .owner = THIS_MODULE, .mount = ubifs_mount, .kill_sb = kill_ubifs_super, }; MODULE_ALIAS_FS("ubifs"); /* * Inode slab cache constructor. */ static void inode_slab_ctor(void *obj) { struct ubifs_inode *ui = obj; inode_init_once(&ui->vfs_inode); } static int __init ubifs_init(void) { int err = -ENOMEM; BUILD_BUG_ON(sizeof(struct ubifs_ch) != 24); /* Make sure node sizes are 8-byte aligned */ BUILD_BUG_ON(UBIFS_CH_SZ & 7); BUILD_BUG_ON(UBIFS_INO_NODE_SZ & 7); BUILD_BUG_ON(UBIFS_DENT_NODE_SZ & 7); BUILD_BUG_ON(UBIFS_XENT_NODE_SZ & 7); BUILD_BUG_ON(UBIFS_DATA_NODE_SZ & 7); BUILD_BUG_ON(UBIFS_TRUN_NODE_SZ & 7); BUILD_BUG_ON(UBIFS_SB_NODE_SZ & 7); BUILD_BUG_ON(UBIFS_MST_NODE_SZ & 7); BUILD_BUG_ON(UBIFS_REF_NODE_SZ & 7); BUILD_BUG_ON(UBIFS_CS_NODE_SZ & 7); BUILD_BUG_ON(UBIFS_ORPH_NODE_SZ & 7); BUILD_BUG_ON(UBIFS_MAX_DENT_NODE_SZ & 7); BUILD_BUG_ON(UBIFS_MAX_XENT_NODE_SZ & 7); BUILD_BUG_ON(UBIFS_MAX_DATA_NODE_SZ & 7); BUILD_BUG_ON(UBIFS_MAX_INO_NODE_SZ & 7); BUILD_BUG_ON(UBIFS_MAX_NODE_SZ & 7); BUILD_BUG_ON(MIN_WRITE_SZ & 7); /* Check min. node size */ BUILD_BUG_ON(UBIFS_INO_NODE_SZ < MIN_WRITE_SZ); BUILD_BUG_ON(UBIFS_DENT_NODE_SZ < MIN_WRITE_SZ); BUILD_BUG_ON(UBIFS_XENT_NODE_SZ < MIN_WRITE_SZ); BUILD_BUG_ON(UBIFS_TRUN_NODE_SZ < MIN_WRITE_SZ); BUILD_BUG_ON(UBIFS_MAX_DENT_NODE_SZ > UBIFS_MAX_NODE_SZ); BUILD_BUG_ON(UBIFS_MAX_XENT_NODE_SZ > UBIFS_MAX_NODE_SZ); BUILD_BUG_ON(UBIFS_MAX_DATA_NODE_SZ > UBIFS_MAX_NODE_SZ); BUILD_BUG_ON(UBIFS_MAX_INO_NODE_SZ > UBIFS_MAX_NODE_SZ); /* Defined node sizes */ BUILD_BUG_ON(UBIFS_SB_NODE_SZ != 4096); BUILD_BUG_ON(UBIFS_MST_NODE_SZ != 512); BUILD_BUG_ON(UBIFS_INO_NODE_SZ != 160); BUILD_BUG_ON(UBIFS_REF_NODE_SZ != 64); /* * We use 2 bit wide bit-fields to store compression type, which should * be amended if more compressors are added. The bit-fields are: * @compr_type in 'struct ubifs_inode', @default_compr in * 'struct ubifs_info' and @compr_type in 'struct ubifs_mount_opts'. */ BUILD_BUG_ON(UBIFS_COMPR_TYPES_CNT > 4); /* * We require that PAGE_SIZE is greater-than-or-equal-to * UBIFS_BLOCK_SIZE. It is assumed that both are powers of 2. */ if (PAGE_SIZE < UBIFS_BLOCK_SIZE) { pr_err("UBIFS error (pid %d): VFS page cache size is %u bytes, but UBIFS requires at least 4096 bytes", current->pid, (unsigned int)PAGE_SIZE); return -EINVAL; } ubifs_inode_slab = kmem_cache_create("ubifs_inode_slab", sizeof(struct ubifs_inode), 0, SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT, &inode_slab_ctor); if (!ubifs_inode_slab) return -ENOMEM; ubifs_shrinker_info = shrinker_alloc(0, "ubifs-slab"); if (!ubifs_shrinker_info) goto out_slab; ubifs_shrinker_info->count_objects = ubifs_shrink_count; ubifs_shrinker_info->scan_objects = ubifs_shrink_scan; shrinker_register(ubifs_shrinker_info); err = ubifs_compressors_init(); if (err) goto out_shrinker; dbg_debugfs_init(); err = ubifs_sysfs_init(); if (err) goto out_dbg; err = register_filesystem(&ubifs_fs_type); if (err) { pr_err("UBIFS error (pid %d): cannot register file system, error %d", current->pid, err); goto out_sysfs; } return 0; out_sysfs: ubifs_sysfs_exit(); out_dbg: dbg_debugfs_exit(); ubifs_compressors_exit(); out_shrinker: shrinker_free(ubifs_shrinker_info); out_slab: kmem_cache_destroy(ubifs_inode_slab); return err; } /* late_initcall to let compressors initialize first */ late_initcall(ubifs_init); static void __exit ubifs_exit(void) { WARN_ON(!list_empty(&ubifs_infos)); WARN_ON(atomic_long_read(&ubifs_clean_zn_cnt) != 0); dbg_debugfs_exit(); ubifs_sysfs_exit(); ubifs_compressors_exit(); shrinker_free(ubifs_shrinker_info); /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(ubifs_inode_slab); unregister_filesystem(&ubifs_fs_type); } module_exit(ubifs_exit); MODULE_LICENSE("GPL"); MODULE_VERSION(__stringify(UBIFS_VERSION)); MODULE_AUTHOR("Artem Bityutskiy, Adrian Hunter"); MODULE_DESCRIPTION("UBIFS - UBI File System"); |
| 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 | // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" #include "alloc_foreground.h" #include "bkey_buf.h" #include "bkey_methods.h" #include "btree_cache.h" #include "btree_gc.h" #include "btree_journal_iter.h" #include "btree_update.h" #include "btree_update_interior.h" #include "btree_io.h" #include "btree_iter.h" #include "btree_locking.h" #include "buckets.h" #include "clock.h" #include "error.h" #include "extents.h" #include "journal.h" #include "journal_reclaim.h" #include "keylist.h" #include "recovery_passes.h" #include "replicas.h" #include "sb-members.h" #include "super-io.h" #include "trace.h" #include <linux/random.h> static const char * const bch2_btree_update_modes[] = { #define x(t) #t, BTREE_UPDATE_MODES() #undef x NULL }; static int bch2_btree_insert_node(struct btree_update *, struct btree_trans *, btree_path_idx_t, struct btree *, struct keylist *); static void bch2_btree_update_add_new_node(struct btree_update *, struct btree *); /* * Verify that child nodes correctly span parent node's range: */ int bch2_btree_node_check_topology(struct btree_trans *trans, struct btree *b) { struct bch_fs *c = trans->c; struct bpos node_min = b->key.k.type == KEY_TYPE_btree_ptr_v2 ? bkey_i_to_btree_ptr_v2(&b->key)->v.min_key : b->data->min_key; struct btree_and_journal_iter iter; struct bkey_s_c k; struct printbuf buf = PRINTBUF; struct bkey_buf prev; int ret = 0; BUG_ON(b->key.k.type == KEY_TYPE_btree_ptr_v2 && !bpos_eq(bkey_i_to_btree_ptr_v2(&b->key)->v.min_key, b->data->min_key)); if (b == btree_node_root(c, b)) { if (!bpos_eq(b->data->min_key, POS_MIN)) { printbuf_reset(&buf); bch2_bpos_to_text(&buf, b->data->min_key); need_fsck_err(trans, btree_root_bad_min_key, "btree root with incorrect min_key: %s", buf.buf); goto topology_repair; } if (!bpos_eq(b->data->max_key, SPOS_MAX)) { printbuf_reset(&buf); bch2_bpos_to_text(&buf, b->data->max_key); need_fsck_err(trans, btree_root_bad_max_key, "btree root with incorrect max_key: %s", buf.buf); goto topology_repair; } } if (!b->c.level) return 0; bch2_bkey_buf_init(&prev); bkey_init(&prev.k->k); bch2_btree_and_journal_iter_init_node_iter(trans, &iter, b); while ((k = bch2_btree_and_journal_iter_peek(&iter)).k) { if (k.k->type != KEY_TYPE_btree_ptr_v2) goto out; struct bkey_s_c_btree_ptr_v2 bp = bkey_s_c_to_btree_ptr_v2(k); struct bpos expected_min = bkey_deleted(&prev.k->k) ? node_min : bpos_successor(prev.k->k.p); if (!bpos_eq(expected_min, bp.v->min_key)) { bch2_topology_error(c); printbuf_reset(&buf); prt_str(&buf, "end of prev node doesn't match start of next node\n"), prt_printf(&buf, " in btree %s level %u node ", bch2_btree_id_str(b->c.btree_id), b->c.level); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); prt_str(&buf, "\n prev "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(prev.k)); prt_str(&buf, "\n next "); bch2_bkey_val_to_text(&buf, c, k); need_fsck_err(trans, btree_node_topology_bad_min_key, "%s", buf.buf); goto topology_repair; } bch2_bkey_buf_reassemble(&prev, c, k); bch2_btree_and_journal_iter_advance(&iter); } if (bkey_deleted(&prev.k->k)) { bch2_topology_error(c); printbuf_reset(&buf); prt_str(&buf, "empty interior node\n"); prt_printf(&buf, " in btree %s level %u node ", bch2_btree_id_str(b->c.btree_id), b->c.level); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); need_fsck_err(trans, btree_node_topology_empty_interior_node, "%s", buf.buf); goto topology_repair; } else if (!bpos_eq(prev.k->k.p, b->key.k.p)) { bch2_topology_error(c); printbuf_reset(&buf); prt_str(&buf, "last child node doesn't end at end of parent node\n"); prt_printf(&buf, " in btree %s level %u node ", bch2_btree_id_str(b->c.btree_id), b->c.level); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); prt_str(&buf, "\n last key "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(prev.k)); need_fsck_err(trans, btree_node_topology_bad_max_key, "%s", buf.buf); goto topology_repair; } out: fsck_err: bch2_btree_and_journal_iter_exit(&iter); bch2_bkey_buf_exit(&prev, c); printbuf_exit(&buf); return ret; topology_repair: if ((c->recovery_passes_explicit & BIT_ULL(BCH_RECOVERY_PASS_check_topology)) && c->curr_recovery_pass > BCH_RECOVERY_PASS_check_topology) { bch2_inconsistent_error(c); ret = -BCH_ERR_btree_need_topology_repair; } else { ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_check_topology); } goto out; } /* Calculate ideal packed bkey format for new btree nodes: */ static void __bch2_btree_calc_format(struct bkey_format_state *s, struct btree *b) { struct bkey_packed *k; struct bkey uk; for_each_bset(b, t) bset_tree_for_each_key(b, t, k) if (!bkey_deleted(k)) { uk = bkey_unpack_key(b, k); bch2_bkey_format_add_key(s, &uk); } } static struct bkey_format bch2_btree_calc_format(struct btree *b) { struct bkey_format_state s; bch2_bkey_format_init(&s); bch2_bkey_format_add_pos(&s, b->data->min_key); bch2_bkey_format_add_pos(&s, b->data->max_key); __bch2_btree_calc_format(&s, b); return bch2_bkey_format_done(&s); } static size_t btree_node_u64s_with_format(struct btree_nr_keys nr, struct bkey_format *old_f, struct bkey_format *new_f) { /* stupid integer promotion rules */ ssize_t delta = (((int) new_f->key_u64s - old_f->key_u64s) * (int) nr.packed_keys) + (((int) new_f->key_u64s - BKEY_U64s) * (int) nr.unpacked_keys); BUG_ON(delta + nr.live_u64s < 0); return nr.live_u64s + delta; } /** * bch2_btree_node_format_fits - check if we could rewrite node with a new format * * @c: filesystem handle * @b: btree node to rewrite * @nr: number of keys for new node (i.e. b->nr) * @new_f: bkey format to translate keys to * * Returns: true if all re-packed keys will be able to fit in a new node. * * Assumes all keys will successfully pack with the new format. */ static bool bch2_btree_node_format_fits(struct bch_fs *c, struct btree *b, struct btree_nr_keys nr, struct bkey_format *new_f) { size_t u64s = btree_node_u64s_with_format(nr, &b->format, new_f); return __vstruct_bytes(struct btree_node, u64s) < btree_buf_bytes(b); } /* Btree node freeing/allocation: */ static void __btree_node_free(struct btree_trans *trans, struct btree *b) { struct bch_fs *c = trans->c; trace_and_count(c, btree_node_free, trans, b); BUG_ON(btree_node_write_blocked(b)); BUG_ON(btree_node_dirty(b)); BUG_ON(btree_node_need_write(b)); BUG_ON(b == btree_node_root(c, b)); BUG_ON(b->ob.nr); BUG_ON(!list_empty(&b->write_blocked)); BUG_ON(b->will_make_reachable); clear_btree_node_noevict(b); mutex_lock(&c->btree_cache.lock); list_move(&b->list, &c->btree_cache.freeable); mutex_unlock(&c->btree_cache.lock); } static void bch2_btree_node_free_inmem(struct btree_trans *trans, struct btree_path *path, struct btree *b) { struct bch_fs *c = trans->c; unsigned i, level = b->c.level; bch2_btree_node_lock_write_nofail(trans, path, &b->c); bch2_btree_node_hash_remove(&c->btree_cache, b); __btree_node_free(trans, b); six_unlock_write(&b->c.lock); mark_btree_node_locked_noreset(path, level, BTREE_NODE_INTENT_LOCKED); trans_for_each_path(trans, path, i) if (path->l[level].b == b) { btree_node_unlock(trans, path, level); path->l[level].b = ERR_PTR(-BCH_ERR_no_btree_node_init); } } static void bch2_btree_node_free_never_used(struct btree_update *as, struct btree_trans *trans, struct btree *b) { struct bch_fs *c = as->c; struct prealloc_nodes *p = &as->prealloc_nodes[b->c.lock.readers != NULL]; struct btree_path *path; unsigned i, level = b->c.level; BUG_ON(!list_empty(&b->write_blocked)); BUG_ON(b->will_make_reachable != (1UL|(unsigned long) as)); b->will_make_reachable = 0; closure_put(&as->cl); clear_btree_node_will_make_reachable(b); clear_btree_node_accessed(b); clear_btree_node_dirty_acct(c, b); clear_btree_node_need_write(b); mutex_lock(&c->btree_cache.lock); list_del_init(&b->list); bch2_btree_node_hash_remove(&c->btree_cache, b); mutex_unlock(&c->btree_cache.lock); BUG_ON(p->nr >= ARRAY_SIZE(p->b)); p->b[p->nr++] = b; six_unlock_intent(&b->c.lock); trans_for_each_path(trans, path, i) if (path->l[level].b == b) { btree_node_unlock(trans, path, level); path->l[level].b = ERR_PTR(-BCH_ERR_no_btree_node_init); } } static struct btree *__bch2_btree_node_alloc(struct btree_trans *trans, struct disk_reservation *res, struct closure *cl, bool interior_node, unsigned flags) { struct bch_fs *c = trans->c; struct write_point *wp; struct btree *b; BKEY_PADDED_ONSTACK(k, BKEY_BTREE_PTR_VAL_U64s_MAX) tmp; struct open_buckets obs = { .nr = 0 }; struct bch_devs_list devs_have = (struct bch_devs_list) { 0 }; enum bch_watermark watermark = flags & BCH_WATERMARK_MASK; unsigned nr_reserve = watermark < BCH_WATERMARK_reclaim ? BTREE_NODE_RESERVE : 0; int ret; b = bch2_btree_node_mem_alloc(trans, interior_node); if (IS_ERR(b)) return b; BUG_ON(b->ob.nr); mutex_lock(&c->btree_reserve_cache_lock); if (c->btree_reserve_cache_nr > nr_reserve) { struct btree_alloc *a = &c->btree_reserve_cache[--c->btree_reserve_cache_nr]; obs = a->ob; bkey_copy(&tmp.k, &a->k); mutex_unlock(&c->btree_reserve_cache_lock); goto out; } mutex_unlock(&c->btree_reserve_cache_lock); retry: ret = bch2_alloc_sectors_start_trans(trans, c->opts.metadata_target ?: c->opts.foreground_target, 0, writepoint_ptr(&c->btree_write_point), &devs_have, res->nr_replicas, min(res->nr_replicas, c->opts.metadata_replicas_required), watermark, 0, cl, &wp); if (unlikely(ret)) goto err; if (wp->sectors_free < btree_sectors(c)) { struct open_bucket *ob; unsigned i; open_bucket_for_each(c, &wp->ptrs, ob, i) if (ob->sectors_free < btree_sectors(c)) ob->sectors_free = 0; bch2_alloc_sectors_done(c, wp); goto retry; } bkey_btree_ptr_v2_init(&tmp.k); bch2_alloc_sectors_append_ptrs(c, wp, &tmp.k, btree_sectors(c), false); bch2_open_bucket_get(c, wp, &obs); bch2_alloc_sectors_done(c, wp); out: bkey_copy(&b->key, &tmp.k); b->ob = obs; six_unlock_write(&b->c.lock); six_unlock_intent(&b->c.lock); return b; err: bch2_btree_node_to_freelist(c, b); return ERR_PTR(ret); } static struct btree *bch2_btree_node_alloc(struct btree_update *as, struct btree_trans *trans, unsigned level) { struct bch_fs *c = as->c; struct btree *b; struct prealloc_nodes *p = &as->prealloc_nodes[!!level]; int ret; BUG_ON(level >= BTREE_MAX_DEPTH); BUG_ON(!p->nr); b = p->b[--p->nr]; btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_intent); btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_write); set_btree_node_accessed(b); set_btree_node_dirty_acct(c, b); set_btree_node_need_write(b); bch2_bset_init_first(b, &b->data->keys); b->c.level = level; b->c.btree_id = as->btree_id; b->version_ondisk = c->sb.version; memset(&b->nr, 0, sizeof(b->nr)); b->data->magic = cpu_to_le64(bset_magic(c)); memset(&b->data->_ptr, 0, sizeof(b->data->_ptr)); b->data->flags = 0; SET_BTREE_NODE_ID(b->data, as->btree_id); SET_BTREE_NODE_LEVEL(b->data, level); if (b->key.k.type == KEY_TYPE_btree_ptr_v2) { struct bkey_i_btree_ptr_v2 *bp = bkey_i_to_btree_ptr_v2(&b->key); bp->v.mem_ptr = 0; bp->v.seq = b->data->keys.seq; bp->v.sectors_written = 0; } SET_BTREE_NODE_NEW_EXTENT_OVERWRITE(b->data, true); bch2_btree_build_aux_trees(b); ret = bch2_btree_node_hash_insert(&c->btree_cache, b, level, as->btree_id); BUG_ON(ret); trace_and_count(c, btree_node_alloc, trans, b); bch2_increment_clock(c, btree_sectors(c), WRITE); return b; } static void btree_set_min(struct btree *b, struct bpos pos) { if (b->key.k.type == KEY_TYPE_btree_ptr_v2) bkey_i_to_btree_ptr_v2(&b->key)->v.min_key = pos; b->data->min_key = pos; } static void btree_set_max(struct btree *b, struct bpos pos) { b->key.k.p = pos; b->data->max_key = pos; } static struct btree *bch2_btree_node_alloc_replacement(struct btree_update *as, struct btree_trans *trans, struct btree *b) { struct btree *n = bch2_btree_node_alloc(as, trans, b->c.level); struct bkey_format format = bch2_btree_calc_format(b); /* * The keys might expand with the new format - if they wouldn't fit in * the btree node anymore, use the old format for now: */ if (!bch2_btree_node_format_fits(as->c, b, b->nr, &format)) format = b->format; SET_BTREE_NODE_SEQ(n->data, BTREE_NODE_SEQ(b->data) + 1); btree_set_min(n, b->data->min_key); btree_set_max(n, b->data->max_key); n->data->format = format; btree_node_set_format(n, format); bch2_btree_sort_into(as->c, n, b); btree_node_reset_sib_u64s(n); return n; } static struct btree *__btree_root_alloc(struct btree_update *as, struct btree_trans *trans, unsigned level) { struct btree *b = bch2_btree_node_alloc(as, trans, level); btree_set_min(b, POS_MIN); btree_set_max(b, SPOS_MAX); b->data->format = bch2_btree_calc_format(b); btree_node_set_format(b, b->data->format); bch2_btree_build_aux_trees(b); return b; } static void bch2_btree_reserve_put(struct btree_update *as, struct btree_trans *trans) { struct bch_fs *c = as->c; struct prealloc_nodes *p; for (p = as->prealloc_nodes; p < as->prealloc_nodes + ARRAY_SIZE(as->prealloc_nodes); p++) { while (p->nr) { struct btree *b = p->b[--p->nr]; mutex_lock(&c->btree_reserve_cache_lock); if (c->btree_reserve_cache_nr < ARRAY_SIZE(c->btree_reserve_cache)) { struct btree_alloc *a = &c->btree_reserve_cache[c->btree_reserve_cache_nr++]; a->ob = b->ob; b->ob.nr = 0; bkey_copy(&a->k, &b->key); } else { bch2_open_buckets_put(c, &b->ob); } mutex_unlock(&c->btree_reserve_cache_lock); btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_intent); btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_write); __btree_node_free(trans, b); six_unlock_write(&b->c.lock); six_unlock_intent(&b->c.lock); } } } static int bch2_btree_reserve_get(struct btree_trans *trans, struct btree_update *as, unsigned nr_nodes[2], unsigned flags, struct closure *cl) { struct btree *b; unsigned interior; int ret = 0; BUG_ON(nr_nodes[0] + nr_nodes[1] > BTREE_RESERVE_MAX); /* * Protects reaping from the btree node cache and using the btree node * open bucket reserve: */ ret = bch2_btree_cache_cannibalize_lock(trans, cl); if (ret) return ret; for (interior = 0; interior < 2; interior++) { struct prealloc_nodes *p = as->prealloc_nodes + interior; while (p->nr < nr_nodes[interior]) { b = __bch2_btree_node_alloc(trans, &as->disk_res, cl, interior, flags); if (IS_ERR(b)) { ret = PTR_ERR(b); goto err; } p->b[p->nr++] = b; } } err: bch2_btree_cache_cannibalize_unlock(trans); return ret; } /* Asynchronous interior node update machinery */ static void bch2_btree_update_free(struct btree_update *as, struct btree_trans *trans) { struct bch_fs *c = as->c; if (as->took_gc_lock) up_read(&c->gc_lock); as->took_gc_lock = false; bch2_journal_pin_drop(&c->journal, &as->journal); bch2_journal_pin_flush(&c->journal, &as->journal); bch2_disk_reservation_put(c, &as->disk_res); bch2_btree_reserve_put(as, trans); bch2_time_stats_update(&c->times[BCH_TIME_btree_interior_update_total], as->start_time); mutex_lock(&c->btree_interior_update_lock); list_del(&as->unwritten_list); list_del(&as->list); closure_debug_destroy(&as->cl); mempool_free(as, &c->btree_interior_update_pool); /* * Have to do the wakeup with btree_interior_update_lock still held, * since being on btree_interior_update_list is our ref on @c: */ closure_wake_up(&c->btree_interior_update_wait); mutex_unlock(&c->btree_interior_update_lock); } static void btree_update_add_key(struct btree_update *as, struct keylist *keys, struct btree *b) { struct bkey_i *k = &b->key; BUG_ON(bch2_keylist_u64s(keys) + k->k.u64s > ARRAY_SIZE(as->_old_keys)); bkey_copy(keys->top, k); bkey_i_to_btree_ptr_v2(keys->top)->v.mem_ptr = b->c.level + 1; bch2_keylist_push(keys); } static bool btree_update_new_nodes_marked_sb(struct btree_update *as) { for_each_keylist_key(&as->new_keys, k) if (!bch2_dev_btree_bitmap_marked(as->c, bkey_i_to_s_c(k))) return false; return true; } static void btree_update_new_nodes_mark_sb(struct btree_update *as) { struct bch_fs *c = as->c; mutex_lock(&c->sb_lock); for_each_keylist_key(&as->new_keys, k) bch2_dev_btree_bitmap_mark(c, bkey_i_to_s_c(k)); bch2_write_super(c); mutex_unlock(&c->sb_lock); } /* * The transactional part of an interior btree node update, where we journal the * update we did to the interior node and update alloc info: */ static int btree_update_nodes_written_trans(struct btree_trans *trans, struct btree_update *as) { struct jset_entry *e = bch2_trans_jset_entry_alloc(trans, as->journal_u64s); int ret = PTR_ERR_OR_ZERO(e); if (ret) return ret; memcpy(e, as->journal_entries, as->journal_u64s * sizeof(u64)); trans->journal_pin = &as->journal; for_each_keylist_key(&as->old_keys, k) { unsigned level = bkey_i_to_btree_ptr_v2(k)->v.mem_ptr; ret = bch2_key_trigger_old(trans, as->btree_id, level, bkey_i_to_s_c(k), BTREE_TRIGGER_transactional); if (ret) return ret; } for_each_keylist_key(&as->new_keys, k) { unsigned level = bkey_i_to_btree_ptr_v2(k)->v.mem_ptr; ret = bch2_key_trigger_new(trans, as->btree_id, level, bkey_i_to_s(k), BTREE_TRIGGER_transactional); if (ret) return ret; } return 0; } static void btree_update_nodes_written(struct btree_update *as) { struct bch_fs *c = as->c; struct btree *b; struct btree_trans *trans = bch2_trans_get(c); u64 journal_seq = 0; unsigned i; int ret; /* * If we're already in an error state, it might be because a btree node * was never written, and we might be trying to free that same btree * node here, but it won't have been marked as allocated and we'll see * spurious disk usage inconsistencies in the transactional part below * if we don't skip it: */ ret = bch2_journal_error(&c->journal); if (ret) goto err; if (!btree_update_new_nodes_marked_sb(as)) btree_update_new_nodes_mark_sb(as); /* * Wait for any in flight writes to finish before we free the old nodes * on disk: */ for (i = 0; i < as->nr_old_nodes; i++) { __le64 seq; b = as->old_nodes[i]; btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_read); seq = b->data ? b->data->keys.seq : 0; six_unlock_read(&b->c.lock); if (seq == as->old_nodes_seq[i]) wait_on_bit_io(&b->flags, BTREE_NODE_write_in_flight_inner, TASK_UNINTERRUPTIBLE); } /* * We did an update to a parent node where the pointers we added pointed * to child nodes that weren't written yet: now, the child nodes have * been written so we can write out the update to the interior node. */ /* * We can't call into journal reclaim here: we'd block on the journal * reclaim lock, but we may need to release the open buckets we have * pinned in order for other btree updates to make forward progress, and * journal reclaim does btree updates when flushing bkey_cached entries, * which may require allocations as well. */ ret = commit_do(trans, &as->disk_res, &journal_seq, BCH_WATERMARK_interior_updates| BCH_TRANS_COMMIT_no_enospc| BCH_TRANS_COMMIT_no_check_rw| BCH_TRANS_COMMIT_journal_reclaim, btree_update_nodes_written_trans(trans, as)); bch2_trans_unlock(trans); bch2_fs_fatal_err_on(ret && !bch2_journal_error(&c->journal), c, "%s", bch2_err_str(ret)); err: /* * We have to be careful because another thread might be getting ready * to free as->b and calling btree_update_reparent() on us - we'll * recheck under btree_update_lock below: */ b = READ_ONCE(as->b); if (b) { /* * @b is the node we did the final insert into: * * On failure to get a journal reservation, we still have to * unblock the write and allow most of the write path to happen * so that shutdown works, but the i->journal_seq mechanism * won't work to prevent the btree write from being visible (we * didn't get a journal sequence number) - instead * __bch2_btree_node_write() doesn't do the actual write if * we're in journal error state: */ /* * Ensure transaction is unlocked before using * btree_node_lock_nopath() (the use of which is always suspect, * we need to work on removing this in the future) * * It should be, but bch2_path_get_unlocked_mut() -> bch2_path_get() * calls bch2_path_upgrade(), before we call path_make_mut(), so * we may rarely end up with a locked path besides the one we * have here: */ bch2_trans_unlock(trans); bch2_trans_begin(trans); btree_path_idx_t path_idx = bch2_path_get_unlocked_mut(trans, as->btree_id, b->c.level, b->key.k.p); struct btree_path *path = trans->paths + path_idx; btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_intent); mark_btree_node_locked(trans, path, b->c.level, BTREE_NODE_INTENT_LOCKED); path->l[b->c.level].lock_seq = six_lock_seq(&b->c.lock); path->l[b->c.level].b = b; bch2_btree_node_lock_write_nofail(trans, path, &b->c); mutex_lock(&c->btree_interior_update_lock); list_del(&as->write_blocked_list); if (list_empty(&b->write_blocked)) clear_btree_node_write_blocked(b); /* * Node might have been freed, recheck under * btree_interior_update_lock: */ if (as->b == b) { BUG_ON(!b->c.level); BUG_ON(!btree_node_dirty(b)); if (!ret) { struct bset *last = btree_bset_last(b); last->journal_seq = cpu_to_le64( max(journal_seq, le64_to_cpu(last->journal_seq))); bch2_btree_add_journal_pin(c, b, journal_seq); } else { /* * If we didn't get a journal sequence number we * can't write this btree node, because recovery * won't know to ignore this write: */ set_btree_node_never_write(b); } } mutex_unlock(&c->btree_interior_update_lock); mark_btree_node_locked_noreset(path, b->c.level, BTREE_NODE_INTENT_LOCKED); six_unlock_write(&b->c.lock); btree_node_write_if_need(c, b, SIX_LOCK_intent); btree_node_unlock(trans, path, b->c.level); bch2_path_put(trans, path_idx, true); } bch2_journal_pin_drop(&c->journal, &as->journal); mutex_lock(&c->btree_interior_update_lock); for (i = 0; i < as->nr_new_nodes; i++) { b = as->new_nodes[i]; BUG_ON(b->will_make_reachable != (unsigned long) as); b->will_make_reachable = 0; clear_btree_node_will_make_reachable(b); } mutex_unlock(&c->btree_interior_update_lock); for (i = 0; i < as->nr_new_nodes; i++) { b = as->new_nodes[i]; btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_read); btree_node_write_if_need(c, b, SIX_LOCK_read); six_unlock_read(&b->c.lock); } for (i = 0; i < as->nr_open_buckets; i++) bch2_open_bucket_put(c, c->open_buckets + as->open_buckets[i]); bch2_btree_update_free(as, trans); bch2_trans_put(trans); } static void btree_interior_update_work(struct work_struct *work) { struct bch_fs *c = container_of(work, struct bch_fs, btree_interior_update_work); struct btree_update *as; while (1) { mutex_lock(&c->btree_interior_update_lock); as = list_first_entry_or_null(&c->btree_interior_updates_unwritten, struct btree_update, unwritten_list); if (as && !as->nodes_written) as = NULL; mutex_unlock(&c->btree_interior_update_lock); if (!as) break; btree_update_nodes_written(as); } } static CLOSURE_CALLBACK(btree_update_set_nodes_written) { closure_type(as, struct btree_update, cl); struct bch_fs *c = as->c; mutex_lock(&c->btree_interior_update_lock); as->nodes_written = true; mutex_unlock(&c->btree_interior_update_lock); queue_work(c->btree_interior_update_worker, &c->btree_interior_update_work); } /* * We're updating @b with pointers to nodes that haven't finished writing yet: * block @b from being written until @as completes */ static void btree_update_updated_node(struct btree_update *as, struct btree *b) { struct bch_fs *c = as->c; BUG_ON(as->mode != BTREE_UPDATE_none); BUG_ON(as->update_level_end < b->c.level); BUG_ON(!btree_node_dirty(b)); BUG_ON(!b->c.level); mutex_lock(&c->btree_interior_update_lock); list_add_tail(&as->unwritten_list, &c->btree_interior_updates_unwritten); as->mode = BTREE_UPDATE_node; as->b = b; as->update_level_end = b->c.level; set_btree_node_write_blocked(b); list_add(&as->write_blocked_list, &b->write_blocked); mutex_unlock(&c->btree_interior_update_lock); } static int bch2_update_reparent_journal_pin_flush(struct journal *j, struct journal_entry_pin *_pin, u64 seq) { return 0; } static void btree_update_reparent(struct btree_update *as, struct btree_update *child) { struct bch_fs *c = as->c; lockdep_assert_held(&c->btree_interior_update_lock); child->b = NULL; child->mode = BTREE_UPDATE_update; bch2_journal_pin_copy(&c->journal, &as->journal, &child->journal, bch2_update_reparent_journal_pin_flush); } static void btree_update_updated_root(struct btree_update *as, struct btree *b) { struct bkey_i *insert = &b->key; struct bch_fs *c = as->c; BUG_ON(as->mode != BTREE_UPDATE_none); BUG_ON(as->journal_u64s + jset_u64s(insert->k.u64s) > ARRAY_SIZE(as->journal_entries)); as->journal_u64s += journal_entry_set((void *) &as->journal_entries[as->journal_u64s], BCH_JSET_ENTRY_btree_root, b->c.btree_id, b->c.level, insert, insert->k.u64s); mutex_lock(&c->btree_interior_update_lock); list_add_tail(&as->unwritten_list, &c->btree_interior_updates_unwritten); as->mode = BTREE_UPDATE_root; mutex_unlock(&c->btree_interior_update_lock); } /* * bch2_btree_update_add_new_node: * * This causes @as to wait on @b to be written, before it gets to * bch2_btree_update_nodes_written * * Additionally, it sets b->will_make_reachable to prevent any additional writes * to @b from happening besides the first until @b is reachable on disk * * And it adds @b to the list of @as's new nodes, so that we can update sector * counts in bch2_btree_update_nodes_written: */ static void bch2_btree_update_add_new_node(struct btree_update *as, struct btree *b) { struct bch_fs *c = as->c; closure_get(&as->cl); mutex_lock(&c->btree_interior_update_lock); BUG_ON(as->nr_new_nodes >= ARRAY_SIZE(as->new_nodes)); BUG_ON(b->will_make_reachable); as->new_nodes[as->nr_new_nodes++] = b; b->will_make_reachable = 1UL|(unsigned long) as; set_btree_node_will_make_reachable(b); mutex_unlock(&c->btree_interior_update_lock); btree_update_add_key(as, &as->new_keys, b); if (b->key.k.type == KEY_TYPE_btree_ptr_v2) { unsigned bytes = vstruct_end(&b->data->keys) - (void *) b->data; unsigned sectors = round_up(bytes, block_bytes(c)) >> 9; bkey_i_to_btree_ptr_v2(&b->key)->v.sectors_written = cpu_to_le16(sectors); } } /* * returns true if @b was a new node */ static void btree_update_drop_new_node(struct bch_fs *c, struct btree *b) { struct btree_update *as; unsigned long v; unsigned i; mutex_lock(&c->btree_interior_update_lock); /* * When b->will_make_reachable != 0, it owns a ref on as->cl that's * dropped when it gets written by bch2_btree_complete_write - the * xchg() is for synchronization with bch2_btree_complete_write: */ v = xchg(&b->will_make_reachable, 0); clear_btree_node_will_make_reachable(b); as = (struct btree_update *) (v & ~1UL); if (!as) { mutex_unlock(&c->btree_interior_update_lock); return; } for (i = 0; i < as->nr_new_nodes; i++) if (as->new_nodes[i] == b) goto found; BUG(); found: array_remove_item(as->new_nodes, as->nr_new_nodes, i); mutex_unlock(&c->btree_interior_update_lock); if (v & 1) closure_put(&as->cl); } static void bch2_btree_update_get_open_buckets(struct btree_update *as, struct btree *b) { while (b->ob.nr) as->open_buckets[as->nr_open_buckets++] = b->ob.v[--b->ob.nr]; } static int bch2_btree_update_will_free_node_journal_pin_flush(struct journal *j, struct journal_entry_pin *_pin, u64 seq) { return 0; } /* * @b is being split/rewritten: it may have pointers to not-yet-written btree * nodes and thus outstanding btree_updates - redirect @b's * btree_updates to point to this btree_update: */ static void bch2_btree_interior_update_will_free_node(struct btree_update *as, struct btree *b) { struct bch_fs *c = as->c; struct btree_update *p, *n; struct btree_write *w; set_btree_node_dying(b); if (btree_node_fake(b)) return; mutex_lock(&c->btree_interior_update_lock); /* * Does this node have any btree_update operations preventing * it from being written? * * If so, redirect them to point to this btree_update: we can * write out our new nodes, but we won't make them visible until those * operations complete */ list_for_each_entry_safe(p, n, &b->write_blocked, write_blocked_list) { list_del_init(&p->write_blocked_list); btree_update_reparent(as, p); /* * for flush_held_btree_writes() waiting on updates to flush or * nodes to be writeable: */ closure_wake_up(&c->btree_interior_update_wait); } clear_btree_node_dirty_acct(c, b); clear_btree_node_need_write(b); clear_btree_node_write_blocked(b); /* * Does this node have unwritten data that has a pin on the journal? * * If so, transfer that pin to the btree_update operation - * note that if we're freeing multiple nodes, we only need to keep the * oldest pin of any of the nodes we're freeing. We'll release the pin * when the new nodes are persistent and reachable on disk: */ w = btree_current_write(b); bch2_journal_pin_copy(&c->journal, &as->journal, &w->journal, bch2_btree_update_will_free_node_journal_pin_flush); bch2_journal_pin_drop(&c->journal, &w->journal); w = btree_prev_write(b); bch2_journal_pin_copy(&c->journal, &as->journal, &w->journal, bch2_btree_update_will_free_node_journal_pin_flush); bch2_journal_pin_drop(&c->journal, &w->journal); mutex_unlock(&c->btree_interior_update_lock); /* * Is this a node that isn't reachable on disk yet? * * Nodes that aren't reachable yet have writes blocked until they're * reachable - now that we've cancelled any pending writes and moved * things waiting on that write to wait on this update, we can drop this * node from the list of nodes that the other update is making * reachable, prior to freeing it: */ btree_update_drop_new_node(c, b); btree_update_add_key(as, &as->old_keys, b); as->old_nodes[as->nr_old_nodes] = b; as->old_nodes_seq[as->nr_old_nodes] = b->data->keys.seq; as->nr_old_nodes++; } static void bch2_btree_update_done(struct btree_update *as, struct btree_trans *trans) { struct bch_fs *c = as->c; u64 start_time = as->start_time; BUG_ON(as->mode == BTREE_UPDATE_none); if (as->took_gc_lock) up_read(&as->c->gc_lock); as->took_gc_lock = false; bch2_btree_reserve_put(as, trans); continue_at(&as->cl, btree_update_set_nodes_written, as->c->btree_interior_update_worker); bch2_time_stats_update(&c->times[BCH_TIME_btree_interior_update_foreground], start_time); } static struct btree_update * bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path, unsigned level_start, bool split, unsigned flags) { struct bch_fs *c = trans->c; struct btree_update *as; u64 start_time = local_clock(); int disk_res_flags = (flags & BCH_TRANS_COMMIT_no_enospc) ? BCH_DISK_RESERVATION_NOFAIL : 0; unsigned nr_nodes[2] = { 0, 0 }; unsigned level_end = level_start; enum bch_watermark watermark = flags & BCH_WATERMARK_MASK; int ret = 0; u32 restart_count = trans->restart_count; BUG_ON(!path->should_be_locked); if (watermark == BCH_WATERMARK_copygc) watermark = BCH_WATERMARK_btree_copygc; if (watermark < BCH_WATERMARK_btree) watermark = BCH_WATERMARK_btree; flags &= ~BCH_WATERMARK_MASK; flags |= watermark; if (watermark < BCH_WATERMARK_reclaim && test_bit(JOURNAL_space_low, &c->journal.flags)) { if (flags & BCH_TRANS_COMMIT_journal_reclaim) return ERR_PTR(-BCH_ERR_journal_reclaim_would_deadlock); ret = drop_locks_do(trans, ({ wait_event(c->journal.wait, !test_bit(JOURNAL_space_low, &c->journal.flags)); 0; })); if (ret) return ERR_PTR(ret); } while (1) { nr_nodes[!!level_end] += 1 + split; level_end++; ret = bch2_btree_path_upgrade(trans, path, level_end + 1); if (ret) return ERR_PTR(ret); if (!btree_path_node(path, level_end)) { /* Allocating new root? */ nr_nodes[1] += split; level_end = BTREE_MAX_DEPTH; break; } /* * Always check for space for two keys, even if we won't have to * split at prior level - it might have been a merge instead: */ if (bch2_btree_node_insert_fits(path->l[level_end].b, BKEY_BTREE_PTR_U64s_MAX * 2)) break; split = path->l[level_end].b->nr.live_u64s > BTREE_SPLIT_THRESHOLD(c); } if (!down_read_trylock(&c->gc_lock)) { ret = drop_locks_do(trans, (down_read(&c->gc_lock), 0)); if (ret) { up_read(&c->gc_lock); return ERR_PTR(ret); } } as = mempool_alloc(&c->btree_interior_update_pool, GFP_NOFS); memset(as, 0, sizeof(*as)); closure_init(&as->cl, NULL); as->c = c; as->start_time = start_time; as->ip_started = _RET_IP_; as->mode = BTREE_UPDATE_none; as->flags = flags; as->took_gc_lock = true; as->btree_id = path->btree_id; as->update_level_start = level_start; as->update_level_end = level_end; INIT_LIST_HEAD(&as->list); INIT_LIST_HEAD(&as->unwritten_list); INIT_LIST_HEAD(&as->write_blocked_list); bch2_keylist_init(&as->old_keys, as->_old_keys); bch2_keylist_init(&as->new_keys, as->_new_keys); bch2_keylist_init(&as->parent_keys, as->inline_keys); mutex_lock(&c->btree_interior_update_lock); list_add_tail(&as->list, &c->btree_interior_update_list); mutex_unlock(&c->btree_interior_update_lock); /* * We don't want to allocate if we're in an error state, that can cause * deadlock on emergency shutdown due to open buckets getting stuck in * the btree_reserve_cache after allocator shutdown has cleared it out. * This check needs to come after adding us to the btree_interior_update * list but before calling bch2_btree_reserve_get, to synchronize with * __bch2_fs_read_only(). */ ret = bch2_journal_error(&c->journal); if (ret) goto err; ret = bch2_disk_reservation_get(c, &as->disk_res, (nr_nodes[0] + nr_nodes[1]) * btree_sectors(c), c->opts.metadata_replicas, disk_res_flags); if (ret) goto err; ret = bch2_btree_reserve_get(trans, as, nr_nodes, flags, NULL); if (bch2_err_matches(ret, ENOSPC) || bch2_err_matches(ret, ENOMEM)) { struct closure cl; /* * XXX: this should probably be a separate BTREE_INSERT_NONBLOCK * flag */ if (bch2_err_matches(ret, ENOSPC) && (flags & BCH_TRANS_COMMIT_journal_reclaim) && watermark < BCH_WATERMARK_reclaim) { ret = -BCH_ERR_journal_reclaim_would_deadlock; goto err; } closure_init_stack(&cl); do { ret = bch2_btree_reserve_get(trans, as, nr_nodes, flags, &cl); bch2_trans_unlock(trans); bch2_wait_on_allocator(c, &cl); } while (bch2_err_matches(ret, BCH_ERR_operation_blocked)); } if (ret) { trace_and_count(c, btree_reserve_get_fail, trans->fn, _RET_IP_, nr_nodes[0] + nr_nodes[1], ret); goto err; } ret = bch2_trans_relock(trans); if (ret) goto err; bch2_trans_verify_not_restarted(trans, restart_count); return as; err: bch2_btree_update_free(as, trans); if (!bch2_err_matches(ret, ENOSPC) && !bch2_err_matches(ret, EROFS) && ret != -BCH_ERR_journal_reclaim_would_deadlock) bch_err_fn_ratelimited(c, ret); return ERR_PTR(ret); } /* Btree root updates: */ static void bch2_btree_set_root_inmem(struct bch_fs *c, struct btree *b) { /* Root nodes cannot be reaped */ mutex_lock(&c->btree_cache.lock); list_del_init(&b->list); mutex_unlock(&c->btree_cache.lock); mutex_lock(&c->btree_root_lock); bch2_btree_id_root(c, b->c.btree_id)->b = b; mutex_unlock(&c->btree_root_lock); bch2_recalc_btree_reserve(c); } static int bch2_btree_set_root(struct btree_update *as, struct btree_trans *trans, struct btree_path *path, struct btree *b, bool nofail) { struct bch_fs *c = as->c; trace_and_count(c, btree_node_set_root, trans, b); struct btree *old = btree_node_root(c, b); /* * Ensure no one is using the old root while we switch to the * new root: */ if (nofail) { bch2_btree_node_lock_write_nofail(trans, path, &old->c); } else { int ret = bch2_btree_node_lock_write(trans, path, &old->c); if (ret) return ret; } bch2_btree_set_root_inmem(c, b); btree_update_updated_root(as, b); /* * Unlock old root after new root is visible: * * The new root isn't persistent, but that's ok: we still have * an intent lock on the new root, and any updates that would * depend on the new root would have to update the new root. */ bch2_btree_node_unlock_write(trans, path, old); return 0; } /* Interior node updates: */ static void bch2_insert_fixup_btree_ptr(struct btree_update *as, struct btree_trans *trans, struct btree_path *path, struct btree *b, struct btree_node_iter *node_iter, struct bkey_i *insert) { struct bch_fs *c = as->c; struct bkey_packed *k; struct printbuf buf = PRINTBUF; unsigned long old, new; BUG_ON(insert->k.type == KEY_TYPE_btree_ptr_v2 && !btree_ptr_sectors_written(bkey_i_to_s_c(insert))); if (unlikely(!test_bit(JOURNAL_replay_done, &c->journal.flags))) bch2_journal_key_overwritten(c, b->c.btree_id, b->c.level, insert->k.p); if (bch2_bkey_validate(c, bkey_i_to_s_c(insert), btree_node_type(b), BCH_VALIDATE_write) ?: bch2_bkey_in_btree_node(c, b, bkey_i_to_s_c(insert), BCH_VALIDATE_write)) { bch2_fs_inconsistent(c, "%s: inserting invalid bkey", __func__); dump_stack(); } BUG_ON(as->journal_u64s + jset_u64s(insert->k.u64s) > ARRAY_SIZE(as->journal_entries)); as->journal_u64s += journal_entry_set((void *) &as->journal_entries[as->journal_u64s], BCH_JSET_ENTRY_btree_keys, b->c.btree_id, b->c.level, insert, insert->k.u64s); while ((k = bch2_btree_node_iter_peek_all(node_iter, b)) && bkey_iter_pos_cmp(b, k, &insert->k.p) < 0) bch2_btree_node_iter_advance(node_iter, b); bch2_btree_bset_insert_key(trans, path, b, node_iter, insert); set_btree_node_dirty_acct(c, b); old = READ_ONCE(b->flags); do { new = old; new &= ~BTREE_WRITE_TYPE_MASK; new |= BTREE_WRITE_interior; new |= 1 << BTREE_NODE_need_write; } while (!try_cmpxchg(&b->flags, &old, new)); printbuf_exit(&buf); } static void bch2_btree_insert_keys_interior(struct btree_update *as, struct btree_trans *trans, struct btree_path *path, struct btree *b, struct btree_node_iter node_iter, struct keylist *keys) { struct bkey_i *insert = bch2_keylist_front(keys); struct bkey_packed *k; BUG_ON(btree_node_type(b) != BKEY_TYPE_btree); while ((k = bch2_btree_node_iter_prev_all(&node_iter, b)) && (bkey_cmp_left_packed(b, k, &insert->k.p) >= 0)) ; while (!bch2_keylist_empty(keys)) { insert = bch2_keylist_front(keys); if (bpos_gt(insert->k.p, b->key.k.p)) break; bch2_insert_fixup_btree_ptr(as, trans, path, b, &node_iter, insert); bch2_keylist_pop_front(keys); } } /* * Move keys from n1 (original replacement node, now lower node) to n2 (higher * node) */ static void __btree_split_node(struct btree_update *as, struct btree_trans *trans, struct btree *b, struct btree *n[2]) { struct bkey_packed *k; struct bpos n1_pos = POS_MIN; struct btree_node_iter iter; struct bset *bsets[2]; struct bkey_format_state format[2]; struct bkey_packed *out[2]; struct bkey uk; unsigned u64s, n1_u64s = (b->nr.live_u64s * 3) / 5; struct { unsigned nr_keys, val_u64s; } nr_keys[2]; int i; memset(&nr_keys, 0, sizeof(nr_keys)); for (i = 0; i < 2; i++) { BUG_ON(n[i]->nsets != 1); bsets[i] = btree_bset_first(n[i]); out[i] = bsets[i]->start; SET_BTREE_NODE_SEQ(n[i]->data, BTREE_NODE_SEQ(b->data) + 1); bch2_bkey_format_init(&format[i]); } u64s = 0; for_each_btree_node_key(b, k, &iter) { if (bkey_deleted(k)) continue; uk = bkey_unpack_key(b, k); if (b->c.level && u64s < n1_u64s && u64s + k->u64s >= n1_u64s && bch2_key_deleted_in_journal(trans, b->c.btree_id, b->c.level, uk.p)) n1_u64s += k->u64s; i = u64s >= n1_u64s; u64s += k->u64s; if (!i) n1_pos = uk.p; bch2_bkey_format_add_key(&format[i], &uk); nr_keys[i].nr_keys++; nr_keys[i].val_u64s += bkeyp_val_u64s(&b->format, k); } btree_set_min(n[0], b->data->min_key); btree_set_max(n[0], n1_pos); btree_set_min(n[1], bpos_successor(n1_pos)); btree_set_max(n[1], b->data->max_key); for (i = 0; i < 2; i++) { bch2_bkey_format_add_pos(&format[i], n[i]->data->min_key); bch2_bkey_format_add_pos(&format[i], n[i]->data->max_key); n[i]->data->format = bch2_bkey_format_done(&format[i]); unsigned u64s = nr_keys[i].nr_keys * n[i]->data->format.key_u64s + nr_keys[i].val_u64s; if (__vstruct_bytes(struct btree_node, u64s) > btree_buf_bytes(b)) n[i]->data->format = b->format; btree_node_set_format(n[i], n[i]->data->format); } u64s = 0; for_each_btree_node_key(b, k, &iter) { if (bkey_deleted(k)) continue; i = u64s >= n1_u64s; u64s += k->u64s; if (bch2_bkey_transform(&n[i]->format, out[i], bkey_packed(k) ? &b->format: &bch2_bkey_format_current, k)) out[i]->format = KEY_FORMAT_LOCAL_BTREE; else bch2_bkey_unpack(b, (void *) out[i], k); out[i]->needs_whiteout = false; btree_keys_account_key_add(&n[i]->nr, 0, out[i]); out[i] = bkey_p_next(out[i]); } for (i = 0; i < 2; i++) { bsets[i]->u64s = cpu_to_le16((u64 *) out[i] - bsets[i]->_data); BUG_ON(!bsets[i]->u64s); set_btree_bset_end(n[i], n[i]->set); btree_node_reset_sib_u64s(n[i]); bch2_verify_btree_nr_keys(n[i]); BUG_ON(bch2_btree_node_check_topology(trans, n[i])); } } /* * For updates to interior nodes, we've got to do the insert before we split * because the stuff we're inserting has to be inserted atomically. Post split, * the keys might have to go in different nodes and the split would no longer be * atomic. * * Worse, if the insert is from btree node coalescing, if we do the insert after * we do the split (and pick the pivot) - the pivot we pick might be between * nodes that were coalesced, and thus in the middle of a child node post * coalescing: */ static void btree_split_insert_keys(struct btree_update *as, struct btree_trans *trans, btree_path_idx_t path_idx, struct btree *b, struct keylist *keys) { struct btree_path *path = trans->paths + path_idx; if (!bch2_keylist_empty(keys) && bpos_le(bch2_keylist_front(keys)->k.p, b->data->max_key)) { struct btree_node_iter node_iter; bch2_btree_node_iter_init(&node_iter, b, &bch2_keylist_front(keys)->k.p); bch2_btree_insert_keys_interior(as, trans, path, b, node_iter, keys); BUG_ON(bch2_btree_node_check_topology(trans, b)); } } static int btree_split(struct btree_update *as, struct btree_trans *trans, btree_path_idx_t path, struct btree *b, struct keylist *keys) { struct bch_fs *c = as->c; struct btree *parent = btree_node_parent(trans->paths + path, b); struct btree *n1, *n2 = NULL, *n3 = NULL; btree_path_idx_t path1 = 0, path2 = 0; u64 start_time = local_clock(); int ret = 0; bch2_verify_btree_nr_keys(b); BUG_ON(!parent && (b != btree_node_root(c, b))); BUG_ON(parent && !btree_node_intent_locked(trans->paths + path, b->c.level + 1)); ret = bch2_btree_node_check_topology(trans, b); if (ret) return ret; bch2_btree_interior_update_will_free_node(as, b); if (b->nr.live_u64s > BTREE_SPLIT_THRESHOLD(c)) { struct btree *n[2]; trace_and_count(c, btree_node_split, trans, b); n[0] = n1 = bch2_btree_node_alloc(as, trans, b->c.level); n[1] = n2 = bch2_btree_node_alloc(as, trans, b->c.level); __btree_split_node(as, trans, b, n); if (keys) { btree_split_insert_keys(as, trans, path, n1, keys); btree_split_insert_keys(as, trans, path, n2, keys); BUG_ON(!bch2_keylist_empty(keys)); } bch2_btree_build_aux_trees(n2); bch2_btree_build_aux_trees(n1); bch2_btree_update_add_new_node(as, n1); bch2_btree_update_add_new_node(as, n2); six_unlock_write(&n2->c.lock); six_unlock_write(&n1->c.lock); path1 = bch2_path_get_unlocked_mut(trans, as->btree_id, n1->c.level, n1->key.k.p); six_lock_increment(&n1->c.lock, SIX_LOCK_intent); mark_btree_node_locked(trans, trans->paths + path1, n1->c.level, BTREE_NODE_INTENT_LOCKED); bch2_btree_path_level_init(trans, trans->paths + path1, n1); path2 = bch2_path_get_unlocked_mut(trans, as->btree_id, n2->c.level, n2->key.k.p); six_lock_increment(&n2->c.lock, SIX_LOCK_intent); mark_btree_node_locked(trans, trans->paths + path2, n2->c.level, BTREE_NODE_INTENT_LOCKED); bch2_btree_path_level_init(trans, trans->paths + path2, n2); /* * Note that on recursive parent_keys == keys, so we * can't start adding new keys to parent_keys before emptying it * out (which we did with btree_split_insert_keys() above) */ bch2_keylist_add(&as->parent_keys, &n1->key); bch2_keylist_add(&as->parent_keys, &n2->key); if (!parent) { /* Depth increases, make a new root */ n3 = __btree_root_alloc(as, trans, b->c.level + 1); bch2_btree_update_add_new_node(as, n3); six_unlock_write(&n3->c.lock); trans->paths[path2].locks_want++; BUG_ON(btree_node_locked(trans->paths + path2, n3->c.level)); six_lock_increment(&n3->c.lock, SIX_LOCK_intent); mark_btree_node_locked(trans, trans->paths + path2, n3->c.level, BTREE_NODE_INTENT_LOCKED); bch2_btree_path_level_init(trans, trans->paths + path2, n3); n3->sib_u64s[0] = U16_MAX; n3->sib_u64s[1] = U16_MAX; btree_split_insert_keys(as, trans, path, n3, &as->parent_keys); } } else { trace_and_count(c, btree_node_compact, trans, b); n1 = bch2_btree_node_alloc_replacement(as, trans, b); if (keys) { btree_split_insert_keys(as, trans, path, n1, keys); BUG_ON(!bch2_keylist_empty(keys)); } bch2_btree_build_aux_trees(n1); bch2_btree_update_add_new_node(as, n1); six_unlock_write(&n1->c.lock); path1 = bch2_path_get_unlocked_mut(trans, as->btree_id, n1->c.level, n1->key.k.p); six_lock_increment(&n1->c.lock, SIX_LOCK_intent); mark_btree_node_locked(trans, trans->paths + path1, n1->c.level, BTREE_NODE_INTENT_LOCKED); bch2_btree_path_level_init(trans, trans->paths + path1, n1); if (parent) bch2_keylist_add(&as->parent_keys, &n1->key); } /* New nodes all written, now make them visible: */ if (parent) { /* Split a non root node */ ret = bch2_btree_insert_node(as, trans, path, parent, &as->parent_keys); } else if (n3) { ret = bch2_btree_set_root(as, trans, trans->paths + path, n3, false); } else { /* Root filled up but didn't need to be split */ ret = bch2_btree_set_root(as, trans, trans->paths + path, n1, false); } if (ret) goto err; if (n3) { bch2_btree_update_get_open_buckets(as, n3); bch2_btree_node_write(c, n3, SIX_LOCK_intent, 0); } if (n2) { bch2_btree_update_get_open_buckets(as, n2); bch2_btree_node_write(c, n2, SIX_LOCK_intent, 0); } bch2_btree_update_get_open_buckets(as, n1); bch2_btree_node_write(c, n1, SIX_LOCK_intent, 0); /* * The old node must be freed (in memory) _before_ unlocking the new * nodes - else another thread could re-acquire a read lock on the old * node after another thread has locked and updated the new node, thus * seeing stale data: */ bch2_btree_node_free_inmem(trans, trans->paths + path, b); if (n3) bch2_trans_node_add(trans, trans->paths + path, n3); if (n2) bch2_trans_node_add(trans, trans->paths + path2, n2); bch2_trans_node_add(trans, trans->paths + path1, n1); if (n3) six_unlock_intent(&n3->c.lock); if (n2) six_unlock_intent(&n2->c.lock); six_unlock_intent(&n1->c.lock); out: if (path2) { __bch2_btree_path_unlock(trans, trans->paths + path2); bch2_path_put(trans, path2, true); } if (path1) { __bch2_btree_path_unlock(trans, trans->paths + path1); bch2_path_put(trans, path1, true); } bch2_trans_verify_locks(trans); bch2_time_stats_update(&c->times[n2 ? BCH_TIME_btree_node_split : BCH_TIME_btree_node_compact], start_time); return ret; err: if (n3) bch2_btree_node_free_never_used(as, trans, n3); if (n2) bch2_btree_node_free_never_used(as, trans, n2); bch2_btree_node_free_never_used(as, trans, n1); goto out; } /** * bch2_btree_insert_node - insert bkeys into a given btree node * * @as: btree_update object * @trans: btree_trans object * @path_idx: path that points to current node * @b: node to insert keys into * @keys: list of keys to insert * * Returns: 0 on success, typically transaction restart error on failure * * Inserts as many keys as it can into a given btree node, splitting it if full. * If a split occurred, this function will return early. This can only happen * for leaf nodes -- inserts into interior nodes have to be atomic. */ static int bch2_btree_insert_node(struct btree_update *as, struct btree_trans *trans, btree_path_idx_t path_idx, struct btree *b, struct keylist *keys) { struct bch_fs *c = as->c; struct btree_path *path = trans->paths + path_idx, *linked; unsigned i; int old_u64s = le16_to_cpu(btree_bset_last(b)->u64s); int old_live_u64s = b->nr.live_u64s; int live_u64s_added, u64s_added; int ret; lockdep_assert_held(&c->gc_lock); BUG_ON(!btree_node_intent_locked(path, b->c.level)); BUG_ON(!b->c.level); BUG_ON(!as || as->b); bch2_verify_keylist_sorted(keys); ret = bch2_btree_node_lock_write(trans, path, &b->c); if (ret) return ret; bch2_btree_node_prep_for_write(trans, path, b); if (!bch2_btree_node_insert_fits(b, bch2_keylist_u64s(keys))) { bch2_btree_node_unlock_write(trans, path, b); goto split; } ret = bch2_btree_node_check_topology(trans, b); if (ret) { bch2_btree_node_unlock_write(trans, path, b); return ret; } bch2_btree_insert_keys_interior(as, trans, path, b, path->l[b->c.level].iter, keys); trans_for_each_path_with_node(trans, b, linked, i) bch2_btree_node_iter_peek(&linked->l[b->c.level].iter, b); bch2_trans_verify_paths(trans); live_u64s_added = (int) b->nr.live_u64s - old_live_u64s; u64s_added = (int) le16_to_cpu(btree_bset_last(b)->u64s) - old_u64s; if (b->sib_u64s[0] != U16_MAX && live_u64s_added < 0) b->sib_u64s[0] = max(0, (int) b->sib_u64s[0] + live_u64s_added); if (b->sib_u64s[1] != U16_MAX && live_u64s_added < 0) b->sib_u64s[1] = max(0, (int) b->sib_u64s[1] + live_u64s_added); if (u64s_added > live_u64s_added && bch2_maybe_compact_whiteouts(c, b)) bch2_trans_node_reinit_iter(trans, b); btree_update_updated_node(as, b); bch2_btree_node_unlock_write(trans, path, b); BUG_ON(bch2_btree_node_check_topology(trans, b)); return 0; split: /* * We could attempt to avoid the transaction restart, by calling * bch2_btree_path_upgrade() and allocating more nodes: */ if (b->c.level >= as->update_level_end) { trace_and_count(c, trans_restart_split_race, trans, _THIS_IP_, b); return btree_trans_restart(trans, BCH_ERR_transaction_restart_split_race); } return btree_split(as, trans, path_idx, b, keys); } int bch2_btree_split_leaf(struct btree_trans *trans, btree_path_idx_t path, unsigned flags) { /* btree_split & merge may both cause paths array to be reallocated */ struct btree *b = path_l(trans->paths + path)->b; struct btree_update *as; unsigned l; int ret = 0; as = bch2_btree_update_start(trans, trans->paths + path, trans->paths[path].level, true, flags); if (IS_ERR(as)) return PTR_ERR(as); ret = btree_split(as, trans, path, b, NULL); if (ret) { bch2_btree_update_free(as, trans); return ret; } bch2_btree_update_done(as, trans); for (l = trans->paths[path].level + 1; btree_node_intent_locked(&trans->paths[path], l) && !ret; l++) ret = bch2_foreground_maybe_merge(trans, path, l, flags); return ret; } static void __btree_increase_depth(struct btree_update *as, struct btree_trans *trans, btree_path_idx_t path_idx) { struct bch_fs *c = as->c; struct btree_path *path = trans->paths + path_idx; struct btree *n, *b = bch2_btree_id_root(c, path->btree_id)->b; BUG_ON(!btree_node_locked(path, b->c.level)); n = __btree_root_alloc(as, trans, b->c.level + 1); bch2_btree_update_add_new_node(as, n); six_unlock_write(&n->c.lock); path->locks_want++; BUG_ON(btree_node_locked(path, n->c.level)); six_lock_increment(&n->c.lock, SIX_LOCK_intent); mark_btree_node_locked(trans, path, n->c.level, BTREE_NODE_INTENT_LOCKED); bch2_btree_path_level_init(trans, path, n); n->sib_u64s[0] = U16_MAX; n->sib_u64s[1] = U16_MAX; bch2_keylist_add(&as->parent_keys, &b->key); btree_split_insert_keys(as, trans, path_idx, n, &as->parent_keys); int ret = bch2_btree_set_root(as, trans, path, n, true); BUG_ON(ret); bch2_btree_update_get_open_buckets(as, n); bch2_btree_node_write(c, n, SIX_LOCK_intent, 0); bch2_trans_node_add(trans, path, n); six_unlock_intent(&n->c.lock); mutex_lock(&c->btree_cache.lock); list_add_tail(&b->list, &c->btree_cache.live); mutex_unlock(&c->btree_cache.lock); bch2_trans_verify_locks(trans); } int bch2_btree_increase_depth(struct btree_trans *trans, btree_path_idx_t path, unsigned flags) { struct bch_fs *c = trans->c; struct btree *b = bch2_btree_id_root(c, trans->paths[path].btree_id)->b; if (btree_node_fake(b)) return bch2_btree_split_leaf(trans, path, flags); struct btree_update *as = bch2_btree_update_start(trans, trans->paths + path, b->c.level, true, flags); if (IS_ERR(as)) return PTR_ERR(as); __btree_increase_depth(as, trans, path); bch2_btree_update_done(as, trans); return 0; } int __bch2_foreground_maybe_merge(struct btree_trans *trans, btree_path_idx_t path, unsigned level, unsigned flags, enum btree_node_sibling sib) { struct bch_fs *c = trans->c; struct btree_update *as; struct bkey_format_state new_s; struct bkey_format new_f; struct bkey_i delete; struct btree *b, *m, *n, *prev, *next, *parent; struct bpos sib_pos; size_t sib_u64s; enum btree_id btree = trans->paths[path].btree_id; btree_path_idx_t sib_path = 0, new_path = 0; u64 start_time = local_clock(); int ret = 0; bch2_trans_verify_not_in_restart(trans); bch2_trans_verify_not_unlocked(trans); BUG_ON(!trans->paths[path].should_be_locked); BUG_ON(!btree_node_locked(&trans->paths[path], level)); /* * Work around a deadlock caused by the btree write buffer not doing * merges and leaving tons of merges for us to do - we really don't need * to be doing merges at all from the interior update path, and if the * interior update path is generating too many new interior updates we * deadlock: */ if ((flags & BCH_WATERMARK_MASK) == BCH_WATERMARK_interior_updates) return 0; if ((flags & BCH_WATERMARK_MASK) <= BCH_WATERMARK_reclaim) { flags &= ~BCH_WATERMARK_MASK; flags |= BCH_WATERMARK_btree; flags |= BCH_TRANS_COMMIT_journal_reclaim; } b = trans->paths[path].l[level].b; if ((sib == btree_prev_sib && bpos_eq(b->data->min_key, POS_MIN)) || (sib == btree_next_sib && bpos_eq(b->data->max_key, SPOS_MAX))) { b->sib_u64s[sib] = U16_MAX; return 0; } sib_pos = sib == btree_prev_sib ? bpos_predecessor(b->data->min_key) : bpos_successor(b->data->max_key); sib_path = bch2_path_get(trans, btree, sib_pos, U8_MAX, level, BTREE_ITER_intent, _THIS_IP_); ret = bch2_btree_path_traverse(trans, sib_path, false); if (ret) goto err; btree_path_set_should_be_locked(trans->paths + sib_path); m = trans->paths[sib_path].l[level].b; if (btree_node_parent(trans->paths + path, b) != btree_node_parent(trans->paths + sib_path, m)) { b->sib_u64s[sib] = U16_MAX; goto out; } if (sib == btree_prev_sib) { prev = m; next = b; } else { prev = b; next = m; } if (!bpos_eq(bpos_successor(prev->data->max_key), next->data->min_key)) { struct printbuf buf1 = PRINTBUF, buf2 = PRINTBUF; bch2_bpos_to_text(&buf1, prev->data->max_key); bch2_bpos_to_text(&buf2, next->data->min_key); bch_err(c, "%s(): btree topology error:\n" " prev ends at %s\n" " next starts at %s", __func__, buf1.buf, buf2.buf); printbuf_exit(&buf1); printbuf_exit(&buf2); ret = bch2_topology_error(c); goto err; } bch2_bkey_format_init(&new_s); bch2_bkey_format_add_pos(&new_s, prev->data->min_key); __bch2_btree_calc_format(&new_s, prev); __bch2_btree_calc_format(&new_s, next); bch2_bkey_format_add_pos(&new_s, next->data->max_key); new_f = bch2_bkey_format_done(&new_s); sib_u64s = btree_node_u64s_with_format(b->nr, &b->format, &new_f) + btree_node_u64s_with_format(m->nr, &m->format, &new_f); if (sib_u64s > BTREE_FOREGROUND_MERGE_HYSTERESIS(c)) { sib_u64s -= BTREE_FOREGROUND_MERGE_HYSTERESIS(c); sib_u64s /= 2; sib_u64s += BTREE_FOREGROUND_MERGE_HYSTERESIS(c); } sib_u64s = min(sib_u64s, btree_max_u64s(c)); sib_u64s = min(sib_u64s, (size_t) U16_MAX - 1); b->sib_u64s[sib] = sib_u64s; if (b->sib_u64s[sib] > c->btree_foreground_merge_threshold) goto out; parent = btree_node_parent(trans->paths + path, b); as = bch2_btree_update_start(trans, trans->paths + path, level, false, BCH_TRANS_COMMIT_no_enospc|flags); ret = PTR_ERR_OR_ZERO(as); if (ret) goto err; trace_and_count(c, btree_node_merge, trans, b); bch2_btree_interior_update_will_free_node(as, b); bch2_btree_interior_update_will_free_node(as, m); n = bch2_btree_node_alloc(as, trans, b->c.level); SET_BTREE_NODE_SEQ(n->data, max(BTREE_NODE_SEQ(b->data), BTREE_NODE_SEQ(m->data)) + 1); btree_set_min(n, prev->data->min_key); btree_set_max(n, next->data->max_key); n->data->format = new_f; btree_node_set_format(n, new_f); bch2_btree_sort_into(c, n, prev); bch2_btree_sort_into(c, n, next); bch2_btree_build_aux_trees(n); bch2_btree_update_add_new_node(as, n); six_unlock_write(&n->c.lock); new_path = bch2_path_get_unlocked_mut(trans, btree, n->c.level, n->key.k.p); six_lock_increment(&n->c.lock, SIX_LOCK_intent); mark_btree_node_locked(trans, trans->paths + new_path, n->c.level, BTREE_NODE_INTENT_LOCKED); bch2_btree_path_level_init(trans, trans->paths + new_path, n); bkey_init(&delete.k); delete.k.p = prev->key.k.p; bch2_keylist_add(&as->parent_keys, &delete); bch2_keylist_add(&as->parent_keys, &n->key); bch2_trans_verify_paths(trans); ret = bch2_btree_insert_node(as, trans, path, parent, &as->parent_keys); if (ret) goto err_free_update; bch2_trans_verify_paths(trans); bch2_btree_update_get_open_buckets(as, n); bch2_btree_node_write(c, n, SIX_LOCK_intent, 0); bch2_btree_node_free_inmem(trans, trans->paths + path, b); bch2_btree_node_free_inmem(trans, trans->paths + sib_path, m); bch2_trans_node_add(trans, trans->paths + path, n); bch2_trans_verify_paths(trans); six_unlock_intent(&n->c.lock); bch2_btree_update_done(as, trans); bch2_time_stats_update(&c->times[BCH_TIME_btree_node_merge], start_time); out: err: if (new_path) bch2_path_put(trans, new_path, true); bch2_path_put(trans, sib_path, true); bch2_trans_verify_locks(trans); if (ret == -BCH_ERR_journal_reclaim_would_deadlock) ret = 0; if (!ret) ret = bch2_trans_relock(trans); return ret; err_free_update: bch2_btree_node_free_never_used(as, trans, n); bch2_btree_update_free(as, trans); goto out; } int bch2_btree_node_rewrite(struct btree_trans *trans, struct btree_iter *iter, struct btree *b, unsigned flags) { struct bch_fs *c = trans->c; struct btree *n, *parent; struct btree_update *as; btree_path_idx_t new_path = 0; int ret; flags |= BCH_TRANS_COMMIT_no_enospc; struct btree_path *path = btree_iter_path(trans, iter); parent = btree_node_parent(path, b); as = bch2_btree_update_start(trans, path, b->c.level, false, flags); ret = PTR_ERR_OR_ZERO(as); if (ret) goto out; bch2_btree_interior_update_will_free_node(as, b); n = bch2_btree_node_alloc_replacement(as, trans, b); bch2_btree_build_aux_trees(n); bch2_btree_update_add_new_node(as, n); six_unlock_write(&n->c.lock); new_path = bch2_path_get_unlocked_mut(trans, iter->btree_id, n->c.level, n->key.k.p); six_lock_increment(&n->c.lock, SIX_LOCK_intent); mark_btree_node_locked(trans, trans->paths + new_path, n->c.level, BTREE_NODE_INTENT_LOCKED); bch2_btree_path_level_init(trans, trans->paths + new_path, n); trace_and_count(c, btree_node_rewrite, trans, b); if (parent) { bch2_keylist_add(&as->parent_keys, &n->key); ret = bch2_btree_insert_node(as, trans, iter->path, parent, &as->parent_keys); } else { ret = bch2_btree_set_root(as, trans, btree_iter_path(trans, iter), n, false); } if (ret) goto err; bch2_btree_update_get_open_buckets(as, n); bch2_btree_node_write(c, n, SIX_LOCK_intent, 0); bch2_btree_node_free_inmem(trans, btree_iter_path(trans, iter), b); bch2_trans_node_add(trans, trans->paths + iter->path, n); six_unlock_intent(&n->c.lock); bch2_btree_update_done(as, trans); out: if (new_path) bch2_path_put(trans, new_path, true); bch2_trans_downgrade(trans); return ret; err: bch2_btree_node_free_never_used(as, trans, n); bch2_btree_update_free(as, trans); goto out; } struct async_btree_rewrite { struct bch_fs *c; struct work_struct work; struct list_head list; enum btree_id btree_id; unsigned level; struct bpos pos; __le64 seq; }; static int async_btree_node_rewrite_trans(struct btree_trans *trans, struct async_btree_rewrite *a) { struct bch_fs *c = trans->c; struct btree_iter iter; struct btree *b; int ret; bch2_trans_node_iter_init(trans, &iter, a->btree_id, a->pos, BTREE_MAX_DEPTH, a->level, 0); b = bch2_btree_iter_peek_node(&iter); ret = PTR_ERR_OR_ZERO(b); if (ret) goto out; if (!b || b->data->keys.seq != a->seq) { struct printbuf buf = PRINTBUF; if (b) bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); else prt_str(&buf, "(null"); bch_info(c, "%s: node to rewrite not found:, searching for seq %llu, got\n%s", __func__, a->seq, buf.buf); printbuf_exit(&buf); goto out; } ret = bch2_btree_node_rewrite(trans, &iter, b, 0); out: bch2_trans_iter_exit(trans, &iter); return ret; } static void async_btree_node_rewrite_work(struct work_struct *work) { struct async_btree_rewrite *a = container_of(work, struct async_btree_rewrite, work); struct bch_fs *c = a->c; int ret; ret = bch2_trans_do(c, NULL, NULL, 0, async_btree_node_rewrite_trans(trans, a)); bch_err_fn_ratelimited(c, ret); bch2_write_ref_put(c, BCH_WRITE_REF_node_rewrite); kfree(a); } void bch2_btree_node_rewrite_async(struct bch_fs *c, struct btree *b) { struct async_btree_rewrite *a; int ret; a = kmalloc(sizeof(*a), GFP_NOFS); if (!a) { bch_err(c, "%s: error allocating memory", __func__); return; } a->c = c; a->btree_id = b->c.btree_id; a->level = b->c.level; a->pos = b->key.k.p; a->seq = b->data->keys.seq; INIT_WORK(&a->work, async_btree_node_rewrite_work); if (unlikely(!test_bit(BCH_FS_may_go_rw, &c->flags))) { mutex_lock(&c->pending_node_rewrites_lock); list_add(&a->list, &c->pending_node_rewrites); mutex_unlock(&c->pending_node_rewrites_lock); return; } if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_node_rewrite)) { if (test_bit(BCH_FS_started, &c->flags)) { bch_err(c, "%s: error getting c->writes ref", __func__); kfree(a); return; } ret = bch2_fs_read_write_early(c); bch_err_msg(c, ret, "going read-write"); if (ret) { kfree(a); return; } bch2_write_ref_get(c, BCH_WRITE_REF_node_rewrite); } queue_work(c->btree_node_rewrite_worker, &a->work); } void bch2_do_pending_node_rewrites(struct bch_fs *c) { struct async_btree_rewrite *a, *n; mutex_lock(&c->pending_node_rewrites_lock); list_for_each_entry_safe(a, n, &c->pending_node_rewrites, list) { list_del(&a->list); bch2_write_ref_get(c, BCH_WRITE_REF_node_rewrite); queue_work(c->btree_node_rewrite_worker, &a->work); } mutex_unlock(&c->pending_node_rewrites_lock); } void bch2_free_pending_node_rewrites(struct bch_fs *c) { struct async_btree_rewrite *a, *n; mutex_lock(&c->pending_node_rewrites_lock); list_for_each_entry_safe(a, n, &c->pending_node_rewrites, list) { list_del(&a->list); kfree(a); } mutex_unlock(&c->pending_node_rewrites_lock); } static int __bch2_btree_node_update_key(struct btree_trans *trans, struct btree_iter *iter, struct btree *b, struct btree *new_hash, struct bkey_i *new_key, unsigned commit_flags, bool skip_triggers) { struct bch_fs *c = trans->c; struct btree_iter iter2 = { NULL }; struct btree *parent; int ret; if (!skip_triggers) { ret = bch2_key_trigger_old(trans, b->c.btree_id, b->c.level + 1, bkey_i_to_s_c(&b->key), BTREE_TRIGGER_transactional) ?: bch2_key_trigger_new(trans, b->c.btree_id, b->c.level + 1, bkey_i_to_s(new_key), BTREE_TRIGGER_transactional); if (ret) return ret; } if (new_hash) { bkey_copy(&new_hash->key, new_key); ret = bch2_btree_node_hash_insert(&c->btree_cache, new_hash, b->c.level, b->c.btree_id); BUG_ON(ret); } parent = btree_node_parent(btree_iter_path(trans, iter), b); if (parent) { bch2_trans_copy_iter(&iter2, iter); iter2.path = bch2_btree_path_make_mut(trans, iter2.path, iter2.flags & BTREE_ITER_intent, _THIS_IP_); struct btree_path *path2 = btree_iter_path(trans, &iter2); BUG_ON(path2->level != b->c.level); BUG_ON(!bpos_eq(path2->pos, new_key->k.p)); btree_path_set_level_up(trans, path2); trans->paths_sorted = false; ret = bch2_btree_iter_traverse(&iter2) ?: bch2_trans_update(trans, &iter2, new_key, BTREE_TRIGGER_norun); if (ret) goto err; } else { BUG_ON(btree_node_root(c, b) != b); struct jset_entry *e = bch2_trans_jset_entry_alloc(trans, jset_u64s(new_key->k.u64s)); ret = PTR_ERR_OR_ZERO(e); if (ret) return ret; journal_entry_set(e, BCH_JSET_ENTRY_btree_root, b->c.btree_id, b->c.level, new_key, new_key->k.u64s); } ret = bch2_trans_commit(trans, NULL, NULL, commit_flags); if (ret) goto err; bch2_btree_node_lock_write_nofail(trans, btree_iter_path(trans, iter), &b->c); if (new_hash) { mutex_lock(&c->btree_cache.lock); bch2_btree_node_hash_remove(&c->btree_cache, new_hash); bch2_btree_node_hash_remove(&c->btree_cache, b); bkey_copy(&b->key, new_key); ret = __bch2_btree_node_hash_insert(&c->btree_cache, b); BUG_ON(ret); mutex_unlock(&c->btree_cache.lock); } else { bkey_copy(&b->key, new_key); } bch2_btree_node_unlock_write(trans, btree_iter_path(trans, iter), b); out: bch2_trans_iter_exit(trans, &iter2); return ret; err: if (new_hash) { mutex_lock(&c->btree_cache.lock); bch2_btree_node_hash_remove(&c->btree_cache, b); mutex_unlock(&c->btree_cache.lock); } goto out; } int bch2_btree_node_update_key(struct btree_trans *trans, struct btree_iter *iter, struct btree *b, struct bkey_i *new_key, unsigned commit_flags, bool skip_triggers) { struct bch_fs *c = trans->c; struct btree *new_hash = NULL; struct btree_path *path = btree_iter_path(trans, iter); struct closure cl; int ret = 0; ret = bch2_btree_path_upgrade(trans, path, b->c.level + 1); if (ret) return ret; closure_init_stack(&cl); /* * check btree_ptr_hash_val() after @b is locked by * btree_iter_traverse(): */ if (btree_ptr_hash_val(new_key) != b->hash_val) { ret = bch2_btree_cache_cannibalize_lock(trans, &cl); if (ret) { ret = drop_locks_do(trans, (closure_sync(&cl), 0)); if (ret) return ret; } new_hash = bch2_btree_node_mem_alloc(trans, false); ret = PTR_ERR_OR_ZERO(new_hash); if (ret) goto err; } path->intent_ref++; ret = __bch2_btree_node_update_key(trans, iter, b, new_hash, new_key, commit_flags, skip_triggers); --path->intent_ref; if (new_hash) bch2_btree_node_to_freelist(c, new_hash); err: closure_sync(&cl); bch2_btree_cache_cannibalize_unlock(trans); return ret; } int bch2_btree_node_update_key_get_iter(struct btree_trans *trans, struct btree *b, struct bkey_i *new_key, unsigned commit_flags, bool skip_triggers) { struct btree_iter iter; int ret; bch2_trans_node_iter_init(trans, &iter, b->c.btree_id, b->key.k.p, BTREE_MAX_DEPTH, b->c.level, BTREE_ITER_intent); ret = bch2_btree_iter_traverse(&iter); if (ret) goto out; /* has node been freed? */ if (btree_iter_path(trans, &iter)->l[b->c.level].b != b) { /* node has been freed: */ BUG_ON(!btree_node_dying(b)); goto out; } BUG_ON(!btree_node_hashed(b)); bch2_bkey_drop_ptrs(bkey_i_to_s(new_key), ptr, !bch2_bkey_has_device(bkey_i_to_s(&b->key), ptr->dev)); ret = bch2_btree_node_update_key(trans, &iter, b, new_key, commit_flags, skip_triggers); out: bch2_trans_iter_exit(trans, &iter); return ret; } /* Init code: */ /* * Only for filesystem bringup, when first reading the btree roots or allocating * btree roots when initializing a new filesystem: */ void bch2_btree_set_root_for_read(struct bch_fs *c, struct btree *b) { BUG_ON(btree_node_root(c, b)); bch2_btree_set_root_inmem(c, b); } int bch2_btree_root_alloc_fake_trans(struct btree_trans *trans, enum btree_id id, unsigned level) { struct bch_fs *c = trans->c; struct closure cl; struct btree *b; int ret; closure_init_stack(&cl); do { ret = bch2_btree_cache_cannibalize_lock(trans, &cl); closure_sync(&cl); } while (ret); b = bch2_btree_node_mem_alloc(trans, false); bch2_btree_cache_cannibalize_unlock(trans); ret = PTR_ERR_OR_ZERO(b); if (ret) return ret; set_btree_node_fake(b); set_btree_node_need_rewrite(b); b->c.level = level; b->c.btree_id = id; bkey_btree_ptr_init(&b->key); b->key.k.p = SPOS_MAX; *((u64 *) bkey_i_to_btree_ptr(&b->key)->v.start) = U64_MAX - id; bch2_bset_init_first(b, &b->data->keys); bch2_btree_build_aux_trees(b); b->data->flags = 0; btree_set_min(b, POS_MIN); btree_set_max(b, SPOS_MAX); b->data->format = bch2_btree_calc_format(b); btree_node_set_format(b, b->data->format); ret = bch2_btree_node_hash_insert(&c->btree_cache, b, b->c.level, b->c.btree_id); BUG_ON(ret); bch2_btree_set_root_inmem(c, b); six_unlock_write(&b->c.lock); six_unlock_intent(&b->c.lock); return 0; } void bch2_btree_root_alloc_fake(struct bch_fs *c, enum btree_id id, unsigned level) { bch2_trans_run(c, lockrestart_do(trans, bch2_btree_root_alloc_fake_trans(trans, id, level))); } static void bch2_btree_update_to_text(struct printbuf *out, struct btree_update *as) { prt_printf(out, "%ps: ", (void *) as->ip_started); bch2_trans_commit_flags_to_text(out, as->flags); prt_printf(out, " btree=%s l=%u-%u mode=%s nodes_written=%u cl.remaining=%u journal_seq=%llu\n", bch2_btree_id_str(as->btree_id), as->update_level_start, as->update_level_end, bch2_btree_update_modes[as->mode], as->nodes_written, closure_nr_remaining(&as->cl), as->journal.seq); } void bch2_btree_updates_to_text(struct printbuf *out, struct bch_fs *c) { struct btree_update *as; mutex_lock(&c->btree_interior_update_lock); list_for_each_entry(as, &c->btree_interior_update_list, list) bch2_btree_update_to_text(out, as); mutex_unlock(&c->btree_interior_update_lock); } static bool bch2_btree_interior_updates_pending(struct bch_fs *c) { bool ret; mutex_lock(&c->btree_interior_update_lock); ret = !list_empty(&c->btree_interior_update_list); mutex_unlock(&c->btree_interior_update_lock); return ret; } bool bch2_btree_interior_updates_flush(struct bch_fs *c) { bool ret = bch2_btree_interior_updates_pending(c); if (ret) closure_wait_event(&c->btree_interior_update_wait, !bch2_btree_interior_updates_pending(c)); return ret; } void bch2_journal_entry_to_btree_root(struct bch_fs *c, struct jset_entry *entry) { struct btree_root *r = bch2_btree_id_root(c, entry->btree_id); mutex_lock(&c->btree_root_lock); r->level = entry->level; r->alive = true; bkey_copy(&r->key, (struct bkey_i *) entry->start); mutex_unlock(&c->btree_root_lock); } struct jset_entry * bch2_btree_roots_to_journal_entries(struct bch_fs *c, struct jset_entry *end, unsigned long skip) { unsigned i; mutex_lock(&c->btree_root_lock); for (i = 0; i < btree_id_nr_alive(c); i++) { struct btree_root *r = bch2_btree_id_root(c, i); if (r->alive && !test_bit(i, &skip)) { journal_entry_set(end, BCH_JSET_ENTRY_btree_root, i, r->level, &r->key, r->key.k.u64s); end = vstruct_next(end); } } mutex_unlock(&c->btree_root_lock); return end; } static void bch2_btree_alloc_to_text(struct printbuf *out, struct bch_fs *c, struct btree_alloc *a) { printbuf_indent_add(out, 2); bch2_bkey_val_to_text(out, c, bkey_i_to_s_c(&a->k)); prt_newline(out); struct open_bucket *ob; unsigned i; open_bucket_for_each(c, &a->ob, ob, i) bch2_open_bucket_to_text(out, c, ob); printbuf_indent_sub(out, 2); } void bch2_btree_reserve_cache_to_text(struct printbuf *out, struct bch_fs *c) { for (unsigned i = 0; i < c->btree_reserve_cache_nr; i++) bch2_btree_alloc_to_text(out, c, &c->btree_reserve_cache[i]); } void bch2_fs_btree_interior_update_exit(struct bch_fs *c) { if (c->btree_node_rewrite_worker) destroy_workqueue(c->btree_node_rewrite_worker); if (c->btree_interior_update_worker) destroy_workqueue(c->btree_interior_update_worker); mempool_exit(&c->btree_interior_update_pool); } void bch2_fs_btree_interior_update_init_early(struct bch_fs *c) { mutex_init(&c->btree_reserve_cache_lock); INIT_LIST_HEAD(&c->btree_interior_update_list); INIT_LIST_HEAD(&c->btree_interior_updates_unwritten); mutex_init(&c->btree_interior_update_lock); INIT_WORK(&c->btree_interior_update_work, btree_interior_update_work); INIT_LIST_HEAD(&c->pending_node_rewrites); mutex_init(&c->pending_node_rewrites_lock); } int bch2_fs_btree_interior_update_init(struct bch_fs *c) { c->btree_interior_update_worker = alloc_workqueue("btree_update", WQ_UNBOUND|WQ_MEM_RECLAIM, 8); if (!c->btree_interior_update_worker) return -BCH_ERR_ENOMEM_btree_interior_update_worker_init; c->btree_node_rewrite_worker = alloc_ordered_workqueue("btree_node_rewrite", WQ_UNBOUND); if (!c->btree_node_rewrite_worker) return -BCH_ERR_ENOMEM_btree_interior_update_worker_init; if (mempool_init_kmalloc_pool(&c->btree_interior_update_pool, 1, sizeof(struct btree_update))) return -BCH_ERR_ENOMEM_btree_interior_update_pool_init; return 0; } |
| 88 89 88 58 37 89 89 1 1 1 1 1 1 2 2 2 2 2 6 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 | // SPDX-License-Identifier: GPL-2.0 /* * Block stat tracking code * * Copyright (C) 2016 Jens Axboe */ #include <linux/kernel.h> #include <linux/rculist.h> #include "blk-stat.h" #include "blk-mq.h" #include "blk.h" struct blk_queue_stats { struct list_head callbacks; spinlock_t lock; int accounting; }; void blk_rq_stat_init(struct blk_rq_stat *stat) { stat->min = -1ULL; stat->max = stat->nr_samples = stat->mean = 0; stat->batch = 0; } /* src is a per-cpu stat, mean isn't initialized */ void blk_rq_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src) { if (dst->nr_samples + src->nr_samples <= dst->nr_samples) return; dst->min = min(dst->min, src->min); dst->max = max(dst->max, src->max); dst->mean = div_u64(src->batch + dst->mean * dst->nr_samples, dst->nr_samples + src->nr_samples); dst->nr_samples += src->nr_samples; } void blk_rq_stat_add(struct blk_rq_stat *stat, u64 value) { stat->min = min(stat->min, value); stat->max = max(stat->max, value); stat->batch += value; stat->nr_samples++; } void blk_stat_add(struct request *rq, u64 now) { struct request_queue *q = rq->q; struct blk_stat_callback *cb; struct blk_rq_stat *stat; int bucket, cpu; u64 value; value = (now >= rq->io_start_time_ns) ? now - rq->io_start_time_ns : 0; rcu_read_lock(); cpu = get_cpu(); list_for_each_entry_rcu(cb, &q->stats->callbacks, list) { if (!blk_stat_is_active(cb)) continue; bucket = cb->bucket_fn(rq); if (bucket < 0) continue; stat = &per_cpu_ptr(cb->cpu_stat, cpu)[bucket]; blk_rq_stat_add(stat, value); } put_cpu(); rcu_read_unlock(); } static void blk_stat_timer_fn(struct timer_list *t) { struct blk_stat_callback *cb = from_timer(cb, t, timer); unsigned int bucket; int cpu; for (bucket = 0; bucket < cb->buckets; bucket++) blk_rq_stat_init(&cb->stat[bucket]); for_each_online_cpu(cpu) { struct blk_rq_stat *cpu_stat; cpu_stat = per_cpu_ptr(cb->cpu_stat, cpu); for (bucket = 0; bucket < cb->buckets; bucket++) { blk_rq_stat_sum(&cb->stat[bucket], &cpu_stat[bucket]); blk_rq_stat_init(&cpu_stat[bucket]); } } cb->timer_fn(cb); } struct blk_stat_callback * blk_stat_alloc_callback(void (*timer_fn)(struct blk_stat_callback *), int (*bucket_fn)(const struct request *), unsigned int buckets, void *data) { struct blk_stat_callback *cb; cb = kmalloc(sizeof(*cb), GFP_KERNEL); if (!cb) return NULL; cb->stat = kmalloc_array(buckets, sizeof(struct blk_rq_stat), GFP_KERNEL); if (!cb->stat) { kfree(cb); return NULL; } cb->cpu_stat = __alloc_percpu(buckets * sizeof(struct blk_rq_stat), __alignof__(struct blk_rq_stat)); if (!cb->cpu_stat) { kfree(cb->stat); kfree(cb); return NULL; } cb->timer_fn = timer_fn; cb->bucket_fn = bucket_fn; cb->data = data; cb->buckets = buckets; timer_setup(&cb->timer, blk_stat_timer_fn, 0); return cb; } void blk_stat_add_callback(struct request_queue *q, struct blk_stat_callback *cb) { unsigned int bucket; unsigned long flags; int cpu; for_each_possible_cpu(cpu) { struct blk_rq_stat *cpu_stat; cpu_stat = per_cpu_ptr(cb->cpu_stat, cpu); for (bucket = 0; bucket < cb->buckets; bucket++) blk_rq_stat_init(&cpu_stat[bucket]); } spin_lock_irqsave(&q->stats->lock, flags); list_add_tail_rcu(&cb->list, &q->stats->callbacks); blk_queue_flag_set(QUEUE_FLAG_STATS, q); spin_unlock_irqrestore(&q->stats->lock, flags); } void blk_stat_remove_callback(struct request_queue *q, struct blk_stat_callback *cb) { unsigned long flags; spin_lock_irqsave(&q->stats->lock, flags); list_del_rcu(&cb->list); if (list_empty(&q->stats->callbacks) && !q->stats->accounting) blk_queue_flag_clear(QUEUE_FLAG_STATS, q); spin_unlock_irqrestore(&q->stats->lock, flags); del_timer_sync(&cb->timer); } static void blk_stat_free_callback_rcu(struct rcu_head *head) { struct blk_stat_callback *cb; cb = container_of(head, struct blk_stat_callback, rcu); free_percpu(cb->cpu_stat); kfree(cb->stat); kfree(cb); } void blk_stat_free_callback(struct blk_stat_callback *cb) { if (cb) call_rcu(&cb->rcu, blk_stat_free_callback_rcu); } void blk_stat_disable_accounting(struct request_queue *q) { unsigned long flags; spin_lock_irqsave(&q->stats->lock, flags); if (!--q->stats->accounting && list_empty(&q->stats->callbacks)) blk_queue_flag_clear(QUEUE_FLAG_STATS, q); spin_unlock_irqrestore(&q->stats->lock, flags); } EXPORT_SYMBOL_GPL(blk_stat_disable_accounting); void blk_stat_enable_accounting(struct request_queue *q) { unsigned long flags; spin_lock_irqsave(&q->stats->lock, flags); if (!q->stats->accounting++ && list_empty(&q->stats->callbacks)) blk_queue_flag_set(QUEUE_FLAG_STATS, q); spin_unlock_irqrestore(&q->stats->lock, flags); } EXPORT_SYMBOL_GPL(blk_stat_enable_accounting); struct blk_queue_stats *blk_alloc_queue_stats(void) { struct blk_queue_stats *stats; stats = kmalloc(sizeof(*stats), GFP_KERNEL); if (!stats) return NULL; INIT_LIST_HEAD(&stats->callbacks); spin_lock_init(&stats->lock); stats->accounting = 0; return stats; } void blk_free_queue_stats(struct blk_queue_stats *stats) { if (!stats) return; WARN_ON(!list_empty(&stats->callbacks)); kfree(stats); } |
| 4762 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TIMEKEEPING_H #define _LINUX_TIMEKEEPING_H #include <linux/errno.h> #include <linux/clocksource_ids.h> #include <linux/ktime.h> /* Included from linux/ktime.h */ void timekeeping_init(void); extern int timekeeping_suspended; /* Architecture timer tick functions: */ extern void legacy_timer_tick(unsigned long ticks); /* * Get and set timeofday */ extern int do_settimeofday64(const struct timespec64 *ts); extern int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz); /* * ktime_get() family - read the current time in a multitude of ways. * * The default time reference is CLOCK_MONOTONIC, starting at * boot time but not counting the time spent in suspend. * For other references, use the functions with "real", "clocktai", * "boottime" and "raw" suffixes. * * To get the time in a different format, use the ones with * "ns", "ts64" and "seconds" suffix. * * See Documentation/core-api/timekeeping.rst for more details. */ /* * timespec64 based interfaces */ extern void ktime_get_raw_ts64(struct timespec64 *ts); extern void ktime_get_ts64(struct timespec64 *ts); extern void ktime_get_real_ts64(struct timespec64 *tv); extern void ktime_get_coarse_ts64(struct timespec64 *ts); extern void ktime_get_coarse_real_ts64(struct timespec64 *ts); void getboottime64(struct timespec64 *ts); /* * time64_t base interfaces */ extern time64_t ktime_get_seconds(void); extern time64_t __ktime_get_real_seconds(void); extern time64_t ktime_get_real_seconds(void); /* * ktime_t based interfaces */ enum tk_offsets { TK_OFFS_REAL, TK_OFFS_BOOT, TK_OFFS_TAI, TK_OFFS_MAX, }; extern ktime_t ktime_get(void); extern ktime_t ktime_get_with_offset(enum tk_offsets offs); extern ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs); extern ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs); extern ktime_t ktime_get_raw(void); extern u32 ktime_get_resolution_ns(void); /** * ktime_get_real - get the real (wall-) time in ktime_t format * * Returns: real (wall) time in ktime_t format */ static inline ktime_t ktime_get_real(void) { return ktime_get_with_offset(TK_OFFS_REAL); } static inline ktime_t ktime_get_coarse_real(void) { return ktime_get_coarse_with_offset(TK_OFFS_REAL); } /** * ktime_get_boottime - Get monotonic time since boot in ktime_t format * * This is similar to CLOCK_MONTONIC/ktime_get, but also includes the * time spent in suspend. * * Returns: monotonic time since boot in ktime_t format */ static inline ktime_t ktime_get_boottime(void) { return ktime_get_with_offset(TK_OFFS_BOOT); } static inline ktime_t ktime_get_coarse_boottime(void) { return ktime_get_coarse_with_offset(TK_OFFS_BOOT); } /** * ktime_get_clocktai - Get the TAI time of day in ktime_t format * * Returns: the TAI time of day in ktime_t format */ static inline ktime_t ktime_get_clocktai(void) { return ktime_get_with_offset(TK_OFFS_TAI); } static inline ktime_t ktime_get_coarse_clocktai(void) { return ktime_get_coarse_with_offset(TK_OFFS_TAI); } static inline ktime_t ktime_get_coarse(void) { struct timespec64 ts; ktime_get_coarse_ts64(&ts); return timespec64_to_ktime(ts); } static inline u64 ktime_get_coarse_ns(void) { return ktime_to_ns(ktime_get_coarse()); } static inline u64 ktime_get_coarse_real_ns(void) { return ktime_to_ns(ktime_get_coarse_real()); } static inline u64 ktime_get_coarse_boottime_ns(void) { return ktime_to_ns(ktime_get_coarse_boottime()); } static inline u64 ktime_get_coarse_clocktai_ns(void) { return ktime_to_ns(ktime_get_coarse_clocktai()); } /** * ktime_mono_to_real - Convert monotonic time to clock realtime * @mono: monotonic time to convert * * Returns: time converted to realtime clock */ static inline ktime_t ktime_mono_to_real(ktime_t mono) { return ktime_mono_to_any(mono, TK_OFFS_REAL); } /** * ktime_get_ns - Get the current time in nanoseconds * * Returns: current time converted to nanoseconds */ static inline u64 ktime_get_ns(void) { return ktime_to_ns(ktime_get()); } /** * ktime_get_real_ns - Get the current real/wall time in nanoseconds * * Returns: current real time converted to nanoseconds */ static inline u64 ktime_get_real_ns(void) { return ktime_to_ns(ktime_get_real()); } /** * ktime_get_boottime_ns - Get the monotonic time since boot in nanoseconds * * Returns: current boottime converted to nanoseconds */ static inline u64 ktime_get_boottime_ns(void) { return ktime_to_ns(ktime_get_boottime()); } /** * ktime_get_clocktai_ns - Get the current TAI time of day in nanoseconds * * Returns: current TAI time converted to nanoseconds */ static inline u64 ktime_get_clocktai_ns(void) { return ktime_to_ns(ktime_get_clocktai()); } /** * ktime_get_raw_ns - Get the raw monotonic time in nanoseconds * * Returns: current raw monotonic time converted to nanoseconds */ static inline u64 ktime_get_raw_ns(void) { return ktime_to_ns(ktime_get_raw()); } extern u64 ktime_get_mono_fast_ns(void); extern u64 ktime_get_raw_fast_ns(void); extern u64 ktime_get_boot_fast_ns(void); extern u64 ktime_get_tai_fast_ns(void); extern u64 ktime_get_real_fast_ns(void); /* * timespec64/time64_t interfaces utilizing the ktime based ones * for API completeness, these could be implemented more efficiently * if needed. */ static inline void ktime_get_boottime_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_boottime()); } static inline void ktime_get_coarse_boottime_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_coarse_boottime()); } static inline time64_t ktime_get_boottime_seconds(void) { return ktime_divns(ktime_get_coarse_boottime(), NSEC_PER_SEC); } static inline void ktime_get_clocktai_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_clocktai()); } static inline void ktime_get_coarse_clocktai_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_coarse_clocktai()); } static inline time64_t ktime_get_clocktai_seconds(void) { return ktime_divns(ktime_get_coarse_clocktai(), NSEC_PER_SEC); } /* * RTC specific */ extern bool timekeeping_rtc_skipsuspend(void); extern bool timekeeping_rtc_skipresume(void); extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta); /** * struct ktime_timestamps - Simultaneous mono/boot/real timestamps * @mono: Monotonic timestamp * @boot: Boottime timestamp * @real: Realtime timestamp */ struct ktime_timestamps { u64 mono; u64 boot; u64 real; }; /** * struct system_time_snapshot - simultaneous raw/real time capture with * counter value * @cycles: Clocksource counter value to produce the system times * @real: Realtime system time * @raw: Monotonic raw system time * @cs_id: Clocksource ID * @clock_was_set_seq: The sequence number of clock-was-set events * @cs_was_changed_seq: The sequence number of clocksource change events */ struct system_time_snapshot { u64 cycles; ktime_t real; ktime_t raw; enum clocksource_ids cs_id; unsigned int clock_was_set_seq; u8 cs_was_changed_seq; }; /** * struct system_device_crosststamp - system/device cross-timestamp * (synchronized capture) * @device: Device time * @sys_realtime: Realtime simultaneous with device time * @sys_monoraw: Monotonic raw simultaneous with device time */ struct system_device_crosststamp { ktime_t device; ktime_t sys_realtime; ktime_t sys_monoraw; }; /** * struct system_counterval_t - system counter value with the ID of the * corresponding clocksource * @cycles: System counter value * @cs_id: Clocksource ID corresponding to system counter value. Used by * timekeeping code to verify comparability of two cycle values. * The default ID, CSID_GENERIC, does not identify a specific * clocksource. * @use_nsecs: @cycles is in nanoseconds. */ struct system_counterval_t { u64 cycles; enum clocksource_ids cs_id; bool use_nsecs; }; extern bool ktime_real_to_base_clock(ktime_t treal, enum clocksource_ids base_id, u64 *cycles); extern bool timekeeping_clocksource_has_base(enum clocksource_ids id); /* * Get cross timestamp between system clock and device clock */ extern int get_device_system_crosststamp( int (*get_time_fn)(ktime_t *device_time, struct system_counterval_t *system_counterval, void *ctx), void *ctx, struct system_time_snapshot *history, struct system_device_crosststamp *xtstamp); /* * Simultaneously snapshot realtime and monotonic raw clocks */ extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot); /* NMI safe mono/boot/realtime timestamps */ extern void ktime_get_fast_timestamps(struct ktime_timestamps *snap); /* * Persistent clock related interfaces */ extern int persistent_clock_is_local; extern void read_persistent_clock64(struct timespec64 *ts); void read_persistent_wall_and_boot_offset(struct timespec64 *wall_clock, struct timespec64 *boot_offset); #ifdef CONFIG_GENERIC_CMOS_UPDATE extern int update_persistent_clock64(struct timespec64 now); #endif #endif |
| 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/bitops.h> #include <linux/math.h> #include <linux/string.h> #include <asm/unaligned.h> #ifdef CONFIG_VALGRIND #include <valgrind/memcheck.h> #endif #include "varint.h" /** * bch2_varint_encode - encode a variable length integer * @out: destination to encode to * @v: unsigned integer to encode * Returns: size in bytes of the encoded integer - at most 9 bytes */ int bch2_varint_encode(u8 *out, u64 v) { unsigned bits = fls64(v|1); unsigned bytes = DIV_ROUND_UP(bits, 7); __le64 v_le; if (likely(bytes < 9)) { v <<= bytes; v |= ~(~0 << (bytes - 1)); v_le = cpu_to_le64(v); memcpy(out, &v_le, bytes); } else { *out++ = 255; bytes = 9; put_unaligned_le64(v, out); } return bytes; } /** * bch2_varint_decode - encode a variable length integer * @in: varint to decode * @end: end of buffer to decode from * @out: on success, decoded integer * Returns: size in bytes of the decoded integer - or -1 on failure (would * have read past the end of the buffer) */ int bch2_varint_decode(const u8 *in, const u8 *end, u64 *out) { unsigned bytes = likely(in < end) ? ffz(*in & 255) + 1 : 1; u64 v; if (unlikely(in + bytes > end)) return -1; if (likely(bytes < 9)) { __le64 v_le = 0; memcpy(&v_le, in, bytes); v = le64_to_cpu(v_le); v >>= bytes; } else { v = get_unaligned_le64(++in); } *out = v; return bytes; } /** * bch2_varint_encode_fast - fast version of bch2_varint_encode * @out: destination to encode to * @v: unsigned integer to encode * Returns: size in bytes of the encoded integer - at most 9 bytes * * This version assumes it's always safe to write 8 bytes to @out, even if the * encoded integer would be smaller. */ int bch2_varint_encode_fast(u8 *out, u64 v) { unsigned bits = fls64(v|1); unsigned bytes = DIV_ROUND_UP(bits, 7); if (likely(bytes < 9)) { v <<= bytes; v |= ~(~0U << (bytes - 1)); } else { *out++ = 255; bytes = 9; } put_unaligned_le64(v, out); return bytes; } /** * bch2_varint_decode_fast - fast version of bch2_varint_decode * @in: varint to decode * @end: end of buffer to decode from * @out: on success, decoded integer * Returns: size in bytes of the decoded integer - or -1 on failure (would * have read past the end of the buffer) * * This version assumes that it is safe to read at most 8 bytes past the end of * @end (we still return an error if the varint extends past @end). */ int bch2_varint_decode_fast(const u8 *in, const u8 *end, u64 *out) { #ifdef CONFIG_VALGRIND VALGRIND_MAKE_MEM_DEFINED(in, 8); #endif u64 v = get_unaligned_le64(in); unsigned bytes = ffz(*in) + 1; if (unlikely(in + bytes > end)) return -1; if (likely(bytes < 9)) { v >>= bytes; v &= ~(~0ULL << (7 * bytes)); } else { v = get_unaligned_le64(++in); } *out = v; return bytes; } |
| 1 1 1 1 1 1 1 1 5 5 4 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 | // SPDX-License-Identifier: GPL-2.0-only /* * File: pn_dev.c * * Phonet network device * * Copyright (C) 2008 Nokia Corporation. * * Authors: Sakari Ailus <sakari.ailus@nokia.com> * Rémi Denis-Courmont */ #include <linux/kernel.h> #include <linux/net.h> #include <linux/slab.h> #include <linux/netdevice.h> #include <linux/phonet.h> #include <linux/proc_fs.h> #include <linux/if_arp.h> #include <net/sock.h> #include <net/netns/generic.h> #include <net/phonet/pn_dev.h> struct phonet_routes { struct mutex lock; struct net_device __rcu *table[64]; }; struct phonet_net { struct phonet_device_list pndevs; struct phonet_routes routes; }; static unsigned int phonet_net_id __read_mostly; static struct phonet_net *phonet_pernet(struct net *net) { return net_generic(net, phonet_net_id); } struct phonet_device_list *phonet_device_list(struct net *net) { struct phonet_net *pnn = phonet_pernet(net); return &pnn->pndevs; } /* Allocate new Phonet device. */ static struct phonet_device *__phonet_device_alloc(struct net_device *dev) { struct phonet_device_list *pndevs = phonet_device_list(dev_net(dev)); struct phonet_device *pnd = kmalloc(sizeof(*pnd), GFP_ATOMIC); if (pnd == NULL) return NULL; pnd->netdev = dev; bitmap_zero(pnd->addrs, 64); BUG_ON(!mutex_is_locked(&pndevs->lock)); list_add_rcu(&pnd->list, &pndevs->list); return pnd; } static struct phonet_device *__phonet_get(struct net_device *dev) { struct phonet_device_list *pndevs = phonet_device_list(dev_net(dev)); struct phonet_device *pnd; BUG_ON(!mutex_is_locked(&pndevs->lock)); list_for_each_entry(pnd, &pndevs->list, list) { if (pnd->netdev == dev) return pnd; } return NULL; } static struct phonet_device *__phonet_get_rcu(struct net_device *dev) { struct phonet_device_list *pndevs = phonet_device_list(dev_net(dev)); struct phonet_device *pnd; list_for_each_entry_rcu(pnd, &pndevs->list, list) { if (pnd->netdev == dev) return pnd; } return NULL; } static void phonet_device_destroy(struct net_device *dev) { struct phonet_device_list *pndevs = phonet_device_list(dev_net(dev)); struct phonet_device *pnd; ASSERT_RTNL(); mutex_lock(&pndevs->lock); pnd = __phonet_get(dev); if (pnd) list_del_rcu(&pnd->list); mutex_unlock(&pndevs->lock); if (pnd) { u8 addr; for_each_set_bit(addr, pnd->addrs, 64) phonet_address_notify(RTM_DELADDR, dev, addr); kfree(pnd); } } struct net_device *phonet_device_get(struct net *net) { struct phonet_device_list *pndevs = phonet_device_list(net); struct phonet_device *pnd; struct net_device *dev = NULL; rcu_read_lock(); list_for_each_entry_rcu(pnd, &pndevs->list, list) { dev = pnd->netdev; BUG_ON(!dev); if ((dev->reg_state == NETREG_REGISTERED) && ((pnd->netdev->flags & IFF_UP)) == IFF_UP) break; dev = NULL; } dev_hold(dev); rcu_read_unlock(); return dev; } int phonet_address_add(struct net_device *dev, u8 addr) { struct phonet_device_list *pndevs = phonet_device_list(dev_net(dev)); struct phonet_device *pnd; int err = 0; mutex_lock(&pndevs->lock); /* Find or create Phonet-specific device data */ pnd = __phonet_get(dev); if (pnd == NULL) pnd = __phonet_device_alloc(dev); if (unlikely(pnd == NULL)) err = -ENOMEM; else if (test_and_set_bit(addr >> 2, pnd->addrs)) err = -EEXIST; mutex_unlock(&pndevs->lock); return err; } int phonet_address_del(struct net_device *dev, u8 addr) { struct phonet_device_list *pndevs = phonet_device_list(dev_net(dev)); struct phonet_device *pnd; int err = 0; mutex_lock(&pndevs->lock); pnd = __phonet_get(dev); if (!pnd || !test_and_clear_bit(addr >> 2, pnd->addrs)) { err = -EADDRNOTAVAIL; pnd = NULL; } else if (bitmap_empty(pnd->addrs, 64)) list_del_rcu(&pnd->list); else pnd = NULL; mutex_unlock(&pndevs->lock); if (pnd) kfree_rcu(pnd, rcu); return err; } /* Gets a source address toward a destination, through a interface. */ u8 phonet_address_get(struct net_device *dev, u8 daddr) { struct phonet_device *pnd; u8 saddr; rcu_read_lock(); pnd = __phonet_get_rcu(dev); if (pnd) { BUG_ON(bitmap_empty(pnd->addrs, 64)); /* Use same source address as destination, if possible */ if (test_bit(daddr >> 2, pnd->addrs)) saddr = daddr; else saddr = find_first_bit(pnd->addrs, 64) << 2; } else saddr = PN_NO_ADDR; rcu_read_unlock(); if (saddr == PN_NO_ADDR) { /* Fallback to another device */ struct net_device *def_dev; def_dev = phonet_device_get(dev_net(dev)); if (def_dev) { if (def_dev != dev) saddr = phonet_address_get(def_dev, daddr); dev_put(def_dev); } } return saddr; } int phonet_address_lookup(struct net *net, u8 addr) { struct phonet_device_list *pndevs = phonet_device_list(net); struct phonet_device *pnd; int err = -EADDRNOTAVAIL; rcu_read_lock(); list_for_each_entry_rcu(pnd, &pndevs->list, list) { /* Don't allow unregistering devices! */ if ((pnd->netdev->reg_state != NETREG_REGISTERED) || ((pnd->netdev->flags & IFF_UP)) != IFF_UP) continue; if (test_bit(addr >> 2, pnd->addrs)) { err = 0; goto found; } } found: rcu_read_unlock(); return err; } /* automatically configure a Phonet device, if supported */ static int phonet_device_autoconf(struct net_device *dev) { struct if_phonet_req req; int ret; if (!dev->netdev_ops->ndo_siocdevprivate) return -EOPNOTSUPP; ret = dev->netdev_ops->ndo_siocdevprivate(dev, (struct ifreq *)&req, NULL, SIOCPNGAUTOCONF); if (ret < 0) return ret; ASSERT_RTNL(); ret = phonet_address_add(dev, req.ifr_phonet_autoconf.device); if (ret) return ret; phonet_address_notify(RTM_NEWADDR, dev, req.ifr_phonet_autoconf.device); return 0; } static void phonet_route_autodel(struct net_device *dev) { struct phonet_net *pnn = phonet_pernet(dev_net(dev)); unsigned int i; DECLARE_BITMAP(deleted, 64); /* Remove left-over Phonet routes */ bitmap_zero(deleted, 64); mutex_lock(&pnn->routes.lock); for (i = 0; i < 64; i++) if (rcu_access_pointer(pnn->routes.table[i]) == dev) { RCU_INIT_POINTER(pnn->routes.table[i], NULL); set_bit(i, deleted); } mutex_unlock(&pnn->routes.lock); if (bitmap_empty(deleted, 64)) return; /* short-circuit RCU */ synchronize_rcu(); for_each_set_bit(i, deleted, 64) { rtm_phonet_notify(RTM_DELROUTE, dev, i); dev_put(dev); } } /* notify Phonet of device events */ static int phonet_device_notify(struct notifier_block *me, unsigned long what, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); switch (what) { case NETDEV_REGISTER: if (dev->type == ARPHRD_PHONET) phonet_device_autoconf(dev); break; case NETDEV_UNREGISTER: phonet_device_destroy(dev); phonet_route_autodel(dev); break; } return 0; } static struct notifier_block phonet_device_notifier = { .notifier_call = phonet_device_notify, .priority = 0, }; /* Per-namespace Phonet devices handling */ static int __net_init phonet_init_net(struct net *net) { struct phonet_net *pnn = phonet_pernet(net); if (!proc_create_net("phonet", 0, net->proc_net, &pn_sock_seq_ops, sizeof(struct seq_net_private))) return -ENOMEM; INIT_LIST_HEAD(&pnn->pndevs.list); mutex_init(&pnn->pndevs.lock); mutex_init(&pnn->routes.lock); return 0; } static void __net_exit phonet_exit_net(struct net *net) { struct phonet_net *pnn = phonet_pernet(net); remove_proc_entry("phonet", net->proc_net); WARN_ON_ONCE(!list_empty(&pnn->pndevs.list)); } static struct pernet_operations phonet_net_ops = { .init = phonet_init_net, .exit = phonet_exit_net, .id = &phonet_net_id, .size = sizeof(struct phonet_net), }; /* Initialize Phonet devices list */ int __init phonet_device_init(void) { int err = register_pernet_subsys(&phonet_net_ops); if (err) return err; proc_create_net("pnresource", 0, init_net.proc_net, &pn_res_seq_ops, sizeof(struct seq_net_private)); register_netdevice_notifier(&phonet_device_notifier); err = phonet_netlink_register(); if (err) phonet_device_exit(); return err; } void phonet_device_exit(void) { rtnl_unregister_all(PF_PHONET); unregister_netdevice_notifier(&phonet_device_notifier); unregister_pernet_subsys(&phonet_net_ops); remove_proc_entry("pnresource", init_net.proc_net); } int phonet_route_add(struct net_device *dev, u8 daddr) { struct phonet_net *pnn = phonet_pernet(dev_net(dev)); struct phonet_routes *routes = &pnn->routes; int err = -EEXIST; daddr = daddr >> 2; mutex_lock(&routes->lock); if (routes->table[daddr] == NULL) { rcu_assign_pointer(routes->table[daddr], dev); dev_hold(dev); err = 0; } mutex_unlock(&routes->lock); return err; } int phonet_route_del(struct net_device *dev, u8 daddr) { struct phonet_net *pnn = phonet_pernet(dev_net(dev)); struct phonet_routes *routes = &pnn->routes; daddr = daddr >> 2; mutex_lock(&routes->lock); if (rcu_access_pointer(routes->table[daddr]) == dev) RCU_INIT_POINTER(routes->table[daddr], NULL); else dev = NULL; mutex_unlock(&routes->lock); if (!dev) return -ENOENT; synchronize_rcu(); dev_put(dev); return 0; } struct net_device *phonet_route_get_rcu(struct net *net, u8 daddr) { struct phonet_net *pnn = phonet_pernet(net); struct phonet_routes *routes = &pnn->routes; struct net_device *dev; daddr >>= 2; dev = rcu_dereference(routes->table[daddr]); return dev; } struct net_device *phonet_route_output(struct net *net, u8 daddr) { struct phonet_net *pnn = phonet_pernet(net); struct phonet_routes *routes = &pnn->routes; struct net_device *dev; daddr >>= 2; rcu_read_lock(); dev = rcu_dereference(routes->table[daddr]); dev_hold(dev); rcu_read_unlock(); if (!dev) dev = phonet_device_get(net); /* Default route */ return dev; } |
| 59 19 326 219 324 324 325 324 4 15 418 407 14 11 14 6 14 7 7 7 2 2 2 9 8 3 4 3 9 9 9 9 8 1 1 1 9 3 8 8 7 8 3 301 304 7 9 9 418 414 413 412 15 7 4 15 253 253 252 66 3 249 211 40 306 140 166 264 307 45 265 266 148 266 266 148 13 253 253 253 253 251 265 304 305 140 165 263 42 305 263 41 309 305 52 253 234 19 305 428 383 62 406 405 406 406 405 406 406 328 328 325 329 140 10 140 162 34 3 162 335 40 335 108 47 94 99 92 78 109 90 171 10 162 162 162 6 6 109 71 31 160 117 109 125 102 106 109 323 323 29 319 320 319 88 88 65 85 319 329 162 248 328 91 315 299 328 299 297 297 172 173 171 3 171 3 329 324 280 118 300 97 257 190 59 174 157 315 256 220 35 172 190 56 56 55 406 381 9 2 59 6 53 24 2 2 24 33 37 17 17 37 37 37 315 315 227 184 315 315 2 2 2 2 2 1 2 350 350 29 1 207 51 37 187 191 397 396 59 23 396 72 370 244 186 101 44 71 350 395 59 399 398 376 19 17 203 66 395 369 1 395 370 24 406 252 195 26 263 37 330 133 396 307 307 400 304 237 161 397 244 320 37 297 17 17 2 2 315 396 396 304 381 56 395 24 394 280 281 281 281 281 281 281 281 280 280 280 280 281 281 281 281 7 281 1 131 150 279 279 1 1 1 1 1 1 1 1 1 1 281 278 34 281 281 281 280 280 281 279 269 12 281 281 17 17 17 14 3 17 17 17 17 17 17 17 17 17 15 15 15 15 15 377 1 377 4 376 375 376 375 331 140 1 376 241 134 135 123 49 374 376 332 331 331 1 327 2 329 32 32 32 127 31 32 9 25 25 9 8 25 25 23 32 406 248 146 130 130 106 32 130 25 57 53 7 9 4 24 5 2 2 130 81 60 119 130 124 130 128 6 83 60 59 404 399 74 23 20 1 2 106 106 106 105 74 413 232 247 26 77 79 74 28 74 150 147 147 147 147 147 147 253 253 405 102 55 54 55 55 97 97 53 50 50 8 48 10 50 97 97 97 97 97 69 69 69 69 19 69 69 66 3 81 58 1 23 23 23 7 23 23 23 23 23 23 515 147 435 435 51 51 434 2 49 49 49 49 405 372 374 374 230 261 261 225 51 409 413 412 411 373 106 106 148 324 148 325 323 142 406 81 81 81 81 80 81 23 59 59 425 428 387 53 35 59 51 51 338 338 377 74 405 20 160 299 3 330 81 330 406 364 55 330 33 44 406 164 17 161 161 161 19 142 140 140 10 1 130 140 140 140 170 151 33 168 3 168 148 33 164 5 11 157 19 5 9 135 57 57 164 5 5 8 8 13 9 1 8 3 2 1 5 5 5 5 5 7 1 10 10 10 16 16 16 3 2 12 12 1 11 13 6 8 11 1 10 14 15 2 13 7 2 9 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2003-2006, Cluster File Systems, Inc, info@clusterfs.com * Written by Alex Tomas <alex@clusterfs.com> */ /* * mballoc.c contains the multiblocks allocation routines */ #include "ext4_jbd2.h" #include "mballoc.h" #include <linux/log2.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/nospec.h> #include <linux/backing-dev.h> #include <linux/freezer.h> #include <trace/events/ext4.h> #include <kunit/static_stub.h> /* * MUSTDO: * - test ext4_ext_search_left() and ext4_ext_search_right() * - search for metadata in few groups * * TODO v4: * - normalization should take into account whether file is still open * - discard preallocations if no free space left (policy?) * - don't normalize tails * - quota * - reservation for superuser * * TODO v3: * - bitmap read-ahead (proposed by Oleg Drokin aka green) * - track min/max extents in each group for better group selection * - mb_mark_used() may allocate chunk right after splitting buddy * - tree of groups sorted by number of free blocks * - error handling */ /* * The allocation request involve request for multiple number of blocks * near to the goal(block) value specified. * * During initialization phase of the allocator we decide to use the * group preallocation or inode preallocation depending on the size of * the file. The size of the file could be the resulting file size we * would have after allocation, or the current file size, which ever * is larger. If the size is less than sbi->s_mb_stream_request we * select to use the group preallocation. The default value of * s_mb_stream_request is 16 blocks. This can also be tuned via * /sys/fs/ext4/<partition>/mb_stream_req. The value is represented in * terms of number of blocks. * * The main motivation for having small file use group preallocation is to * ensure that we have small files closer together on the disk. * * First stage the allocator looks at the inode prealloc list, * ext4_inode_info->i_prealloc_list, which contains list of prealloc * spaces for this particular inode. The inode prealloc space is * represented as: * * pa_lstart -> the logical start block for this prealloc space * pa_pstart -> the physical start block for this prealloc space * pa_len -> length for this prealloc space (in clusters) * pa_free -> free space available in this prealloc space (in clusters) * * The inode preallocation space is used looking at the _logical_ start * block. If only the logical file block falls within the range of prealloc * space we will consume the particular prealloc space. This makes sure that * we have contiguous physical blocks representing the file blocks * * The important thing to be noted in case of inode prealloc space is that * we don't modify the values associated to inode prealloc space except * pa_free. * * If we are not able to find blocks in the inode prealloc space and if we * have the group allocation flag set then we look at the locality group * prealloc space. These are per CPU prealloc list represented as * * ext4_sb_info.s_locality_groups[smp_processor_id()] * * The reason for having a per cpu locality group is to reduce the contention * between CPUs. It is possible to get scheduled at this point. * * The locality group prealloc space is used looking at whether we have * enough free space (pa_free) within the prealloc space. * * If we can't allocate blocks via inode prealloc or/and locality group * prealloc then we look at the buddy cache. The buddy cache is represented * by ext4_sb_info.s_buddy_cache (struct inode) whose file offset gets * mapped to the buddy and bitmap information regarding different * groups. The buddy information is attached to buddy cache inode so that * we can access them through the page cache. The information regarding * each group is loaded via ext4_mb_load_buddy. The information involve * block bitmap and buddy information. The information are stored in the * inode as: * * { page } * [ group 0 bitmap][ group 0 buddy] [group 1][ group 1]... * * * one block each for bitmap and buddy information. So for each group we * take up 2 blocks. A page can contain blocks_per_page (PAGE_SIZE / * blocksize) blocks. So it can have information regarding groups_per_page * which is blocks_per_page/2 * * The buddy cache inode is not stored on disk. The inode is thrown * away when the filesystem is unmounted. * * We look for count number of blocks in the buddy cache. If we were able * to locate that many free blocks we return with additional information * regarding rest of the contiguous physical block available * * Before allocating blocks via buddy cache we normalize the request * blocks. This ensure we ask for more blocks that we needed. The extra * blocks that we get after allocation is added to the respective prealloc * list. In case of inode preallocation we follow a list of heuristics * based on file size. This can be found in ext4_mb_normalize_request. If * we are doing a group prealloc we try to normalize the request to * sbi->s_mb_group_prealloc. The default value of s_mb_group_prealloc is * dependent on the cluster size; for non-bigalloc file systems, it is * 512 blocks. This can be tuned via * /sys/fs/ext4/<partition>/mb_group_prealloc. The value is represented in * terms of number of blocks. If we have mounted the file system with -O * stripe=<value> option the group prealloc request is normalized to the * smallest multiple of the stripe value (sbi->s_stripe) which is * greater than the default mb_group_prealloc. * * If "mb_optimize_scan" mount option is set, we maintain in memory group info * structures in two data structures: * * 1) Array of largest free order lists (sbi->s_mb_largest_free_orders) * * Locking: sbi->s_mb_largest_free_orders_locks(array of rw locks) * * This is an array of lists where the index in the array represents the * largest free order in the buddy bitmap of the participating group infos of * that list. So, there are exactly MB_NUM_ORDERS(sb) (which means total * number of buddy bitmap orders possible) number of lists. Group-infos are * placed in appropriate lists. * * 2) Average fragment size lists (sbi->s_mb_avg_fragment_size) * * Locking: sbi->s_mb_avg_fragment_size_locks(array of rw locks) * * This is an array of lists where in the i-th list there are groups with * average fragment size >= 2^i and < 2^(i+1). The average fragment size * is computed as ext4_group_info->bb_free / ext4_group_info->bb_fragments. * Note that we don't bother with a special list for completely empty groups * so we only have MB_NUM_ORDERS(sb) lists. * * When "mb_optimize_scan" mount option is set, mballoc consults the above data * structures to decide the order in which groups are to be traversed for * fulfilling an allocation request. * * At CR_POWER2_ALIGNED , we look for groups which have the largest_free_order * >= the order of the request. We directly look at the largest free order list * in the data structure (1) above where largest_free_order = order of the * request. If that list is empty, we look at remaining list in the increasing * order of largest_free_order. This allows us to perform CR_POWER2_ALIGNED * lookup in O(1) time. * * At CR_GOAL_LEN_FAST, we only consider groups where * average fragment size > request size. So, we lookup a group which has average * fragment size just above or equal to request size using our average fragment * size group lists (data structure 2) in O(1) time. * * At CR_BEST_AVAIL_LEN, we aim to optimize allocations which can't be satisfied * in CR_GOAL_LEN_FAST. The fact that we couldn't find a group in * CR_GOAL_LEN_FAST suggests that there is no BG that has avg * fragment size > goal length. So before falling to the slower * CR_GOAL_LEN_SLOW, in CR_BEST_AVAIL_LEN we proactively trim goal length and * then use the same fragment lists as CR_GOAL_LEN_FAST to find a BG with a big * enough average fragment size. This increases the chances of finding a * suitable block group in O(1) time and results in faster allocation at the * cost of reduced size of allocation. * * If "mb_optimize_scan" mount option is not set, mballoc traverses groups in * linear order which requires O(N) search time for each CR_POWER2_ALIGNED and * CR_GOAL_LEN_FAST phase. * * The regular allocator (using the buddy cache) supports a few tunables. * * /sys/fs/ext4/<partition>/mb_min_to_scan * /sys/fs/ext4/<partition>/mb_max_to_scan * /sys/fs/ext4/<partition>/mb_order2_req * /sys/fs/ext4/<partition>/mb_linear_limit * * The regular allocator uses buddy scan only if the request len is power of * 2 blocks and the order of allocation is >= sbi->s_mb_order2_reqs. The * value of s_mb_order2_reqs can be tuned via * /sys/fs/ext4/<partition>/mb_order2_req. If the request len is equal to * stripe size (sbi->s_stripe), we try to search for contiguous block in * stripe size. This should result in better allocation on RAID setups. If * not, we search in the specific group using bitmap for best extents. The * tunable min_to_scan and max_to_scan control the behaviour here. * min_to_scan indicate how long the mballoc __must__ look for a best * extent and max_to_scan indicates how long the mballoc __can__ look for a * best extent in the found extents. Searching for the blocks starts with * the group specified as the goal value in allocation context via * ac_g_ex. Each group is first checked based on the criteria whether it * can be used for allocation. ext4_mb_good_group explains how the groups are * checked. * * When "mb_optimize_scan" is turned on, as mentioned above, the groups may not * get traversed linearly. That may result in subsequent allocations being not * close to each other. And so, the underlying device may get filled up in a * non-linear fashion. While that may not matter on non-rotational devices, for * rotational devices that may result in higher seek times. "mb_linear_limit" * tells mballoc how many groups mballoc should search linearly before * performing consulting above data structures for more efficient lookups. For * non rotational devices, this value defaults to 0 and for rotational devices * this is set to MB_DEFAULT_LINEAR_LIMIT. * * Both the prealloc space are getting populated as above. So for the first * request we will hit the buddy cache which will result in this prealloc * space getting filled. The prealloc space is then later used for the * subsequent request. */ /* * mballoc operates on the following data: * - on-disk bitmap * - in-core buddy (actually includes buddy and bitmap) * - preallocation descriptors (PAs) * * there are two types of preallocations: * - inode * assiged to specific inode and can be used for this inode only. * it describes part of inode's space preallocated to specific * physical blocks. any block from that preallocated can be used * independent. the descriptor just tracks number of blocks left * unused. so, before taking some block from descriptor, one must * make sure corresponded logical block isn't allocated yet. this * also means that freeing any block within descriptor's range * must discard all preallocated blocks. * - locality group * assigned to specific locality group which does not translate to * permanent set of inodes: inode can join and leave group. space * from this type of preallocation can be used for any inode. thus * it's consumed from the beginning to the end. * * relation between them can be expressed as: * in-core buddy = on-disk bitmap + preallocation descriptors * * this mean blocks mballoc considers used are: * - allocated blocks (persistent) * - preallocated blocks (non-persistent) * * consistency in mballoc world means that at any time a block is either * free or used in ALL structures. notice: "any time" should not be read * literally -- time is discrete and delimited by locks. * * to keep it simple, we don't use block numbers, instead we count number of * blocks: how many blocks marked used/free in on-disk bitmap, buddy and PA. * * all operations can be expressed as: * - init buddy: buddy = on-disk + PAs * - new PA: buddy += N; PA = N * - use inode PA: on-disk += N; PA -= N * - discard inode PA buddy -= on-disk - PA; PA = 0 * - use locality group PA on-disk += N; PA -= N * - discard locality group PA buddy -= PA; PA = 0 * note: 'buddy -= on-disk - PA' is used to show that on-disk bitmap * is used in real operation because we can't know actual used * bits from PA, only from on-disk bitmap * * if we follow this strict logic, then all operations above should be atomic. * given some of them can block, we'd have to use something like semaphores * killing performance on high-end SMP hardware. let's try to relax it using * the following knowledge: * 1) if buddy is referenced, it's already initialized * 2) while block is used in buddy and the buddy is referenced, * nobody can re-allocate that block * 3) we work on bitmaps and '+' actually means 'set bits'. if on-disk has * bit set and PA claims same block, it's OK. IOW, one can set bit in * on-disk bitmap if buddy has same bit set or/and PA covers corresponded * block * * so, now we're building a concurrency table: * - init buddy vs. * - new PA * blocks for PA are allocated in the buddy, buddy must be referenced * until PA is linked to allocation group to avoid concurrent buddy init * - use inode PA * we need to make sure that either on-disk bitmap or PA has uptodate data * given (3) we care that PA-=N operation doesn't interfere with init * - discard inode PA * the simplest way would be to have buddy initialized by the discard * - use locality group PA * again PA-=N must be serialized with init * - discard locality group PA * the simplest way would be to have buddy initialized by the discard * - new PA vs. * - use inode PA * i_data_sem serializes them * - discard inode PA * discard process must wait until PA isn't used by another process * - use locality group PA * some mutex should serialize them * - discard locality group PA * discard process must wait until PA isn't used by another process * - use inode PA * - use inode PA * i_data_sem or another mutex should serializes them * - discard inode PA * discard process must wait until PA isn't used by another process * - use locality group PA * nothing wrong here -- they're different PAs covering different blocks * - discard locality group PA * discard process must wait until PA isn't used by another process * * now we're ready to make few consequences: * - PA is referenced and while it is no discard is possible * - PA is referenced until block isn't marked in on-disk bitmap * - PA changes only after on-disk bitmap * - discard must not compete with init. either init is done before * any discard or they're serialized somehow * - buddy init as sum of on-disk bitmap and PAs is done atomically * * a special case when we've used PA to emptiness. no need to modify buddy * in this case, but we should care about concurrent init * */ /* * Logic in few words: * * - allocation: * load group * find blocks * mark bits in on-disk bitmap * release group * * - use preallocation: * find proper PA (per-inode or group) * load group * mark bits in on-disk bitmap * release group * release PA * * - free: * load group * mark bits in on-disk bitmap * release group * * - discard preallocations in group: * mark PAs deleted * move them onto local list * load on-disk bitmap * load group * remove PA from object (inode or locality group) * mark free blocks in-core * * - discard inode's preallocations: */ /* * Locking rules * * Locks: * - bitlock on a group (group) * - object (inode/locality) (object) * - per-pa lock (pa) * - cr_power2_aligned lists lock (cr_power2_aligned) * - cr_goal_len_fast lists lock (cr_goal_len_fast) * * Paths: * - new pa * object * group * * - find and use pa: * pa * * - release consumed pa: * pa * group * object * * - generate in-core bitmap: * group * pa * * - discard all for given object (inode, locality group): * object * pa * group * * - discard all for given group: * group * pa * group * object * * - allocation path (ext4_mb_regular_allocator) * group * cr_power2_aligned/cr_goal_len_fast */ static struct kmem_cache *ext4_pspace_cachep; static struct kmem_cache *ext4_ac_cachep; static struct kmem_cache *ext4_free_data_cachep; /* We create slab caches for groupinfo data structures based on the * superblock block size. There will be one per mounted filesystem for * each unique s_blocksize_bits */ #define NR_GRPINFO_CACHES 8 static struct kmem_cache *ext4_groupinfo_caches[NR_GRPINFO_CACHES]; static const char * const ext4_groupinfo_slab_names[NR_GRPINFO_CACHES] = { "ext4_groupinfo_1k", "ext4_groupinfo_2k", "ext4_groupinfo_4k", "ext4_groupinfo_8k", "ext4_groupinfo_16k", "ext4_groupinfo_32k", "ext4_groupinfo_64k", "ext4_groupinfo_128k" }; static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, ext4_group_t group); static void ext4_mb_new_preallocation(struct ext4_allocation_context *ac); static bool ext4_mb_good_group(struct ext4_allocation_context *ac, ext4_group_t group, enum criteria cr); static int ext4_try_to_trim_range(struct super_block *sb, struct ext4_buddy *e4b, ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks); /* * The algorithm using this percpu seq counter goes below: * 1. We sample the percpu discard_pa_seq counter before trying for block * allocation in ext4_mb_new_blocks(). * 2. We increment this percpu discard_pa_seq counter when we either allocate * or free these blocks i.e. while marking those blocks as used/free in * mb_mark_used()/mb_free_blocks(). * 3. We also increment this percpu seq counter when we successfully identify * that the bb_prealloc_list is not empty and hence proceed for discarding * of those PAs inside ext4_mb_discard_group_preallocations(). * * Now to make sure that the regular fast path of block allocation is not * affected, as a small optimization we only sample the percpu seq counter * on that cpu. Only when the block allocation fails and when freed blocks * found were 0, that is when we sample percpu seq counter for all cpus using * below function ext4_get_discard_pa_seq_sum(). This happens after making * sure that all the PAs on grp->bb_prealloc_list got freed or if it's empty. */ static DEFINE_PER_CPU(u64, discard_pa_seq); static inline u64 ext4_get_discard_pa_seq_sum(void) { int __cpu; u64 __seq = 0; for_each_possible_cpu(__cpu) __seq += per_cpu(discard_pa_seq, __cpu); return __seq; } static inline void *mb_correct_addr_and_bit(int *bit, void *addr) { #if BITS_PER_LONG == 64 *bit += ((unsigned long) addr & 7UL) << 3; addr = (void *) ((unsigned long) addr & ~7UL); #elif BITS_PER_LONG == 32 *bit += ((unsigned long) addr & 3UL) << 3; addr = (void *) ((unsigned long) addr & ~3UL); #else #error "how many bits you are?!" #endif return addr; } static inline int mb_test_bit(int bit, void *addr) { /* * ext4_test_bit on architecture like powerpc * needs unsigned long aligned address */ addr = mb_correct_addr_and_bit(&bit, addr); return ext4_test_bit(bit, addr); } static inline void mb_set_bit(int bit, void *addr) { addr = mb_correct_addr_and_bit(&bit, addr); ext4_set_bit(bit, addr); } static inline void mb_clear_bit(int bit, void *addr) { addr = mb_correct_addr_and_bit(&bit, addr); ext4_clear_bit(bit, addr); } static inline int mb_test_and_clear_bit(int bit, void *addr) { addr = mb_correct_addr_and_bit(&bit, addr); return ext4_test_and_clear_bit(bit, addr); } static inline int mb_find_next_zero_bit(void *addr, int max, int start) { int fix = 0, ret, tmpmax; addr = mb_correct_addr_and_bit(&fix, addr); tmpmax = max + fix; start += fix; ret = ext4_find_next_zero_bit(addr, tmpmax, start) - fix; if (ret > max) return max; return ret; } static inline int mb_find_next_bit(void *addr, int max, int start) { int fix = 0, ret, tmpmax; addr = mb_correct_addr_and_bit(&fix, addr); tmpmax = max + fix; start += fix; ret = ext4_find_next_bit(addr, tmpmax, start) - fix; if (ret > max) return max; return ret; } static void *mb_find_buddy(struct ext4_buddy *e4b, int order, int *max) { char *bb; BUG_ON(e4b->bd_bitmap == e4b->bd_buddy); BUG_ON(max == NULL); if (order > e4b->bd_blkbits + 1) { *max = 0; return NULL; } /* at order 0 we see each particular block */ if (order == 0) { *max = 1 << (e4b->bd_blkbits + 3); return e4b->bd_bitmap; } bb = e4b->bd_buddy + EXT4_SB(e4b->bd_sb)->s_mb_offsets[order]; *max = EXT4_SB(e4b->bd_sb)->s_mb_maxs[order]; return bb; } #ifdef DOUBLE_CHECK static void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b, int first, int count) { int i; struct super_block *sb = e4b->bd_sb; if (unlikely(e4b->bd_info->bb_bitmap == NULL)) return; assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group)); for (i = 0; i < count; i++) { if (!mb_test_bit(first + i, e4b->bd_info->bb_bitmap)) { ext4_fsblk_t blocknr; blocknr = ext4_group_first_block_no(sb, e4b->bd_group); blocknr += EXT4_C2B(EXT4_SB(sb), first + i); ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); ext4_grp_locked_error(sb, e4b->bd_group, inode ? inode->i_ino : 0, blocknr, "freeing block already freed " "(bit %u)", first + i); } mb_clear_bit(first + i, e4b->bd_info->bb_bitmap); } } static void mb_mark_used_double(struct ext4_buddy *e4b, int first, int count) { int i; if (unlikely(e4b->bd_info->bb_bitmap == NULL)) return; assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group)); for (i = 0; i < count; i++) { BUG_ON(mb_test_bit(first + i, e4b->bd_info->bb_bitmap)); mb_set_bit(first + i, e4b->bd_info->bb_bitmap); } } static void mb_cmp_bitmaps(struct ext4_buddy *e4b, void *bitmap) { if (unlikely(e4b->bd_info->bb_bitmap == NULL)) return; if (memcmp(e4b->bd_info->bb_bitmap, bitmap, e4b->bd_sb->s_blocksize)) { unsigned char *b1, *b2; int i; b1 = (unsigned char *) e4b->bd_info->bb_bitmap; b2 = (unsigned char *) bitmap; for (i = 0; i < e4b->bd_sb->s_blocksize; i++) { if (b1[i] != b2[i]) { ext4_msg(e4b->bd_sb, KERN_ERR, "corruption in group %u " "at byte %u(%u): %x in copy != %x " "on disk/prealloc", e4b->bd_group, i, i * 8, b1[i], b2[i]); BUG(); } } } } static void mb_group_bb_bitmap_alloc(struct super_block *sb, struct ext4_group_info *grp, ext4_group_t group) { struct buffer_head *bh; grp->bb_bitmap = kmalloc(sb->s_blocksize, GFP_NOFS); if (!grp->bb_bitmap) return; bh = ext4_read_block_bitmap(sb, group); if (IS_ERR_OR_NULL(bh)) { kfree(grp->bb_bitmap); grp->bb_bitmap = NULL; return; } memcpy(grp->bb_bitmap, bh->b_data, sb->s_blocksize); put_bh(bh); } static void mb_group_bb_bitmap_free(struct ext4_group_info *grp) { kfree(grp->bb_bitmap); } #else static inline void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b, int first, int count) { return; } static inline void mb_mark_used_double(struct ext4_buddy *e4b, int first, int count) { return; } static inline void mb_cmp_bitmaps(struct ext4_buddy *e4b, void *bitmap) { return; } static inline void mb_group_bb_bitmap_alloc(struct super_block *sb, struct ext4_group_info *grp, ext4_group_t group) { return; } static inline void mb_group_bb_bitmap_free(struct ext4_group_info *grp) { return; } #endif #ifdef AGGRESSIVE_CHECK #define MB_CHECK_ASSERT(assert) \ do { \ if (!(assert)) { \ printk(KERN_EMERG \ "Assertion failure in %s() at %s:%d: \"%s\"\n", \ function, file, line, # assert); \ BUG(); \ } \ } while (0) static void __mb_check_buddy(struct ext4_buddy *e4b, char *file, const char *function, int line) { struct super_block *sb = e4b->bd_sb; int order = e4b->bd_blkbits + 1; int max; int max2; int i; int j; int k; int count; struct ext4_group_info *grp; int fragments = 0; int fstart; struct list_head *cur; void *buddy; void *buddy2; if (e4b->bd_info->bb_check_counter++ % 10) return; while (order > 1) { buddy = mb_find_buddy(e4b, order, &max); MB_CHECK_ASSERT(buddy); buddy2 = mb_find_buddy(e4b, order - 1, &max2); MB_CHECK_ASSERT(buddy2); MB_CHECK_ASSERT(buddy != buddy2); MB_CHECK_ASSERT(max * 2 == max2); count = 0; for (i = 0; i < max; i++) { if (mb_test_bit(i, buddy)) { /* only single bit in buddy2 may be 0 */ if (!mb_test_bit(i << 1, buddy2)) { MB_CHECK_ASSERT( mb_test_bit((i<<1)+1, buddy2)); } continue; } /* both bits in buddy2 must be 1 */ MB_CHECK_ASSERT(mb_test_bit(i << 1, buddy2)); MB_CHECK_ASSERT(mb_test_bit((i << 1) + 1, buddy2)); for (j = 0; j < (1 << order); j++) { k = (i * (1 << order)) + j; MB_CHECK_ASSERT( !mb_test_bit(k, e4b->bd_bitmap)); } count++; } MB_CHECK_ASSERT(e4b->bd_info->bb_counters[order] == count); order--; } fstart = -1; buddy = mb_find_buddy(e4b, 0, &max); for (i = 0; i < max; i++) { if (!mb_test_bit(i, buddy)) { MB_CHECK_ASSERT(i >= e4b->bd_info->bb_first_free); if (fstart == -1) { fragments++; fstart = i; } continue; } fstart = -1; /* check used bits only */ for (j = 0; j < e4b->bd_blkbits + 1; j++) { buddy2 = mb_find_buddy(e4b, j, &max2); k = i >> j; MB_CHECK_ASSERT(k < max2); MB_CHECK_ASSERT(mb_test_bit(k, buddy2)); } } MB_CHECK_ASSERT(!EXT4_MB_GRP_NEED_INIT(e4b->bd_info)); MB_CHECK_ASSERT(e4b->bd_info->bb_fragments == fragments); grp = ext4_get_group_info(sb, e4b->bd_group); if (!grp) return; list_for_each(cur, &grp->bb_prealloc_list) { ext4_group_t groupnr; struct ext4_prealloc_space *pa; pa = list_entry(cur, struct ext4_prealloc_space, pa_group_list); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &groupnr, &k); MB_CHECK_ASSERT(groupnr == e4b->bd_group); for (i = 0; i < pa->pa_len; i++) MB_CHECK_ASSERT(mb_test_bit(k + i, buddy)); } } #undef MB_CHECK_ASSERT #define mb_check_buddy(e4b) __mb_check_buddy(e4b, \ __FILE__, __func__, __LINE__) #else #define mb_check_buddy(e4b) #endif /* * Divide blocks started from @first with length @len into * smaller chunks with power of 2 blocks. * Clear the bits in bitmap which the blocks of the chunk(s) covered, * then increase bb_counters[] for corresponded chunk size. */ static void ext4_mb_mark_free_simple(struct super_block *sb, void *buddy, ext4_grpblk_t first, ext4_grpblk_t len, struct ext4_group_info *grp) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_grpblk_t min; ext4_grpblk_t max; ext4_grpblk_t chunk; unsigned int border; BUG_ON(len > EXT4_CLUSTERS_PER_GROUP(sb)); border = 2 << sb->s_blocksize_bits; while (len > 0) { /* find how many blocks can be covered since this position */ max = ffs(first | border) - 1; /* find how many blocks of power 2 we need to mark */ min = fls(len) - 1; if (max < min) min = max; chunk = 1 << min; /* mark multiblock chunks only */ grp->bb_counters[min]++; if (min > 0) mb_clear_bit(first >> min, buddy + sbi->s_mb_offsets[min]); len -= chunk; first += chunk; } } static int mb_avg_fragment_size_order(struct super_block *sb, ext4_grpblk_t len) { int order; /* * We don't bother with a special lists groups with only 1 block free * extents and for completely empty groups. */ order = fls(len) - 2; if (order < 0) return 0; if (order == MB_NUM_ORDERS(sb)) order--; if (WARN_ON_ONCE(order > MB_NUM_ORDERS(sb))) order = MB_NUM_ORDERS(sb) - 1; return order; } /* Move group to appropriate avg_fragment_size list */ static void mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp) { struct ext4_sb_info *sbi = EXT4_SB(sb); int new_order; if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_fragments == 0) return; new_order = mb_avg_fragment_size_order(sb, grp->bb_free / grp->bb_fragments); if (new_order == grp->bb_avg_fragment_size_order) return; if (grp->bb_avg_fragment_size_order != -1) { write_lock(&sbi->s_mb_avg_fragment_size_locks[ grp->bb_avg_fragment_size_order]); list_del(&grp->bb_avg_fragment_size_node); write_unlock(&sbi->s_mb_avg_fragment_size_locks[ grp->bb_avg_fragment_size_order]); } grp->bb_avg_fragment_size_order = new_order; write_lock(&sbi->s_mb_avg_fragment_size_locks[ grp->bb_avg_fragment_size_order]); list_add_tail(&grp->bb_avg_fragment_size_node, &sbi->s_mb_avg_fragment_size[grp->bb_avg_fragment_size_order]); write_unlock(&sbi->s_mb_avg_fragment_size_locks[ grp->bb_avg_fragment_size_order]); } /* * Choose next group by traversing largest_free_order lists. Updates *new_cr if * cr level needs an update. */ static void ext4_mb_choose_next_group_p2_aligned(struct ext4_allocation_context *ac, enum criteria *new_cr, ext4_group_t *group) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_group_info *iter; int i; if (ac->ac_status == AC_STATUS_FOUND) return; if (unlikely(sbi->s_mb_stats && ac->ac_flags & EXT4_MB_CR_POWER2_ALIGNED_OPTIMIZED)) atomic_inc(&sbi->s_bal_p2_aligned_bad_suggestions); for (i = ac->ac_2order; i < MB_NUM_ORDERS(ac->ac_sb); i++) { if (list_empty(&sbi->s_mb_largest_free_orders[i])) continue; read_lock(&sbi->s_mb_largest_free_orders_locks[i]); if (list_empty(&sbi->s_mb_largest_free_orders[i])) { read_unlock(&sbi->s_mb_largest_free_orders_locks[i]); continue; } list_for_each_entry(iter, &sbi->s_mb_largest_free_orders[i], bb_largest_free_order_node) { if (sbi->s_mb_stats) atomic64_inc(&sbi->s_bal_cX_groups_considered[CR_POWER2_ALIGNED]); if (likely(ext4_mb_good_group(ac, iter->bb_group, CR_POWER2_ALIGNED))) { *group = iter->bb_group; ac->ac_flags |= EXT4_MB_CR_POWER2_ALIGNED_OPTIMIZED; read_unlock(&sbi->s_mb_largest_free_orders_locks[i]); return; } } read_unlock(&sbi->s_mb_largest_free_orders_locks[i]); } /* Increment cr and search again if no group is found */ *new_cr = CR_GOAL_LEN_FAST; } /* * Find a suitable group of given order from the average fragments list. */ static struct ext4_group_info * ext4_mb_find_good_group_avg_frag_lists(struct ext4_allocation_context *ac, int order) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct list_head *frag_list = &sbi->s_mb_avg_fragment_size[order]; rwlock_t *frag_list_lock = &sbi->s_mb_avg_fragment_size_locks[order]; struct ext4_group_info *grp = NULL, *iter; enum criteria cr = ac->ac_criteria; if (list_empty(frag_list)) return NULL; read_lock(frag_list_lock); if (list_empty(frag_list)) { read_unlock(frag_list_lock); return NULL; } list_for_each_entry(iter, frag_list, bb_avg_fragment_size_node) { if (sbi->s_mb_stats) atomic64_inc(&sbi->s_bal_cX_groups_considered[cr]); if (likely(ext4_mb_good_group(ac, iter->bb_group, cr))) { grp = iter; break; } } read_unlock(frag_list_lock); return grp; } /* * Choose next group by traversing average fragment size list of suitable * order. Updates *new_cr if cr level needs an update. */ static void ext4_mb_choose_next_group_goal_fast(struct ext4_allocation_context *ac, enum criteria *new_cr, ext4_group_t *group) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_group_info *grp = NULL; int i; if (unlikely(ac->ac_flags & EXT4_MB_CR_GOAL_LEN_FAST_OPTIMIZED)) { if (sbi->s_mb_stats) atomic_inc(&sbi->s_bal_goal_fast_bad_suggestions); } for (i = mb_avg_fragment_size_order(ac->ac_sb, ac->ac_g_ex.fe_len); i < MB_NUM_ORDERS(ac->ac_sb); i++) { grp = ext4_mb_find_good_group_avg_frag_lists(ac, i); if (grp) { *group = grp->bb_group; ac->ac_flags |= EXT4_MB_CR_GOAL_LEN_FAST_OPTIMIZED; return; } } /* * CR_BEST_AVAIL_LEN works based on the concept that we have * a larger normalized goal len request which can be trimmed to * a smaller goal len such that it can still satisfy original * request len. However, allocation request for non-regular * files never gets normalized. * See function ext4_mb_normalize_request() (EXT4_MB_HINT_DATA). */ if (ac->ac_flags & EXT4_MB_HINT_DATA) *new_cr = CR_BEST_AVAIL_LEN; else *new_cr = CR_GOAL_LEN_SLOW; } /* * We couldn't find a group in CR_GOAL_LEN_FAST so try to find the highest free fragment * order we have and proactively trim the goal request length to that order to * find a suitable group faster. * * This optimizes allocation speed at the cost of slightly reduced * preallocations. However, we make sure that we don't trim the request too * much and fall to CR_GOAL_LEN_SLOW in that case. */ static void ext4_mb_choose_next_group_best_avail(struct ext4_allocation_context *ac, enum criteria *new_cr, ext4_group_t *group) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_group_info *grp = NULL; int i, order, min_order; unsigned long num_stripe_clusters = 0; if (unlikely(ac->ac_flags & EXT4_MB_CR_BEST_AVAIL_LEN_OPTIMIZED)) { if (sbi->s_mb_stats) atomic_inc(&sbi->s_bal_best_avail_bad_suggestions); } /* * mb_avg_fragment_size_order() returns order in a way that makes * retrieving back the length using (1 << order) inaccurate. Hence, use * fls() instead since we need to know the actual length while modifying * goal length. */ order = fls(ac->ac_g_ex.fe_len) - 1; if (WARN_ON_ONCE(order - 1 > MB_NUM_ORDERS(ac->ac_sb))) order = MB_NUM_ORDERS(ac->ac_sb); min_order = order - sbi->s_mb_best_avail_max_trim_order; if (min_order < 0) min_order = 0; if (sbi->s_stripe > 0) { /* * We are assuming that stripe size is always a multiple of * cluster ratio otherwise __ext4_fill_super exists early. */ num_stripe_clusters = EXT4_NUM_B2C(sbi, sbi->s_stripe); if (1 << min_order < num_stripe_clusters) /* * We consider 1 order less because later we round * up the goal len to num_stripe_clusters */ min_order = fls(num_stripe_clusters) - 1; } if (1 << min_order < ac->ac_o_ex.fe_len) min_order = fls(ac->ac_o_ex.fe_len); for (i = order; i >= min_order; i--) { int frag_order; /* * Scale down goal len to make sure we find something * in the free fragments list. Basically, reduce * preallocations. */ ac->ac_g_ex.fe_len = 1 << i; if (num_stripe_clusters > 0) { /* * Try to round up the adjusted goal length to * stripe size (in cluster units) multiple for * efficiency. */ ac->ac_g_ex.fe_len = roundup(ac->ac_g_ex.fe_len, num_stripe_clusters); } frag_order = mb_avg_fragment_size_order(ac->ac_sb, ac->ac_g_ex.fe_len); grp = ext4_mb_find_good_group_avg_frag_lists(ac, frag_order); if (grp) { *group = grp->bb_group; ac->ac_flags |= EXT4_MB_CR_BEST_AVAIL_LEN_OPTIMIZED; return; } } /* Reset goal length to original goal length before falling into CR_GOAL_LEN_SLOW */ ac->ac_g_ex.fe_len = ac->ac_orig_goal_len; *new_cr = CR_GOAL_LEN_SLOW; } static inline int should_optimize_scan(struct ext4_allocation_context *ac) { if (unlikely(!test_opt2(ac->ac_sb, MB_OPTIMIZE_SCAN))) return 0; if (ac->ac_criteria >= CR_GOAL_LEN_SLOW) return 0; if (!ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)) return 0; return 1; } /* * Return next linear group for allocation. */ static ext4_group_t next_linear_group(ext4_group_t group, ext4_group_t ngroups) { /* * Artificially restricted ngroups for non-extent * files makes group > ngroups possible on first loop. */ return group + 1 >= ngroups ? 0 : group + 1; } /* * ext4_mb_choose_next_group: choose next group for allocation. * * @ac Allocation Context * @new_cr This is an output parameter. If the there is no good group * available at current CR level, this field is updated to indicate * the new cr level that should be used. * @group This is an input / output parameter. As an input it indicates the * next group that the allocator intends to use for allocation. As * output, this field indicates the next group that should be used as * determined by the optimization functions. * @ngroups Total number of groups */ static void ext4_mb_choose_next_group(struct ext4_allocation_context *ac, enum criteria *new_cr, ext4_group_t *group, ext4_group_t ngroups) { *new_cr = ac->ac_criteria; if (!should_optimize_scan(ac)) { *group = next_linear_group(*group, ngroups); return; } /* * Optimized scanning can return non adjacent groups which can cause * seek overhead for rotational disks. So try few linear groups before * trying optimized scan. */ if (ac->ac_groups_linear_remaining) { *group = next_linear_group(*group, ngroups); ac->ac_groups_linear_remaining--; return; } if (*new_cr == CR_POWER2_ALIGNED) { ext4_mb_choose_next_group_p2_aligned(ac, new_cr, group); } else if (*new_cr == CR_GOAL_LEN_FAST) { ext4_mb_choose_next_group_goal_fast(ac, new_cr, group); } else if (*new_cr == CR_BEST_AVAIL_LEN) { ext4_mb_choose_next_group_best_avail(ac, new_cr, group); } else { /* * TODO: For CR_GOAL_LEN_SLOW, we can arrange groups in an * rb tree sorted by bb_free. But until that happens, we should * never come here. */ WARN_ON(1); } } /* * Cache the order of the largest free extent we have available in this block * group. */ static void mb_set_largest_free_order(struct super_block *sb, struct ext4_group_info *grp) { struct ext4_sb_info *sbi = EXT4_SB(sb); int i; for (i = MB_NUM_ORDERS(sb) - 1; i >= 0; i--) if (grp->bb_counters[i] > 0) break; /* No need to move between order lists? */ if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || i == grp->bb_largest_free_order) { grp->bb_largest_free_order = i; return; } if (grp->bb_largest_free_order >= 0) { write_lock(&sbi->s_mb_largest_free_orders_locks[ grp->bb_largest_free_order]); list_del_init(&grp->bb_largest_free_order_node); write_unlock(&sbi->s_mb_largest_free_orders_locks[ grp->bb_largest_free_order]); } grp->bb_largest_free_order = i; if (grp->bb_largest_free_order >= 0 && grp->bb_free) { write_lock(&sbi->s_mb_largest_free_orders_locks[ grp->bb_largest_free_order]); list_add_tail(&grp->bb_largest_free_order_node, &sbi->s_mb_largest_free_orders[grp->bb_largest_free_order]); write_unlock(&sbi->s_mb_largest_free_orders_locks[ grp->bb_largest_free_order]); } } static noinline_for_stack void ext4_mb_generate_buddy(struct super_block *sb, void *buddy, void *bitmap, ext4_group_t group, struct ext4_group_info *grp) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_grpblk_t max = EXT4_CLUSTERS_PER_GROUP(sb); ext4_grpblk_t i = 0; ext4_grpblk_t first; ext4_grpblk_t len; unsigned free = 0; unsigned fragments = 0; unsigned long long period = get_cycles(); /* initialize buddy from bitmap which is aggregation * of on-disk bitmap and preallocations */ i = mb_find_next_zero_bit(bitmap, max, 0); grp->bb_first_free = i; while (i < max) { fragments++; first = i; i = mb_find_next_bit(bitmap, max, i); len = i - first; free += len; if (len > 1) ext4_mb_mark_free_simple(sb, buddy, first, len, grp); else grp->bb_counters[0]++; if (i < max) i = mb_find_next_zero_bit(bitmap, max, i); } grp->bb_fragments = fragments; if (free != grp->bb_free) { ext4_grp_locked_error(sb, group, 0, 0, "block bitmap and bg descriptor " "inconsistent: %u vs %u free clusters", free, grp->bb_free); /* * If we intend to continue, we consider group descriptor * corrupt and update bb_free using bitmap value */ grp->bb_free = free; ext4_mark_group_bitmap_corrupted(sb, group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); } mb_set_largest_free_order(sb, grp); mb_update_avg_fragment_size(sb, grp); clear_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state)); period = get_cycles() - period; atomic_inc(&sbi->s_mb_buddies_generated); atomic64_add(period, &sbi->s_mb_generation_time); } static void mb_regenerate_buddy(struct ext4_buddy *e4b) { int count; int order = 1; void *buddy; while ((buddy = mb_find_buddy(e4b, order++, &count))) mb_set_bits(buddy, 0, count); e4b->bd_info->bb_fragments = 0; memset(e4b->bd_info->bb_counters, 0, sizeof(*e4b->bd_info->bb_counters) * (e4b->bd_sb->s_blocksize_bits + 2)); ext4_mb_generate_buddy(e4b->bd_sb, e4b->bd_buddy, e4b->bd_bitmap, e4b->bd_group, e4b->bd_info); } /* The buddy information is attached the buddy cache inode * for convenience. The information regarding each group * is loaded via ext4_mb_load_buddy. The information involve * block bitmap and buddy information. The information are * stored in the inode as * * { page } * [ group 0 bitmap][ group 0 buddy] [group 1][ group 1]... * * * one block each for bitmap and buddy information. * So for each group we take up 2 blocks. A page can * contain blocks_per_page (PAGE_SIZE / blocksize) blocks. * So it can have information regarding groups_per_page which * is blocks_per_page/2 * * Locking note: This routine takes the block group lock of all groups * for this page; do not hold this lock when calling this routine! */ static int ext4_mb_init_cache(struct folio *folio, char *incore, gfp_t gfp) { ext4_group_t ngroups; unsigned int blocksize; int blocks_per_page; int groups_per_page; int err = 0; int i; ext4_group_t first_group, group; int first_block; struct super_block *sb; struct buffer_head *bhs; struct buffer_head **bh = NULL; struct inode *inode; char *data; char *bitmap; struct ext4_group_info *grinfo; inode = folio->mapping->host; sb = inode->i_sb; ngroups = ext4_get_groups_count(sb); blocksize = i_blocksize(inode); blocks_per_page = PAGE_SIZE / blocksize; mb_debug(sb, "init folio %lu\n", folio->index); groups_per_page = blocks_per_page >> 1; if (groups_per_page == 0) groups_per_page = 1; /* allocate buffer_heads to read bitmaps */ if (groups_per_page > 1) { i = sizeof(struct buffer_head *) * groups_per_page; bh = kzalloc(i, gfp); if (bh == NULL) return -ENOMEM; } else bh = &bhs; first_group = folio->index * blocks_per_page / 2; /* read all groups the folio covers into the cache */ for (i = 0, group = first_group; i < groups_per_page; i++, group++) { if (group >= ngroups) break; grinfo = ext4_get_group_info(sb, group); if (!grinfo) continue; /* * If page is uptodate then we came here after online resize * which added some new uninitialized group info structs, so * we must skip all initialized uptodate buddies on the folio, * which may be currently in use by an allocating task. */ if (folio_test_uptodate(folio) && !EXT4_MB_GRP_NEED_INIT(grinfo)) { bh[i] = NULL; continue; } bh[i] = ext4_read_block_bitmap_nowait(sb, group, false); if (IS_ERR(bh[i])) { err = PTR_ERR(bh[i]); bh[i] = NULL; goto out; } mb_debug(sb, "read bitmap for group %u\n", group); } /* wait for I/O completion */ for (i = 0, group = first_group; i < groups_per_page; i++, group++) { int err2; if (!bh[i]) continue; err2 = ext4_wait_block_bitmap(sb, group, bh[i]); if (!err) err = err2; } first_block = folio->index * blocks_per_page; for (i = 0; i < blocks_per_page; i++) { group = (first_block + i) >> 1; if (group >= ngroups) break; if (!bh[group - first_group]) /* skip initialized uptodate buddy */ continue; if (!buffer_verified(bh[group - first_group])) /* Skip faulty bitmaps */ continue; err = 0; /* * data carry information regarding this * particular group in the format specified * above * */ data = folio_address(folio) + (i * blocksize); bitmap = bh[group - first_group]->b_data; /* * We place the buddy block and bitmap block * close together */ grinfo = ext4_get_group_info(sb, group); if (!grinfo) { err = -EFSCORRUPTED; goto out; } if ((first_block + i) & 1) { /* this is block of buddy */ BUG_ON(incore == NULL); mb_debug(sb, "put buddy for group %u in folio %lu/%x\n", group, folio->index, i * blocksize); trace_ext4_mb_buddy_bitmap_load(sb, group); grinfo->bb_fragments = 0; memset(grinfo->bb_counters, 0, sizeof(*grinfo->bb_counters) * (MB_NUM_ORDERS(sb))); /* * incore got set to the group block bitmap below */ ext4_lock_group(sb, group); /* init the buddy */ memset(data, 0xff, blocksize); ext4_mb_generate_buddy(sb, data, incore, group, grinfo); ext4_unlock_group(sb, group); incore = NULL; } else { /* this is block of bitmap */ BUG_ON(incore != NULL); mb_debug(sb, "put bitmap for group %u in folio %lu/%x\n", group, folio->index, i * blocksize); trace_ext4_mb_bitmap_load(sb, group); /* see comments in ext4_mb_put_pa() */ ext4_lock_group(sb, group); memcpy(data, bitmap, blocksize); /* mark all preallocated blks used in in-core bitmap */ ext4_mb_generate_from_pa(sb, data, group); WARN_ON_ONCE(!RB_EMPTY_ROOT(&grinfo->bb_free_root)); ext4_unlock_group(sb, group); /* set incore so that the buddy information can be * generated using this */ incore = data; } } folio_mark_uptodate(folio); out: if (bh) { for (i = 0; i < groups_per_page; i++) brelse(bh[i]); if (bh != &bhs) kfree(bh); } return err; } /* * Lock the buddy and bitmap pages. This make sure other parallel init_group * on the same buddy page doesn't happen whild holding the buddy page lock. * Return locked buddy and bitmap pages on e4b struct. If buddy and bitmap * are on the same page e4b->bd_buddy_folio is NULL and return value is 0. */ static int ext4_mb_get_buddy_page_lock(struct super_block *sb, ext4_group_t group, struct ext4_buddy *e4b, gfp_t gfp) { struct inode *inode = EXT4_SB(sb)->s_buddy_cache; int block, pnum, poff; int blocks_per_page; struct folio *folio; e4b->bd_buddy_folio = NULL; e4b->bd_bitmap_folio = NULL; blocks_per_page = PAGE_SIZE / sb->s_blocksize; /* * the buddy cache inode stores the block bitmap * and buddy information in consecutive blocks. * So for each group we need two blocks. */ block = group * 2; pnum = block / blocks_per_page; poff = block % blocks_per_page; folio = __filemap_get_folio(inode->i_mapping, pnum, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp); if (IS_ERR(folio)) return PTR_ERR(folio); BUG_ON(folio->mapping != inode->i_mapping); e4b->bd_bitmap_folio = folio; e4b->bd_bitmap = folio_address(folio) + (poff * sb->s_blocksize); if (blocks_per_page >= 2) { /* buddy and bitmap are on the same page */ return 0; } /* blocks_per_page == 1, hence we need another page for the buddy */ folio = __filemap_get_folio(inode->i_mapping, block + 1, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp); if (IS_ERR(folio)) return PTR_ERR(folio); BUG_ON(folio->mapping != inode->i_mapping); e4b->bd_buddy_folio = folio; return 0; } static void ext4_mb_put_buddy_page_lock(struct ext4_buddy *e4b) { if (e4b->bd_bitmap_folio) { folio_unlock(e4b->bd_bitmap_folio); folio_put(e4b->bd_bitmap_folio); } if (e4b->bd_buddy_folio) { folio_unlock(e4b->bd_buddy_folio); folio_put(e4b->bd_buddy_folio); } } /* * Locking note: This routine calls ext4_mb_init_cache(), which takes the * block group lock of all groups for this page; do not hold the BG lock when * calling this routine! */ static noinline_for_stack int ext4_mb_init_group(struct super_block *sb, ext4_group_t group, gfp_t gfp) { struct ext4_group_info *this_grp; struct ext4_buddy e4b; struct folio *folio; int ret = 0; might_sleep(); mb_debug(sb, "init group %u\n", group); this_grp = ext4_get_group_info(sb, group); if (!this_grp) return -EFSCORRUPTED; /* * This ensures that we don't reinit the buddy cache * page which map to the group from which we are already * allocating. If we are looking at the buddy cache we would * have taken a reference using ext4_mb_load_buddy and that * would have pinned buddy page to page cache. * The call to ext4_mb_get_buddy_page_lock will mark the * page accessed. */ ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b, gfp); if (ret || !EXT4_MB_GRP_NEED_INIT(this_grp)) { /* * somebody initialized the group * return without doing anything */ goto err; } folio = e4b.bd_bitmap_folio; ret = ext4_mb_init_cache(folio, NULL, gfp); if (ret) goto err; if (!folio_test_uptodate(folio)) { ret = -EIO; goto err; } if (e4b.bd_buddy_folio == NULL) { /* * If both the bitmap and buddy are in * the same page we don't need to force * init the buddy */ ret = 0; goto err; } /* init buddy cache */ folio = e4b.bd_buddy_folio; ret = ext4_mb_init_cache(folio, e4b.bd_bitmap, gfp); if (ret) goto err; if (!folio_test_uptodate(folio)) { ret = -EIO; goto err; } err: ext4_mb_put_buddy_page_lock(&e4b); return ret; } /* * Locking note: This routine calls ext4_mb_init_cache(), which takes the * block group lock of all groups for this page; do not hold the BG lock when * calling this routine! */ static noinline_for_stack int ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group, struct ext4_buddy *e4b, gfp_t gfp) { int blocks_per_page; int block; int pnum; int poff; struct folio *folio; int ret; struct ext4_group_info *grp; struct ext4_sb_info *sbi = EXT4_SB(sb); struct inode *inode = sbi->s_buddy_cache; might_sleep(); mb_debug(sb, "load group %u\n", group); blocks_per_page = PAGE_SIZE / sb->s_blocksize; grp = ext4_get_group_info(sb, group); if (!grp) return -EFSCORRUPTED; e4b->bd_blkbits = sb->s_blocksize_bits; e4b->bd_info = grp; e4b->bd_sb = sb; e4b->bd_group = group; e4b->bd_buddy_folio = NULL; e4b->bd_bitmap_folio = NULL; if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { /* * we need full data about the group * to make a good selection */ ret = ext4_mb_init_group(sb, group, gfp); if (ret) return ret; } /* * the buddy cache inode stores the block bitmap * and buddy information in consecutive blocks. * So for each group we need two blocks. */ block = group * 2; pnum = block / blocks_per_page; poff = block % blocks_per_page; /* Avoid locking the folio in the fast path ... */ folio = __filemap_get_folio(inode->i_mapping, pnum, FGP_ACCESSED, 0); if (IS_ERR(folio) || !folio_test_uptodate(folio)) { if (!IS_ERR(folio)) /* * drop the folio reference and try * to get the folio with lock. If we * are not uptodate that implies * somebody just created the folio but * is yet to initialize it. So * wait for it to initialize. */ folio_put(folio); folio = __filemap_get_folio(inode->i_mapping, pnum, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp); if (!IS_ERR(folio)) { if (WARN_RATELIMIT(folio->mapping != inode->i_mapping, "ext4: bitmap's mapping != inode->i_mapping\n")) { /* should never happen */ folio_unlock(folio); ret = -EINVAL; goto err; } if (!folio_test_uptodate(folio)) { ret = ext4_mb_init_cache(folio, NULL, gfp); if (ret) { folio_unlock(folio); goto err; } mb_cmp_bitmaps(e4b, folio_address(folio) + (poff * sb->s_blocksize)); } folio_unlock(folio); } } if (IS_ERR(folio)) { ret = PTR_ERR(folio); goto err; } if (!folio_test_uptodate(folio)) { ret = -EIO; goto err; } /* Folios marked accessed already */ e4b->bd_bitmap_folio = folio; e4b->bd_bitmap = folio_address(folio) + (poff * sb->s_blocksize); block++; pnum = block / blocks_per_page; poff = block % blocks_per_page; folio = __filemap_get_folio(inode->i_mapping, pnum, FGP_ACCESSED, 0); if (IS_ERR(folio) || !folio_test_uptodate(folio)) { if (!IS_ERR(folio)) folio_put(folio); folio = __filemap_get_folio(inode->i_mapping, pnum, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp); if (!IS_ERR(folio)) { if (WARN_RATELIMIT(folio->mapping != inode->i_mapping, "ext4: buddy bitmap's mapping != inode->i_mapping\n")) { /* should never happen */ folio_unlock(folio); ret = -EINVAL; goto err; } if (!folio_test_uptodate(folio)) { ret = ext4_mb_init_cache(folio, e4b->bd_bitmap, gfp); if (ret) { folio_unlock(folio); goto err; } } folio_unlock(folio); } } if (IS_ERR(folio)) { ret = PTR_ERR(folio); goto err; } if (!folio_test_uptodate(folio)) { ret = -EIO; goto err; } /* Folios marked accessed already */ e4b->bd_buddy_folio = folio; e4b->bd_buddy = folio_address(folio) + (poff * sb->s_blocksize); return 0; err: if (!IS_ERR_OR_NULL(folio)) folio_put(folio); if (e4b->bd_bitmap_folio) folio_put(e4b->bd_bitmap_folio); e4b->bd_buddy = NULL; e4b->bd_bitmap = NULL; return ret; } static int ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, struct ext4_buddy *e4b) { return ext4_mb_load_buddy_gfp(sb, group, e4b, GFP_NOFS); } static void ext4_mb_unload_buddy(struct ext4_buddy *e4b) { if (e4b->bd_bitmap_folio) folio_put(e4b->bd_bitmap_folio); if (e4b->bd_buddy_folio) folio_put(e4b->bd_buddy_folio); } static int mb_find_order_for_block(struct ext4_buddy *e4b, int block) { int order = 1, max; void *bb; BUG_ON(e4b->bd_bitmap == e4b->bd_buddy); BUG_ON(block >= (1 << (e4b->bd_blkbits + 3))); while (order <= e4b->bd_blkbits + 1) { bb = mb_find_buddy(e4b, order, &max); if (!mb_test_bit(block >> order, bb)) { /* this block is part of buddy of order 'order' */ return order; } order++; } return 0; } static void mb_clear_bits(void *bm, int cur, int len) { __u32 *addr; len = cur + len; while (cur < len) { if ((cur & 31) == 0 && (len - cur) >= 32) { /* fast path: clear whole word at once */ addr = bm + (cur >> 3); *addr = 0; cur += 32; continue; } mb_clear_bit(cur, bm); cur++; } } /* clear bits in given range * will return first found zero bit if any, -1 otherwise */ static int mb_test_and_clear_bits(void *bm, int cur, int len) { __u32 *addr; int zero_bit = -1; len = cur + len; while (cur < len) { if ((cur & 31) == 0 && (len - cur) >= 32) { /* fast path: clear whole word at once */ addr = bm + (cur >> 3); if (*addr != (__u32)(-1) && zero_bit == -1) zero_bit = cur + mb_find_next_zero_bit(addr, 32, 0); *addr = 0; cur += 32; continue; } if (!mb_test_and_clear_bit(cur, bm) && zero_bit == -1) zero_bit = cur; cur++; } return zero_bit; } void mb_set_bits(void *bm, int cur, int len) { __u32 *addr; len = cur + len; while (cur < len) { if ((cur & 31) == 0 && (len - cur) >= 32) { /* fast path: set whole word at once */ addr = bm + (cur >> 3); *addr = 0xffffffff; cur += 32; continue; } mb_set_bit(cur, bm); cur++; } } static inline int mb_buddy_adjust_border(int* bit, void* bitmap, int side) { if (mb_test_bit(*bit + side, bitmap)) { mb_clear_bit(*bit, bitmap); (*bit) -= side; return 1; } else { (*bit) += side; mb_set_bit(*bit, bitmap); return -1; } } static void mb_buddy_mark_free(struct ext4_buddy *e4b, int first, int last) { int max; int order = 1; void *buddy = mb_find_buddy(e4b, order, &max); while (buddy) { void *buddy2; /* Bits in range [first; last] are known to be set since * corresponding blocks were allocated. Bits in range * (first; last) will stay set because they form buddies on * upper layer. We just deal with borders if they don't * align with upper layer and then go up. * Releasing entire group is all about clearing * single bit of highest order buddy. */ /* Example: * --------------------------------- * | 1 | 1 | 1 | 1 | * --------------------------------- * | 0 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | * --------------------------------- * 0 1 2 3 4 5 6 7 * \_____________________/ * * Neither [1] nor [6] is aligned to above layer. * Left neighbour [0] is free, so mark it busy, * decrease bb_counters and extend range to * [0; 6] * Right neighbour [7] is busy. It can't be coaleasced with [6], so * mark [6] free, increase bb_counters and shrink range to * [0; 5]. * Then shift range to [0; 2], go up and do the same. */ if (first & 1) e4b->bd_info->bb_counters[order] += mb_buddy_adjust_border(&first, buddy, -1); if (!(last & 1)) e4b->bd_info->bb_counters[order] += mb_buddy_adjust_border(&last, buddy, 1); if (first > last) break; order++; buddy2 = mb_find_buddy(e4b, order, &max); if (!buddy2) { mb_clear_bits(buddy, first, last - first + 1); e4b->bd_info->bb_counters[order - 1] += last - first + 1; break; } first >>= 1; last >>= 1; buddy = buddy2; } } static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, int first, int count) { int left_is_free = 0; int right_is_free = 0; int block; int last = first + count - 1; struct super_block *sb = e4b->bd_sb; if (WARN_ON(count == 0)) return; BUG_ON(last >= (sb->s_blocksize << 3)); assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group)); /* Don't bother if the block group is corrupt. */ if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) return; mb_check_buddy(e4b); mb_free_blocks_double(inode, e4b, first, count); /* access memory sequentially: check left neighbour, * clear range and then check right neighbour */ if (first != 0) left_is_free = !mb_test_bit(first - 1, e4b->bd_bitmap); block = mb_test_and_clear_bits(e4b->bd_bitmap, first, count); if (last + 1 < EXT4_SB(sb)->s_mb_maxs[0]) right_is_free = !mb_test_bit(last + 1, e4b->bd_bitmap); if (unlikely(block != -1)) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t blocknr; /* * Fastcommit replay can free already freed blocks which * corrupts allocation info. Regenerate it. */ if (sbi->s_mount_state & EXT4_FC_REPLAY) { mb_regenerate_buddy(e4b); goto check; } blocknr = ext4_group_first_block_no(sb, e4b->bd_group); blocknr += EXT4_C2B(sbi, block); ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); ext4_grp_locked_error(sb, e4b->bd_group, inode ? inode->i_ino : 0, blocknr, "freeing already freed block (bit %u); block bitmap corrupt.", block); return; } this_cpu_inc(discard_pa_seq); e4b->bd_info->bb_free += count; if (first < e4b->bd_info->bb_first_free) e4b->bd_info->bb_first_free = first; /* let's maintain fragments counter */ if (left_is_free && right_is_free) e4b->bd_info->bb_fragments--; else if (!left_is_free && !right_is_free) e4b->bd_info->bb_fragments++; /* buddy[0] == bd_bitmap is a special case, so handle * it right away and let mb_buddy_mark_free stay free of * zero order checks. * Check if neighbours are to be coaleasced, * adjust bitmap bb_counters and borders appropriately. */ if (first & 1) { first += !left_is_free; e4b->bd_info->bb_counters[0] += left_is_free ? -1 : 1; } if (!(last & 1)) { last -= !right_is_free; e4b->bd_info->bb_counters[0] += right_is_free ? -1 : 1; } if (first <= last) mb_buddy_mark_free(e4b, first >> 1, last >> 1); mb_set_largest_free_order(sb, e4b->bd_info); mb_update_avg_fragment_size(sb, e4b->bd_info); check: mb_check_buddy(e4b); } static int mb_find_extent(struct ext4_buddy *e4b, int block, int needed, struct ext4_free_extent *ex) { int max, order, next; void *buddy; assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group)); BUG_ON(ex == NULL); buddy = mb_find_buddy(e4b, 0, &max); BUG_ON(buddy == NULL); BUG_ON(block >= max); if (mb_test_bit(block, buddy)) { ex->fe_len = 0; ex->fe_start = 0; ex->fe_group = 0; return 0; } /* find actual order */ order = mb_find_order_for_block(e4b, block); ex->fe_len = (1 << order) - (block & ((1 << order) - 1)); ex->fe_start = block; ex->fe_group = e4b->bd_group; block = block >> order; while (needed > ex->fe_len && mb_find_buddy(e4b, order, &max)) { if (block + 1 >= max) break; next = (block + 1) * (1 << order); if (mb_test_bit(next, e4b->bd_bitmap)) break; order = mb_find_order_for_block(e4b, next); block = next >> order; ex->fe_len += 1 << order; } if (ex->fe_start + ex->fe_len > EXT4_CLUSTERS_PER_GROUP(e4b->bd_sb)) { /* Should never happen! (but apparently sometimes does?!?) */ WARN_ON(1); ext4_grp_locked_error(e4b->bd_sb, e4b->bd_group, 0, 0, "corruption or bug in mb_find_extent " "block=%d, order=%d needed=%d ex=%u/%d/%d@%u", block, order, needed, ex->fe_group, ex->fe_start, ex->fe_len, ex->fe_logical); ex->fe_len = 0; ex->fe_start = 0; ex->fe_group = 0; } return ex->fe_len; } static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex) { int ord; int mlen = 0; int max = 0; int start = ex->fe_start; int len = ex->fe_len; unsigned ret = 0; int len0 = len; void *buddy; int ord_start, ord_end; BUG_ON(start + len > (e4b->bd_sb->s_blocksize << 3)); BUG_ON(e4b->bd_group != ex->fe_group); assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group)); mb_check_buddy(e4b); mb_mark_used_double(e4b, start, len); this_cpu_inc(discard_pa_seq); e4b->bd_info->bb_free -= len; if (e4b->bd_info->bb_first_free == start) e4b->bd_info->bb_first_free += len; /* let's maintain fragments counter */ if (start != 0) mlen = !mb_test_bit(start - 1, e4b->bd_bitmap); if (start + len < EXT4_SB(e4b->bd_sb)->s_mb_maxs[0]) max = !mb_test_bit(start + len, e4b->bd_bitmap); if (mlen && max) e4b->bd_info->bb_fragments++; else if (!mlen && !max) e4b->bd_info->bb_fragments--; /* let's maintain buddy itself */ while (len) { ord = mb_find_order_for_block(e4b, start); if (((start >> ord) << ord) == start && len >= (1 << ord)) { /* the whole chunk may be allocated at once! */ mlen = 1 << ord; buddy = mb_find_buddy(e4b, ord, &max); BUG_ON((start >> ord) >= max); mb_set_bit(start >> ord, buddy); e4b->bd_info->bb_counters[ord]--; start += mlen; len -= mlen; BUG_ON(len < 0); continue; } /* store for history */ if (ret == 0) ret = len | (ord << 16); BUG_ON(ord <= 0); buddy = mb_find_buddy(e4b, ord, &max); mb_set_bit(start >> ord, buddy); e4b->bd_info->bb_counters[ord]--; ord_start = (start >> ord) << ord; ord_end = ord_start + (1 << ord); /* first chunk */ if (start > ord_start) ext4_mb_mark_free_simple(e4b->bd_sb, e4b->bd_buddy, ord_start, start - ord_start, e4b->bd_info); /* last chunk */ if (start + len < ord_end) { ext4_mb_mark_free_simple(e4b->bd_sb, e4b->bd_buddy, start + len, ord_end - (start + len), e4b->bd_info); break; } len = start + len - ord_end; start = ord_end; } mb_set_largest_free_order(e4b->bd_sb, e4b->bd_info); mb_update_avg_fragment_size(e4b->bd_sb, e4b->bd_info); mb_set_bits(e4b->bd_bitmap, ex->fe_start, len0); mb_check_buddy(e4b); return ret; } /* * Must be called under group lock! */ static void ext4_mb_use_best_found(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); int ret; BUG_ON(ac->ac_b_ex.fe_group != e4b->bd_group); BUG_ON(ac->ac_status == AC_STATUS_FOUND); ac->ac_b_ex.fe_len = min(ac->ac_b_ex.fe_len, ac->ac_g_ex.fe_len); ac->ac_b_ex.fe_logical = ac->ac_g_ex.fe_logical; ret = mb_mark_used(e4b, &ac->ac_b_ex); /* preallocation can change ac_b_ex, thus we store actually * allocated blocks for history */ ac->ac_f_ex = ac->ac_b_ex; ac->ac_status = AC_STATUS_FOUND; ac->ac_tail = ret & 0xffff; ac->ac_buddy = ret >> 16; /* * take the page reference. We want the page to be pinned * so that we don't get a ext4_mb_init_cache_call for this * group until we update the bitmap. That would mean we * double allocate blocks. The reference is dropped * in ext4_mb_release_context */ ac->ac_bitmap_folio = e4b->bd_bitmap_folio; folio_get(ac->ac_bitmap_folio); ac->ac_buddy_folio = e4b->bd_buddy_folio; folio_get(ac->ac_buddy_folio); /* store last allocated for subsequent stream allocation */ if (ac->ac_flags & EXT4_MB_STREAM_ALLOC) { spin_lock(&sbi->s_md_lock); sbi->s_mb_last_group = ac->ac_f_ex.fe_group; sbi->s_mb_last_start = ac->ac_f_ex.fe_start; spin_unlock(&sbi->s_md_lock); } /* * As we've just preallocated more space than * user requested originally, we store allocated * space in a special descriptor. */ if (ac->ac_o_ex.fe_len < ac->ac_b_ex.fe_len) ext4_mb_new_preallocation(ac); } static void ext4_mb_check_limits(struct ext4_allocation_context *ac, struct ext4_buddy *e4b, int finish_group) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_free_extent *bex = &ac->ac_b_ex; struct ext4_free_extent *gex = &ac->ac_g_ex; if (ac->ac_status == AC_STATUS_FOUND) return; /* * We don't want to scan for a whole year */ if (ac->ac_found > sbi->s_mb_max_to_scan && !(ac->ac_flags & EXT4_MB_HINT_FIRST)) { ac->ac_status = AC_STATUS_BREAK; return; } /* * Haven't found good chunk so far, let's continue */ if (bex->fe_len < gex->fe_len) return; if (finish_group || ac->ac_found > sbi->s_mb_min_to_scan) ext4_mb_use_best_found(ac, e4b); } /* * The routine checks whether found extent is good enough. If it is, * then the extent gets marked used and flag is set to the context * to stop scanning. Otherwise, the extent is compared with the * previous found extent and if new one is better, then it's stored * in the context. Later, the best found extent will be used, if * mballoc can't find good enough extent. * * The algorithm used is roughly as follows: * * * If free extent found is exactly as big as goal, then * stop the scan and use it immediately * * * If free extent found is smaller than goal, then keep retrying * upto a max of sbi->s_mb_max_to_scan times (default 200). After * that stop scanning and use whatever we have. * * * If free extent found is bigger than goal, then keep retrying * upto a max of sbi->s_mb_min_to_scan times (default 10) before * stopping the scan and using the extent. * * * FIXME: real allocation policy is to be designed yet! */ static void ext4_mb_measure_extent(struct ext4_allocation_context *ac, struct ext4_free_extent *ex, struct ext4_buddy *e4b) { struct ext4_free_extent *bex = &ac->ac_b_ex; struct ext4_free_extent *gex = &ac->ac_g_ex; BUG_ON(ex->fe_len <= 0); BUG_ON(ex->fe_len > EXT4_CLUSTERS_PER_GROUP(ac->ac_sb)); BUG_ON(ex->fe_start >= EXT4_CLUSTERS_PER_GROUP(ac->ac_sb)); BUG_ON(ac->ac_status != AC_STATUS_CONTINUE); ac->ac_found++; ac->ac_cX_found[ac->ac_criteria]++; /* * The special case - take what you catch first */ if (unlikely(ac->ac_flags & EXT4_MB_HINT_FIRST)) { *bex = *ex; ext4_mb_use_best_found(ac, e4b); return; } /* * Let's check whether the chuck is good enough */ if (ex->fe_len == gex->fe_len) { *bex = *ex; ext4_mb_use_best_found(ac, e4b); return; } /* * If this is first found extent, just store it in the context */ if (bex->fe_len == 0) { *bex = *ex; return; } /* * If new found extent is better, store it in the context */ if (bex->fe_len < gex->fe_len) { /* if the request isn't satisfied, any found extent * larger than previous best one is better */ if (ex->fe_len > bex->fe_len) *bex = *ex; } else if (ex->fe_len > gex->fe_len) { /* if the request is satisfied, then we try to find * an extent that still satisfy the request, but is * smaller than previous one */ if (ex->fe_len < bex->fe_len) *bex = *ex; } ext4_mb_check_limits(ac, e4b, 0); } static noinline_for_stack void ext4_mb_try_best_found(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct ext4_free_extent ex = ac->ac_b_ex; ext4_group_t group = ex.fe_group; int max; int err; BUG_ON(ex.fe_len <= 0); err = ext4_mb_load_buddy(ac->ac_sb, group, e4b); if (err) return; ext4_lock_group(ac->ac_sb, group); if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) goto out; max = mb_find_extent(e4b, ex.fe_start, ex.fe_len, &ex); if (max > 0) { ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); } out: ext4_unlock_group(ac->ac_sb, group); ext4_mb_unload_buddy(e4b); } static noinline_for_stack int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { ext4_group_t group = ac->ac_g_ex.fe_group; int max; int err; struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group); struct ext4_free_extent ex; if (!grp) return -EFSCORRUPTED; if (!(ac->ac_flags & (EXT4_MB_HINT_TRY_GOAL | EXT4_MB_HINT_GOAL_ONLY))) return 0; if (grp->bb_free == 0) return 0; err = ext4_mb_load_buddy(ac->ac_sb, group, e4b); if (err) return err; ext4_lock_group(ac->ac_sb, group); if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) goto out; max = mb_find_extent(e4b, ac->ac_g_ex.fe_start, ac->ac_g_ex.fe_len, &ex); ex.fe_logical = 0xDEADFA11; /* debug value */ if (max >= ac->ac_g_ex.fe_len && ac->ac_g_ex.fe_len == EXT4_B2C(sbi, sbi->s_stripe)) { ext4_fsblk_t start; start = ext4_grp_offs_to_block(ac->ac_sb, &ex); /* use do_div to get remainder (would be 64-bit modulo) */ if (do_div(start, sbi->s_stripe) == 0) { ac->ac_found++; ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); } } else if (max >= ac->ac_g_ex.fe_len) { BUG_ON(ex.fe_len <= 0); BUG_ON(ex.fe_group != ac->ac_g_ex.fe_group); BUG_ON(ex.fe_start != ac->ac_g_ex.fe_start); ac->ac_found++; ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); } else if (max > 0 && (ac->ac_flags & EXT4_MB_HINT_MERGE)) { /* Sometimes, caller may want to merge even small * number of blocks to an existing extent */ BUG_ON(ex.fe_len <= 0); BUG_ON(ex.fe_group != ac->ac_g_ex.fe_group); BUG_ON(ex.fe_start != ac->ac_g_ex.fe_start); ac->ac_found++; ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); } out: ext4_unlock_group(ac->ac_sb, group); ext4_mb_unload_buddy(e4b); return 0; } /* * The routine scans buddy structures (not bitmap!) from given order * to max order and tries to find big enough chunk to satisfy the req */ static noinline_for_stack void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct super_block *sb = ac->ac_sb; struct ext4_group_info *grp = e4b->bd_info; void *buddy; int i; int k; int max; BUG_ON(ac->ac_2order <= 0); for (i = ac->ac_2order; i < MB_NUM_ORDERS(sb); i++) { if (grp->bb_counters[i] == 0) continue; buddy = mb_find_buddy(e4b, i, &max); if (WARN_RATELIMIT(buddy == NULL, "ext4: mb_simple_scan_group: mb_find_buddy failed, (%d)\n", i)) continue; k = mb_find_next_zero_bit(buddy, max, 0); if (k >= max) { ext4_mark_group_bitmap_corrupted(ac->ac_sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); ext4_grp_locked_error(ac->ac_sb, e4b->bd_group, 0, 0, "%d free clusters of order %d. But found 0", grp->bb_counters[i], i); break; } ac->ac_found++; ac->ac_cX_found[ac->ac_criteria]++; ac->ac_b_ex.fe_len = 1 << i; ac->ac_b_ex.fe_start = k << i; ac->ac_b_ex.fe_group = e4b->bd_group; ext4_mb_use_best_found(ac, e4b); BUG_ON(ac->ac_f_ex.fe_len != ac->ac_g_ex.fe_len); if (EXT4_SB(sb)->s_mb_stats) atomic_inc(&EXT4_SB(sb)->s_bal_2orders); break; } } /* * The routine scans the group and measures all found extents. * In order to optimize scanning, caller must pass number of * free blocks in the group, so the routine can know upper limit. */ static noinline_for_stack void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct super_block *sb = ac->ac_sb; void *bitmap = e4b->bd_bitmap; struct ext4_free_extent ex; int i, j, freelen; int free; free = e4b->bd_info->bb_free; if (WARN_ON(free <= 0)) return; i = e4b->bd_info->bb_first_free; while (free && ac->ac_status == AC_STATUS_CONTINUE) { i = mb_find_next_zero_bit(bitmap, EXT4_CLUSTERS_PER_GROUP(sb), i); if (i >= EXT4_CLUSTERS_PER_GROUP(sb)) { /* * IF we have corrupt bitmap, we won't find any * free blocks even though group info says we * have free blocks */ ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); ext4_grp_locked_error(sb, e4b->bd_group, 0, 0, "%d free clusters as per " "group info. But bitmap says 0", free); break; } if (!ext4_mb_cr_expensive(ac->ac_criteria)) { /* * In CR_GOAL_LEN_FAST and CR_BEST_AVAIL_LEN, we are * sure that this group will have a large enough * continuous free extent, so skip over the smaller free * extents */ j = mb_find_next_bit(bitmap, EXT4_CLUSTERS_PER_GROUP(sb), i); freelen = j - i; if (freelen < ac->ac_g_ex.fe_len) { i = j; free -= freelen; continue; } } mb_find_extent(e4b, i, ac->ac_g_ex.fe_len, &ex); if (WARN_ON(ex.fe_len <= 0)) break; if (free < ex.fe_len) { ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); ext4_grp_locked_error(sb, e4b->bd_group, 0, 0, "%d free clusters as per " "group info. But got %d blocks", free, ex.fe_len); /* * The number of free blocks differs. This mostly * indicate that the bitmap is corrupt. So exit * without claiming the space. */ break; } ex.fe_logical = 0xDEADC0DE; /* debug value */ ext4_mb_measure_extent(ac, &ex, e4b); i += ex.fe_len; free -= ex.fe_len; } ext4_mb_check_limits(ac, e4b, 1); } /* * This is a special case for storages like raid5 * we try to find stripe-aligned chunks for stripe-size-multiple requests */ static noinline_for_stack void ext4_mb_scan_aligned(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct super_block *sb = ac->ac_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); void *bitmap = e4b->bd_bitmap; struct ext4_free_extent ex; ext4_fsblk_t first_group_block; ext4_fsblk_t a; ext4_grpblk_t i, stripe; int max; BUG_ON(sbi->s_stripe == 0); /* find first stripe-aligned block in group */ first_group_block = ext4_group_first_block_no(sb, e4b->bd_group); a = first_group_block + sbi->s_stripe - 1; do_div(a, sbi->s_stripe); i = (a * sbi->s_stripe) - first_group_block; stripe = EXT4_B2C(sbi, sbi->s_stripe); i = EXT4_B2C(sbi, i); while (i < EXT4_CLUSTERS_PER_GROUP(sb)) { if (!mb_test_bit(i, bitmap)) { max = mb_find_extent(e4b, i, stripe, &ex); if (max >= stripe) { ac->ac_found++; ac->ac_cX_found[ac->ac_criteria]++; ex.fe_logical = 0xDEADF00D; /* debug value */ ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); break; } } i += stripe; } } /* * This is also called BEFORE we load the buddy bitmap. * Returns either 1 or 0 indicating that the group is either suitable * for the allocation or not. */ static bool ext4_mb_good_group(struct ext4_allocation_context *ac, ext4_group_t group, enum criteria cr) { ext4_grpblk_t free, fragments; int flex_size = ext4_flex_bg_size(EXT4_SB(ac->ac_sb)); struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group); BUG_ON(cr < CR_POWER2_ALIGNED || cr >= EXT4_MB_NUM_CRS); if (unlikely(!grp || EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) return false; free = grp->bb_free; if (free == 0) return false; fragments = grp->bb_fragments; if (fragments == 0) return false; switch (cr) { case CR_POWER2_ALIGNED: BUG_ON(ac->ac_2order == 0); /* Avoid using the first bg of a flexgroup for data files */ if ((ac->ac_flags & EXT4_MB_HINT_DATA) && (flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) && ((group % flex_size) == 0)) return false; if (free < ac->ac_g_ex.fe_len) return false; if (ac->ac_2order >= MB_NUM_ORDERS(ac->ac_sb)) return true; if (grp->bb_largest_free_order < ac->ac_2order) return false; return true; case CR_GOAL_LEN_FAST: case CR_BEST_AVAIL_LEN: if ((free / fragments) >= ac->ac_g_ex.fe_len) return true; break; case CR_GOAL_LEN_SLOW: if (free >= ac->ac_g_ex.fe_len) return true; break; case CR_ANY_FREE: return true; default: BUG(); } return false; } /* * This could return negative error code if something goes wrong * during ext4_mb_init_group(). This should not be called with * ext4_lock_group() held. * * Note: because we are conditionally operating with the group lock in * the EXT4_MB_STRICT_CHECK case, we need to fake out sparse in this * function using __acquire and __release. This means we need to be * super careful before messing with the error path handling via "goto * out"! */ static int ext4_mb_good_group_nolock(struct ext4_allocation_context *ac, ext4_group_t group, enum criteria cr) { struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group); struct super_block *sb = ac->ac_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); bool should_lock = ac->ac_flags & EXT4_MB_STRICT_CHECK; ext4_grpblk_t free; int ret = 0; if (!grp) return -EFSCORRUPTED; if (sbi->s_mb_stats) atomic64_inc(&sbi->s_bal_cX_groups_considered[ac->ac_criteria]); if (should_lock) { ext4_lock_group(sb, group); __release(ext4_group_lock_ptr(sb, group)); } free = grp->bb_free; if (free == 0) goto out; /* * In all criterias except CR_ANY_FREE we try to avoid groups that * can't possibly satisfy the full goal request due to insufficient * free blocks. */ if (cr < CR_ANY_FREE && free < ac->ac_g_ex.fe_len) goto out; if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) goto out; if (should_lock) { __acquire(ext4_group_lock_ptr(sb, group)); ext4_unlock_group(sb, group); } /* We only do this if the grp has never been initialized */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL); int ret; /* * CR_POWER2_ALIGNED/CR_GOAL_LEN_FAST is a very optimistic * search to find large good chunks almost for free. If buddy * data is not ready, then this optimization makes no sense. But * we never skip the first block group in a flex_bg, since this * gets used for metadata block allocation, and we want to make * sure we locate metadata blocks in the first block group in * the flex_bg if possible. */ if (!ext4_mb_cr_expensive(cr) && (!sbi->s_log_groups_per_flex || ((group & ((1 << sbi->s_log_groups_per_flex) - 1)) != 0)) && !(ext4_has_group_desc_csum(sb) && (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))) return 0; ret = ext4_mb_init_group(sb, group, GFP_NOFS); if (ret) return ret; } if (should_lock) { ext4_lock_group(sb, group); __release(ext4_group_lock_ptr(sb, group)); } ret = ext4_mb_good_group(ac, group, cr); out: if (should_lock) { __acquire(ext4_group_lock_ptr(sb, group)); ext4_unlock_group(sb, group); } return ret; } /* * Start prefetching @nr block bitmaps starting at @group. * Return the next group which needs to be prefetched. */ ext4_group_t ext4_mb_prefetch(struct super_block *sb, ext4_group_t group, unsigned int nr, int *cnt) { ext4_group_t ngroups = ext4_get_groups_count(sb); struct buffer_head *bh; struct blk_plug plug; blk_start_plug(&plug); while (nr-- > 0) { struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL); struct ext4_group_info *grp = ext4_get_group_info(sb, group); /* * Prefetch block groups with free blocks; but don't * bother if it is marked uninitialized on disk, since * it won't require I/O to read. Also only try to * prefetch once, so we avoid getblk() call, which can * be expensive. */ if (gdp && grp && !EXT4_MB_GRP_TEST_AND_SET_READ(grp) && EXT4_MB_GRP_NEED_INIT(grp) && ext4_free_group_clusters(sb, gdp) > 0 ) { bh = ext4_read_block_bitmap_nowait(sb, group, true); if (bh && !IS_ERR(bh)) { if (!buffer_uptodate(bh) && cnt) (*cnt)++; brelse(bh); } } if (++group >= ngroups) group = 0; } blk_finish_plug(&plug); return group; } /* * Prefetching reads the block bitmap into the buffer cache; but we * need to make sure that the buddy bitmap in the page cache has been * initialized. Note that ext4_mb_init_group() will block if the I/O * is not yet completed, or indeed if it was not initiated by * ext4_mb_prefetch did not start the I/O. * * TODO: We should actually kick off the buddy bitmap setup in a work * queue when the buffer I/O is completed, so that we don't block * waiting for the block allocation bitmap read to finish when * ext4_mb_prefetch_fini is called from ext4_mb_regular_allocator(). */ void ext4_mb_prefetch_fini(struct super_block *sb, ext4_group_t group, unsigned int nr) { struct ext4_group_desc *gdp; struct ext4_group_info *grp; while (nr-- > 0) { if (!group) group = ext4_get_groups_count(sb); group--; gdp = ext4_get_group_desc(sb, group, NULL); grp = ext4_get_group_info(sb, group); if (grp && gdp && EXT4_MB_GRP_NEED_INIT(grp) && ext4_free_group_clusters(sb, gdp) > 0) { if (ext4_mb_init_group(sb, group, GFP_NOFS)) break; } } } static noinline_for_stack int ext4_mb_regular_allocator(struct ext4_allocation_context *ac) { ext4_group_t prefetch_grp = 0, ngroups, group, i; enum criteria new_cr, cr = CR_GOAL_LEN_FAST; int err = 0, first_err = 0; unsigned int nr = 0, prefetch_ios = 0; struct ext4_sb_info *sbi; struct super_block *sb; struct ext4_buddy e4b; int lost; sb = ac->ac_sb; sbi = EXT4_SB(sb); ngroups = ext4_get_groups_count(sb); /* non-extent files are limited to low blocks/groups */ if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS))) ngroups = sbi->s_blockfile_groups; BUG_ON(ac->ac_status == AC_STATUS_FOUND); /* first, try the goal */ err = ext4_mb_find_by_goal(ac, &e4b); if (err || ac->ac_status == AC_STATUS_FOUND) goto out; if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY)) goto out; /* * ac->ac_2order is set only if the fe_len is a power of 2 * if ac->ac_2order is set we also set criteria to CR_POWER2_ALIGNED * so that we try exact allocation using buddy. */ i = fls(ac->ac_g_ex.fe_len); ac->ac_2order = 0; /* * We search using buddy data only if the order of the request * is greater than equal to the sbi_s_mb_order2_reqs * You can tune it via /sys/fs/ext4/<partition>/mb_order2_req * We also support searching for power-of-two requests only for * requests upto maximum buddy size we have constructed. */ if (i >= sbi->s_mb_order2_reqs && i <= MB_NUM_ORDERS(sb)) { if (is_power_of_2(ac->ac_g_ex.fe_len)) ac->ac_2order = array_index_nospec(i - 1, MB_NUM_ORDERS(sb)); } /* if stream allocation is enabled, use global goal */ if (ac->ac_flags & EXT4_MB_STREAM_ALLOC) { /* TBD: may be hot point */ spin_lock(&sbi->s_md_lock); ac->ac_g_ex.fe_group = sbi->s_mb_last_group; ac->ac_g_ex.fe_start = sbi->s_mb_last_start; spin_unlock(&sbi->s_md_lock); } /* * Let's just scan groups to find more-less suitable blocks We * start with CR_GOAL_LEN_FAST, unless it is power of 2 * aligned, in which case let's do that faster approach first. */ if (ac->ac_2order) cr = CR_POWER2_ALIGNED; repeat: for (; cr < EXT4_MB_NUM_CRS && ac->ac_status == AC_STATUS_CONTINUE; cr++) { ac->ac_criteria = cr; /* * searching for the right group start * from the goal value specified */ group = ac->ac_g_ex.fe_group; ac->ac_groups_linear_remaining = sbi->s_mb_max_linear_groups; prefetch_grp = group; nr = 0; for (i = 0, new_cr = cr; i < ngroups; i++, ext4_mb_choose_next_group(ac, &new_cr, &group, ngroups)) { int ret = 0; cond_resched(); if (new_cr != cr) { cr = new_cr; goto repeat; } /* * Batch reads of the block allocation bitmaps * to get multiple READs in flight; limit * prefetching at inexpensive CR, otherwise mballoc * can spend a lot of time loading imperfect groups */ if ((prefetch_grp == group) && (ext4_mb_cr_expensive(cr) || prefetch_ios < sbi->s_mb_prefetch_limit)) { nr = sbi->s_mb_prefetch; if (ext4_has_feature_flex_bg(sb)) { nr = 1 << sbi->s_log_groups_per_flex; nr -= group & (nr - 1); nr = min(nr, sbi->s_mb_prefetch); } prefetch_grp = ext4_mb_prefetch(sb, group, nr, &prefetch_ios); } /* This now checks without needing the buddy page */ ret = ext4_mb_good_group_nolock(ac, group, cr); if (ret <= 0) { if (!first_err) first_err = ret; continue; } err = ext4_mb_load_buddy(sb, group, &e4b); if (err) goto out; ext4_lock_group(sb, group); /* * We need to check again after locking the * block group */ ret = ext4_mb_good_group(ac, group, cr); if (ret == 0) { ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); continue; } ac->ac_groups_scanned++; if (cr == CR_POWER2_ALIGNED) ext4_mb_simple_scan_group(ac, &e4b); else { bool is_stripe_aligned = sbi->s_stripe && !(ac->ac_g_ex.fe_len % EXT4_B2C(sbi, sbi->s_stripe)); if ((cr == CR_GOAL_LEN_FAST || cr == CR_BEST_AVAIL_LEN) && is_stripe_aligned) ext4_mb_scan_aligned(ac, &e4b); if (ac->ac_status == AC_STATUS_CONTINUE) ext4_mb_complex_scan_group(ac, &e4b); } ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); if (ac->ac_status != AC_STATUS_CONTINUE) break; } /* Processed all groups and haven't found blocks */ if (sbi->s_mb_stats && i == ngroups) atomic64_inc(&sbi->s_bal_cX_failed[cr]); if (i == ngroups && ac->ac_criteria == CR_BEST_AVAIL_LEN) /* Reset goal length to original goal length before * falling into CR_GOAL_LEN_SLOW */ ac->ac_g_ex.fe_len = ac->ac_orig_goal_len; } if (ac->ac_b_ex.fe_len > 0 && ac->ac_status != AC_STATUS_FOUND && !(ac->ac_flags & EXT4_MB_HINT_FIRST)) { /* * We've been searching too long. Let's try to allocate * the best chunk we've found so far */ ext4_mb_try_best_found(ac, &e4b); if (ac->ac_status != AC_STATUS_FOUND) { /* * Someone more lucky has already allocated it. * The only thing we can do is just take first * found block(s) */ lost = atomic_inc_return(&sbi->s_mb_lost_chunks); mb_debug(sb, "lost chunk, group: %u, start: %d, len: %d, lost: %d\n", ac->ac_b_ex.fe_group, ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len, lost); ac->ac_b_ex.fe_group = 0; ac->ac_b_ex.fe_start = 0; ac->ac_b_ex.fe_len = 0; ac->ac_status = AC_STATUS_CONTINUE; ac->ac_flags |= EXT4_MB_HINT_FIRST; cr = CR_ANY_FREE; goto repeat; } } if (sbi->s_mb_stats && ac->ac_status == AC_STATUS_FOUND) atomic64_inc(&sbi->s_bal_cX_hits[ac->ac_criteria]); out: if (!err && ac->ac_status != AC_STATUS_FOUND && first_err) err = first_err; mb_debug(sb, "Best len %d, origin len %d, ac_status %u, ac_flags 0x%x, cr %d ret %d\n", ac->ac_b_ex.fe_len, ac->ac_o_ex.fe_len, ac->ac_status, ac->ac_flags, cr, err); if (nr) ext4_mb_prefetch_fini(sb, prefetch_grp, nr); return err; } static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos) { struct super_block *sb = pde_data(file_inode(seq->file)); ext4_group_t group; if (*pos < 0 || *pos >= ext4_get_groups_count(sb)) return NULL; group = *pos + 1; return (void *) ((unsigned long) group); } static void *ext4_mb_seq_groups_next(struct seq_file *seq, void *v, loff_t *pos) { struct super_block *sb = pde_data(file_inode(seq->file)); ext4_group_t group; ++*pos; if (*pos < 0 || *pos >= ext4_get_groups_count(sb)) return NULL; group = *pos + 1; return (void *) ((unsigned long) group); } static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) { struct super_block *sb = pde_data(file_inode(seq->file)); ext4_group_t group = (ext4_group_t) ((unsigned long) v); int i, err; char nbuf[16]; struct ext4_buddy e4b; struct ext4_group_info *grinfo; unsigned char blocksize_bits = min_t(unsigned char, sb->s_blocksize_bits, EXT4_MAX_BLOCK_LOG_SIZE); struct sg { struct ext4_group_info info; ext4_grpblk_t counters[EXT4_MAX_BLOCK_LOG_SIZE + 2]; } sg; group--; if (group == 0) seq_puts(seq, "#group: free frags first [" " 2^0 2^1 2^2 2^3 2^4 2^5 2^6 " " 2^7 2^8 2^9 2^10 2^11 2^12 2^13 ]\n"); i = (blocksize_bits + 2) * sizeof(sg.info.bb_counters[0]) + sizeof(struct ext4_group_info); grinfo = ext4_get_group_info(sb, group); if (!grinfo) return 0; /* Load the group info in memory only if not already loaded. */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grinfo))) { err = ext4_mb_load_buddy(sb, group, &e4b); if (err) { seq_printf(seq, "#%-5u: %s\n", group, ext4_decode_error(NULL, err, nbuf)); return 0; } ext4_mb_unload_buddy(&e4b); } /* * We care only about free space counters in the group info and * these are safe to access even after the buddy has been unloaded */ memcpy(&sg, grinfo, i); seq_printf(seq, "#%-5u: %-5u %-5u %-5u [", group, sg.info.bb_free, sg.info.bb_fragments, sg.info.bb_first_free); for (i = 0; i <= 13; i++) seq_printf(seq, " %-5u", i <= blocksize_bits + 1 ? sg.info.bb_counters[i] : 0); seq_puts(seq, " ]"); if (EXT4_MB_GRP_BBITMAP_CORRUPT(&sg.info)) seq_puts(seq, " Block bitmap corrupted!"); seq_puts(seq, "\n"); return 0; } static void ext4_mb_seq_groups_stop(struct seq_file *seq, void *v) { } const struct seq_operations ext4_mb_seq_groups_ops = { .start = ext4_mb_seq_groups_start, .next = ext4_mb_seq_groups_next, .stop = ext4_mb_seq_groups_stop, .show = ext4_mb_seq_groups_show, }; int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset) { struct super_block *sb = seq->private; struct ext4_sb_info *sbi = EXT4_SB(sb); seq_puts(seq, "mballoc:\n"); if (!sbi->s_mb_stats) { seq_puts(seq, "\tmb stats collection turned off.\n"); seq_puts( seq, "\tTo enable, please write \"1\" to sysfs file mb_stats.\n"); return 0; } seq_printf(seq, "\treqs: %u\n", atomic_read(&sbi->s_bal_reqs)); seq_printf(seq, "\tsuccess: %u\n", atomic_read(&sbi->s_bal_success)); seq_printf(seq, "\tgroups_scanned: %u\n", atomic_read(&sbi->s_bal_groups_scanned)); /* CR_POWER2_ALIGNED stats */ seq_puts(seq, "\tcr_p2_aligned_stats:\n"); seq_printf(seq, "\t\thits: %llu\n", atomic64_read(&sbi->s_bal_cX_hits[CR_POWER2_ALIGNED])); seq_printf( seq, "\t\tgroups_considered: %llu\n", atomic64_read( &sbi->s_bal_cX_groups_considered[CR_POWER2_ALIGNED])); seq_printf(seq, "\t\textents_scanned: %u\n", atomic_read(&sbi->s_bal_cX_ex_scanned[CR_POWER2_ALIGNED])); seq_printf(seq, "\t\tuseless_loops: %llu\n", atomic64_read(&sbi->s_bal_cX_failed[CR_POWER2_ALIGNED])); seq_printf(seq, "\t\tbad_suggestions: %u\n", atomic_read(&sbi->s_bal_p2_aligned_bad_suggestions)); /* CR_GOAL_LEN_FAST stats */ seq_puts(seq, "\tcr_goal_fast_stats:\n"); seq_printf(seq, "\t\thits: %llu\n", atomic64_read(&sbi->s_bal_cX_hits[CR_GOAL_LEN_FAST])); seq_printf(seq, "\t\tgroups_considered: %llu\n", atomic64_read( &sbi->s_bal_cX_groups_considered[CR_GOAL_LEN_FAST])); seq_printf(seq, "\t\textents_scanned: %u\n", atomic_read(&sbi->s_bal_cX_ex_scanned[CR_GOAL_LEN_FAST])); seq_printf(seq, "\t\tuseless_loops: %llu\n", atomic64_read(&sbi->s_bal_cX_failed[CR_GOAL_LEN_FAST])); seq_printf(seq, "\t\tbad_suggestions: %u\n", atomic_read(&sbi->s_bal_goal_fast_bad_suggestions)); /* CR_BEST_AVAIL_LEN stats */ seq_puts(seq, "\tcr_best_avail_stats:\n"); seq_printf(seq, "\t\thits: %llu\n", atomic64_read(&sbi->s_bal_cX_hits[CR_BEST_AVAIL_LEN])); seq_printf( seq, "\t\tgroups_considered: %llu\n", atomic64_read( &sbi->s_bal_cX_groups_considered[CR_BEST_AVAIL_LEN])); seq_printf(seq, "\t\textents_scanned: %u\n", atomic_read(&sbi->s_bal_cX_ex_scanned[CR_BEST_AVAIL_LEN])); seq_printf(seq, "\t\tuseless_loops: %llu\n", atomic64_read(&sbi->s_bal_cX_failed[CR_BEST_AVAIL_LEN])); seq_printf(seq, "\t\tbad_suggestions: %u\n", atomic_read(&sbi->s_bal_best_avail_bad_suggestions)); /* CR_GOAL_LEN_SLOW stats */ seq_puts(seq, "\tcr_goal_slow_stats:\n"); seq_printf(seq, "\t\thits: %llu\n", atomic64_read(&sbi->s_bal_cX_hits[CR_GOAL_LEN_SLOW])); seq_printf(seq, "\t\tgroups_considered: %llu\n", atomic64_read( &sbi->s_bal_cX_groups_considered[CR_GOAL_LEN_SLOW])); seq_printf(seq, "\t\textents_scanned: %u\n", atomic_read(&sbi->s_bal_cX_ex_scanned[CR_GOAL_LEN_SLOW])); seq_printf(seq, "\t\tuseless_loops: %llu\n", atomic64_read(&sbi->s_bal_cX_failed[CR_GOAL_LEN_SLOW])); /* CR_ANY_FREE stats */ seq_puts(seq, "\tcr_any_free_stats:\n"); seq_printf(seq, "\t\thits: %llu\n", atomic64_read(&sbi->s_bal_cX_hits[CR_ANY_FREE])); seq_printf( seq, "\t\tgroups_considered: %llu\n", atomic64_read(&sbi->s_bal_cX_groups_considered[CR_ANY_FREE])); seq_printf(seq, "\t\textents_scanned: %u\n", atomic_read(&sbi->s_bal_cX_ex_scanned[CR_ANY_FREE])); seq_printf(seq, "\t\tuseless_loops: %llu\n", atomic64_read(&sbi->s_bal_cX_failed[CR_ANY_FREE])); /* Aggregates */ seq_printf(seq, "\textents_scanned: %u\n", atomic_read(&sbi->s_bal_ex_scanned)); seq_printf(seq, "\t\tgoal_hits: %u\n", atomic_read(&sbi->s_bal_goals)); seq_printf(seq, "\t\tlen_goal_hits: %u\n", atomic_read(&sbi->s_bal_len_goals)); seq_printf(seq, "\t\t2^n_hits: %u\n", atomic_read(&sbi->s_bal_2orders)); seq_printf(seq, "\t\tbreaks: %u\n", atomic_read(&sbi->s_bal_breaks)); seq_printf(seq, "\t\tlost: %u\n", atomic_read(&sbi->s_mb_lost_chunks)); seq_printf(seq, "\tbuddies_generated: %u/%u\n", atomic_read(&sbi->s_mb_buddies_generated), ext4_get_groups_count(sb)); seq_printf(seq, "\tbuddies_time_used: %llu\n", atomic64_read(&sbi->s_mb_generation_time)); seq_printf(seq, "\tpreallocated: %u\n", atomic_read(&sbi->s_mb_preallocated)); seq_printf(seq, "\tdiscarded: %u\n", atomic_read(&sbi->s_mb_discarded)); return 0; } static void *ext4_mb_seq_structs_summary_start(struct seq_file *seq, loff_t *pos) { struct super_block *sb = pde_data(file_inode(seq->file)); unsigned long position; if (*pos < 0 || *pos >= 2*MB_NUM_ORDERS(sb)) return NULL; position = *pos + 1; return (void *) ((unsigned long) position); } static void *ext4_mb_seq_structs_summary_next(struct seq_file *seq, void *v, loff_t *pos) { struct super_block *sb = pde_data(file_inode(seq->file)); unsigned long position; ++*pos; if (*pos < 0 || *pos >= 2*MB_NUM_ORDERS(sb)) return NULL; position = *pos + 1; return (void *) ((unsigned long) position); } static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v) { struct super_block *sb = pde_data(file_inode(seq->file)); struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned long position = ((unsigned long) v); struct ext4_group_info *grp; unsigned int count; position--; if (position >= MB_NUM_ORDERS(sb)) { position -= MB_NUM_ORDERS(sb); if (position == 0) seq_puts(seq, "avg_fragment_size_lists:\n"); count = 0; read_lock(&sbi->s_mb_avg_fragment_size_locks[position]); list_for_each_entry(grp, &sbi->s_mb_avg_fragment_size[position], bb_avg_fragment_size_node) count++; read_unlock(&sbi->s_mb_avg_fragment_size_locks[position]); seq_printf(seq, "\tlist_order_%u_groups: %u\n", (unsigned int)position, count); return 0; } if (position == 0) { seq_printf(seq, "optimize_scan: %d\n", test_opt2(sb, MB_OPTIMIZE_SCAN) ? 1 : 0); seq_puts(seq, "max_free_order_lists:\n"); } count = 0; read_lock(&sbi->s_mb_largest_free_orders_locks[position]); list_for_each_entry(grp, &sbi->s_mb_largest_free_orders[position], bb_largest_free_order_node) count++; read_unlock(&sbi->s_mb_largest_free_orders_locks[position]); seq_printf(seq, "\tlist_order_%u_groups: %u\n", (unsigned int)position, count); return 0; } static void ext4_mb_seq_structs_summary_stop(struct seq_file *seq, void *v) { } const struct seq_operations ext4_mb_seq_structs_summary_ops = { .start = ext4_mb_seq_structs_summary_start, .next = ext4_mb_seq_structs_summary_next, .stop = ext4_mb_seq_structs_summary_stop, .show = ext4_mb_seq_structs_summary_show, }; static struct kmem_cache *get_groupinfo_cache(int blocksize_bits) { int cache_index = blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE; struct kmem_cache *cachep = ext4_groupinfo_caches[cache_index]; BUG_ON(!cachep); return cachep; } /* * Allocate the top-level s_group_info array for the specified number * of groups */ int ext4_mb_alloc_groupinfo(struct super_block *sb, ext4_group_t ngroups) { struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned size; struct ext4_group_info ***old_groupinfo, ***new_groupinfo; size = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >> EXT4_DESC_PER_BLOCK_BITS(sb); if (size <= sbi->s_group_info_size) return 0; size = roundup_pow_of_two(sizeof(*sbi->s_group_info) * size); new_groupinfo = kvzalloc(size, GFP_KERNEL); if (!new_groupinfo) { ext4_msg(sb, KERN_ERR, "can't allocate buddy meta group"); return -ENOMEM; } rcu_read_lock(); old_groupinfo = rcu_dereference(sbi->s_group_info); if (old_groupinfo) memcpy(new_groupinfo, old_groupinfo, sbi->s_group_info_size * sizeof(*sbi->s_group_info)); rcu_read_unlock(); rcu_assign_pointer(sbi->s_group_info, new_groupinfo); sbi->s_group_info_size = size / sizeof(*sbi->s_group_info); if (old_groupinfo) ext4_kvfree_array_rcu(old_groupinfo); ext4_debug("allocated s_groupinfo array for %d meta_bg's\n", sbi->s_group_info_size); return 0; } /* Create and initialize ext4_group_info data for the given group. */ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, struct ext4_group_desc *desc) { int i; int metalen = 0; int idx = group >> EXT4_DESC_PER_BLOCK_BITS(sb); struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_info **meta_group_info; struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits); /* * First check if this group is the first of a reserved block. * If it's true, we have to allocate a new table of pointers * to ext4_group_info structures */ if (group % EXT4_DESC_PER_BLOCK(sb) == 0) { metalen = sizeof(*meta_group_info) << EXT4_DESC_PER_BLOCK_BITS(sb); meta_group_info = kmalloc(metalen, GFP_NOFS); if (meta_group_info == NULL) { ext4_msg(sb, KERN_ERR, "can't allocate mem " "for a buddy group"); return -ENOMEM; } rcu_read_lock(); rcu_dereference(sbi->s_group_info)[idx] = meta_group_info; rcu_read_unlock(); } meta_group_info = sbi_array_rcu_deref(sbi, s_group_info, idx); i = group & (EXT4_DESC_PER_BLOCK(sb) - 1); meta_group_info[i] = kmem_cache_zalloc(cachep, GFP_NOFS); if (meta_group_info[i] == NULL) { ext4_msg(sb, KERN_ERR, "can't allocate buddy mem"); goto exit_group_info; } set_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(meta_group_info[i]->bb_state)); /* * initialize bb_free to be able to skip * empty groups without initialization */ if (ext4_has_group_desc_csum(sb) && (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { meta_group_info[i]->bb_free = ext4_free_clusters_after_init(sb, group, desc); } else { meta_group_info[i]->bb_free = ext4_free_group_clusters(sb, desc); } INIT_LIST_HEAD(&meta_group_info[i]->bb_prealloc_list); init_rwsem(&meta_group_info[i]->alloc_sem); meta_group_info[i]->bb_free_root = RB_ROOT; INIT_LIST_HEAD(&meta_group_info[i]->bb_largest_free_order_node); INIT_LIST_HEAD(&meta_group_info[i]->bb_avg_fragment_size_node); meta_group_info[i]->bb_largest_free_order = -1; /* uninit */ meta_group_info[i]->bb_avg_fragment_size_order = -1; /* uninit */ meta_group_info[i]->bb_group = group; mb_group_bb_bitmap_alloc(sb, meta_group_info[i], group); return 0; exit_group_info: /* If a meta_group_info table has been allocated, release it now */ if (group % EXT4_DESC_PER_BLOCK(sb) == 0) { struct ext4_group_info ***group_info; rcu_read_lock(); group_info = rcu_dereference(sbi->s_group_info); kfree(group_info[idx]); group_info[idx] = NULL; rcu_read_unlock(); } return -ENOMEM; } /* ext4_mb_add_groupinfo */ static int ext4_mb_init_backend(struct super_block *sb) { ext4_group_t ngroups = ext4_get_groups_count(sb); ext4_group_t i; struct ext4_sb_info *sbi = EXT4_SB(sb); int err; struct ext4_group_desc *desc; struct ext4_group_info ***group_info; struct kmem_cache *cachep; err = ext4_mb_alloc_groupinfo(sb, ngroups); if (err) return err; sbi->s_buddy_cache = new_inode(sb); if (sbi->s_buddy_cache == NULL) { ext4_msg(sb, KERN_ERR, "can't get new inode"); goto err_freesgi; } /* To avoid potentially colliding with an valid on-disk inode number, * use EXT4_BAD_INO for the buddy cache inode number. This inode is * not in the inode hash, so it should never be found by iget(), but * this will avoid confusion if it ever shows up during debugging. */ sbi->s_buddy_cache->i_ino = EXT4_BAD_INO; EXT4_I(sbi->s_buddy_cache)->i_disksize = 0; for (i = 0; i < ngroups; i++) { cond_resched(); desc = ext4_get_group_desc(sb, i, NULL); if (desc == NULL) { ext4_msg(sb, KERN_ERR, "can't read descriptor %u", i); goto err_freebuddy; } if (ext4_mb_add_groupinfo(sb, i, desc) != 0) goto err_freebuddy; } if (ext4_has_feature_flex_bg(sb)) { /* a single flex group is supposed to be read by a single IO. * 2 ^ s_log_groups_per_flex != UINT_MAX as s_mb_prefetch is * unsigned integer, so the maximum shift is 32. */ if (sbi->s_es->s_log_groups_per_flex >= 32) { ext4_msg(sb, KERN_ERR, "too many log groups per flexible block group"); goto err_freebuddy; } sbi->s_mb_prefetch = min_t(uint, 1 << sbi->s_es->s_log_groups_per_flex, BLK_MAX_SEGMENT_SIZE >> (sb->s_blocksize_bits - 9)); sbi->s_mb_prefetch *= 8; /* 8 prefetch IOs in flight at most */ } else { sbi->s_mb_prefetch = 32; } if (sbi->s_mb_prefetch > ext4_get_groups_count(sb)) sbi->s_mb_prefetch = ext4_get_groups_count(sb); /* * now many real IOs to prefetch within a single allocation at * CR_POWER2_ALIGNED. Given CR_POWER2_ALIGNED is an CPU-related * optimization we shouldn't try to load too many groups, at some point * we should start to use what we've got in memory. * with an average random access time 5ms, it'd take a second to get * 200 groups (* N with flex_bg), so let's make this limit 4 */ sbi->s_mb_prefetch_limit = sbi->s_mb_prefetch * 4; if (sbi->s_mb_prefetch_limit > ext4_get_groups_count(sb)) sbi->s_mb_prefetch_limit = ext4_get_groups_count(sb); return 0; err_freebuddy: cachep = get_groupinfo_cache(sb->s_blocksize_bits); while (i-- > 0) { struct ext4_group_info *grp = ext4_get_group_info(sb, i); if (grp) kmem_cache_free(cachep, grp); } i = sbi->s_group_info_size; rcu_read_lock(); group_info = rcu_dereference(sbi->s_group_info); while (i-- > 0) kfree(group_info[i]); rcu_read_unlock(); iput(sbi->s_buddy_cache); err_freesgi: rcu_read_lock(); kvfree(rcu_dereference(sbi->s_group_info)); rcu_read_unlock(); return -ENOMEM; } static void ext4_groupinfo_destroy_slabs(void) { int i; for (i = 0; i < NR_GRPINFO_CACHES; i++) { kmem_cache_destroy(ext4_groupinfo_caches[i]); ext4_groupinfo_caches[i] = NULL; } } static int ext4_groupinfo_create_slab(size_t size) { static DEFINE_MUTEX(ext4_grpinfo_slab_create_mutex); int slab_size; int blocksize_bits = order_base_2(size); int cache_index = blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE; struct kmem_cache *cachep; if (cache_index >= NR_GRPINFO_CACHES) return -EINVAL; if (unlikely(cache_index < 0)) cache_index = 0; mutex_lock(&ext4_grpinfo_slab_create_mutex); if (ext4_groupinfo_caches[cache_index]) { mutex_unlock(&ext4_grpinfo_slab_create_mutex); return 0; /* Already created */ } slab_size = offsetof(struct ext4_group_info, bb_counters[blocksize_bits + 2]); cachep = kmem_cache_create(ext4_groupinfo_slab_names[cache_index], slab_size, 0, SLAB_RECLAIM_ACCOUNT, NULL); ext4_groupinfo_caches[cache_index] = cachep; mutex_unlock(&ext4_grpinfo_slab_create_mutex); if (!cachep) { printk(KERN_EMERG "EXT4-fs: no memory for groupinfo slab cache\n"); return -ENOMEM; } return 0; } static void ext4_discard_work(struct work_struct *work) { struct ext4_sb_info *sbi = container_of(work, struct ext4_sb_info, s_discard_work); struct super_block *sb = sbi->s_sb; struct ext4_free_data *fd, *nfd; struct ext4_buddy e4b; LIST_HEAD(discard_list); ext4_group_t grp, load_grp; int err = 0; spin_lock(&sbi->s_md_lock); list_splice_init(&sbi->s_discard_list, &discard_list); spin_unlock(&sbi->s_md_lock); load_grp = UINT_MAX; list_for_each_entry_safe(fd, nfd, &discard_list, efd_list) { /* * If filesystem is umounting or no memory or suffering * from no space, give up the discard */ if ((sb->s_flags & SB_ACTIVE) && !err && !atomic_read(&sbi->s_retry_alloc_pending)) { grp = fd->efd_group; if (grp != load_grp) { if (load_grp != UINT_MAX) ext4_mb_unload_buddy(&e4b); err = ext4_mb_load_buddy(sb, grp, &e4b); if (err) { kmem_cache_free(ext4_free_data_cachep, fd); load_grp = UINT_MAX; continue; } else { load_grp = grp; } } ext4_lock_group(sb, grp); ext4_try_to_trim_range(sb, &e4b, fd->efd_start_cluster, fd->efd_start_cluster + fd->efd_count - 1, 1); ext4_unlock_group(sb, grp); } kmem_cache_free(ext4_free_data_cachep, fd); } if (load_grp != UINT_MAX) ext4_mb_unload_buddy(&e4b); } int ext4_mb_init(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned i, j; unsigned offset, offset_incr; unsigned max; int ret; i = MB_NUM_ORDERS(sb) * sizeof(*sbi->s_mb_offsets); sbi->s_mb_offsets = kmalloc(i, GFP_KERNEL); if (sbi->s_mb_offsets == NULL) { ret = -ENOMEM; goto out; } i = MB_NUM_ORDERS(sb) * sizeof(*sbi->s_mb_maxs); sbi->s_mb_maxs = kmalloc(i, GFP_KERNEL); if (sbi->s_mb_maxs == NULL) { ret = -ENOMEM; goto out; } ret = ext4_groupinfo_create_slab(sb->s_blocksize); if (ret < 0) goto out; /* order 0 is regular bitmap */ sbi->s_mb_maxs[0] = sb->s_blocksize << 3; sbi->s_mb_offsets[0] = 0; i = 1; offset = 0; offset_incr = 1 << (sb->s_blocksize_bits - 1); max = sb->s_blocksize << 2; do { sbi->s_mb_offsets[i] = offset; sbi->s_mb_maxs[i] = max; offset += offset_incr; offset_incr = offset_incr >> 1; max = max >> 1; i++; } while (i < MB_NUM_ORDERS(sb)); sbi->s_mb_avg_fragment_size = kmalloc_array(MB_NUM_ORDERS(sb), sizeof(struct list_head), GFP_KERNEL); if (!sbi->s_mb_avg_fragment_size) { ret = -ENOMEM; goto out; } sbi->s_mb_avg_fragment_size_locks = kmalloc_array(MB_NUM_ORDERS(sb), sizeof(rwlock_t), GFP_KERNEL); if (!sbi->s_mb_avg_fragment_size_locks) { ret = -ENOMEM; goto out; } for (i = 0; i < MB_NUM_ORDERS(sb); i++) { INIT_LIST_HEAD(&sbi->s_mb_avg_fragment_size[i]); rwlock_init(&sbi->s_mb_avg_fragment_size_locks[i]); } sbi->s_mb_largest_free_orders = kmalloc_array(MB_NUM_ORDERS(sb), sizeof(struct list_head), GFP_KERNEL); if (!sbi->s_mb_largest_free_orders) { ret = -ENOMEM; goto out; } sbi->s_mb_largest_free_orders_locks = kmalloc_array(MB_NUM_ORDERS(sb), sizeof(rwlock_t), GFP_KERNEL); if (!sbi->s_mb_largest_free_orders_locks) { ret = -ENOMEM; goto out; } for (i = 0; i < MB_NUM_ORDERS(sb); i++) { INIT_LIST_HEAD(&sbi->s_mb_largest_free_orders[i]); rwlock_init(&sbi->s_mb_largest_free_orders_locks[i]); } spin_lock_init(&sbi->s_md_lock); sbi->s_mb_free_pending = 0; INIT_LIST_HEAD(&sbi->s_freed_data_list[0]); INIT_LIST_HEAD(&sbi->s_freed_data_list[1]); INIT_LIST_HEAD(&sbi->s_discard_list); INIT_WORK(&sbi->s_discard_work, ext4_discard_work); atomic_set(&sbi->s_retry_alloc_pending, 0); sbi->s_mb_max_to_scan = MB_DEFAULT_MAX_TO_SCAN; sbi->s_mb_min_to_scan = MB_DEFAULT_MIN_TO_SCAN; sbi->s_mb_stats = MB_DEFAULT_STATS; sbi->s_mb_stream_request = MB_DEFAULT_STREAM_THRESHOLD; sbi->s_mb_order2_reqs = MB_DEFAULT_ORDER2_REQS; sbi->s_mb_best_avail_max_trim_order = MB_DEFAULT_BEST_AVAIL_TRIM_ORDER; /* * The default group preallocation is 512, which for 4k block * sizes translates to 2 megabytes. However for bigalloc file * systems, this is probably too big (i.e, if the cluster size * is 1 megabyte, then group preallocation size becomes half a * gigabyte!). As a default, we will keep a two megabyte * group pralloc size for cluster sizes up to 64k, and after * that, we will force a minimum group preallocation size of * 32 clusters. This translates to 8 megs when the cluster * size is 256k, and 32 megs when the cluster size is 1 meg, * which seems reasonable as a default. */ sbi->s_mb_group_prealloc = max(MB_DEFAULT_GROUP_PREALLOC >> sbi->s_cluster_bits, 32); /* * If there is a s_stripe > 1, then we set the s_mb_group_prealloc * to the lowest multiple of s_stripe which is bigger than * the s_mb_group_prealloc as determined above. We want * the preallocation size to be an exact multiple of the * RAID stripe size so that preallocations don't fragment * the stripes. */ if (sbi->s_stripe > 1) { sbi->s_mb_group_prealloc = roundup( sbi->s_mb_group_prealloc, EXT4_B2C(sbi, sbi->s_stripe)); } sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group); if (sbi->s_locality_groups == NULL) { ret = -ENOMEM; goto out; } for_each_possible_cpu(i) { struct ext4_locality_group *lg; lg = per_cpu_ptr(sbi->s_locality_groups, i); mutex_init(&lg->lg_mutex); for (j = 0; j < PREALLOC_TB_SIZE; j++) INIT_LIST_HEAD(&lg->lg_prealloc_list[j]); spin_lock_init(&lg->lg_prealloc_lock); } if (bdev_nonrot(sb->s_bdev)) sbi->s_mb_max_linear_groups = 0; else sbi->s_mb_max_linear_groups = MB_DEFAULT_LINEAR_LIMIT; /* init file for buddy data */ ret = ext4_mb_init_backend(sb); if (ret != 0) goto out_free_locality_groups; return 0; out_free_locality_groups: free_percpu(sbi->s_locality_groups); sbi->s_locality_groups = NULL; out: kfree(sbi->s_mb_avg_fragment_size); kfree(sbi->s_mb_avg_fragment_size_locks); kfree(sbi->s_mb_largest_free_orders); kfree(sbi->s_mb_largest_free_orders_locks); kfree(sbi->s_mb_offsets); sbi->s_mb_offsets = NULL; kfree(sbi->s_mb_maxs); sbi->s_mb_maxs = NULL; return ret; } /* need to called with the ext4 group lock held */ static int ext4_mb_cleanup_pa(struct ext4_group_info *grp) { struct ext4_prealloc_space *pa; struct list_head *cur, *tmp; int count = 0; list_for_each_safe(cur, tmp, &grp->bb_prealloc_list) { pa = list_entry(cur, struct ext4_prealloc_space, pa_group_list); list_del(&pa->pa_group_list); count++; kmem_cache_free(ext4_pspace_cachep, pa); } return count; } void ext4_mb_release(struct super_block *sb) { ext4_group_t ngroups = ext4_get_groups_count(sb); ext4_group_t i; int num_meta_group_infos; struct ext4_group_info *grinfo, ***group_info; struct ext4_sb_info *sbi = EXT4_SB(sb); struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits); int count; if (test_opt(sb, DISCARD)) { /* * wait the discard work to drain all of ext4_free_data */ flush_work(&sbi->s_discard_work); WARN_ON_ONCE(!list_empty(&sbi->s_discard_list)); } if (sbi->s_group_info) { for (i = 0; i < ngroups; i++) { cond_resched(); grinfo = ext4_get_group_info(sb, i); if (!grinfo) continue; mb_group_bb_bitmap_free(grinfo); ext4_lock_group(sb, i); count = ext4_mb_cleanup_pa(grinfo); if (count) mb_debug(sb, "mballoc: %d PAs left\n", count); ext4_unlock_group(sb, i); kmem_cache_free(cachep, grinfo); } num_meta_group_infos = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >> EXT4_DESC_PER_BLOCK_BITS(sb); rcu_read_lock(); group_info = rcu_dereference(sbi->s_group_info); for (i = 0; i < num_meta_group_infos; i++) kfree(group_info[i]); kvfree(group_info); rcu_read_unlock(); } kfree(sbi->s_mb_avg_fragment_size); kfree(sbi->s_mb_avg_fragment_size_locks); kfree(sbi->s_mb_largest_free_orders); kfree(sbi->s_mb_largest_free_orders_locks); kfree(sbi->s_mb_offsets); kfree(sbi->s_mb_maxs); iput(sbi->s_buddy_cache); if (sbi->s_mb_stats) { ext4_msg(sb, KERN_INFO, "mballoc: %u blocks %u reqs (%u success)", atomic_read(&sbi->s_bal_allocated), atomic_read(&sbi->s_bal_reqs), atomic_read(&sbi->s_bal_success)); ext4_msg(sb, KERN_INFO, "mballoc: %u extents scanned, %u groups scanned, %u goal hits, " "%u 2^N hits, %u breaks, %u lost", atomic_read(&sbi->s_bal_ex_scanned), atomic_read(&sbi->s_bal_groups_scanned), atomic_read(&sbi->s_bal_goals), atomic_read(&sbi->s_bal_2orders), atomic_read(&sbi->s_bal_breaks), atomic_read(&sbi->s_mb_lost_chunks)); ext4_msg(sb, KERN_INFO, "mballoc: %u generated and it took %llu", atomic_read(&sbi->s_mb_buddies_generated), atomic64_read(&sbi->s_mb_generation_time)); ext4_msg(sb, KERN_INFO, "mballoc: %u preallocated, %u discarded", atomic_read(&sbi->s_mb_preallocated), atomic_read(&sbi->s_mb_discarded)); } free_percpu(sbi->s_locality_groups); } static inline int ext4_issue_discard(struct super_block *sb, ext4_group_t block_group, ext4_grpblk_t cluster, int count) { ext4_fsblk_t discard_block; discard_block = (EXT4_C2B(EXT4_SB(sb), cluster) + ext4_group_first_block_no(sb, block_group)); count = EXT4_C2B(EXT4_SB(sb), count); trace_ext4_discard_blocks(sb, (unsigned long long) discard_block, count); return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0); } static void ext4_free_data_in_buddy(struct super_block *sb, struct ext4_free_data *entry) { struct ext4_buddy e4b; struct ext4_group_info *db; int err, count = 0; mb_debug(sb, "gonna free %u blocks in group %u (0x%p):", entry->efd_count, entry->efd_group, entry); err = ext4_mb_load_buddy(sb, entry->efd_group, &e4b); /* we expect to find existing buddy because it's pinned */ BUG_ON(err != 0); spin_lock(&EXT4_SB(sb)->s_md_lock); EXT4_SB(sb)->s_mb_free_pending -= entry->efd_count; spin_unlock(&EXT4_SB(sb)->s_md_lock); db = e4b.bd_info; /* there are blocks to put in buddy to make them really free */ count += entry->efd_count; ext4_lock_group(sb, entry->efd_group); /* Take it out of per group rb tree */ rb_erase(&entry->efd_node, &(db->bb_free_root)); mb_free_blocks(NULL, &e4b, entry->efd_start_cluster, entry->efd_count); /* * Clear the trimmed flag for the group so that the next * ext4_trim_fs can trim it. * If the volume is mounted with -o discard, online discard * is supported and the free blocks will be trimmed online. */ if (!test_opt(sb, DISCARD)) EXT4_MB_GRP_CLEAR_TRIMMED(db); if (!db->bb_free_root.rb_node) { /* No more items in the per group rb tree * balance refcounts from ext4_mb_free_metadata() */ folio_put(e4b.bd_buddy_folio); folio_put(e4b.bd_bitmap_folio); } ext4_unlock_group(sb, entry->efd_group); ext4_mb_unload_buddy(&e4b); mb_debug(sb, "freed %d blocks in 1 structures\n", count); } /* * This function is called by the jbd2 layer once the commit has finished, * so we know we can free the blocks that were released with that commit. */ void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_free_data *entry, *tmp; LIST_HEAD(freed_data_list); struct list_head *s_freed_head = &sbi->s_freed_data_list[commit_tid & 1]; bool wake; list_replace_init(s_freed_head, &freed_data_list); list_for_each_entry(entry, &freed_data_list, efd_list) ext4_free_data_in_buddy(sb, entry); if (test_opt(sb, DISCARD)) { spin_lock(&sbi->s_md_lock); wake = list_empty(&sbi->s_discard_list); list_splice_tail(&freed_data_list, &sbi->s_discard_list); spin_unlock(&sbi->s_md_lock); if (wake) queue_work(system_unbound_wq, &sbi->s_discard_work); } else { list_for_each_entry_safe(entry, tmp, &freed_data_list, efd_list) kmem_cache_free(ext4_free_data_cachep, entry); } } int __init ext4_init_mballoc(void) { ext4_pspace_cachep = KMEM_CACHE(ext4_prealloc_space, SLAB_RECLAIM_ACCOUNT); if (ext4_pspace_cachep == NULL) goto out; ext4_ac_cachep = KMEM_CACHE(ext4_allocation_context, SLAB_RECLAIM_ACCOUNT); if (ext4_ac_cachep == NULL) goto out_pa_free; ext4_free_data_cachep = KMEM_CACHE(ext4_free_data, SLAB_RECLAIM_ACCOUNT); if (ext4_free_data_cachep == NULL) goto out_ac_free; return 0; out_ac_free: kmem_cache_destroy(ext4_ac_cachep); out_pa_free: kmem_cache_destroy(ext4_pspace_cachep); out: return -ENOMEM; } void ext4_exit_mballoc(void) { /* * Wait for completion of call_rcu()'s on ext4_pspace_cachep * before destroying the slab cache. */ rcu_barrier(); kmem_cache_destroy(ext4_pspace_cachep); kmem_cache_destroy(ext4_ac_cachep); kmem_cache_destroy(ext4_free_data_cachep); ext4_groupinfo_destroy_slabs(); } #define EXT4_MB_BITMAP_MARKED_CHECK 0x0001 #define EXT4_MB_SYNC_UPDATE 0x0002 static int ext4_mb_mark_context(handle_t *handle, struct super_block *sb, bool state, ext4_group_t group, ext4_grpblk_t blkoff, ext4_grpblk_t len, int flags, ext4_grpblk_t *ret_changed) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct buffer_head *bitmap_bh = NULL; struct ext4_group_desc *gdp; struct buffer_head *gdp_bh; int err; unsigned int i, already, changed = len; KUNIT_STATIC_STUB_REDIRECT(ext4_mb_mark_context, handle, sb, state, group, blkoff, len, flags, ret_changed); if (ret_changed) *ret_changed = 0; bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(bitmap_bh)) return PTR_ERR(bitmap_bh); if (handle) { BUFFER_TRACE(bitmap_bh, "getting write access"); err = ext4_journal_get_write_access(handle, sb, bitmap_bh, EXT4_JTR_NONE); if (err) goto out_err; } err = -EIO; gdp = ext4_get_group_desc(sb, group, &gdp_bh); if (!gdp) goto out_err; if (handle) { BUFFER_TRACE(gdp_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, sb, gdp_bh, EXT4_JTR_NONE); if (err) goto out_err; } ext4_lock_group(sb, group); if (ext4_has_group_desc_csum(sb) && (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); ext4_free_group_clusters_set(sb, gdp, ext4_free_clusters_after_init(sb, group, gdp)); } if (flags & EXT4_MB_BITMAP_MARKED_CHECK) { already = 0; for (i = 0; i < len; i++) if (mb_test_bit(blkoff + i, bitmap_bh->b_data) == state) already++; changed = len - already; } if (state) { mb_set_bits(bitmap_bh->b_data, blkoff, len); ext4_free_group_clusters_set(sb, gdp, ext4_free_group_clusters(sb, gdp) - changed); } else { mb_clear_bits(bitmap_bh->b_data, blkoff, len); ext4_free_group_clusters_set(sb, gdp, ext4_free_group_clusters(sb, gdp) + changed); } ext4_block_bitmap_csum_set(sb, gdp, bitmap_bh); ext4_group_desc_csum_set(sb, group, gdp); ext4_unlock_group(sb, group); if (ret_changed) *ret_changed = changed; if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, group); struct flex_groups *fg = sbi_array_rcu_deref(sbi, s_flex_groups, flex_group); if (state) atomic64_sub(changed, &fg->free_clusters); else atomic64_add(changed, &fg->free_clusters); } err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); if (err) goto out_err; err = ext4_handle_dirty_metadata(handle, NULL, gdp_bh); if (err) goto out_err; if (flags & EXT4_MB_SYNC_UPDATE) { sync_dirty_buffer(bitmap_bh); sync_dirty_buffer(gdp_bh); } out_err: brelse(bitmap_bh); return err; } /* * Check quota and mark chosen space (ac->ac_b_ex) non-free in bitmaps * Returns 0 if success or error code */ static noinline_for_stack int ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, handle_t *handle, unsigned int reserv_clstrs) { struct ext4_group_desc *gdp; struct ext4_sb_info *sbi; struct super_block *sb; ext4_fsblk_t block; int err, len; int flags = 0; ext4_grpblk_t changed; BUG_ON(ac->ac_status != AC_STATUS_FOUND); BUG_ON(ac->ac_b_ex.fe_len <= 0); sb = ac->ac_sb; sbi = EXT4_SB(sb); gdp = ext4_get_group_desc(sb, ac->ac_b_ex.fe_group, NULL); if (!gdp) return -EIO; ext4_debug("using block group %u(%d)\n", ac->ac_b_ex.fe_group, ext4_free_group_clusters(sb, gdp)); block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); len = EXT4_C2B(sbi, ac->ac_b_ex.fe_len); if (!ext4_inode_block_valid(ac->ac_inode, block, len)) { ext4_error(sb, "Allocating blocks %llu-%llu which overlap " "fs metadata", block, block+len); /* File system mounted not to panic on error * Fix the bitmap and return EFSCORRUPTED * We leak some of the blocks here. */ err = ext4_mb_mark_context(handle, sb, true, ac->ac_b_ex.fe_group, ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len, 0, NULL); if (!err) err = -EFSCORRUPTED; return err; } #ifdef AGGRESSIVE_CHECK flags |= EXT4_MB_BITMAP_MARKED_CHECK; #endif err = ext4_mb_mark_context(handle, sb, true, ac->ac_b_ex.fe_group, ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len, flags, &changed); if (err && changed == 0) return err; #ifdef AGGRESSIVE_CHECK BUG_ON(changed != ac->ac_b_ex.fe_len); #endif percpu_counter_sub(&sbi->s_freeclusters_counter, ac->ac_b_ex.fe_len); /* * Now reduce the dirty block count also. Should not go negative */ if (!(ac->ac_flags & EXT4_MB_DELALLOC_RESERVED)) /* release all the reserved blocks if non delalloc */ percpu_counter_sub(&sbi->s_dirtyclusters_counter, reserv_clstrs); return err; } /* * Idempotent helper for Ext4 fast commit replay path to set the state of * blocks in bitmaps and update counters. */ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block, int len, bool state) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_group_t group; ext4_grpblk_t blkoff; int err = 0; unsigned int clen, thisgrp_len; while (len > 0) { ext4_get_group_no_and_offset(sb, block, &group, &blkoff); /* * Check to see if we are freeing blocks across a group * boundary. * In case of flex_bg, this can happen that (block, len) may * span across more than one group. In that case we need to * get the corresponding group metadata to work with. * For this we have goto again loop. */ thisgrp_len = min_t(unsigned int, (unsigned int)len, EXT4_BLOCKS_PER_GROUP(sb) - EXT4_C2B(sbi, blkoff)); clen = EXT4_NUM_B2C(sbi, thisgrp_len); if (!ext4_sb_block_valid(sb, NULL, block, thisgrp_len)) { ext4_error(sb, "Marking blocks in system zone - " "Block = %llu, len = %u", block, thisgrp_len); break; } err = ext4_mb_mark_context(NULL, sb, state, group, blkoff, clen, EXT4_MB_BITMAP_MARKED_CHECK | EXT4_MB_SYNC_UPDATE, NULL); if (err) break; block += thisgrp_len; len -= thisgrp_len; BUG_ON(len < 0); } } /* * here we normalize request for locality group * Group request are normalized to s_mb_group_prealloc, which goes to * s_strip if we set the same via mount option. * s_mb_group_prealloc can be configured via * /sys/fs/ext4/<partition>/mb_group_prealloc * * XXX: should we try to preallocate more than the group has now? */ static void ext4_mb_normalize_group_request(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; struct ext4_locality_group *lg = ac->ac_lg; BUG_ON(lg == NULL); ac->ac_g_ex.fe_len = EXT4_SB(sb)->s_mb_group_prealloc; mb_debug(sb, "goal %u blocks for locality group\n", ac->ac_g_ex.fe_len); } /* * This function returns the next element to look at during inode * PA rbtree walk. We assume that we have held the inode PA rbtree lock * (ei->i_prealloc_lock) * * new_start The start of the range we want to compare * cur_start The existing start that we are comparing against * node The node of the rb_tree */ static inline struct rb_node* ext4_mb_pa_rb_next_iter(ext4_lblk_t new_start, ext4_lblk_t cur_start, struct rb_node *node) { if (new_start < cur_start) return node->rb_left; else return node->rb_right; } static inline void ext4_mb_pa_assert_overlap(struct ext4_allocation_context *ac, ext4_lblk_t start, loff_t end) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_inode_info *ei = EXT4_I(ac->ac_inode); struct ext4_prealloc_space *tmp_pa; ext4_lblk_t tmp_pa_start; loff_t tmp_pa_end; struct rb_node *iter; read_lock(&ei->i_prealloc_lock); for (iter = ei->i_prealloc_node.rb_node; iter; iter = ext4_mb_pa_rb_next_iter(start, tmp_pa_start, iter)) { tmp_pa = rb_entry(iter, struct ext4_prealloc_space, pa_node.inode_node); tmp_pa_start = tmp_pa->pa_lstart; tmp_pa_end = pa_logical_end(sbi, tmp_pa); spin_lock(&tmp_pa->pa_lock); if (tmp_pa->pa_deleted == 0) BUG_ON(!(start >= tmp_pa_end || end <= tmp_pa_start)); spin_unlock(&tmp_pa->pa_lock); } read_unlock(&ei->i_prealloc_lock); } /* * Given an allocation context "ac" and a range "start", "end", check * and adjust boundaries if the range overlaps with any of the existing * preallocatoins stored in the corresponding inode of the allocation context. * * Parameters: * ac allocation context * start start of the new range * end end of the new range */ static inline void ext4_mb_pa_adjust_overlap(struct ext4_allocation_context *ac, ext4_lblk_t *start, loff_t *end) { struct ext4_inode_info *ei = EXT4_I(ac->ac_inode); struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_prealloc_space *tmp_pa = NULL, *left_pa = NULL, *right_pa = NULL; struct rb_node *iter; ext4_lblk_t new_start, tmp_pa_start, right_pa_start = -1; loff_t new_end, tmp_pa_end, left_pa_end = -1; new_start = *start; new_end = *end; /* * Adjust the normalized range so that it doesn't overlap with any * existing preallocated blocks(PAs). Make sure to hold the rbtree lock * so it doesn't change underneath us. */ read_lock(&ei->i_prealloc_lock); /* Step 1: find any one immediate neighboring PA of the normalized range */ for (iter = ei->i_prealloc_node.rb_node; iter; iter = ext4_mb_pa_rb_next_iter(ac->ac_o_ex.fe_logical, tmp_pa_start, iter)) { tmp_pa = rb_entry(iter, struct ext4_prealloc_space, pa_node.inode_node); tmp_pa_start = tmp_pa->pa_lstart; tmp_pa_end = pa_logical_end(sbi, tmp_pa); /* PA must not overlap original request */ spin_lock(&tmp_pa->pa_lock); if (tmp_pa->pa_deleted == 0) BUG_ON(!(ac->ac_o_ex.fe_logical >= tmp_pa_end || ac->ac_o_ex.fe_logical < tmp_pa_start)); spin_unlock(&tmp_pa->pa_lock); } /* * Step 2: check if the found PA is left or right neighbor and * get the other neighbor */ if (tmp_pa) { if (tmp_pa->pa_lstart < ac->ac_o_ex.fe_logical) { struct rb_node *tmp; left_pa = tmp_pa; tmp = rb_next(&left_pa->pa_node.inode_node); if (tmp) { right_pa = rb_entry(tmp, struct ext4_prealloc_space, pa_node.inode_node); } } else { struct rb_node *tmp; right_pa = tmp_pa; tmp = rb_prev(&right_pa->pa_node.inode_node); if (tmp) { left_pa = rb_entry(tmp, struct ext4_prealloc_space, pa_node.inode_node); } } } /* Step 3: get the non deleted neighbors */ if (left_pa) { for (iter = &left_pa->pa_node.inode_node;; iter = rb_prev(iter)) { if (!iter) { left_pa = NULL; break; } tmp_pa = rb_entry(iter, struct ext4_prealloc_space, pa_node.inode_node); left_pa = tmp_pa; spin_lock(&tmp_pa->pa_lock); if (tmp_pa->pa_deleted == 0) { spin_unlock(&tmp_pa->pa_lock); break; } spin_unlock(&tmp_pa->pa_lock); } } if (right_pa) { for (iter = &right_pa->pa_node.inode_node;; iter = rb_next(iter)) { if (!iter) { right_pa = NULL; break; } tmp_pa = rb_entry(iter, struct ext4_prealloc_space, pa_node.inode_node); right_pa = tmp_pa; spin_lock(&tmp_pa->pa_lock); if (tmp_pa->pa_deleted == 0) { spin_unlock(&tmp_pa->pa_lock); break; } spin_unlock(&tmp_pa->pa_lock); } } if (left_pa) { left_pa_end = pa_logical_end(sbi, left_pa); BUG_ON(left_pa_end > ac->ac_o_ex.fe_logical); } if (right_pa) { right_pa_start = right_pa->pa_lstart; BUG_ON(right_pa_start <= ac->ac_o_ex.fe_logical); } /* Step 4: trim our normalized range to not overlap with the neighbors */ if (left_pa) { if (left_pa_end > new_start) new_start = left_pa_end; } if (right_pa) { if (right_pa_start < new_end) new_end = right_pa_start; } read_unlock(&ei->i_prealloc_lock); /* XXX: extra loop to check we really don't overlap preallocations */ ext4_mb_pa_assert_overlap(ac, new_start, new_end); *start = new_start; *end = new_end; } /* * Normalization means making request better in terms of * size and alignment */ static noinline_for_stack void ext4_mb_normalize_request(struct ext4_allocation_context *ac, struct ext4_allocation_request *ar) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_super_block *es = sbi->s_es; int bsbits, max; loff_t size, start_off, end; loff_t orig_size __maybe_unused; ext4_lblk_t start; /* do normalize only data requests, metadata requests do not need preallocation */ if (!(ac->ac_flags & EXT4_MB_HINT_DATA)) return; /* sometime caller may want exact blocks */ if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY)) return; /* caller may indicate that preallocation isn't * required (it's a tail, for example) */ if (ac->ac_flags & EXT4_MB_HINT_NOPREALLOC) return; if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC) { ext4_mb_normalize_group_request(ac); return ; } bsbits = ac->ac_sb->s_blocksize_bits; /* first, let's learn actual file size * given current request is allocated */ size = extent_logical_end(sbi, &ac->ac_o_ex); size = size << bsbits; if (size < i_size_read(ac->ac_inode)) size = i_size_read(ac->ac_inode); orig_size = size; /* max size of free chunks */ max = 2 << bsbits; #define NRL_CHECK_SIZE(req, size, max, chunk_size) \ (req <= (size) || max <= (chunk_size)) /* first, try to predict filesize */ /* XXX: should this table be tunable? */ start_off = 0; if (size <= 16 * 1024) { size = 16 * 1024; } else if (size <= 32 * 1024) { size = 32 * 1024; } else if (size <= 64 * 1024) { size = 64 * 1024; } else if (size <= 128 * 1024) { size = 128 * 1024; } else if (size <= 256 * 1024) { size = 256 * 1024; } else if (size <= 512 * 1024) { size = 512 * 1024; } else if (size <= 1024 * 1024) { size = 1024 * 1024; } else if (NRL_CHECK_SIZE(size, 4 * 1024 * 1024, max, 2 * 1024)) { start_off = ((loff_t)ac->ac_o_ex.fe_logical >> (21 - bsbits)) << 21; size = 2 * 1024 * 1024; } else if (NRL_CHECK_SIZE(size, 8 * 1024 * 1024, max, 4 * 1024)) { start_off = ((loff_t)ac->ac_o_ex.fe_logical >> (22 - bsbits)) << 22; size = 4 * 1024 * 1024; } else if (NRL_CHECK_SIZE(EXT4_C2B(sbi, ac->ac_o_ex.fe_len), (8<<20)>>bsbits, max, 8 * 1024)) { start_off = ((loff_t)ac->ac_o_ex.fe_logical >> (23 - bsbits)) << 23; size = 8 * 1024 * 1024; } else { start_off = (loff_t) ac->ac_o_ex.fe_logical << bsbits; size = (loff_t) EXT4_C2B(sbi, ac->ac_o_ex.fe_len) << bsbits; } size = size >> bsbits; start = start_off >> bsbits; /* * For tiny groups (smaller than 8MB) the chosen allocation * alignment may be larger than group size. Make sure the * alignment does not move allocation to a different group which * makes mballoc fail assertions later. */ start = max(start, rounddown(ac->ac_o_ex.fe_logical, (ext4_lblk_t)EXT4_BLOCKS_PER_GROUP(ac->ac_sb))); /* avoid unnecessary preallocation that may trigger assertions */ if (start + size > EXT_MAX_BLOCKS) size = EXT_MAX_BLOCKS - start; /* don't cover already allocated blocks in selected range */ if (ar->pleft && start <= ar->lleft) { size -= ar->lleft + 1 - start; start = ar->lleft + 1; } if (ar->pright && start + size - 1 >= ar->lright) size -= start + size - ar->lright; /* * Trim allocation request for filesystems with artificially small * groups. */ if (size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb)) size = EXT4_BLOCKS_PER_GROUP(ac->ac_sb); end = start + size; ext4_mb_pa_adjust_overlap(ac, &start, &end); size = end - start; /* * In this function "start" and "size" are normalized for better * alignment and length such that we could preallocate more blocks. * This normalization is done such that original request of * ac->ac_o_ex.fe_logical & fe_len should always lie within "start" and * "size" boundaries. * (Note fe_len can be relaxed since FS block allocation API does not * provide gurantee on number of contiguous blocks allocation since that * depends upon free space left, etc). * In case of inode pa, later we use the allocated blocks * [pa_pstart + fe_logical - pa_lstart, fe_len/size] from the preallocated * range of goal/best blocks [start, size] to put it at the * ac_o_ex.fe_logical extent of this inode. * (See ext4_mb_use_inode_pa() for more details) */ if (start + size <= ac->ac_o_ex.fe_logical || start > ac->ac_o_ex.fe_logical) { ext4_msg(ac->ac_sb, KERN_ERR, "start %lu, size %lu, fe_logical %lu", (unsigned long) start, (unsigned long) size, (unsigned long) ac->ac_o_ex.fe_logical); BUG(); } BUG_ON(size <= 0 || size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb)); /* now prepare goal request */ /* XXX: is it better to align blocks WRT to logical * placement or satisfy big request as is */ ac->ac_g_ex.fe_logical = start; ac->ac_g_ex.fe_len = EXT4_NUM_B2C(sbi, size); ac->ac_orig_goal_len = ac->ac_g_ex.fe_len; /* define goal start in order to merge */ if (ar->pright && (ar->lright == (start + size)) && ar->pright >= size && ar->pright - size >= le32_to_cpu(es->s_first_data_block)) { /* merge to the right */ ext4_get_group_no_and_offset(ac->ac_sb, ar->pright - size, &ac->ac_g_ex.fe_group, &ac->ac_g_ex.fe_start); ac->ac_flags |= EXT4_MB_HINT_TRY_GOAL; } if (ar->pleft && (ar->lleft + 1 == start) && ar->pleft + 1 < ext4_blocks_count(es)) { /* merge to the left */ ext4_get_group_no_and_offset(ac->ac_sb, ar->pleft + 1, &ac->ac_g_ex.fe_group, &ac->ac_g_ex.fe_start); ac->ac_flags |= EXT4_MB_HINT_TRY_GOAL; } mb_debug(ac->ac_sb, "goal: %lld(was %lld) blocks at %u\n", size, orig_size, start); } static void ext4_mb_collect_stats(struct ext4_allocation_context *ac) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); if (sbi->s_mb_stats && ac->ac_g_ex.fe_len >= 1) { atomic_inc(&sbi->s_bal_reqs); atomic_add(ac->ac_b_ex.fe_len, &sbi->s_bal_allocated); if (ac->ac_b_ex.fe_len >= ac->ac_o_ex.fe_len) atomic_inc(&sbi->s_bal_success); atomic_add(ac->ac_found, &sbi->s_bal_ex_scanned); for (int i=0; i<EXT4_MB_NUM_CRS; i++) { atomic_add(ac->ac_cX_found[i], &sbi->s_bal_cX_ex_scanned[i]); } atomic_add(ac->ac_groups_scanned, &sbi->s_bal_groups_scanned); if (ac->ac_g_ex.fe_start == ac->ac_b_ex.fe_start && ac->ac_g_ex.fe_group == ac->ac_b_ex.fe_group) atomic_inc(&sbi->s_bal_goals); /* did we allocate as much as normalizer originally wanted? */ if (ac->ac_f_ex.fe_len == ac->ac_orig_goal_len) atomic_inc(&sbi->s_bal_len_goals); if (ac->ac_found > sbi->s_mb_max_to_scan) atomic_inc(&sbi->s_bal_breaks); } if (ac->ac_op == EXT4_MB_HISTORY_ALLOC) trace_ext4_mballoc_alloc(ac); else trace_ext4_mballoc_prealloc(ac); } /* * Called on failure; free up any blocks from the inode PA for this * context. We don't need this for MB_GROUP_PA because we only change * pa_free in ext4_mb_release_context(), but on failure, we've already * zeroed out ac->ac_b_ex.fe_len, so group_pa->pa_free is not changed. */ static void ext4_discard_allocated_blocks(struct ext4_allocation_context *ac) { struct ext4_prealloc_space *pa = ac->ac_pa; struct ext4_buddy e4b; int err; if (pa == NULL) { if (ac->ac_f_ex.fe_len == 0) return; err = ext4_mb_load_buddy(ac->ac_sb, ac->ac_f_ex.fe_group, &e4b); if (WARN_RATELIMIT(err, "ext4: mb_load_buddy failed (%d)", err)) /* * This should never happen since we pin the * pages in the ext4_allocation_context so * ext4_mb_load_buddy() should never fail. */ return; ext4_lock_group(ac->ac_sb, ac->ac_f_ex.fe_group); mb_free_blocks(ac->ac_inode, &e4b, ac->ac_f_ex.fe_start, ac->ac_f_ex.fe_len); ext4_unlock_group(ac->ac_sb, ac->ac_f_ex.fe_group); ext4_mb_unload_buddy(&e4b); return; } if (pa->pa_type == MB_INODE_PA) { spin_lock(&pa->pa_lock); pa->pa_free += ac->ac_b_ex.fe_len; spin_unlock(&pa->pa_lock); } } /* * use blocks preallocated to inode */ static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); ext4_fsblk_t start; ext4_fsblk_t end; int len; /* found preallocated blocks, use them */ start = pa->pa_pstart + (ac->ac_o_ex.fe_logical - pa->pa_lstart); end = min(pa->pa_pstart + EXT4_C2B(sbi, pa->pa_len), start + EXT4_C2B(sbi, ac->ac_o_ex.fe_len)); len = EXT4_NUM_B2C(sbi, end - start); ext4_get_group_no_and_offset(ac->ac_sb, start, &ac->ac_b_ex.fe_group, &ac->ac_b_ex.fe_start); ac->ac_b_ex.fe_len = len; ac->ac_status = AC_STATUS_FOUND; ac->ac_pa = pa; BUG_ON(start < pa->pa_pstart); BUG_ON(end > pa->pa_pstart + EXT4_C2B(sbi, pa->pa_len)); BUG_ON(pa->pa_free < len); BUG_ON(ac->ac_b_ex.fe_len <= 0); pa->pa_free -= len; mb_debug(ac->ac_sb, "use %llu/%d from inode pa %p\n", start, len, pa); } /* * use blocks preallocated to locality group */ static void ext4_mb_use_group_pa(struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa) { unsigned int len = ac->ac_o_ex.fe_len; ext4_get_group_no_and_offset(ac->ac_sb, pa->pa_pstart, &ac->ac_b_ex.fe_group, &ac->ac_b_ex.fe_start); ac->ac_b_ex.fe_len = len; ac->ac_status = AC_STATUS_FOUND; ac->ac_pa = pa; /* we don't correct pa_pstart or pa_len here to avoid * possible race when the group is being loaded concurrently * instead we correct pa later, after blocks are marked * in on-disk bitmap -- see ext4_mb_release_context() * Other CPUs are prevented from allocating from this pa by lg_mutex */ mb_debug(ac->ac_sb, "use %u/%u from group pa %p\n", pa->pa_lstart, len, pa); } /* * Return the prealloc space that have minimal distance * from the goal block. @cpa is the prealloc * space that is having currently known minimal distance * from the goal block. */ static struct ext4_prealloc_space * ext4_mb_check_group_pa(ext4_fsblk_t goal_block, struct ext4_prealloc_space *pa, struct ext4_prealloc_space *cpa) { ext4_fsblk_t cur_distance, new_distance; if (cpa == NULL) { atomic_inc(&pa->pa_count); return pa; } cur_distance = abs(goal_block - cpa->pa_pstart); new_distance = abs(goal_block - pa->pa_pstart); if (cur_distance <= new_distance) return cpa; /* drop the previous reference */ atomic_dec(&cpa->pa_count); atomic_inc(&pa->pa_count); return pa; } /* * check if found pa meets EXT4_MB_HINT_GOAL_ONLY */ static bool ext4_mb_pa_goal_check(struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); ext4_fsblk_t start; if (likely(!(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY))) return true; /* * If EXT4_MB_HINT_GOAL_ONLY is set, ac_g_ex will not be adjusted * in ext4_mb_normalize_request and will keep same with ac_o_ex * from ext4_mb_initialize_context. Choose ac_g_ex here to keep * consistent with ext4_mb_find_by_goal. */ start = pa->pa_pstart + (ac->ac_g_ex.fe_logical - pa->pa_lstart); if (ext4_grp_offs_to_block(ac->ac_sb, &ac->ac_g_ex) != start) return false; if (ac->ac_g_ex.fe_len > pa->pa_len - EXT4_B2C(sbi, ac->ac_g_ex.fe_logical - pa->pa_lstart)) return false; return true; } /* * search goal blocks in preallocated space */ static noinline_for_stack bool ext4_mb_use_preallocated(struct ext4_allocation_context *ac) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); int order, i; struct ext4_inode_info *ei = EXT4_I(ac->ac_inode); struct ext4_locality_group *lg; struct ext4_prealloc_space *tmp_pa = NULL, *cpa = NULL; struct rb_node *iter; ext4_fsblk_t goal_block; /* only data can be preallocated */ if (!(ac->ac_flags & EXT4_MB_HINT_DATA)) return false; /* * first, try per-file preallocation by searching the inode pa rbtree. * * Here, we can't do a direct traversal of the tree because * ext4_mb_discard_group_preallocation() can paralelly mark the pa * deleted and that can cause direct traversal to skip some entries. */ read_lock(&ei->i_prealloc_lock); if (RB_EMPTY_ROOT(&ei->i_prealloc_node)) { goto try_group_pa; } /* * Step 1: Find a pa with logical start immediately adjacent to the * original logical start. This could be on the left or right. * * (tmp_pa->pa_lstart never changes so we can skip locking for it). */ for (iter = ei->i_prealloc_node.rb_node; iter; iter = ext4_mb_pa_rb_next_iter(ac->ac_o_ex.fe_logical, tmp_pa->pa_lstart, iter)) { tmp_pa = rb_entry(iter, struct ext4_prealloc_space, pa_node.inode_node); } /* * Step 2: The adjacent pa might be to the right of logical start, find * the left adjacent pa. After this step we'd have a valid tmp_pa whose * logical start is towards the left of original request's logical start */ if (tmp_pa->pa_lstart > ac->ac_o_ex.fe_logical) { struct rb_node *tmp; tmp = rb_prev(&tmp_pa->pa_node.inode_node); if (tmp) { tmp_pa = rb_entry(tmp, struct ext4_prealloc_space, pa_node.inode_node); } else { /* * If there is no adjacent pa to the left then finding * an overlapping pa is not possible hence stop searching * inode pa tree */ goto try_group_pa; } } BUG_ON(!(tmp_pa && tmp_pa->pa_lstart <= ac->ac_o_ex.fe_logical)); /* * Step 3: If the left adjacent pa is deleted, keep moving left to find * the first non deleted adjacent pa. After this step we should have a * valid tmp_pa which is guaranteed to be non deleted. */ for (iter = &tmp_pa->pa_node.inode_node;; iter = rb_prev(iter)) { if (!iter) { /* * no non deleted left adjacent pa, so stop searching * inode pa tree */ goto try_group_pa; } tmp_pa = rb_entry(iter, struct ext4_prealloc_space, pa_node.inode_node); spin_lock(&tmp_pa->pa_lock); if (tmp_pa->pa_deleted == 0) { /* * We will keep holding the pa_lock from * this point on because we don't want group discard * to delete this pa underneath us. Since group * discard is anyways an ENOSPC operation it * should be okay for it to wait a few more cycles. */ break; } else { spin_unlock(&tmp_pa->pa_lock); } } BUG_ON(!(tmp_pa && tmp_pa->pa_lstart <= ac->ac_o_ex.fe_logical)); BUG_ON(tmp_pa->pa_deleted == 1); /* * Step 4: We now have the non deleted left adjacent pa. Only this * pa can possibly satisfy the request hence check if it overlaps * original logical start and stop searching if it doesn't. */ if (ac->ac_o_ex.fe_logical >= pa_logical_end(sbi, tmp_pa)) { spin_unlock(&tmp_pa->pa_lock); goto try_group_pa; } /* non-extent files can't have physical blocks past 2^32 */ if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)) && (tmp_pa->pa_pstart + EXT4_C2B(sbi, tmp_pa->pa_len) > EXT4_MAX_BLOCK_FILE_PHYS)) { /* * Since PAs don't overlap, we won't find any other PA to * satisfy this. */ spin_unlock(&tmp_pa->pa_lock); goto try_group_pa; } if (tmp_pa->pa_free && likely(ext4_mb_pa_goal_check(ac, tmp_pa))) { atomic_inc(&tmp_pa->pa_count); ext4_mb_use_inode_pa(ac, tmp_pa); spin_unlock(&tmp_pa->pa_lock); read_unlock(&ei->i_prealloc_lock); return true; } else { /* * We found a valid overlapping pa but couldn't use it because * it had no free blocks. This should ideally never happen * because: * * 1. When a new inode pa is added to rbtree it must have * pa_free > 0 since otherwise we won't actually need * preallocation. * * 2. An inode pa that is in the rbtree can only have it's * pa_free become zero when another thread calls: * ext4_mb_new_blocks * ext4_mb_use_preallocated * ext4_mb_use_inode_pa * * 3. Further, after the above calls make pa_free == 0, we will * immediately remove it from the rbtree in: * ext4_mb_new_blocks * ext4_mb_release_context * ext4_mb_put_pa * * 4. Since the pa_free becoming 0 and pa_free getting removed * from tree both happen in ext4_mb_new_blocks, which is always * called with i_data_sem held for data allocations, we can be * sure that another process will never see a pa in rbtree with * pa_free == 0. */ WARN_ON_ONCE(tmp_pa->pa_free == 0); } spin_unlock(&tmp_pa->pa_lock); try_group_pa: read_unlock(&ei->i_prealloc_lock); /* can we use group allocation? */ if (!(ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC)) return false; /* inode may have no locality group for some reason */ lg = ac->ac_lg; if (lg == NULL) return false; order = fls(ac->ac_o_ex.fe_len) - 1; if (order > PREALLOC_TB_SIZE - 1) /* The max size of hash table is PREALLOC_TB_SIZE */ order = PREALLOC_TB_SIZE - 1; goal_block = ext4_grp_offs_to_block(ac->ac_sb, &ac->ac_g_ex); /* * search for the prealloc space that is having * minimal distance from the goal block. */ for (i = order; i < PREALLOC_TB_SIZE; i++) { rcu_read_lock(); list_for_each_entry_rcu(tmp_pa, &lg->lg_prealloc_list[i], pa_node.lg_list) { spin_lock(&tmp_pa->pa_lock); if (tmp_pa->pa_deleted == 0 && tmp_pa->pa_free >= ac->ac_o_ex.fe_len) { cpa = ext4_mb_check_group_pa(goal_block, tmp_pa, cpa); } spin_unlock(&tmp_pa->pa_lock); } rcu_read_unlock(); } if (cpa) { ext4_mb_use_group_pa(ac, cpa); return true; } return false; } /* * the function goes through all preallocation in this group and marks them * used in in-core bitmap. buddy must be generated from this bitmap * Need to be called with ext4 group lock held */ static noinline_for_stack void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, ext4_group_t group) { struct ext4_group_info *grp = ext4_get_group_info(sb, group); struct ext4_prealloc_space *pa; struct list_head *cur; ext4_group_t groupnr; ext4_grpblk_t start; int preallocated = 0; int len; if (!grp) return; /* all form of preallocation discards first load group, * so the only competing code is preallocation use. * we don't need any locking here * notice we do NOT ignore preallocations with pa_deleted * otherwise we could leave used blocks available for * allocation in buddy when concurrent ext4_mb_put_pa() * is dropping preallocation */ list_for_each(cur, &grp->bb_prealloc_list) { pa = list_entry(cur, struct ext4_prealloc_space, pa_group_list); spin_lock(&pa->pa_lock); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &groupnr, &start); len = pa->pa_len; spin_unlock(&pa->pa_lock); if (unlikely(len == 0)) continue; BUG_ON(groupnr != group); mb_set_bits(bitmap, start, len); preallocated += len; } mb_debug(sb, "preallocated %d for group %u\n", preallocated, group); } static void ext4_mb_mark_pa_deleted(struct super_block *sb, struct ext4_prealloc_space *pa) { struct ext4_inode_info *ei; if (pa->pa_deleted) { ext4_warning(sb, "deleted pa, type:%d, pblk:%llu, lblk:%u, len:%d\n", pa->pa_type, pa->pa_pstart, pa->pa_lstart, pa->pa_len); return; } pa->pa_deleted = 1; if (pa->pa_type == MB_INODE_PA) { ei = EXT4_I(pa->pa_inode); atomic_dec(&ei->i_prealloc_active); } } static inline void ext4_mb_pa_free(struct ext4_prealloc_space *pa) { BUG_ON(!pa); BUG_ON(atomic_read(&pa->pa_count)); BUG_ON(pa->pa_deleted == 0); kmem_cache_free(ext4_pspace_cachep, pa); } static void ext4_mb_pa_callback(struct rcu_head *head) { struct ext4_prealloc_space *pa; pa = container_of(head, struct ext4_prealloc_space, u.pa_rcu); ext4_mb_pa_free(pa); } /* * drops a reference to preallocated space descriptor * if this was the last reference and the space is consumed */ static void ext4_mb_put_pa(struct ext4_allocation_context *ac, struct super_block *sb, struct ext4_prealloc_space *pa) { ext4_group_t grp; ext4_fsblk_t grp_blk; struct ext4_inode_info *ei = EXT4_I(ac->ac_inode); /* in this short window concurrent discard can set pa_deleted */ spin_lock(&pa->pa_lock); if (!atomic_dec_and_test(&pa->pa_count) || pa->pa_free != 0) { spin_unlock(&pa->pa_lock); return; } if (pa->pa_deleted == 1) { spin_unlock(&pa->pa_lock); return; } ext4_mb_mark_pa_deleted(sb, pa); spin_unlock(&pa->pa_lock); grp_blk = pa->pa_pstart; /* * If doing group-based preallocation, pa_pstart may be in the * next group when pa is used up */ if (pa->pa_type == MB_GROUP_PA) grp_blk--; grp = ext4_get_group_number(sb, grp_blk); /* * possible race: * * P1 (buddy init) P2 (regular allocation) * find block B in PA * copy on-disk bitmap to buddy * mark B in on-disk bitmap * drop PA from group * mark all PAs in buddy * * thus, P1 initializes buddy with B available. to prevent this * we make "copy" and "mark all PAs" atomic and serialize "drop PA" * against that pair */ ext4_lock_group(sb, grp); list_del(&pa->pa_group_list); ext4_unlock_group(sb, grp); if (pa->pa_type == MB_INODE_PA) { write_lock(pa->pa_node_lock.inode_lock); rb_erase(&pa->pa_node.inode_node, &ei->i_prealloc_node); write_unlock(pa->pa_node_lock.inode_lock); ext4_mb_pa_free(pa); } else { spin_lock(pa->pa_node_lock.lg_lock); list_del_rcu(&pa->pa_node.lg_list); spin_unlock(pa->pa_node_lock.lg_lock); call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback); } } static void ext4_mb_pa_rb_insert(struct rb_root *root, struct rb_node *new) { struct rb_node **iter = &root->rb_node, *parent = NULL; struct ext4_prealloc_space *iter_pa, *new_pa; ext4_lblk_t iter_start, new_start; while (*iter) { iter_pa = rb_entry(*iter, struct ext4_prealloc_space, pa_node.inode_node); new_pa = rb_entry(new, struct ext4_prealloc_space, pa_node.inode_node); iter_start = iter_pa->pa_lstart; new_start = new_pa->pa_lstart; parent = *iter; if (new_start < iter_start) iter = &((*iter)->rb_left); else iter = &((*iter)->rb_right); } rb_link_node(new, parent, iter); rb_insert_color(new, root); } /* * creates new preallocated space for given inode */ static noinline_for_stack void ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_prealloc_space *pa; struct ext4_group_info *grp; struct ext4_inode_info *ei; /* preallocate only when found space is larger then requested */ BUG_ON(ac->ac_o_ex.fe_len >= ac->ac_b_ex.fe_len); BUG_ON(ac->ac_status != AC_STATUS_FOUND); BUG_ON(!S_ISREG(ac->ac_inode->i_mode)); BUG_ON(ac->ac_pa == NULL); pa = ac->ac_pa; if (ac->ac_b_ex.fe_len < ac->ac_orig_goal_len) { struct ext4_free_extent ex = { .fe_logical = ac->ac_g_ex.fe_logical, .fe_len = ac->ac_orig_goal_len, }; loff_t orig_goal_end = extent_logical_end(sbi, &ex); loff_t o_ex_end = extent_logical_end(sbi, &ac->ac_o_ex); /* * We can't allocate as much as normalizer wants, so we try * to get proper lstart to cover the original request, except * when the goal doesn't cover the original request as below: * * orig_ex:2045/2055(10), isize:8417280 -> normalized:0/2048 * best_ex:0/200(200) -> adjusted: 1848/2048(200) */ BUG_ON(ac->ac_g_ex.fe_logical > ac->ac_o_ex.fe_logical); BUG_ON(ac->ac_g_ex.fe_len < ac->ac_o_ex.fe_len); /* * Use the below logic for adjusting best extent as it keeps * fragmentation in check while ensuring logical range of best * extent doesn't overflow out of goal extent: * * 1. Check if best ex can be kept at end of goal (before * cr_best_avail trimmed it) and still cover original start * 2. Else, check if best ex can be kept at start of goal and * still cover original end * 3. Else, keep the best ex at start of original request. */ ex.fe_len = ac->ac_b_ex.fe_len; ex.fe_logical = orig_goal_end - EXT4_C2B(sbi, ex.fe_len); if (ac->ac_o_ex.fe_logical >= ex.fe_logical) goto adjust_bex; ex.fe_logical = ac->ac_g_ex.fe_logical; if (o_ex_end <= extent_logical_end(sbi, &ex)) goto adjust_bex; ex.fe_logical = ac->ac_o_ex.fe_logical; adjust_bex: ac->ac_b_ex.fe_logical = ex.fe_logical; BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical); BUG_ON(extent_logical_end(sbi, &ex) > orig_goal_end); } pa->pa_lstart = ac->ac_b_ex.fe_logical; pa->pa_pstart = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); pa->pa_len = ac->ac_b_ex.fe_len; pa->pa_free = pa->pa_len; spin_lock_init(&pa->pa_lock); INIT_LIST_HEAD(&pa->pa_group_list); pa->pa_deleted = 0; pa->pa_type = MB_INODE_PA; mb_debug(sb, "new inode pa %p: %llu/%d for %u\n", pa, pa->pa_pstart, pa->pa_len, pa->pa_lstart); trace_ext4_mb_new_inode_pa(ac, pa); atomic_add(pa->pa_free, &sbi->s_mb_preallocated); ext4_mb_use_inode_pa(ac, pa); ei = EXT4_I(ac->ac_inode); grp = ext4_get_group_info(sb, ac->ac_b_ex.fe_group); if (!grp) return; pa->pa_node_lock.inode_lock = &ei->i_prealloc_lock; pa->pa_inode = ac->ac_inode; list_add(&pa->pa_group_list, &grp->bb_prealloc_list); write_lock(pa->pa_node_lock.inode_lock); ext4_mb_pa_rb_insert(&ei->i_prealloc_node, &pa->pa_node.inode_node); write_unlock(pa->pa_node_lock.inode_lock); atomic_inc(&ei->i_prealloc_active); } /* * creates new preallocated space for locality group inodes belongs to */ static noinline_for_stack void ext4_mb_new_group_pa(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; struct ext4_locality_group *lg; struct ext4_prealloc_space *pa; struct ext4_group_info *grp; /* preallocate only when found space is larger then requested */ BUG_ON(ac->ac_o_ex.fe_len >= ac->ac_b_ex.fe_len); BUG_ON(ac->ac_status != AC_STATUS_FOUND); BUG_ON(!S_ISREG(ac->ac_inode->i_mode)); BUG_ON(ac->ac_pa == NULL); pa = ac->ac_pa; pa->pa_pstart = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); pa->pa_lstart = pa->pa_pstart; pa->pa_len = ac->ac_b_ex.fe_len; pa->pa_free = pa->pa_len; spin_lock_init(&pa->pa_lock); INIT_LIST_HEAD(&pa->pa_node.lg_list); INIT_LIST_HEAD(&pa->pa_group_list); pa->pa_deleted = 0; pa->pa_type = MB_GROUP_PA; mb_debug(sb, "new group pa %p: %llu/%d for %u\n", pa, pa->pa_pstart, pa->pa_len, pa->pa_lstart); trace_ext4_mb_new_group_pa(ac, pa); ext4_mb_use_group_pa(ac, pa); atomic_add(pa->pa_free, &EXT4_SB(sb)->s_mb_preallocated); grp = ext4_get_group_info(sb, ac->ac_b_ex.fe_group); if (!grp) return; lg = ac->ac_lg; BUG_ON(lg == NULL); pa->pa_node_lock.lg_lock = &lg->lg_prealloc_lock; pa->pa_inode = NULL; list_add(&pa->pa_group_list, &grp->bb_prealloc_list); /* * We will later add the new pa to the right bucket * after updating the pa_free in ext4_mb_release_context */ } static void ext4_mb_new_preallocation(struct ext4_allocation_context *ac) { if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC) ext4_mb_new_group_pa(ac); else ext4_mb_new_inode_pa(ac); } /* * finds all unused blocks in on-disk bitmap, frees them in * in-core bitmap and buddy. * @pa must be unlinked from inode and group lists, so that * nobody else can find/use it. * the caller MUST hold group/inode locks. * TODO: optimize the case when there are no in-core structures yet */ static noinline_for_stack void ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh, struct ext4_prealloc_space *pa) { struct super_block *sb = e4b->bd_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned int end; unsigned int next; ext4_group_t group; ext4_grpblk_t bit; unsigned long long grp_blk_start; int free = 0; BUG_ON(pa->pa_deleted == 0); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit); grp_blk_start = pa->pa_pstart - EXT4_C2B(sbi, bit); BUG_ON(group != e4b->bd_group && pa->pa_len != 0); end = bit + pa->pa_len; while (bit < end) { bit = mb_find_next_zero_bit(bitmap_bh->b_data, end, bit); if (bit >= end) break; next = mb_find_next_bit(bitmap_bh->b_data, end, bit); mb_debug(sb, "free preallocated %u/%u in group %u\n", (unsigned) ext4_group_first_block_no(sb, group) + bit, (unsigned) next - bit, (unsigned) group); free += next - bit; trace_ext4_mballoc_discard(sb, NULL, group, bit, next - bit); trace_ext4_mb_release_inode_pa(pa, (grp_blk_start + EXT4_C2B(sbi, bit)), next - bit); mb_free_blocks(pa->pa_inode, e4b, bit, next - bit); bit = next + 1; } if (free != pa->pa_free) { ext4_msg(e4b->bd_sb, KERN_CRIT, "pa %p: logic %lu, phys. %lu, len %d", pa, (unsigned long) pa->pa_lstart, (unsigned long) pa->pa_pstart, pa->pa_len); ext4_grp_locked_error(sb, group, 0, 0, "free %u, pa_free %u", free, pa->pa_free); /* * pa is already deleted so we use the value obtained * from the bitmap and continue. */ } atomic_add(free, &sbi->s_mb_discarded); } static noinline_for_stack void ext4_mb_release_group_pa(struct ext4_buddy *e4b, struct ext4_prealloc_space *pa) { struct super_block *sb = e4b->bd_sb; ext4_group_t group; ext4_grpblk_t bit; trace_ext4_mb_release_group_pa(sb, pa); BUG_ON(pa->pa_deleted == 0); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit); if (unlikely(group != e4b->bd_group && pa->pa_len != 0)) { ext4_warning(sb, "bad group: expected %u, group %u, pa_start %llu", e4b->bd_group, group, pa->pa_pstart); return; } mb_free_blocks(pa->pa_inode, e4b, bit, pa->pa_len); atomic_add(pa->pa_len, &EXT4_SB(sb)->s_mb_discarded); trace_ext4_mballoc_discard(sb, NULL, group, bit, pa->pa_len); } /* * releases all preallocations in given group * * first, we need to decide discard policy: * - when do we discard * 1) ENOSPC * - how many do we discard * 1) how many requested */ static noinline_for_stack int ext4_mb_discard_group_preallocations(struct super_block *sb, ext4_group_t group, int *busy) { struct ext4_group_info *grp = ext4_get_group_info(sb, group); struct buffer_head *bitmap_bh = NULL; struct ext4_prealloc_space *pa, *tmp; LIST_HEAD(list); struct ext4_buddy e4b; struct ext4_inode_info *ei; int err; int free = 0; if (!grp) return 0; mb_debug(sb, "discard preallocation for group %u\n", group); if (list_empty(&grp->bb_prealloc_list)) goto out_dbg; bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(bitmap_bh)) { err = PTR_ERR(bitmap_bh); ext4_error_err(sb, -err, "Error %d reading block bitmap for %u", err, group); goto out_dbg; } err = ext4_mb_load_buddy(sb, group, &e4b); if (err) { ext4_warning(sb, "Error %d loading buddy information for %u", err, group); put_bh(bitmap_bh); goto out_dbg; } ext4_lock_group(sb, group); list_for_each_entry_safe(pa, tmp, &grp->bb_prealloc_list, pa_group_list) { spin_lock(&pa->pa_lock); if (atomic_read(&pa->pa_count)) { spin_unlock(&pa->pa_lock); *busy = 1; continue; } if (pa->pa_deleted) { spin_unlock(&pa->pa_lock); continue; } /* seems this one can be freed ... */ ext4_mb_mark_pa_deleted(sb, pa); if (!free) this_cpu_inc(discard_pa_seq); /* we can trust pa_free ... */ free += pa->pa_free; spin_unlock(&pa->pa_lock); list_del(&pa->pa_group_list); list_add(&pa->u.pa_tmp_list, &list); } /* now free all selected PAs */ list_for_each_entry_safe(pa, tmp, &list, u.pa_tmp_list) { /* remove from object (inode or locality group) */ if (pa->pa_type == MB_GROUP_PA) { spin_lock(pa->pa_node_lock.lg_lock); list_del_rcu(&pa->pa_node.lg_list); spin_unlock(pa->pa_node_lock.lg_lock); } else { write_lock(pa->pa_node_lock.inode_lock); ei = EXT4_I(pa->pa_inode); rb_erase(&pa->pa_node.inode_node, &ei->i_prealloc_node); write_unlock(pa->pa_node_lock.inode_lock); } list_del(&pa->u.pa_tmp_list); if (pa->pa_type == MB_GROUP_PA) { ext4_mb_release_group_pa(&e4b, pa); call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback); } else { ext4_mb_release_inode_pa(&e4b, bitmap_bh, pa); ext4_mb_pa_free(pa); } } ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); put_bh(bitmap_bh); out_dbg: mb_debug(sb, "discarded (%d) blocks preallocated for group %u bb_free (%d)\n", free, group, grp->bb_free); return free; } /* * releases all non-used preallocated blocks for given inode * * It's important to discard preallocations under i_data_sem * We don't want another block to be served from the prealloc * space when we are discarding the inode prealloc space. * * FIXME!! Make sure it is valid at all the call sites */ void ext4_discard_preallocations(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct super_block *sb = inode->i_sb; struct buffer_head *bitmap_bh = NULL; struct ext4_prealloc_space *pa, *tmp; ext4_group_t group = 0; LIST_HEAD(list); struct ext4_buddy e4b; struct rb_node *iter; int err; if (!S_ISREG(inode->i_mode)) return; if (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY) return; mb_debug(sb, "discard preallocation for inode %lu\n", inode->i_ino); trace_ext4_discard_preallocations(inode, atomic_read(&ei->i_prealloc_active)); repeat: /* first, collect all pa's in the inode */ write_lock(&ei->i_prealloc_lock); for (iter = rb_first(&ei->i_prealloc_node); iter; iter = rb_next(iter)) { pa = rb_entry(iter, struct ext4_prealloc_space, pa_node.inode_node); BUG_ON(pa->pa_node_lock.inode_lock != &ei->i_prealloc_lock); spin_lock(&pa->pa_lock); if (atomic_read(&pa->pa_count)) { /* this shouldn't happen often - nobody should * use preallocation while we're discarding it */ spin_unlock(&pa->pa_lock); write_unlock(&ei->i_prealloc_lock); ext4_msg(sb, KERN_ERR, "uh-oh! used pa while discarding"); WARN_ON(1); schedule_timeout_uninterruptible(HZ); goto repeat; } if (pa->pa_deleted == 0) { ext4_mb_mark_pa_deleted(sb, pa); spin_unlock(&pa->pa_lock); rb_erase(&pa->pa_node.inode_node, &ei->i_prealloc_node); list_add(&pa->u.pa_tmp_list, &list); continue; } /* someone is deleting pa right now */ spin_unlock(&pa->pa_lock); write_unlock(&ei->i_prealloc_lock); /* we have to wait here because pa_deleted * doesn't mean pa is already unlinked from * the list. as we might be called from * ->clear_inode() the inode will get freed * and concurrent thread which is unlinking * pa from inode's list may access already * freed memory, bad-bad-bad */ /* XXX: if this happens too often, we can * add a flag to force wait only in case * of ->clear_inode(), but not in case of * regular truncate */ schedule_timeout_uninterruptible(HZ); goto repeat; } write_unlock(&ei->i_prealloc_lock); list_for_each_entry_safe(pa, tmp, &list, u.pa_tmp_list) { BUG_ON(pa->pa_type != MB_INODE_PA); group = ext4_get_group_number(sb, pa->pa_pstart); err = ext4_mb_load_buddy_gfp(sb, group, &e4b, GFP_NOFS|__GFP_NOFAIL); if (err) { ext4_error_err(sb, -err, "Error %d loading buddy information for %u", err, group); continue; } bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(bitmap_bh)) { err = PTR_ERR(bitmap_bh); ext4_error_err(sb, -err, "Error %d reading block bitmap for %u", err, group); ext4_mb_unload_buddy(&e4b); continue; } ext4_lock_group(sb, group); list_del(&pa->pa_group_list); ext4_mb_release_inode_pa(&e4b, bitmap_bh, pa); ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); put_bh(bitmap_bh); list_del(&pa->u.pa_tmp_list); ext4_mb_pa_free(pa); } } static int ext4_mb_pa_alloc(struct ext4_allocation_context *ac) { struct ext4_prealloc_space *pa; BUG_ON(ext4_pspace_cachep == NULL); pa = kmem_cache_zalloc(ext4_pspace_cachep, GFP_NOFS); if (!pa) return -ENOMEM; atomic_set(&pa->pa_count, 1); ac->ac_pa = pa; return 0; } static void ext4_mb_pa_put_free(struct ext4_allocation_context *ac) { struct ext4_prealloc_space *pa = ac->ac_pa; BUG_ON(!pa); ac->ac_pa = NULL; WARN_ON(!atomic_dec_and_test(&pa->pa_count)); /* * current function is only called due to an error or due to * len of found blocks < len of requested blocks hence the PA has not * been added to grp->bb_prealloc_list. So we don't need to lock it */ pa->pa_deleted = 1; ext4_mb_pa_free(pa); } #ifdef CONFIG_EXT4_DEBUG static inline void ext4_mb_show_pa(struct super_block *sb) { ext4_group_t i, ngroups; if (ext4_forced_shutdown(sb)) return; ngroups = ext4_get_groups_count(sb); mb_debug(sb, "groups: "); for (i = 0; i < ngroups; i++) { struct ext4_group_info *grp = ext4_get_group_info(sb, i); struct ext4_prealloc_space *pa; ext4_grpblk_t start; struct list_head *cur; if (!grp) continue; ext4_lock_group(sb, i); list_for_each(cur, &grp->bb_prealloc_list) { pa = list_entry(cur, struct ext4_prealloc_space, pa_group_list); spin_lock(&pa->pa_lock); ext4_get_group_no_and_offset(sb, pa->pa_pstart, NULL, &start); spin_unlock(&pa->pa_lock); mb_debug(sb, "PA:%u:%d:%d\n", i, start, pa->pa_len); } ext4_unlock_group(sb, i); mb_debug(sb, "%u: %d/%d\n", i, grp->bb_free, grp->bb_fragments); } } static void ext4_mb_show_ac(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; if (ext4_forced_shutdown(sb)) return; mb_debug(sb, "Can't allocate:" " Allocation context details:"); mb_debug(sb, "status %u flags 0x%x", ac->ac_status, ac->ac_flags); mb_debug(sb, "orig %lu/%lu/%lu@%lu, " "goal %lu/%lu/%lu@%lu, " "best %lu/%lu/%lu@%lu cr %d", (unsigned long)ac->ac_o_ex.fe_group, (unsigned long)ac->ac_o_ex.fe_start, (unsigned long)ac->ac_o_ex.fe_len, (unsigned long)ac->ac_o_ex.fe_logical, (unsigned long)ac->ac_g_ex.fe_group, (unsigned long)ac->ac_g_ex.fe_start, (unsigned long)ac->ac_g_ex.fe_len, (unsigned long)ac->ac_g_ex.fe_logical, (unsigned long)ac->ac_b_ex.fe_group, (unsigned long)ac->ac_b_ex.fe_start, (unsigned long)ac->ac_b_ex.fe_len, (unsigned long)ac->ac_b_ex.fe_logical, (int)ac->ac_criteria); mb_debug(sb, "%u found", ac->ac_found); mb_debug(sb, "used pa: %s, ", ac->ac_pa ? "yes" : "no"); if (ac->ac_pa) mb_debug(sb, "pa_type %s\n", ac->ac_pa->pa_type == MB_GROUP_PA ? "group pa" : "inode pa"); ext4_mb_show_pa(sb); } #else static inline void ext4_mb_show_pa(struct super_block *sb) { } static inline void ext4_mb_show_ac(struct ext4_allocation_context *ac) { ext4_mb_show_pa(ac->ac_sb); } #endif /* * We use locality group preallocation for small size file. The size of the * file is determined by the current size or the resulting size after * allocation which ever is larger * * One can tune this size via /sys/fs/ext4/<partition>/mb_stream_req */ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); int bsbits = ac->ac_sb->s_blocksize_bits; loff_t size, isize; bool inode_pa_eligible, group_pa_eligible; if (!(ac->ac_flags & EXT4_MB_HINT_DATA)) return; if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY)) return; group_pa_eligible = sbi->s_mb_group_prealloc > 0; inode_pa_eligible = true; size = extent_logical_end(sbi, &ac->ac_o_ex); isize = (i_size_read(ac->ac_inode) + ac->ac_sb->s_blocksize - 1) >> bsbits; /* No point in using inode preallocation for closed files */ if ((size == isize) && !ext4_fs_is_busy(sbi) && !inode_is_open_for_write(ac->ac_inode)) inode_pa_eligible = false; size = max(size, isize); /* Don't use group allocation for large files */ if (size > sbi->s_mb_stream_request) group_pa_eligible = false; if (!group_pa_eligible) { if (inode_pa_eligible) ac->ac_flags |= EXT4_MB_STREAM_ALLOC; else ac->ac_flags |= EXT4_MB_HINT_NOPREALLOC; return; } BUG_ON(ac->ac_lg != NULL); /* * locality group prealloc space are per cpu. The reason for having * per cpu locality group is to reduce the contention between block * request from multiple CPUs. */ ac->ac_lg = raw_cpu_ptr(sbi->s_locality_groups); /* we're going to use group allocation */ ac->ac_flags |= EXT4_MB_HINT_GROUP_ALLOC; /* serialize all allocations in the group */ mutex_lock(&ac->ac_lg->lg_mutex); } static noinline_for_stack void ext4_mb_initialize_context(struct ext4_allocation_context *ac, struct ext4_allocation_request *ar) { struct super_block *sb = ar->inode->i_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; ext4_group_t group; unsigned int len; ext4_fsblk_t goal; ext4_grpblk_t block; /* we can't allocate > group size */ len = ar->len; /* just a dirty hack to filter too big requests */ if (len >= EXT4_CLUSTERS_PER_GROUP(sb)) len = EXT4_CLUSTERS_PER_GROUP(sb); /* start searching from the goal */ goal = ar->goal; if (goal < le32_to_cpu(es->s_first_data_block) || goal >= ext4_blocks_count(es)) goal = le32_to_cpu(es->s_first_data_block); ext4_get_group_no_and_offset(sb, goal, &group, &block); /* set up allocation goals */ ac->ac_b_ex.fe_logical = EXT4_LBLK_CMASK(sbi, ar->logical); ac->ac_status = AC_STATUS_CONTINUE; ac->ac_sb = sb; ac->ac_inode = ar->inode; ac->ac_o_ex.fe_logical = ac->ac_b_ex.fe_logical; ac->ac_o_ex.fe_group = group; ac->ac_o_ex.fe_start = block; ac->ac_o_ex.fe_len = len; ac->ac_g_ex = ac->ac_o_ex; ac->ac_orig_goal_len = ac->ac_g_ex.fe_len; ac->ac_flags = ar->flags; /* we have to define context: we'll work with a file or * locality group. this is a policy, actually */ ext4_mb_group_or_file(ac); mb_debug(sb, "init ac: %u blocks @ %u, goal %u, flags 0x%x, 2^%d, " "left: %u/%u, right %u/%u to %swritable\n", (unsigned) ar->len, (unsigned) ar->logical, (unsigned) ar->goal, ac->ac_flags, ac->ac_2order, (unsigned) ar->lleft, (unsigned) ar->pleft, (unsigned) ar->lright, (unsigned) ar->pright, inode_is_open_for_write(ar->inode) ? "" : "non-"); } static noinline_for_stack void ext4_mb_discard_lg_preallocations(struct super_block *sb, struct ext4_locality_group *lg, int order, int total_entries) { ext4_group_t group = 0; struct ext4_buddy e4b; LIST_HEAD(discard_list); struct ext4_prealloc_space *pa, *tmp; mb_debug(sb, "discard locality group preallocation\n"); spin_lock(&lg->lg_prealloc_lock); list_for_each_entry_rcu(pa, &lg->lg_prealloc_list[order], pa_node.lg_list, lockdep_is_held(&lg->lg_prealloc_lock)) { spin_lock(&pa->pa_lock); if (atomic_read(&pa->pa_count)) { /* * This is the pa that we just used * for block allocation. So don't * free that */ spin_unlock(&pa->pa_lock); continue; } if (pa->pa_deleted) { spin_unlock(&pa->pa_lock); continue; } /* only lg prealloc space */ BUG_ON(pa->pa_type != MB_GROUP_PA); /* seems this one can be freed ... */ ext4_mb_mark_pa_deleted(sb, pa); spin_unlock(&pa->pa_lock); list_del_rcu(&pa->pa_node.lg_list); list_add(&pa->u.pa_tmp_list, &discard_list); total_entries--; if (total_entries <= 5) { /* * we want to keep only 5 entries * allowing it to grow to 8. This * mak sure we don't call discard * soon for this list. */ break; } } spin_unlock(&lg->lg_prealloc_lock); list_for_each_entry_safe(pa, tmp, &discard_list, u.pa_tmp_list) { int err; group = ext4_get_group_number(sb, pa->pa_pstart); err = ext4_mb_load_buddy_gfp(sb, group, &e4b, GFP_NOFS|__GFP_NOFAIL); if (err) { ext4_error_err(sb, -err, "Error %d loading buddy information for %u", err, group); continue; } ext4_lock_group(sb, group); list_del(&pa->pa_group_list); ext4_mb_release_group_pa(&e4b, pa); ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); list_del(&pa->u.pa_tmp_list); call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback); } } /* * We have incremented pa_count. So it cannot be freed at this * point. Also we hold lg_mutex. So no parallel allocation is * possible from this lg. That means pa_free cannot be updated. * * A parallel ext4_mb_discard_group_preallocations is possible. * which can cause the lg_prealloc_list to be updated. */ static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac) { int order, added = 0, lg_prealloc_count = 1; struct super_block *sb = ac->ac_sb; struct ext4_locality_group *lg = ac->ac_lg; struct ext4_prealloc_space *tmp_pa, *pa = ac->ac_pa; order = fls(pa->pa_free) - 1; if (order > PREALLOC_TB_SIZE - 1) /* The max size of hash table is PREALLOC_TB_SIZE */ order = PREALLOC_TB_SIZE - 1; /* Add the prealloc space to lg */ spin_lock(&lg->lg_prealloc_lock); list_for_each_entry_rcu(tmp_pa, &lg->lg_prealloc_list[order], pa_node.lg_list, lockdep_is_held(&lg->lg_prealloc_lock)) { spin_lock(&tmp_pa->pa_lock); if (tmp_pa->pa_deleted) { spin_unlock(&tmp_pa->pa_lock); continue; } if (!added && pa->pa_free < tmp_pa->pa_free) { /* Add to the tail of the previous entry */ list_add_tail_rcu(&pa->pa_node.lg_list, &tmp_pa->pa_node.lg_list); added = 1; /* * we want to count the total * number of entries in the list */ } spin_unlock(&tmp_pa->pa_lock); lg_prealloc_count++; } if (!added) list_add_tail_rcu(&pa->pa_node.lg_list, &lg->lg_prealloc_list[order]); spin_unlock(&lg->lg_prealloc_lock); /* Now trim the list to be not more than 8 elements */ if (lg_prealloc_count > 8) ext4_mb_discard_lg_preallocations(sb, lg, order, lg_prealloc_count); } /* * release all resource we used in allocation */ static void ext4_mb_release_context(struct ext4_allocation_context *ac) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_prealloc_space *pa = ac->ac_pa; if (pa) { if (pa->pa_type == MB_GROUP_PA) { /* see comment in ext4_mb_use_group_pa() */ spin_lock(&pa->pa_lock); pa->pa_pstart += EXT4_C2B(sbi, ac->ac_b_ex.fe_len); pa->pa_lstart += EXT4_C2B(sbi, ac->ac_b_ex.fe_len); pa->pa_free -= ac->ac_b_ex.fe_len; pa->pa_len -= ac->ac_b_ex.fe_len; spin_unlock(&pa->pa_lock); /* * We want to add the pa to the right bucket. * Remove it from the list and while adding * make sure the list to which we are adding * doesn't grow big. */ if (likely(pa->pa_free)) { spin_lock(pa->pa_node_lock.lg_lock); list_del_rcu(&pa->pa_node.lg_list); spin_unlock(pa->pa_node_lock.lg_lock); ext4_mb_add_n_trim(ac); } } ext4_mb_put_pa(ac, ac->ac_sb, pa); } if (ac->ac_bitmap_folio) folio_put(ac->ac_bitmap_folio); if (ac->ac_buddy_folio) folio_put(ac->ac_buddy_folio); if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC) mutex_unlock(&ac->ac_lg->lg_mutex); ext4_mb_collect_stats(ac); } static int ext4_mb_discard_preallocations(struct super_block *sb, int needed) { ext4_group_t i, ngroups = ext4_get_groups_count(sb); int ret; int freed = 0, busy = 0; int retry = 0; trace_ext4_mb_discard_preallocations(sb, needed); if (needed == 0) needed = EXT4_CLUSTERS_PER_GROUP(sb) + 1; repeat: for (i = 0; i < ngroups && needed > 0; i++) { ret = ext4_mb_discard_group_preallocations(sb, i, &busy); freed += ret; needed -= ret; cond_resched(); } if (needed > 0 && busy && ++retry < 3) { busy = 0; goto repeat; } return freed; } static bool ext4_mb_discard_preallocations_should_retry(struct super_block *sb, struct ext4_allocation_context *ac, u64 *seq) { int freed; u64 seq_retry = 0; bool ret = false; freed = ext4_mb_discard_preallocations(sb, ac->ac_o_ex.fe_len); if (freed) { ret = true; goto out_dbg; } seq_retry = ext4_get_discard_pa_seq_sum(); if (!(ac->ac_flags & EXT4_MB_STRICT_CHECK) || seq_retry != *seq) { ac->ac_flags |= EXT4_MB_STRICT_CHECK; *seq = seq_retry; ret = true; } out_dbg: mb_debug(sb, "freed %d, retry ? %s\n", freed, ret ? "yes" : "no"); return ret; } /* * Simple allocator for Ext4 fast commit replay path. It searches for blocks * linearly starting at the goal block and also excludes the blocks which * are going to be in use after fast commit replay. */ static ext4_fsblk_t ext4_mb_new_blocks_simple(struct ext4_allocation_request *ar, int *errp) { struct buffer_head *bitmap_bh; struct super_block *sb = ar->inode->i_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_group_t group, nr; ext4_grpblk_t blkoff; ext4_grpblk_t max = EXT4_CLUSTERS_PER_GROUP(sb); ext4_grpblk_t i = 0; ext4_fsblk_t goal, block; struct ext4_super_block *es = sbi->s_es; goal = ar->goal; if (goal < le32_to_cpu(es->s_first_data_block) || goal >= ext4_blocks_count(es)) goal = le32_to_cpu(es->s_first_data_block); ar->len = 0; ext4_get_group_no_and_offset(sb, goal, &group, &blkoff); for (nr = ext4_get_groups_count(sb); nr > 0; nr--) { bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(bitmap_bh)) { *errp = PTR_ERR(bitmap_bh); pr_warn("Failed to read block bitmap\n"); return 0; } while (1) { i = mb_find_next_zero_bit(bitmap_bh->b_data, max, blkoff); if (i >= max) break; if (ext4_fc_replay_check_excluded(sb, ext4_group_first_block_no(sb, group) + EXT4_C2B(sbi, i))) { blkoff = i + 1; } else break; } brelse(bitmap_bh); if (i < max) break; if (++group >= ext4_get_groups_count(sb)) group = 0; blkoff = 0; } if (i >= max) { *errp = -ENOSPC; return 0; } block = ext4_group_first_block_no(sb, group) + EXT4_C2B(sbi, i); ext4_mb_mark_bb(sb, block, 1, true); ar->len = 1; *errp = 0; return block; } /* * Main entry point into mballoc to allocate blocks * it tries to use preallocation first, then falls back * to usual allocation */ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, struct ext4_allocation_request *ar, int *errp) { struct ext4_allocation_context *ac = NULL; struct ext4_sb_info *sbi; struct super_block *sb; ext4_fsblk_t block = 0; unsigned int inquota = 0; unsigned int reserv_clstrs = 0; int retries = 0; u64 seq; might_sleep(); sb = ar->inode->i_sb; sbi = EXT4_SB(sb); trace_ext4_request_blocks(ar); if (sbi->s_mount_state & EXT4_FC_REPLAY) return ext4_mb_new_blocks_simple(ar, errp); /* Allow to use superuser reservation for quota file */ if (ext4_is_quota_file(ar->inode)) ar->flags |= EXT4_MB_USE_ROOT_BLOCKS; if ((ar->flags & EXT4_MB_DELALLOC_RESERVED) == 0) { /* Without delayed allocation we need to verify * there is enough free blocks to do block allocation * and verify allocation doesn't exceed the quota limits. */ while (ar->len && ext4_claim_free_clusters(sbi, ar->len, ar->flags)) { /* let others to free the space */ cond_resched(); ar->len = ar->len >> 1; } if (!ar->len) { ext4_mb_show_pa(sb); *errp = -ENOSPC; return 0; } reserv_clstrs = ar->len; if (ar->flags & EXT4_MB_USE_ROOT_BLOCKS) { dquot_alloc_block_nofail(ar->inode, EXT4_C2B(sbi, ar->len)); } else { while (ar->len && dquot_alloc_block(ar->inode, EXT4_C2B(sbi, ar->len))) { ar->flags |= EXT4_MB_HINT_NOPREALLOC; ar->len--; } } inquota = ar->len; if (ar->len == 0) { *errp = -EDQUOT; goto out; } } ac = kmem_cache_zalloc(ext4_ac_cachep, GFP_NOFS); if (!ac) { ar->len = 0; *errp = -ENOMEM; goto out; } ext4_mb_initialize_context(ac, ar); ac->ac_op = EXT4_MB_HISTORY_PREALLOC; seq = this_cpu_read(discard_pa_seq); if (!ext4_mb_use_preallocated(ac)) { ac->ac_op = EXT4_MB_HISTORY_ALLOC; ext4_mb_normalize_request(ac, ar); *errp = ext4_mb_pa_alloc(ac); if (*errp) goto errout; repeat: /* allocate space in core */ *errp = ext4_mb_regular_allocator(ac); /* * pa allocated above is added to grp->bb_prealloc_list only * when we were able to allocate some block i.e. when * ac->ac_status == AC_STATUS_FOUND. * And error from above mean ac->ac_status != AC_STATUS_FOUND * So we have to free this pa here itself. */ if (*errp) { ext4_mb_pa_put_free(ac); ext4_discard_allocated_blocks(ac); goto errout; } if (ac->ac_status == AC_STATUS_FOUND && ac->ac_o_ex.fe_len >= ac->ac_f_ex.fe_len) ext4_mb_pa_put_free(ac); } if (likely(ac->ac_status == AC_STATUS_FOUND)) { *errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_clstrs); if (*errp) { ext4_discard_allocated_blocks(ac); goto errout; } else { block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); ar->len = ac->ac_b_ex.fe_len; } } else { if (++retries < 3 && ext4_mb_discard_preallocations_should_retry(sb, ac, &seq)) goto repeat; /* * If block allocation fails then the pa allocated above * needs to be freed here itself. */ ext4_mb_pa_put_free(ac); *errp = -ENOSPC; } if (*errp) { errout: ac->ac_b_ex.fe_len = 0; ar->len = 0; ext4_mb_show_ac(ac); } ext4_mb_release_context(ac); kmem_cache_free(ext4_ac_cachep, ac); out: if (inquota && ar->len < inquota) dquot_free_block(ar->inode, EXT4_C2B(sbi, inquota - ar->len)); if (!ar->len) { if ((ar->flags & EXT4_MB_DELALLOC_RESERVED) == 0) /* release all the reserved blocks if non delalloc */ percpu_counter_sub(&sbi->s_dirtyclusters_counter, reserv_clstrs); } trace_ext4_allocate_blocks(ar, (unsigned long long)block); return block; } /* * We can merge two free data extents only if the physical blocks * are contiguous, AND the extents were freed by the same transaction, * AND the blocks are associated with the same group. */ static void ext4_try_merge_freed_extent(struct ext4_sb_info *sbi, struct ext4_free_data *entry, struct ext4_free_data *new_entry, struct rb_root *entry_rb_root) { if ((entry->efd_tid != new_entry->efd_tid) || (entry->efd_group != new_entry->efd_group)) return; if (entry->efd_start_cluster + entry->efd_count == new_entry->efd_start_cluster) { new_entry->efd_start_cluster = entry->efd_start_cluster; new_entry->efd_count += entry->efd_count; } else if (new_entry->efd_start_cluster + new_entry->efd_count == entry->efd_start_cluster) { new_entry->efd_count += entry->efd_count; } else return; spin_lock(&sbi->s_md_lock); list_del(&entry->efd_list); spin_unlock(&sbi->s_md_lock); rb_erase(&entry->efd_node, entry_rb_root); kmem_cache_free(ext4_free_data_cachep, entry); } static noinline_for_stack void ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b, struct ext4_free_data *new_entry) { ext4_group_t group = e4b->bd_group; ext4_grpblk_t cluster; ext4_grpblk_t clusters = new_entry->efd_count; struct ext4_free_data *entry; struct ext4_group_info *db = e4b->bd_info; struct super_block *sb = e4b->bd_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); struct rb_node **n = &db->bb_free_root.rb_node, *node; struct rb_node *parent = NULL, *new_node; BUG_ON(!ext4_handle_valid(handle)); BUG_ON(e4b->bd_bitmap_folio == NULL); BUG_ON(e4b->bd_buddy_folio == NULL); new_node = &new_entry->efd_node; cluster = new_entry->efd_start_cluster; if (!*n) { /* first free block exent. We need to protect buddy cache from being freed, * otherwise we'll refresh it from * on-disk bitmap and lose not-yet-available * blocks */ folio_get(e4b->bd_buddy_folio); folio_get(e4b->bd_bitmap_folio); } while (*n) { parent = *n; entry = rb_entry(parent, struct ext4_free_data, efd_node); if (cluster < entry->efd_start_cluster) n = &(*n)->rb_left; else if (cluster >= (entry->efd_start_cluster + entry->efd_count)) n = &(*n)->rb_right; else { ext4_grp_locked_error(sb, group, 0, ext4_group_first_block_no(sb, group) + EXT4_C2B(sbi, cluster), "Block already on to-be-freed list"); kmem_cache_free(ext4_free_data_cachep, new_entry); return; } } rb_link_node(new_node, parent, n); rb_insert_color(new_node, &db->bb_free_root); /* Now try to see the extent can be merged to left and right */ node = rb_prev(new_node); if (node) { entry = rb_entry(node, struct ext4_free_data, efd_node); ext4_try_merge_freed_extent(sbi, entry, new_entry, &(db->bb_free_root)); } node = rb_next(new_node); if (node) { entry = rb_entry(node, struct ext4_free_data, efd_node); ext4_try_merge_freed_extent(sbi, entry, new_entry, &(db->bb_free_root)); } spin_lock(&sbi->s_md_lock); list_add_tail(&new_entry->efd_list, &sbi->s_freed_data_list[new_entry->efd_tid & 1]); sbi->s_mb_free_pending += clusters; spin_unlock(&sbi->s_md_lock); } static void ext4_free_blocks_simple(struct inode *inode, ext4_fsblk_t block, unsigned long count) { struct super_block *sb = inode->i_sb; ext4_group_t group; ext4_grpblk_t blkoff; ext4_get_group_no_and_offset(sb, block, &group, &blkoff); ext4_mb_mark_context(NULL, sb, false, group, blkoff, count, EXT4_MB_BITMAP_MARKED_CHECK | EXT4_MB_SYNC_UPDATE, NULL); } /** * ext4_mb_clear_bb() -- helper function for freeing blocks. * Used by ext4_free_blocks() * @handle: handle for this transaction * @inode: inode * @block: starting physical block to be freed * @count: number of blocks to be freed * @flags: flags used by ext4_free_blocks */ static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode, ext4_fsblk_t block, unsigned long count, int flags) { struct super_block *sb = inode->i_sb; struct ext4_group_info *grp; unsigned int overflow; ext4_grpblk_t bit; ext4_group_t block_group; struct ext4_sb_info *sbi; struct ext4_buddy e4b; unsigned int count_clusters; int err = 0; int mark_flags = 0; ext4_grpblk_t changed; sbi = EXT4_SB(sb); if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && !ext4_inode_block_valid(inode, block, count)) { ext4_error(sb, "Freeing blocks in system zone - " "Block = %llu, count = %lu", block, count); /* err = 0. ext4_std_error should be a no op */ goto error_out; } flags |= EXT4_FREE_BLOCKS_VALIDATED; do_more: overflow = 0; ext4_get_group_no_and_offset(sb, block, &block_group, &bit); grp = ext4_get_group_info(sb, block_group); if (unlikely(!grp || EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) return; /* * Check to see if we are freeing blocks across a group * boundary. */ if (EXT4_C2B(sbi, bit) + count > EXT4_BLOCKS_PER_GROUP(sb)) { overflow = EXT4_C2B(sbi, bit) + count - EXT4_BLOCKS_PER_GROUP(sb); count -= overflow; /* The range changed so it's no longer validated */ flags &= ~EXT4_FREE_BLOCKS_VALIDATED; } count_clusters = EXT4_NUM_B2C(sbi, count); trace_ext4_mballoc_free(sb, inode, block_group, bit, count_clusters); /* __GFP_NOFAIL: retry infinitely, ignore TIF_MEMDIE and memcg limit. */ err = ext4_mb_load_buddy_gfp(sb, block_group, &e4b, GFP_NOFS|__GFP_NOFAIL); if (err) goto error_out; if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && !ext4_inode_block_valid(inode, block, count)) { ext4_error(sb, "Freeing blocks in system zone - " "Block = %llu, count = %lu", block, count); /* err = 0. ext4_std_error should be a no op */ goto error_clean; } #ifdef AGGRESSIVE_CHECK mark_flags |= EXT4_MB_BITMAP_MARKED_CHECK; #endif err = ext4_mb_mark_context(handle, sb, false, block_group, bit, count_clusters, mark_flags, &changed); if (err && changed == 0) goto error_clean; #ifdef AGGRESSIVE_CHECK BUG_ON(changed != count_clusters); #endif /* * We need to make sure we don't reuse the freed block until after the * transaction is committed. We make an exception if the inode is to be * written in writeback mode since writeback mode has weak data * consistency guarantees. */ if (ext4_handle_valid(handle) && ((flags & EXT4_FREE_BLOCKS_METADATA) || !ext4_should_writeback_data(inode))) { struct ext4_free_data *new_entry; /* * We use __GFP_NOFAIL because ext4_free_blocks() is not allowed * to fail. */ new_entry = kmem_cache_alloc(ext4_free_data_cachep, GFP_NOFS|__GFP_NOFAIL); new_entry->efd_start_cluster = bit; new_entry->efd_group = block_group; new_entry->efd_count = count_clusters; new_entry->efd_tid = handle->h_transaction->t_tid; ext4_lock_group(sb, block_group); ext4_mb_free_metadata(handle, &e4b, new_entry); } else { if (test_opt(sb, DISCARD)) { err = ext4_issue_discard(sb, block_group, bit, count_clusters); /* * Ignore EOPNOTSUPP error. This is consistent with * what happens when using journal. */ if (err == -EOPNOTSUPP) err = 0; if (err) ext4_msg(sb, KERN_WARNING, "discard request in" " group:%u block:%d count:%lu failed" " with %d", block_group, bit, count, err); } else EXT4_MB_GRP_CLEAR_TRIMMED(e4b.bd_info); ext4_lock_group(sb, block_group); mb_free_blocks(inode, &e4b, bit, count_clusters); } ext4_unlock_group(sb, block_group); /* * on a bigalloc file system, defer the s_freeclusters_counter * update to the caller (ext4_remove_space and friends) so they * can determine if a cluster freed here should be rereserved */ if (!(flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER)) { if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE)) dquot_free_block(inode, EXT4_C2B(sbi, count_clusters)); percpu_counter_add(&sbi->s_freeclusters_counter, count_clusters); } if (overflow && !err) { block += count; count = overflow; ext4_mb_unload_buddy(&e4b); /* The range changed so it's no longer validated */ flags &= ~EXT4_FREE_BLOCKS_VALIDATED; goto do_more; } error_clean: ext4_mb_unload_buddy(&e4b); error_out: ext4_std_error(sb, err); } /** * ext4_free_blocks() -- Free given blocks and update quota * @handle: handle for this transaction * @inode: inode * @bh: optional buffer of the block to be freed * @block: starting physical block to be freed * @count: number of blocks to be freed * @flags: flags used by ext4_free_blocks */ void ext4_free_blocks(handle_t *handle, struct inode *inode, struct buffer_head *bh, ext4_fsblk_t block, unsigned long count, int flags) { struct super_block *sb = inode->i_sb; unsigned int overflow; struct ext4_sb_info *sbi; sbi = EXT4_SB(sb); if (bh) { if (block) BUG_ON(block != bh->b_blocknr); else block = bh->b_blocknr; } if (sbi->s_mount_state & EXT4_FC_REPLAY) { ext4_free_blocks_simple(inode, block, EXT4_NUM_B2C(sbi, count)); return; } might_sleep(); if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && !ext4_inode_block_valid(inode, block, count)) { ext4_error(sb, "Freeing blocks not in datazone - " "block = %llu, count = %lu", block, count); return; } flags |= EXT4_FREE_BLOCKS_VALIDATED; ext4_debug("freeing block %llu\n", block); trace_ext4_free_blocks(inode, block, count, flags); if (bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { BUG_ON(count > 1); ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA, inode, bh, block); } /* * If the extent to be freed does not begin on a cluster * boundary, we need to deal with partial clusters at the * beginning and end of the extent. Normally we will free * blocks at the beginning or the end unless we are explicitly * requested to avoid doing so. */ overflow = EXT4_PBLK_COFF(sbi, block); if (overflow) { if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) { overflow = sbi->s_cluster_ratio - overflow; block += overflow; if (count > overflow) count -= overflow; else return; } else { block -= overflow; count += overflow; } /* The range changed so it's no longer validated */ flags &= ~EXT4_FREE_BLOCKS_VALIDATED; } overflow = EXT4_LBLK_COFF(sbi, count); if (overflow) { if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) { if (count > overflow) count -= overflow; else return; } else count += sbi->s_cluster_ratio - overflow; /* The range changed so it's no longer validated */ flags &= ~EXT4_FREE_BLOCKS_VALIDATED; } if (!bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { int i; int is_metadata = flags & EXT4_FREE_BLOCKS_METADATA; for (i = 0; i < count; i++) { cond_resched(); if (is_metadata) bh = sb_find_get_block(inode->i_sb, block + i); ext4_forget(handle, is_metadata, inode, bh, block + i); } } ext4_mb_clear_bb(handle, inode, block, count, flags); } /** * ext4_group_add_blocks() -- Add given blocks to an existing group * @handle: handle to this transaction * @sb: super block * @block: start physical block to add to the block group * @count: number of blocks to free * * This marks the blocks as free in the bitmap and buddy. */ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, ext4_fsblk_t block, unsigned long count) { ext4_group_t block_group; ext4_grpblk_t bit; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_buddy e4b; int err = 0; ext4_fsblk_t first_cluster = EXT4_B2C(sbi, block); ext4_fsblk_t last_cluster = EXT4_B2C(sbi, block + count - 1); unsigned long cluster_count = last_cluster - first_cluster + 1; ext4_grpblk_t changed; ext4_debug("Adding block(s) %llu-%llu\n", block, block + count - 1); if (cluster_count == 0) return 0; ext4_get_group_no_and_offset(sb, block, &block_group, &bit); /* * Check to see if we are freeing blocks across a group * boundary. */ if (bit + cluster_count > EXT4_CLUSTERS_PER_GROUP(sb)) { ext4_warning(sb, "too many blocks added to group %u", block_group); err = -EINVAL; goto error_out; } err = ext4_mb_load_buddy(sb, block_group, &e4b); if (err) goto error_out; if (!ext4_sb_block_valid(sb, NULL, block, count)) { ext4_error(sb, "Adding blocks in system zones - " "Block = %llu, count = %lu", block, count); err = -EINVAL; goto error_clean; } err = ext4_mb_mark_context(handle, sb, false, block_group, bit, cluster_count, EXT4_MB_BITMAP_MARKED_CHECK, &changed); if (err && changed == 0) goto error_clean; if (changed != cluster_count) ext4_error(sb, "bit already cleared in group %u", block_group); ext4_lock_group(sb, block_group); mb_free_blocks(NULL, &e4b, bit, cluster_count); ext4_unlock_group(sb, block_group); percpu_counter_add(&sbi->s_freeclusters_counter, changed); error_clean: ext4_mb_unload_buddy(&e4b); error_out: ext4_std_error(sb, err); return err; } /** * ext4_trim_extent -- function to TRIM one single free extent in the group * @sb: super block for the file system * @start: starting block of the free extent in the alloc. group * @count: number of blocks to TRIM * @e4b: ext4 buddy for the group * * Trim "count" blocks starting at "start" in the "group". To assure that no * one will allocate those blocks, mark it as used in buddy bitmap. This must * be called with under the group lock. */ static int ext4_trim_extent(struct super_block *sb, int start, int count, struct ext4_buddy *e4b) __releases(bitlock) __acquires(bitlock) { struct ext4_free_extent ex; ext4_group_t group = e4b->bd_group; int ret = 0; trace_ext4_trim_extent(sb, group, start, count); assert_spin_locked(ext4_group_lock_ptr(sb, group)); ex.fe_start = start; ex.fe_group = group; ex.fe_len = count; /* * Mark blocks used, so no one can reuse them while * being trimmed. */ mb_mark_used(e4b, &ex); ext4_unlock_group(sb, group); ret = ext4_issue_discard(sb, group, start, count); ext4_lock_group(sb, group); mb_free_blocks(NULL, e4b, start, ex.fe_len); return ret; } static ext4_grpblk_t ext4_last_grp_cluster(struct super_block *sb, ext4_group_t grp) { unsigned long nr_clusters_in_group; if (grp < (ext4_get_groups_count(sb) - 1)) nr_clusters_in_group = EXT4_CLUSTERS_PER_GROUP(sb); else nr_clusters_in_group = (ext4_blocks_count(EXT4_SB(sb)->s_es) - ext4_group_first_block_no(sb, grp)) >> EXT4_CLUSTER_BITS(sb); return nr_clusters_in_group - 1; } static bool ext4_trim_interrupted(void) { return fatal_signal_pending(current) || freezing(current); } static int ext4_try_to_trim_range(struct super_block *sb, struct ext4_buddy *e4b, ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks) __acquires(ext4_group_lock_ptr(sb, e4b->bd_group)) __releases(ext4_group_lock_ptr(sb, e4b->bd_group)) { ext4_grpblk_t next, count, free_count, last, origin_start; bool set_trimmed = false; void *bitmap; if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) return 0; last = ext4_last_grp_cluster(sb, e4b->bd_group); bitmap = e4b->bd_bitmap; if (start == 0 && max >= last) set_trimmed = true; origin_start = start; start = max(e4b->bd_info->bb_first_free, start); count = 0; free_count = 0; while (start <= max) { start = mb_find_next_zero_bit(bitmap, max + 1, start); if (start > max) break; next = mb_find_next_bit(bitmap, last + 1, start); if (origin_start == 0 && next >= last) set_trimmed = true; if ((next - start) >= minblocks) { int ret = ext4_trim_extent(sb, start, next - start, e4b); if (ret && ret != -EOPNOTSUPP) return count; count += next - start; } free_count += next - start; start = next + 1; if (ext4_trim_interrupted()) return count; if (need_resched()) { ext4_unlock_group(sb, e4b->bd_group); cond_resched(); ext4_lock_group(sb, e4b->bd_group); } if ((e4b->bd_info->bb_free - free_count) < minblocks) break; } if (set_trimmed) EXT4_MB_GRP_SET_TRIMMED(e4b->bd_info); return count; } /** * ext4_trim_all_free -- function to trim all free space in alloc. group * @sb: super block for file system * @group: group to be trimmed * @start: first group block to examine * @max: last group block to examine * @minblocks: minimum extent block count * * ext4_trim_all_free walks through group's block bitmap searching for free * extents. When the free extent is found, mark it as used in group buddy * bitmap. Then issue a TRIM command on this extent and free the extent in * the group buddy bitmap. */ static ext4_grpblk_t ext4_trim_all_free(struct super_block *sb, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks) { struct ext4_buddy e4b; int ret; trace_ext4_trim_all_free(sb, group, start, max); ret = ext4_mb_load_buddy(sb, group, &e4b); if (ret) { ext4_warning(sb, "Error %d loading buddy information for %u", ret, group); return ret; } ext4_lock_group(sb, group); if (!EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) || minblocks < EXT4_SB(sb)->s_last_trim_minblks) ret = ext4_try_to_trim_range(sb, &e4b, start, max, minblocks); else ret = 0; ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); ext4_debug("trimmed %d blocks in the group %d\n", ret, group); return ret; } /** * ext4_trim_fs() -- trim ioctl handle function * @sb: superblock for filesystem * @range: fstrim_range structure * * start: First Byte to trim * len: number of Bytes to trim from start * minlen: minimum extent length in Bytes * ext4_trim_fs goes through all allocation groups containing Bytes from * start to start+len. For each such a group ext4_trim_all_free function * is invoked to trim all free space. */ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) { unsigned int discard_granularity = bdev_discard_granularity(sb->s_bdev); struct ext4_group_info *grp; ext4_group_t group, first_group, last_group; ext4_grpblk_t cnt = 0, first_cluster, last_cluster; uint64_t start, end, minlen, trimmed = 0; ext4_fsblk_t first_data_blk = le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block); ext4_fsblk_t max_blks = ext4_blocks_count(EXT4_SB(sb)->s_es); int ret = 0; start = range->start >> sb->s_blocksize_bits; end = start + (range->len >> sb->s_blocksize_bits) - 1; minlen = EXT4_NUM_B2C(EXT4_SB(sb), range->minlen >> sb->s_blocksize_bits); if (minlen > EXT4_CLUSTERS_PER_GROUP(sb) || start >= max_blks || range->len < sb->s_blocksize) return -EINVAL; /* No point to try to trim less than discard granularity */ if (range->minlen < discard_granularity) { minlen = EXT4_NUM_B2C(EXT4_SB(sb), discard_granularity >> sb->s_blocksize_bits); if (minlen > EXT4_CLUSTERS_PER_GROUP(sb)) goto out; } if (end >= max_blks - 1) end = max_blks - 1; if (end <= first_data_blk) goto out; if (start < first_data_blk) start = first_data_blk; /* Determine first and last group to examine based on start and end */ ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) start, &first_group, &first_cluster); ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) end, &last_group, &last_cluster); /* end now represents the last cluster to discard in this group */ end = EXT4_CLUSTERS_PER_GROUP(sb) - 1; for (group = first_group; group <= last_group; group++) { if (ext4_trim_interrupted()) break; grp = ext4_get_group_info(sb, group); if (!grp) continue; /* We only do this if the grp has never been initialized */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { ret = ext4_mb_init_group(sb, group, GFP_NOFS); if (ret) break; } /* * For all the groups except the last one, last cluster will * always be EXT4_CLUSTERS_PER_GROUP(sb)-1, so we only need to * change it for the last group, note that last_cluster is * already computed earlier by ext4_get_group_no_and_offset() */ if (group == last_group) end = last_cluster; if (grp->bb_free >= minlen) { cnt = ext4_trim_all_free(sb, group, first_cluster, end, minlen); if (cnt < 0) { ret = cnt; break; } trimmed += cnt; } /* * For every group except the first one, we are sure * that the first cluster to discard will be cluster #0. */ first_cluster = 0; } if (!ret) EXT4_SB(sb)->s_last_trim_minblks = minlen; out: range->len = EXT4_C2B(EXT4_SB(sb), trimmed) << sb->s_blocksize_bits; return ret; } /* Iterate all the free extents in the group. */ int ext4_mballoc_query_range( struct super_block *sb, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t end, ext4_mballoc_query_range_fn formatter, void *priv) { void *bitmap; ext4_grpblk_t next; struct ext4_buddy e4b; int error; error = ext4_mb_load_buddy(sb, group, &e4b); if (error) return error; bitmap = e4b.bd_bitmap; ext4_lock_group(sb, group); start = max(e4b.bd_info->bb_first_free, start); if (end >= EXT4_CLUSTERS_PER_GROUP(sb)) end = EXT4_CLUSTERS_PER_GROUP(sb) - 1; while (start <= end) { start = mb_find_next_zero_bit(bitmap, end + 1, start); if (start > end) break; next = mb_find_next_bit(bitmap, end + 1, start); ext4_unlock_group(sb, group); error = formatter(sb, group, start, next - start, priv); if (error) goto out_unload; ext4_lock_group(sb, group); start = next + 1; } ext4_unlock_group(sb, group); out_unload: ext4_mb_unload_buddy(&e4b); return error; } #ifdef CONFIG_EXT4_KUNIT_TESTS #include "mballoc-test.c" #endif |
| 1 2 1 29 29 1 9 20 47 45 3 4 1 11 1 4 1 8 16 4 1 3 1 4 3 1 1 1 9 2 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 * Phillip Lougher <phillip@squashfs.org.uk> * * inode.c */ /* * This file implements code to create and read inodes from disk. * * Inodes in Squashfs are identified by a 48-bit inode which encodes the * location of the compressed metadata block containing the inode, and the byte * offset into that block where the inode is placed (<block, offset>). * * To maximise compression there are different inodes for each file type * (regular file, directory, device, etc.), the inode contents and length * varying with the type. * * To further maximise compression, two types of regular file inode and * directory inode are defined: inodes optimised for frequently occurring * regular files and directories, and extended types where extra * information has to be stored. */ #include <linux/fs.h> #include <linux/vfs.h> #include <linux/xattr.h> #include <linux/pagemap.h> #include "squashfs_fs.h" #include "squashfs_fs_sb.h" #include "squashfs_fs_i.h" #include "squashfs.h" #include "xattr.h" /* * Initialise VFS inode with the base inode information common to all * Squashfs inode types. Sqsh_ino contains the unswapped base inode * off disk. */ static int squashfs_new_inode(struct super_block *sb, struct inode *inode, struct squashfs_base_inode *sqsh_ino) { uid_t i_uid; gid_t i_gid; int err; inode->i_ino = le32_to_cpu(sqsh_ino->inode_number); if (inode->i_ino == 0) return -EINVAL; err = squashfs_get_id(sb, le16_to_cpu(sqsh_ino->uid), &i_uid); if (err) return err; err = squashfs_get_id(sb, le16_to_cpu(sqsh_ino->guid), &i_gid); if (err) return err; i_uid_write(inode, i_uid); i_gid_write(inode, i_gid); inode_set_mtime(inode, le32_to_cpu(sqsh_ino->mtime), 0); inode_set_atime(inode, inode_get_mtime_sec(inode), 0); inode_set_ctime(inode, inode_get_mtime_sec(inode), 0); inode->i_mode = le16_to_cpu(sqsh_ino->mode); inode->i_size = 0; return err; } struct inode *squashfs_iget(struct super_block *sb, long long ino, unsigned int ino_number) { struct inode *inode = iget_locked(sb, ino_number); int err; TRACE("Entered squashfs_iget\n"); if (!inode) return ERR_PTR(-ENOMEM); if (!(inode->i_state & I_NEW)) return inode; err = squashfs_read_inode(inode, ino); if (err) { iget_failed(inode); return ERR_PTR(err); } unlock_new_inode(inode); return inode; } /* * Initialise VFS inode by reading inode from inode table (compressed * metadata). The format and amount of data read depends on type. */ int squashfs_read_inode(struct inode *inode, long long ino) { struct super_block *sb = inode->i_sb; struct squashfs_sb_info *msblk = sb->s_fs_info; u64 block = SQUASHFS_INODE_BLK(ino) + msblk->inode_table; int err, type, offset = SQUASHFS_INODE_OFFSET(ino); union squashfs_inode squashfs_ino; struct squashfs_base_inode *sqshb_ino = &squashfs_ino.base; int xattr_id = SQUASHFS_INVALID_XATTR; TRACE("Entered squashfs_read_inode\n"); /* * Read inode base common to all inode types. */ err = squashfs_read_metadata(sb, sqshb_ino, &block, &offset, sizeof(*sqshb_ino)); if (err < 0) goto failed_read; err = squashfs_new_inode(sb, inode, sqshb_ino); if (err) goto failed_read; block = SQUASHFS_INODE_BLK(ino) + msblk->inode_table; offset = SQUASHFS_INODE_OFFSET(ino); type = le16_to_cpu(sqshb_ino->inode_type); switch (type) { case SQUASHFS_REG_TYPE: { unsigned int frag_offset, frag; int frag_size; u64 frag_blk; struct squashfs_reg_inode *sqsh_ino = &squashfs_ino.reg; err = squashfs_read_metadata(sb, sqsh_ino, &block, &offset, sizeof(*sqsh_ino)); if (err < 0) goto failed_read; frag = le32_to_cpu(sqsh_ino->fragment); if (frag != SQUASHFS_INVALID_FRAG) { frag_offset = le32_to_cpu(sqsh_ino->offset); frag_size = squashfs_frag_lookup(sb, frag, &frag_blk); if (frag_size < 0) { err = frag_size; goto failed_read; } } else { frag_blk = SQUASHFS_INVALID_BLK; frag_size = 0; frag_offset = 0; } set_nlink(inode, 1); inode->i_size = le32_to_cpu(sqsh_ino->file_size); inode->i_fop = &generic_ro_fops; inode->i_mode |= S_IFREG; inode->i_blocks = ((inode->i_size - 1) >> 9) + 1; squashfs_i(inode)->fragment_block = frag_blk; squashfs_i(inode)->fragment_size = frag_size; squashfs_i(inode)->fragment_offset = frag_offset; squashfs_i(inode)->start = le32_to_cpu(sqsh_ino->start_block); squashfs_i(inode)->block_list_start = block; squashfs_i(inode)->offset = offset; inode->i_data.a_ops = &squashfs_aops; TRACE("File inode %x:%x, start_block %llx, block_list_start " "%llx, offset %x\n", SQUASHFS_INODE_BLK(ino), offset, squashfs_i(inode)->start, block, offset); break; } case SQUASHFS_LREG_TYPE: { unsigned int frag_offset, frag; int frag_size; u64 frag_blk; struct squashfs_lreg_inode *sqsh_ino = &squashfs_ino.lreg; err = squashfs_read_metadata(sb, sqsh_ino, &block, &offset, sizeof(*sqsh_ino)); if (err < 0) goto failed_read; frag = le32_to_cpu(sqsh_ino->fragment); if (frag != SQUASHFS_INVALID_FRAG) { frag_offset = le32_to_cpu(sqsh_ino->offset); frag_size = squashfs_frag_lookup(sb, frag, &frag_blk); if (frag_size < 0) { err = frag_size; goto failed_read; } } else { frag_blk = SQUASHFS_INVALID_BLK; frag_size = 0; frag_offset = 0; } xattr_id = le32_to_cpu(sqsh_ino->xattr); set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); inode->i_size = le64_to_cpu(sqsh_ino->file_size); inode->i_op = &squashfs_inode_ops; inode->i_fop = &generic_ro_fops; inode->i_mode |= S_IFREG; inode->i_blocks = (inode->i_size - le64_to_cpu(sqsh_ino->sparse) + 511) >> 9; squashfs_i(inode)->fragment_block = frag_blk; squashfs_i(inode)->fragment_size = frag_size; squashfs_i(inode)->fragment_offset = frag_offset; squashfs_i(inode)->start = le64_to_cpu(sqsh_ino->start_block); squashfs_i(inode)->block_list_start = block; squashfs_i(inode)->offset = offset; inode->i_data.a_ops = &squashfs_aops; TRACE("File inode %x:%x, start_block %llx, block_list_start " "%llx, offset %x\n", SQUASHFS_INODE_BLK(ino), offset, squashfs_i(inode)->start, block, offset); break; } case SQUASHFS_DIR_TYPE: { struct squashfs_dir_inode *sqsh_ino = &squashfs_ino.dir; err = squashfs_read_metadata(sb, sqsh_ino, &block, &offset, sizeof(*sqsh_ino)); if (err < 0) goto failed_read; set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); inode->i_size = le16_to_cpu(sqsh_ino->file_size); inode->i_op = &squashfs_dir_inode_ops; inode->i_fop = &squashfs_dir_ops; inode->i_mode |= S_IFDIR; squashfs_i(inode)->start = le32_to_cpu(sqsh_ino->start_block); squashfs_i(inode)->offset = le16_to_cpu(sqsh_ino->offset); squashfs_i(inode)->dir_idx_cnt = 0; squashfs_i(inode)->parent = le32_to_cpu(sqsh_ino->parent_inode); TRACE("Directory inode %x:%x, start_block %llx, offset %x\n", SQUASHFS_INODE_BLK(ino), offset, squashfs_i(inode)->start, le16_to_cpu(sqsh_ino->offset)); break; } case SQUASHFS_LDIR_TYPE: { struct squashfs_ldir_inode *sqsh_ino = &squashfs_ino.ldir; err = squashfs_read_metadata(sb, sqsh_ino, &block, &offset, sizeof(*sqsh_ino)); if (err < 0) goto failed_read; xattr_id = le32_to_cpu(sqsh_ino->xattr); set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); inode->i_size = le32_to_cpu(sqsh_ino->file_size); inode->i_op = &squashfs_dir_inode_ops; inode->i_fop = &squashfs_dir_ops; inode->i_mode |= S_IFDIR; squashfs_i(inode)->start = le32_to_cpu(sqsh_ino->start_block); squashfs_i(inode)->offset = le16_to_cpu(sqsh_ino->offset); squashfs_i(inode)->dir_idx_start = block; squashfs_i(inode)->dir_idx_offset = offset; squashfs_i(inode)->dir_idx_cnt = le16_to_cpu(sqsh_ino->i_count); squashfs_i(inode)->parent = le32_to_cpu(sqsh_ino->parent_inode); TRACE("Long directory inode %x:%x, start_block %llx, offset " "%x\n", SQUASHFS_INODE_BLK(ino), offset, squashfs_i(inode)->start, le16_to_cpu(sqsh_ino->offset)); break; } case SQUASHFS_SYMLINK_TYPE: case SQUASHFS_LSYMLINK_TYPE: { struct squashfs_symlink_inode *sqsh_ino = &squashfs_ino.symlink; err = squashfs_read_metadata(sb, sqsh_ino, &block, &offset, sizeof(*sqsh_ino)); if (err < 0) goto failed_read; inode->i_size = le32_to_cpu(sqsh_ino->symlink_size); if (inode->i_size > PAGE_SIZE) { ERROR("Corrupted symlink\n"); return -EINVAL; } set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); inode->i_op = &squashfs_symlink_inode_ops; inode_nohighmem(inode); inode->i_data.a_ops = &squashfs_symlink_aops; inode->i_mode |= S_IFLNK; squashfs_i(inode)->start = block; squashfs_i(inode)->offset = offset; if (type == SQUASHFS_LSYMLINK_TYPE) { __le32 xattr; err = squashfs_read_metadata(sb, NULL, &block, &offset, inode->i_size); if (err < 0) goto failed_read; err = squashfs_read_metadata(sb, &xattr, &block, &offset, sizeof(xattr)); if (err < 0) goto failed_read; xattr_id = le32_to_cpu(xattr); } TRACE("Symbolic link inode %x:%x, start_block %llx, offset " "%x\n", SQUASHFS_INODE_BLK(ino), offset, block, offset); break; } case SQUASHFS_BLKDEV_TYPE: case SQUASHFS_CHRDEV_TYPE: { struct squashfs_dev_inode *sqsh_ino = &squashfs_ino.dev; unsigned int rdev; err = squashfs_read_metadata(sb, sqsh_ino, &block, &offset, sizeof(*sqsh_ino)); if (err < 0) goto failed_read; if (type == SQUASHFS_CHRDEV_TYPE) inode->i_mode |= S_IFCHR; else inode->i_mode |= S_IFBLK; set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); rdev = le32_to_cpu(sqsh_ino->rdev); init_special_inode(inode, inode->i_mode, new_decode_dev(rdev)); TRACE("Device inode %x:%x, rdev %x\n", SQUASHFS_INODE_BLK(ino), offset, rdev); break; } case SQUASHFS_LBLKDEV_TYPE: case SQUASHFS_LCHRDEV_TYPE: { struct squashfs_ldev_inode *sqsh_ino = &squashfs_ino.ldev; unsigned int rdev; err = squashfs_read_metadata(sb, sqsh_ino, &block, &offset, sizeof(*sqsh_ino)); if (err < 0) goto failed_read; if (type == SQUASHFS_LCHRDEV_TYPE) inode->i_mode |= S_IFCHR; else inode->i_mode |= S_IFBLK; xattr_id = le32_to_cpu(sqsh_ino->xattr); inode->i_op = &squashfs_inode_ops; set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); rdev = le32_to_cpu(sqsh_ino->rdev); init_special_inode(inode, inode->i_mode, new_decode_dev(rdev)); TRACE("Device inode %x:%x, rdev %x\n", SQUASHFS_INODE_BLK(ino), offset, rdev); break; } case SQUASHFS_FIFO_TYPE: case SQUASHFS_SOCKET_TYPE: { struct squashfs_ipc_inode *sqsh_ino = &squashfs_ino.ipc; err = squashfs_read_metadata(sb, sqsh_ino, &block, &offset, sizeof(*sqsh_ino)); if (err < 0) goto failed_read; if (type == SQUASHFS_FIFO_TYPE) inode->i_mode |= S_IFIFO; else inode->i_mode |= S_IFSOCK; set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); init_special_inode(inode, inode->i_mode, 0); break; } case SQUASHFS_LFIFO_TYPE: case SQUASHFS_LSOCKET_TYPE: { struct squashfs_lipc_inode *sqsh_ino = &squashfs_ino.lipc; err = squashfs_read_metadata(sb, sqsh_ino, &block, &offset, sizeof(*sqsh_ino)); if (err < 0) goto failed_read; if (type == SQUASHFS_LFIFO_TYPE) inode->i_mode |= S_IFIFO; else inode->i_mode |= S_IFSOCK; xattr_id = le32_to_cpu(sqsh_ino->xattr); inode->i_op = &squashfs_inode_ops; set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); init_special_inode(inode, inode->i_mode, 0); break; } default: ERROR("Unknown inode type %d in squashfs_iget!\n", type); return -EINVAL; } if (xattr_id != SQUASHFS_INVALID_XATTR && msblk->xattr_id_table) { err = squashfs_xattr_lookup(sb, xattr_id, &squashfs_i(inode)->xattr_count, &squashfs_i(inode)->xattr_size, &squashfs_i(inode)->xattr); if (err < 0) goto failed_read; inode->i_blocks += ((squashfs_i(inode)->xattr_size - 1) >> 9) + 1; } else squashfs_i(inode)->xattr_count = 0; return 0; failed_read: ERROR("Unable to read inode 0x%llx\n", ino); return err; } const struct inode_operations squashfs_inode_ops = { .listxattr = squashfs_listxattr }; |
| 117 96 117 117 33 7 77 30 38 33 13 13 13 111 101 101 109 3 112 110 3 63 7 42 21 113 108 38 6 7 7 44 44 3 111 115 1 116 115 107 37 2 40 108 110 7 100 25 88 13 2 13 96 96 42 42 31 2 18 15 8 7 2 1 7 6 1 1 1 1 7 5 1 2 2 1 47 46 32 24 46 5 18 1 1 1 1 1 1 1 1 1 1 8 7 1 8 6 6 2 11 11 6 4 5 31 15 11 14 31 31 31 14 45 10 10 1 8 1 9 8 7 11 11 48 31 30 48 31 31 35 22 48 48 48 48 13 11 11 9 11 9 2 2 2 2 2 7 4 3 8 8 8 13 4 7 11 11 2 7 11 8 10 11 13 13 13 3 13 13 13 13 13 15 15 15 13 4 6 10 2 12 12 10 3 7 7 10 10 24 11 11 11 14 22 30 30 30 30 22 22 22 22 8 17 22 11 11 11 5 6 11 24 30 11 22 30 30 9 9 2 8 5 7 7 5 7 7 1 7 9 12 6 5 1 7 7 12 14 7 7 7 12 14 14 14 13 14 14 12 12 12 12 12 12 69 44 43 44 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 | // SPDX-License-Identifier: GPL-2.0+ /* * NILFS B-tree. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * * Written by Koji Sato. */ #include <linux/slab.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/pagevec.h> #include "nilfs.h" #include "page.h" #include "btnode.h" #include "btree.h" #include "alloc.h" #include "dat.h" static void __nilfs_btree_init(struct nilfs_bmap *bmap); static struct nilfs_btree_path *nilfs_btree_alloc_path(void) { struct nilfs_btree_path *path; int level = NILFS_BTREE_LEVEL_DATA; path = kmem_cache_alloc(nilfs_btree_path_cache, GFP_NOFS); if (path == NULL) goto out; for (; level < NILFS_BTREE_LEVEL_MAX; level++) { path[level].bp_bh = NULL; path[level].bp_sib_bh = NULL; path[level].bp_index = 0; path[level].bp_oldreq.bpr_ptr = NILFS_BMAP_INVALID_PTR; path[level].bp_newreq.bpr_ptr = NILFS_BMAP_INVALID_PTR; path[level].bp_op = NULL; } out: return path; } static void nilfs_btree_free_path(struct nilfs_btree_path *path) { int level = NILFS_BTREE_LEVEL_DATA; for (; level < NILFS_BTREE_LEVEL_MAX; level++) brelse(path[level].bp_bh); kmem_cache_free(nilfs_btree_path_cache, path); } /* * B-tree node operations */ static int nilfs_btree_get_new_block(const struct nilfs_bmap *btree, __u64 ptr, struct buffer_head **bhp) { struct inode *btnc_inode = NILFS_BMAP_I(btree)->i_assoc_inode; struct address_space *btnc = btnc_inode->i_mapping; struct buffer_head *bh; bh = nilfs_btnode_create_block(btnc, ptr); if (IS_ERR(bh)) return PTR_ERR(bh); set_buffer_nilfs_volatile(bh); *bhp = bh; return 0; } static int nilfs_btree_node_get_flags(const struct nilfs_btree_node *node) { return node->bn_flags; } static void nilfs_btree_node_set_flags(struct nilfs_btree_node *node, int flags) { node->bn_flags = flags; } static int nilfs_btree_node_root(const struct nilfs_btree_node *node) { return nilfs_btree_node_get_flags(node) & NILFS_BTREE_NODE_ROOT; } static int nilfs_btree_node_get_level(const struct nilfs_btree_node *node) { return node->bn_level; } static void nilfs_btree_node_set_level(struct nilfs_btree_node *node, int level) { node->bn_level = level; } static int nilfs_btree_node_get_nchildren(const struct nilfs_btree_node *node) { return le16_to_cpu(node->bn_nchildren); } static void nilfs_btree_node_set_nchildren(struct nilfs_btree_node *node, int nchildren) { node->bn_nchildren = cpu_to_le16(nchildren); } static int nilfs_btree_node_size(const struct nilfs_bmap *btree) { return i_blocksize(btree->b_inode); } static int nilfs_btree_nchildren_per_block(const struct nilfs_bmap *btree) { return btree->b_nchildren_per_block; } static __le64 * nilfs_btree_node_dkeys(const struct nilfs_btree_node *node) { return (__le64 *)((char *)(node + 1) + (nilfs_btree_node_root(node) ? 0 : NILFS_BTREE_NODE_EXTRA_PAD_SIZE)); } static __le64 * nilfs_btree_node_dptrs(const struct nilfs_btree_node *node, int ncmax) { return (__le64 *)(nilfs_btree_node_dkeys(node) + ncmax); } static __u64 nilfs_btree_node_get_key(const struct nilfs_btree_node *node, int index) { return le64_to_cpu(*(nilfs_btree_node_dkeys(node) + index)); } static void nilfs_btree_node_set_key(struct nilfs_btree_node *node, int index, __u64 key) { *(nilfs_btree_node_dkeys(node) + index) = cpu_to_le64(key); } static __u64 nilfs_btree_node_get_ptr(const struct nilfs_btree_node *node, int index, int ncmax) { return le64_to_cpu(*(nilfs_btree_node_dptrs(node, ncmax) + index)); } static void nilfs_btree_node_set_ptr(struct nilfs_btree_node *node, int index, __u64 ptr, int ncmax) { *(nilfs_btree_node_dptrs(node, ncmax) + index) = cpu_to_le64(ptr); } static void nilfs_btree_node_init(struct nilfs_btree_node *node, int flags, int level, int nchildren, int ncmax, const __u64 *keys, const __u64 *ptrs) { __le64 *dkeys; __le64 *dptrs; int i; nilfs_btree_node_set_flags(node, flags); nilfs_btree_node_set_level(node, level); nilfs_btree_node_set_nchildren(node, nchildren); dkeys = nilfs_btree_node_dkeys(node); dptrs = nilfs_btree_node_dptrs(node, ncmax); for (i = 0; i < nchildren; i++) { dkeys[i] = cpu_to_le64(keys[i]); dptrs[i] = cpu_to_le64(ptrs[i]); } } /* Assume the buffer heads corresponding to left and right are locked. */ static void nilfs_btree_node_move_left(struct nilfs_btree_node *left, struct nilfs_btree_node *right, int n, int lncmax, int rncmax) { __le64 *ldkeys, *rdkeys; __le64 *ldptrs, *rdptrs; int lnchildren, rnchildren; ldkeys = nilfs_btree_node_dkeys(left); ldptrs = nilfs_btree_node_dptrs(left, lncmax); lnchildren = nilfs_btree_node_get_nchildren(left); rdkeys = nilfs_btree_node_dkeys(right); rdptrs = nilfs_btree_node_dptrs(right, rncmax); rnchildren = nilfs_btree_node_get_nchildren(right); memcpy(ldkeys + lnchildren, rdkeys, n * sizeof(*rdkeys)); memcpy(ldptrs + lnchildren, rdptrs, n * sizeof(*rdptrs)); memmove(rdkeys, rdkeys + n, (rnchildren - n) * sizeof(*rdkeys)); memmove(rdptrs, rdptrs + n, (rnchildren - n) * sizeof(*rdptrs)); lnchildren += n; rnchildren -= n; nilfs_btree_node_set_nchildren(left, lnchildren); nilfs_btree_node_set_nchildren(right, rnchildren); } /* Assume that the buffer heads corresponding to left and right are locked. */ static void nilfs_btree_node_move_right(struct nilfs_btree_node *left, struct nilfs_btree_node *right, int n, int lncmax, int rncmax) { __le64 *ldkeys, *rdkeys; __le64 *ldptrs, *rdptrs; int lnchildren, rnchildren; ldkeys = nilfs_btree_node_dkeys(left); ldptrs = nilfs_btree_node_dptrs(left, lncmax); lnchildren = nilfs_btree_node_get_nchildren(left); rdkeys = nilfs_btree_node_dkeys(right); rdptrs = nilfs_btree_node_dptrs(right, rncmax); rnchildren = nilfs_btree_node_get_nchildren(right); memmove(rdkeys + n, rdkeys, rnchildren * sizeof(*rdkeys)); memmove(rdptrs + n, rdptrs, rnchildren * sizeof(*rdptrs)); memcpy(rdkeys, ldkeys + lnchildren - n, n * sizeof(*rdkeys)); memcpy(rdptrs, ldptrs + lnchildren - n, n * sizeof(*rdptrs)); lnchildren -= n; rnchildren += n; nilfs_btree_node_set_nchildren(left, lnchildren); nilfs_btree_node_set_nchildren(right, rnchildren); } /* Assume that the buffer head corresponding to node is locked. */ static void nilfs_btree_node_insert(struct nilfs_btree_node *node, int index, __u64 key, __u64 ptr, int ncmax) { __le64 *dkeys; __le64 *dptrs; int nchildren; dkeys = nilfs_btree_node_dkeys(node); dptrs = nilfs_btree_node_dptrs(node, ncmax); nchildren = nilfs_btree_node_get_nchildren(node); if (index < nchildren) { memmove(dkeys + index + 1, dkeys + index, (nchildren - index) * sizeof(*dkeys)); memmove(dptrs + index + 1, dptrs + index, (nchildren - index) * sizeof(*dptrs)); } dkeys[index] = cpu_to_le64(key); dptrs[index] = cpu_to_le64(ptr); nchildren++; nilfs_btree_node_set_nchildren(node, nchildren); } /* Assume that the buffer head corresponding to node is locked. */ static void nilfs_btree_node_delete(struct nilfs_btree_node *node, int index, __u64 *keyp, __u64 *ptrp, int ncmax) { __u64 key; __u64 ptr; __le64 *dkeys; __le64 *dptrs; int nchildren; dkeys = nilfs_btree_node_dkeys(node); dptrs = nilfs_btree_node_dptrs(node, ncmax); key = le64_to_cpu(dkeys[index]); ptr = le64_to_cpu(dptrs[index]); nchildren = nilfs_btree_node_get_nchildren(node); if (keyp != NULL) *keyp = key; if (ptrp != NULL) *ptrp = ptr; if (index < nchildren - 1) { memmove(dkeys + index, dkeys + index + 1, (nchildren - index - 1) * sizeof(*dkeys)); memmove(dptrs + index, dptrs + index + 1, (nchildren - index - 1) * sizeof(*dptrs)); } nchildren--; nilfs_btree_node_set_nchildren(node, nchildren); } static int nilfs_btree_node_lookup(const struct nilfs_btree_node *node, __u64 key, int *indexp) { __u64 nkey; int index, low, high, s; /* binary search */ low = 0; high = nilfs_btree_node_get_nchildren(node) - 1; index = 0; s = 0; while (low <= high) { index = (low + high) / 2; nkey = nilfs_btree_node_get_key(node, index); if (nkey == key) { s = 0; goto out; } else if (nkey < key) { low = index + 1; s = -1; } else { high = index - 1; s = 1; } } /* adjust index */ if (nilfs_btree_node_get_level(node) > NILFS_BTREE_LEVEL_NODE_MIN) { if (s > 0 && index > 0) index--; } else if (s < 0) index++; out: *indexp = index; return s == 0; } /** * nilfs_btree_node_broken - verify consistency of btree node * @node: btree node block to be examined * @size: node size (in bytes) * @inode: host inode of btree * @blocknr: block number * * Return Value: If node is broken, 1 is returned. Otherwise, 0 is returned. */ static int nilfs_btree_node_broken(const struct nilfs_btree_node *node, size_t size, struct inode *inode, sector_t blocknr) { int level, flags, nchildren; int ret = 0; level = nilfs_btree_node_get_level(node); flags = nilfs_btree_node_get_flags(node); nchildren = nilfs_btree_node_get_nchildren(node); if (unlikely(level < NILFS_BTREE_LEVEL_NODE_MIN || level >= NILFS_BTREE_LEVEL_MAX || (flags & NILFS_BTREE_NODE_ROOT) || nchildren < 0 || nchildren > NILFS_BTREE_NODE_NCHILDREN_MAX(size))) { nilfs_crit(inode->i_sb, "bad btree node (ino=%lu, blocknr=%llu): level = %d, flags = 0x%x, nchildren = %d", inode->i_ino, (unsigned long long)blocknr, level, flags, nchildren); ret = 1; } return ret; } /** * nilfs_btree_root_broken - verify consistency of btree root node * @node: btree root node to be examined * @inode: host inode of btree * * Return Value: If node is broken, 1 is returned. Otherwise, 0 is returned. */ static int nilfs_btree_root_broken(const struct nilfs_btree_node *node, struct inode *inode) { int level, flags, nchildren; int ret = 0; level = nilfs_btree_node_get_level(node); flags = nilfs_btree_node_get_flags(node); nchildren = nilfs_btree_node_get_nchildren(node); if (unlikely(level < NILFS_BTREE_LEVEL_NODE_MIN || level >= NILFS_BTREE_LEVEL_MAX || nchildren < 0 || nchildren > NILFS_BTREE_ROOT_NCHILDREN_MAX)) { nilfs_crit(inode->i_sb, "bad btree root (ino=%lu): level = %d, flags = 0x%x, nchildren = %d", inode->i_ino, level, flags, nchildren); ret = 1; } return ret; } int nilfs_btree_broken_node_block(struct buffer_head *bh) { struct inode *inode; int ret; if (buffer_nilfs_checked(bh)) return 0; inode = bh->b_folio->mapping->host; ret = nilfs_btree_node_broken((struct nilfs_btree_node *)bh->b_data, bh->b_size, inode, bh->b_blocknr); if (likely(!ret)) set_buffer_nilfs_checked(bh); return ret; } static struct nilfs_btree_node * nilfs_btree_get_root(const struct nilfs_bmap *btree) { return (struct nilfs_btree_node *)btree->b_u.u_data; } static struct nilfs_btree_node * nilfs_btree_get_nonroot_node(const struct nilfs_btree_path *path, int level) { return (struct nilfs_btree_node *)path[level].bp_bh->b_data; } static struct nilfs_btree_node * nilfs_btree_get_sib_node(const struct nilfs_btree_path *path, int level) { return (struct nilfs_btree_node *)path[level].bp_sib_bh->b_data; } static int nilfs_btree_height(const struct nilfs_bmap *btree) { return nilfs_btree_node_get_level(nilfs_btree_get_root(btree)) + 1; } static struct nilfs_btree_node * nilfs_btree_get_node(const struct nilfs_bmap *btree, const struct nilfs_btree_path *path, int level, int *ncmaxp) { struct nilfs_btree_node *node; if (level == nilfs_btree_height(btree) - 1) { node = nilfs_btree_get_root(btree); *ncmaxp = NILFS_BTREE_ROOT_NCHILDREN_MAX; } else { node = nilfs_btree_get_nonroot_node(path, level); *ncmaxp = nilfs_btree_nchildren_per_block(btree); } return node; } static int nilfs_btree_bad_node(const struct nilfs_bmap *btree, struct nilfs_btree_node *node, int level) { if (unlikely(nilfs_btree_node_get_level(node) != level)) { dump_stack(); nilfs_crit(btree->b_inode->i_sb, "btree level mismatch (ino=%lu): %d != %d", btree->b_inode->i_ino, nilfs_btree_node_get_level(node), level); return 1; } return 0; } struct nilfs_btree_readahead_info { struct nilfs_btree_node *node; /* parent node */ int max_ra_blocks; /* max nof blocks to read ahead */ int index; /* current index on the parent node */ int ncmax; /* nof children in the parent node */ }; static int __nilfs_btree_get_block(const struct nilfs_bmap *btree, __u64 ptr, struct buffer_head **bhp, const struct nilfs_btree_readahead_info *ra) { struct inode *btnc_inode = NILFS_BMAP_I(btree)->i_assoc_inode; struct address_space *btnc = btnc_inode->i_mapping; struct buffer_head *bh, *ra_bh; sector_t submit_ptr = 0; int ret; ret = nilfs_btnode_submit_block(btnc, ptr, 0, REQ_OP_READ, &bh, &submit_ptr); if (ret) { if (likely(ret == -EEXIST)) goto out_check; if (ret == -ENOENT) { /* * Block address translation failed due to invalid * value of 'ptr'. In this case, return internal code * -EINVAL (broken bmap) to notify bmap layer of fatal * metadata corruption. */ ret = -EINVAL; } return ret; } if (ra) { int i, n; __u64 ptr2; /* read ahead sibling nodes */ for (n = ra->max_ra_blocks, i = ra->index + 1; n > 0 && i < ra->ncmax; n--, i++) { ptr2 = nilfs_btree_node_get_ptr(ra->node, i, ra->ncmax); ret = nilfs_btnode_submit_block(btnc, ptr2, 0, REQ_OP_READ | REQ_RAHEAD, &ra_bh, &submit_ptr); if (likely(!ret || ret == -EEXIST)) brelse(ra_bh); else if (ret != -EBUSY) break; if (!buffer_locked(bh)) goto out_no_wait; } } wait_on_buffer(bh); out_no_wait: if (!buffer_uptodate(bh)) { nilfs_err(btree->b_inode->i_sb, "I/O error reading b-tree node block (ino=%lu, blocknr=%llu)", btree->b_inode->i_ino, (unsigned long long)ptr); brelse(bh); return -EIO; } out_check: if (nilfs_btree_broken_node_block(bh)) { clear_buffer_uptodate(bh); brelse(bh); return -EINVAL; } *bhp = bh; return 0; } static int nilfs_btree_get_block(const struct nilfs_bmap *btree, __u64 ptr, struct buffer_head **bhp) { return __nilfs_btree_get_block(btree, ptr, bhp, NULL); } static int nilfs_btree_do_lookup(const struct nilfs_bmap *btree, struct nilfs_btree_path *path, __u64 key, __u64 *ptrp, int minlevel, int readahead) { struct nilfs_btree_node *node; struct nilfs_btree_readahead_info p, *ra; __u64 ptr; int level, index, found, ncmax, ret; node = nilfs_btree_get_root(btree); level = nilfs_btree_node_get_level(node); if (level < minlevel || nilfs_btree_node_get_nchildren(node) <= 0) return -ENOENT; found = nilfs_btree_node_lookup(node, key, &index); ptr = nilfs_btree_node_get_ptr(node, index, NILFS_BTREE_ROOT_NCHILDREN_MAX); path[level].bp_bh = NULL; path[level].bp_index = index; ncmax = nilfs_btree_nchildren_per_block(btree); while (--level >= minlevel) { ra = NULL; if (level == NILFS_BTREE_LEVEL_NODE_MIN && readahead) { p.node = nilfs_btree_get_node(btree, path, level + 1, &p.ncmax); p.index = index; p.max_ra_blocks = 7; ra = &p; } ret = __nilfs_btree_get_block(btree, ptr, &path[level].bp_bh, ra); if (ret < 0) return ret; node = nilfs_btree_get_nonroot_node(path, level); if (nilfs_btree_bad_node(btree, node, level)) return -EINVAL; if (!found) found = nilfs_btree_node_lookup(node, key, &index); else index = 0; if (index < ncmax) { ptr = nilfs_btree_node_get_ptr(node, index, ncmax); } else { WARN_ON(found || level != NILFS_BTREE_LEVEL_NODE_MIN); /* insert */ ptr = NILFS_BMAP_INVALID_PTR; } path[level].bp_index = index; } if (!found) return -ENOENT; if (ptrp != NULL) *ptrp = ptr; return 0; } static int nilfs_btree_do_lookup_last(const struct nilfs_bmap *btree, struct nilfs_btree_path *path, __u64 *keyp, __u64 *ptrp) { struct nilfs_btree_node *node; __u64 ptr; int index, level, ncmax, ret; node = nilfs_btree_get_root(btree); index = nilfs_btree_node_get_nchildren(node) - 1; if (index < 0) return -ENOENT; level = nilfs_btree_node_get_level(node); ptr = nilfs_btree_node_get_ptr(node, index, NILFS_BTREE_ROOT_NCHILDREN_MAX); path[level].bp_bh = NULL; path[level].bp_index = index; ncmax = nilfs_btree_nchildren_per_block(btree); for (level--; level > 0; level--) { ret = nilfs_btree_get_block(btree, ptr, &path[level].bp_bh); if (ret < 0) return ret; node = nilfs_btree_get_nonroot_node(path, level); if (nilfs_btree_bad_node(btree, node, level)) return -EINVAL; index = nilfs_btree_node_get_nchildren(node) - 1; ptr = nilfs_btree_node_get_ptr(node, index, ncmax); path[level].bp_index = index; } if (keyp != NULL) *keyp = nilfs_btree_node_get_key(node, index); if (ptrp != NULL) *ptrp = ptr; return 0; } /** * nilfs_btree_get_next_key - get next valid key from btree path array * @btree: bmap struct of btree * @path: array of nilfs_btree_path struct * @minlevel: start level * @nextkey: place to store the next valid key * * Return Value: If a next key was found, 0 is returned. Otherwise, * -ENOENT is returned. */ static int nilfs_btree_get_next_key(const struct nilfs_bmap *btree, const struct nilfs_btree_path *path, int minlevel, __u64 *nextkey) { struct nilfs_btree_node *node; int maxlevel = nilfs_btree_height(btree) - 1; int index, next_adj, level; /* Next index is already set to bp_index for leaf nodes. */ next_adj = 0; for (level = minlevel; level <= maxlevel; level++) { if (level == maxlevel) node = nilfs_btree_get_root(btree); else node = nilfs_btree_get_nonroot_node(path, level); index = path[level].bp_index + next_adj; if (index < nilfs_btree_node_get_nchildren(node)) { /* Next key is in this node */ *nextkey = nilfs_btree_node_get_key(node, index); return 0; } /* For non-leaf nodes, next index is stored at bp_index + 1. */ next_adj = 1; } return -ENOENT; } static int nilfs_btree_lookup(const struct nilfs_bmap *btree, __u64 key, int level, __u64 *ptrp) { struct nilfs_btree_path *path; int ret; path = nilfs_btree_alloc_path(); if (path == NULL) return -ENOMEM; ret = nilfs_btree_do_lookup(btree, path, key, ptrp, level, 0); nilfs_btree_free_path(path); return ret; } static int nilfs_btree_lookup_contig(const struct nilfs_bmap *btree, __u64 key, __u64 *ptrp, unsigned int maxblocks) { struct nilfs_btree_path *path; struct nilfs_btree_node *node; struct inode *dat = NULL; __u64 ptr, ptr2; sector_t blocknr; int level = NILFS_BTREE_LEVEL_NODE_MIN; int ret, cnt, index, maxlevel, ncmax; struct nilfs_btree_readahead_info p; path = nilfs_btree_alloc_path(); if (path == NULL) return -ENOMEM; ret = nilfs_btree_do_lookup(btree, path, key, &ptr, level, 1); if (ret < 0) goto out; if (NILFS_BMAP_USE_VBN(btree)) { dat = nilfs_bmap_get_dat(btree); ret = nilfs_dat_translate(dat, ptr, &blocknr); if (ret < 0) goto dat_error; ptr = blocknr; } cnt = 1; if (cnt == maxblocks) goto end; maxlevel = nilfs_btree_height(btree) - 1; node = nilfs_btree_get_node(btree, path, level, &ncmax); index = path[level].bp_index + 1; for (;;) { while (index < nilfs_btree_node_get_nchildren(node)) { if (nilfs_btree_node_get_key(node, index) != key + cnt) goto end; ptr2 = nilfs_btree_node_get_ptr(node, index, ncmax); if (dat) { ret = nilfs_dat_translate(dat, ptr2, &blocknr); if (ret < 0) goto dat_error; ptr2 = blocknr; } if (ptr2 != ptr + cnt || ++cnt == maxblocks) goto end; index++; } if (level == maxlevel) break; /* look-up right sibling node */ p.node = nilfs_btree_get_node(btree, path, level + 1, &p.ncmax); p.index = path[level + 1].bp_index + 1; p.max_ra_blocks = 7; if (p.index >= nilfs_btree_node_get_nchildren(p.node) || nilfs_btree_node_get_key(p.node, p.index) != key + cnt) break; ptr2 = nilfs_btree_node_get_ptr(p.node, p.index, p.ncmax); path[level + 1].bp_index = p.index; brelse(path[level].bp_bh); path[level].bp_bh = NULL; ret = __nilfs_btree_get_block(btree, ptr2, &path[level].bp_bh, &p); if (ret < 0) goto out; node = nilfs_btree_get_nonroot_node(path, level); ncmax = nilfs_btree_nchildren_per_block(btree); index = 0; path[level].bp_index = index; } end: *ptrp = ptr; ret = cnt; out: nilfs_btree_free_path(path); return ret; dat_error: if (ret == -ENOENT) ret = -EINVAL; /* Notify bmap layer of metadata corruption */ goto out; } static void nilfs_btree_promote_key(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, __u64 key) { if (level < nilfs_btree_height(btree) - 1) { do { nilfs_btree_node_set_key( nilfs_btree_get_nonroot_node(path, level), path[level].bp_index, key); if (!buffer_dirty(path[level].bp_bh)) mark_buffer_dirty(path[level].bp_bh); } while ((path[level].bp_index == 0) && (++level < nilfs_btree_height(btree) - 1)); } /* root */ if (level == nilfs_btree_height(btree) - 1) { nilfs_btree_node_set_key(nilfs_btree_get_root(btree), path[level].bp_index, key); } } static void nilfs_btree_do_insert(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, __u64 *keyp, __u64 *ptrp) { struct nilfs_btree_node *node; int ncblk; if (level < nilfs_btree_height(btree) - 1) { node = nilfs_btree_get_nonroot_node(path, level); ncblk = nilfs_btree_nchildren_per_block(btree); nilfs_btree_node_insert(node, path[level].bp_index, *keyp, *ptrp, ncblk); if (!buffer_dirty(path[level].bp_bh)) mark_buffer_dirty(path[level].bp_bh); if (path[level].bp_index == 0) nilfs_btree_promote_key(btree, path, level + 1, nilfs_btree_node_get_key(node, 0)); } else { node = nilfs_btree_get_root(btree); nilfs_btree_node_insert(node, path[level].bp_index, *keyp, *ptrp, NILFS_BTREE_ROOT_NCHILDREN_MAX); } } static void nilfs_btree_carry_left(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, __u64 *keyp, __u64 *ptrp) { struct nilfs_btree_node *node, *left; int nchildren, lnchildren, n, move, ncblk; node = nilfs_btree_get_nonroot_node(path, level); left = nilfs_btree_get_sib_node(path, level); nchildren = nilfs_btree_node_get_nchildren(node); lnchildren = nilfs_btree_node_get_nchildren(left); ncblk = nilfs_btree_nchildren_per_block(btree); move = 0; n = (nchildren + lnchildren + 1) / 2 - lnchildren; if (n > path[level].bp_index) { /* move insert point */ n--; move = 1; } nilfs_btree_node_move_left(left, node, n, ncblk, ncblk); if (!buffer_dirty(path[level].bp_bh)) mark_buffer_dirty(path[level].bp_bh); if (!buffer_dirty(path[level].bp_sib_bh)) mark_buffer_dirty(path[level].bp_sib_bh); nilfs_btree_promote_key(btree, path, level + 1, nilfs_btree_node_get_key(node, 0)); if (move) { brelse(path[level].bp_bh); path[level].bp_bh = path[level].bp_sib_bh; path[level].bp_sib_bh = NULL; path[level].bp_index += lnchildren; path[level + 1].bp_index--; } else { brelse(path[level].bp_sib_bh); path[level].bp_sib_bh = NULL; path[level].bp_index -= n; } nilfs_btree_do_insert(btree, path, level, keyp, ptrp); } static void nilfs_btree_carry_right(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, __u64 *keyp, __u64 *ptrp) { struct nilfs_btree_node *node, *right; int nchildren, rnchildren, n, move, ncblk; node = nilfs_btree_get_nonroot_node(path, level); right = nilfs_btree_get_sib_node(path, level); nchildren = nilfs_btree_node_get_nchildren(node); rnchildren = nilfs_btree_node_get_nchildren(right); ncblk = nilfs_btree_nchildren_per_block(btree); move = 0; n = (nchildren + rnchildren + 1) / 2 - rnchildren; if (n > nchildren - path[level].bp_index) { /* move insert point */ n--; move = 1; } nilfs_btree_node_move_right(node, right, n, ncblk, ncblk); if (!buffer_dirty(path[level].bp_bh)) mark_buffer_dirty(path[level].bp_bh); if (!buffer_dirty(path[level].bp_sib_bh)) mark_buffer_dirty(path[level].bp_sib_bh); path[level + 1].bp_index++; nilfs_btree_promote_key(btree, path, level + 1, nilfs_btree_node_get_key(right, 0)); path[level + 1].bp_index--; if (move) { brelse(path[level].bp_bh); path[level].bp_bh = path[level].bp_sib_bh; path[level].bp_sib_bh = NULL; path[level].bp_index -= nilfs_btree_node_get_nchildren(node); path[level + 1].bp_index++; } else { brelse(path[level].bp_sib_bh); path[level].bp_sib_bh = NULL; } nilfs_btree_do_insert(btree, path, level, keyp, ptrp); } static void nilfs_btree_split(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, __u64 *keyp, __u64 *ptrp) { struct nilfs_btree_node *node, *right; int nchildren, n, move, ncblk; node = nilfs_btree_get_nonroot_node(path, level); right = nilfs_btree_get_sib_node(path, level); nchildren = nilfs_btree_node_get_nchildren(node); ncblk = nilfs_btree_nchildren_per_block(btree); move = 0; n = (nchildren + 1) / 2; if (n > nchildren - path[level].bp_index) { n--; move = 1; } nilfs_btree_node_move_right(node, right, n, ncblk, ncblk); if (!buffer_dirty(path[level].bp_bh)) mark_buffer_dirty(path[level].bp_bh); if (!buffer_dirty(path[level].bp_sib_bh)) mark_buffer_dirty(path[level].bp_sib_bh); if (move) { path[level].bp_index -= nilfs_btree_node_get_nchildren(node); nilfs_btree_node_insert(right, path[level].bp_index, *keyp, *ptrp, ncblk); *keyp = nilfs_btree_node_get_key(right, 0); *ptrp = path[level].bp_newreq.bpr_ptr; brelse(path[level].bp_bh); path[level].bp_bh = path[level].bp_sib_bh; path[level].bp_sib_bh = NULL; } else { nilfs_btree_do_insert(btree, path, level, keyp, ptrp); *keyp = nilfs_btree_node_get_key(right, 0); *ptrp = path[level].bp_newreq.bpr_ptr; brelse(path[level].bp_sib_bh); path[level].bp_sib_bh = NULL; } path[level + 1].bp_index++; } static void nilfs_btree_grow(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, __u64 *keyp, __u64 *ptrp) { struct nilfs_btree_node *root, *child; int n, ncblk; root = nilfs_btree_get_root(btree); child = nilfs_btree_get_sib_node(path, level); ncblk = nilfs_btree_nchildren_per_block(btree); n = nilfs_btree_node_get_nchildren(root); nilfs_btree_node_move_right(root, child, n, NILFS_BTREE_ROOT_NCHILDREN_MAX, ncblk); nilfs_btree_node_set_level(root, level + 1); if (!buffer_dirty(path[level].bp_sib_bh)) mark_buffer_dirty(path[level].bp_sib_bh); path[level].bp_bh = path[level].bp_sib_bh; path[level].bp_sib_bh = NULL; nilfs_btree_do_insert(btree, path, level, keyp, ptrp); *keyp = nilfs_btree_node_get_key(child, 0); *ptrp = path[level].bp_newreq.bpr_ptr; } static __u64 nilfs_btree_find_near(const struct nilfs_bmap *btree, const struct nilfs_btree_path *path) { struct nilfs_btree_node *node; int level, ncmax; if (path == NULL) return NILFS_BMAP_INVALID_PTR; /* left sibling */ level = NILFS_BTREE_LEVEL_NODE_MIN; if (path[level].bp_index > 0) { node = nilfs_btree_get_node(btree, path, level, &ncmax); return nilfs_btree_node_get_ptr(node, path[level].bp_index - 1, ncmax); } /* parent */ level = NILFS_BTREE_LEVEL_NODE_MIN + 1; if (level <= nilfs_btree_height(btree) - 1) { node = nilfs_btree_get_node(btree, path, level, &ncmax); return nilfs_btree_node_get_ptr(node, path[level].bp_index, ncmax); } return NILFS_BMAP_INVALID_PTR; } static __u64 nilfs_btree_find_target_v(const struct nilfs_bmap *btree, const struct nilfs_btree_path *path, __u64 key) { __u64 ptr; ptr = nilfs_bmap_find_target_seq(btree, key); if (ptr != NILFS_BMAP_INVALID_PTR) /* sequential access */ return ptr; ptr = nilfs_btree_find_near(btree, path); if (ptr != NILFS_BMAP_INVALID_PTR) /* near */ return ptr; /* block group */ return nilfs_bmap_find_target_in_group(btree); } static int nilfs_btree_prepare_insert(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int *levelp, __u64 key, __u64 ptr, struct nilfs_bmap_stats *stats) { struct buffer_head *bh; struct nilfs_btree_node *node, *parent, *sib; __u64 sibptr; int pindex, level, ncmax, ncblk, ret; struct inode *dat = NULL; stats->bs_nblocks = 0; level = NILFS_BTREE_LEVEL_DATA; /* allocate a new ptr for data block */ if (NILFS_BMAP_USE_VBN(btree)) { path[level].bp_newreq.bpr_ptr = nilfs_btree_find_target_v(btree, path, key); dat = nilfs_bmap_get_dat(btree); } ret = nilfs_bmap_prepare_alloc_ptr(btree, &path[level].bp_newreq, dat); if (ret < 0) goto err_out_data; ncblk = nilfs_btree_nchildren_per_block(btree); for (level = NILFS_BTREE_LEVEL_NODE_MIN; level < nilfs_btree_height(btree) - 1; level++) { node = nilfs_btree_get_nonroot_node(path, level); if (nilfs_btree_node_get_nchildren(node) < ncblk) { path[level].bp_op = nilfs_btree_do_insert; stats->bs_nblocks++; goto out; } parent = nilfs_btree_get_node(btree, path, level + 1, &ncmax); pindex = path[level + 1].bp_index; /* left sibling */ if (pindex > 0) { sibptr = nilfs_btree_node_get_ptr(parent, pindex - 1, ncmax); ret = nilfs_btree_get_block(btree, sibptr, &bh); if (ret < 0) goto err_out_child_node; sib = (struct nilfs_btree_node *)bh->b_data; if (nilfs_btree_node_get_nchildren(sib) < ncblk) { path[level].bp_sib_bh = bh; path[level].bp_op = nilfs_btree_carry_left; stats->bs_nblocks++; goto out; } else { brelse(bh); } } /* right sibling */ if (pindex < nilfs_btree_node_get_nchildren(parent) - 1) { sibptr = nilfs_btree_node_get_ptr(parent, pindex + 1, ncmax); ret = nilfs_btree_get_block(btree, sibptr, &bh); if (ret < 0) goto err_out_child_node; sib = (struct nilfs_btree_node *)bh->b_data; if (nilfs_btree_node_get_nchildren(sib) < ncblk) { path[level].bp_sib_bh = bh; path[level].bp_op = nilfs_btree_carry_right; stats->bs_nblocks++; goto out; } else { brelse(bh); } } /* split */ path[level].bp_newreq.bpr_ptr = path[level - 1].bp_newreq.bpr_ptr + 1; ret = nilfs_bmap_prepare_alloc_ptr(btree, &path[level].bp_newreq, dat); if (ret < 0) goto err_out_child_node; ret = nilfs_btree_get_new_block(btree, path[level].bp_newreq.bpr_ptr, &bh); if (ret < 0) goto err_out_curr_node; stats->bs_nblocks++; sib = (struct nilfs_btree_node *)bh->b_data; nilfs_btree_node_init(sib, 0, level, 0, ncblk, NULL, NULL); path[level].bp_sib_bh = bh; path[level].bp_op = nilfs_btree_split; } /* root */ node = nilfs_btree_get_root(btree); if (nilfs_btree_node_get_nchildren(node) < NILFS_BTREE_ROOT_NCHILDREN_MAX) { path[level].bp_op = nilfs_btree_do_insert; stats->bs_nblocks++; goto out; } /* grow */ path[level].bp_newreq.bpr_ptr = path[level - 1].bp_newreq.bpr_ptr + 1; ret = nilfs_bmap_prepare_alloc_ptr(btree, &path[level].bp_newreq, dat); if (ret < 0) goto err_out_child_node; ret = nilfs_btree_get_new_block(btree, path[level].bp_newreq.bpr_ptr, &bh); if (ret < 0) goto err_out_curr_node; nilfs_btree_node_init((struct nilfs_btree_node *)bh->b_data, 0, level, 0, ncblk, NULL, NULL); path[level].bp_sib_bh = bh; path[level].bp_op = nilfs_btree_grow; level++; path[level].bp_op = nilfs_btree_do_insert; /* a newly-created node block and a data block are added */ stats->bs_nblocks += 2; /* success */ out: *levelp = level; return ret; /* error */ err_out_curr_node: nilfs_bmap_abort_alloc_ptr(btree, &path[level].bp_newreq, dat); err_out_child_node: for (level--; level > NILFS_BTREE_LEVEL_DATA; level--) { nilfs_btnode_delete(path[level].bp_sib_bh); nilfs_bmap_abort_alloc_ptr(btree, &path[level].bp_newreq, dat); } nilfs_bmap_abort_alloc_ptr(btree, &path[level].bp_newreq, dat); err_out_data: *levelp = level; stats->bs_nblocks = 0; return ret; } static void nilfs_btree_commit_insert(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int maxlevel, __u64 key, __u64 ptr) { struct inode *dat = NULL; int level; set_buffer_nilfs_volatile((struct buffer_head *)((unsigned long)ptr)); ptr = path[NILFS_BTREE_LEVEL_DATA].bp_newreq.bpr_ptr; if (NILFS_BMAP_USE_VBN(btree)) { nilfs_bmap_set_target_v(btree, key, ptr); dat = nilfs_bmap_get_dat(btree); } for (level = NILFS_BTREE_LEVEL_NODE_MIN; level <= maxlevel; level++) { nilfs_bmap_commit_alloc_ptr(btree, &path[level - 1].bp_newreq, dat); path[level].bp_op(btree, path, level, &key, &ptr); } if (!nilfs_bmap_dirty(btree)) nilfs_bmap_set_dirty(btree); } static int nilfs_btree_insert(struct nilfs_bmap *btree, __u64 key, __u64 ptr) { struct nilfs_btree_path *path; struct nilfs_bmap_stats stats; int level, ret; path = nilfs_btree_alloc_path(); if (path == NULL) return -ENOMEM; ret = nilfs_btree_do_lookup(btree, path, key, NULL, NILFS_BTREE_LEVEL_NODE_MIN, 0); if (ret != -ENOENT) { if (ret == 0) ret = -EEXIST; goto out; } ret = nilfs_btree_prepare_insert(btree, path, &level, key, ptr, &stats); if (ret < 0) goto out; nilfs_btree_commit_insert(btree, path, level, key, ptr); nilfs_inode_add_blocks(btree->b_inode, stats.bs_nblocks); out: nilfs_btree_free_path(path); return ret; } static void nilfs_btree_do_delete(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, __u64 *keyp, __u64 *ptrp) { struct nilfs_btree_node *node; int ncblk; if (level < nilfs_btree_height(btree) - 1) { node = nilfs_btree_get_nonroot_node(path, level); ncblk = nilfs_btree_nchildren_per_block(btree); nilfs_btree_node_delete(node, path[level].bp_index, keyp, ptrp, ncblk); if (!buffer_dirty(path[level].bp_bh)) mark_buffer_dirty(path[level].bp_bh); if (path[level].bp_index == 0) nilfs_btree_promote_key(btree, path, level + 1, nilfs_btree_node_get_key(node, 0)); } else { node = nilfs_btree_get_root(btree); nilfs_btree_node_delete(node, path[level].bp_index, keyp, ptrp, NILFS_BTREE_ROOT_NCHILDREN_MAX); } } static void nilfs_btree_borrow_left(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, __u64 *keyp, __u64 *ptrp) { struct nilfs_btree_node *node, *left; int nchildren, lnchildren, n, ncblk; nilfs_btree_do_delete(btree, path, level, keyp, ptrp); node = nilfs_btree_get_nonroot_node(path, level); left = nilfs_btree_get_sib_node(path, level); nchildren = nilfs_btree_node_get_nchildren(node); lnchildren = nilfs_btree_node_get_nchildren(left); ncblk = nilfs_btree_nchildren_per_block(btree); n = (nchildren + lnchildren) / 2 - nchildren; nilfs_btree_node_move_right(left, node, n, ncblk, ncblk); if (!buffer_dirty(path[level].bp_bh)) mark_buffer_dirty(path[level].bp_bh); if (!buffer_dirty(path[level].bp_sib_bh)) mark_buffer_dirty(path[level].bp_sib_bh); nilfs_btree_promote_key(btree, path, level + 1, nilfs_btree_node_get_key(node, 0)); brelse(path[level].bp_sib_bh); path[level].bp_sib_bh = NULL; path[level].bp_index += n; } static void nilfs_btree_borrow_right(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, __u64 *keyp, __u64 *ptrp) { struct nilfs_btree_node *node, *right; int nchildren, rnchildren, n, ncblk; nilfs_btree_do_delete(btree, path, level, keyp, ptrp); node = nilfs_btree_get_nonroot_node(path, level); right = nilfs_btree_get_sib_node(path, level); nchildren = nilfs_btree_node_get_nchildren(node); rnchildren = nilfs_btree_node_get_nchildren(right); ncblk = nilfs_btree_nchildren_per_block(btree); n = (nchildren + rnchildren) / 2 - nchildren; nilfs_btree_node_move_left(node, right, n, ncblk, ncblk); if (!buffer_dirty(path[level].bp_bh)) mark_buffer_dirty(path[level].bp_bh); if (!buffer_dirty(path[level].bp_sib_bh)) mark_buffer_dirty(path[level].bp_sib_bh); path[level + 1].bp_index++; nilfs_btree_promote_key(btree, path, level + 1, nilfs_btree_node_get_key(right, 0)); path[level + 1].bp_index--; brelse(path[level].bp_sib_bh); path[level].bp_sib_bh = NULL; } static void nilfs_btree_concat_left(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, __u64 *keyp, __u64 *ptrp) { struct nilfs_btree_node *node, *left; int n, ncblk; nilfs_btree_do_delete(btree, path, level, keyp, ptrp); node = nilfs_btree_get_nonroot_node(path, level); left = nilfs_btree_get_sib_node(path, level); ncblk = nilfs_btree_nchildren_per_block(btree); n = nilfs_btree_node_get_nchildren(node); nilfs_btree_node_move_left(left, node, n, ncblk, ncblk); if (!buffer_dirty(path[level].bp_sib_bh)) mark_buffer_dirty(path[level].bp_sib_bh); nilfs_btnode_delete(path[level].bp_bh); path[level].bp_bh = path[level].bp_sib_bh; path[level].bp_sib_bh = NULL; path[level].bp_index += nilfs_btree_node_get_nchildren(left); } static void nilfs_btree_concat_right(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, __u64 *keyp, __u64 *ptrp) { struct nilfs_btree_node *node, *right; int n, ncblk; nilfs_btree_do_delete(btree, path, level, keyp, ptrp); node = nilfs_btree_get_nonroot_node(path, level); right = nilfs_btree_get_sib_node(path, level); ncblk = nilfs_btree_nchildren_per_block(btree); n = nilfs_btree_node_get_nchildren(right); nilfs_btree_node_move_left(node, right, n, ncblk, ncblk); if (!buffer_dirty(path[level].bp_bh)) mark_buffer_dirty(path[level].bp_bh); nilfs_btnode_delete(path[level].bp_sib_bh); path[level].bp_sib_bh = NULL; path[level + 1].bp_index++; } static void nilfs_btree_shrink(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, __u64 *keyp, __u64 *ptrp) { struct nilfs_btree_node *root, *child; int n, ncblk; nilfs_btree_do_delete(btree, path, level, keyp, ptrp); root = nilfs_btree_get_root(btree); child = nilfs_btree_get_nonroot_node(path, level); ncblk = nilfs_btree_nchildren_per_block(btree); nilfs_btree_node_delete(root, 0, NULL, NULL, NILFS_BTREE_ROOT_NCHILDREN_MAX); nilfs_btree_node_set_level(root, level); n = nilfs_btree_node_get_nchildren(child); nilfs_btree_node_move_left(root, child, n, NILFS_BTREE_ROOT_NCHILDREN_MAX, ncblk); nilfs_btnode_delete(path[level].bp_bh); path[level].bp_bh = NULL; } static void nilfs_btree_nop(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, __u64 *keyp, __u64 *ptrp) { } static int nilfs_btree_prepare_delete(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int *levelp, struct nilfs_bmap_stats *stats, struct inode *dat) { struct buffer_head *bh; struct nilfs_btree_node *node, *parent, *sib; __u64 sibptr; int pindex, dindex, level, ncmin, ncmax, ncblk, ret; ret = 0; stats->bs_nblocks = 0; ncmin = NILFS_BTREE_NODE_NCHILDREN_MIN(nilfs_btree_node_size(btree)); ncblk = nilfs_btree_nchildren_per_block(btree); for (level = NILFS_BTREE_LEVEL_NODE_MIN, dindex = path[level].bp_index; level < nilfs_btree_height(btree) - 1; level++) { node = nilfs_btree_get_nonroot_node(path, level); path[level].bp_oldreq.bpr_ptr = nilfs_btree_node_get_ptr(node, dindex, ncblk); ret = nilfs_bmap_prepare_end_ptr(btree, &path[level].bp_oldreq, dat); if (ret < 0) goto err_out_child_node; if (nilfs_btree_node_get_nchildren(node) > ncmin) { path[level].bp_op = nilfs_btree_do_delete; stats->bs_nblocks++; goto out; } parent = nilfs_btree_get_node(btree, path, level + 1, &ncmax); pindex = path[level + 1].bp_index; dindex = pindex; if (pindex > 0) { /* left sibling */ sibptr = nilfs_btree_node_get_ptr(parent, pindex - 1, ncmax); ret = nilfs_btree_get_block(btree, sibptr, &bh); if (ret < 0) goto err_out_curr_node; sib = (struct nilfs_btree_node *)bh->b_data; if (nilfs_btree_node_get_nchildren(sib) > ncmin) { path[level].bp_sib_bh = bh; path[level].bp_op = nilfs_btree_borrow_left; stats->bs_nblocks++; goto out; } else { path[level].bp_sib_bh = bh; path[level].bp_op = nilfs_btree_concat_left; stats->bs_nblocks++; /* continue; */ } } else if (pindex < nilfs_btree_node_get_nchildren(parent) - 1) { /* right sibling */ sibptr = nilfs_btree_node_get_ptr(parent, pindex + 1, ncmax); ret = nilfs_btree_get_block(btree, sibptr, &bh); if (ret < 0) goto err_out_curr_node; sib = (struct nilfs_btree_node *)bh->b_data; if (nilfs_btree_node_get_nchildren(sib) > ncmin) { path[level].bp_sib_bh = bh; path[level].bp_op = nilfs_btree_borrow_right; stats->bs_nblocks++; goto out; } else { path[level].bp_sib_bh = bh; path[level].bp_op = nilfs_btree_concat_right; stats->bs_nblocks++; /* * When merging right sibling node * into the current node, pointer to * the right sibling node must be * terminated instead. The adjustment * below is required for that. */ dindex = pindex + 1; /* continue; */ } } else { /* no siblings */ /* the only child of the root node */ WARN_ON(level != nilfs_btree_height(btree) - 2); if (nilfs_btree_node_get_nchildren(node) - 1 <= NILFS_BTREE_ROOT_NCHILDREN_MAX) { path[level].bp_op = nilfs_btree_shrink; stats->bs_nblocks += 2; level++; path[level].bp_op = nilfs_btree_nop; goto shrink_root_child; } else { path[level].bp_op = nilfs_btree_do_delete; stats->bs_nblocks++; goto out; } } } /* child of the root node is deleted */ path[level].bp_op = nilfs_btree_do_delete; stats->bs_nblocks++; shrink_root_child: node = nilfs_btree_get_root(btree); path[level].bp_oldreq.bpr_ptr = nilfs_btree_node_get_ptr(node, dindex, NILFS_BTREE_ROOT_NCHILDREN_MAX); ret = nilfs_bmap_prepare_end_ptr(btree, &path[level].bp_oldreq, dat); if (ret < 0) goto err_out_child_node; /* success */ out: *levelp = level; return ret; /* error */ err_out_curr_node: nilfs_bmap_abort_end_ptr(btree, &path[level].bp_oldreq, dat); err_out_child_node: for (level--; level >= NILFS_BTREE_LEVEL_NODE_MIN; level--) { brelse(path[level].bp_sib_bh); nilfs_bmap_abort_end_ptr(btree, &path[level].bp_oldreq, dat); } *levelp = level; stats->bs_nblocks = 0; return ret; } static void nilfs_btree_commit_delete(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int maxlevel, struct inode *dat) { int level; for (level = NILFS_BTREE_LEVEL_NODE_MIN; level <= maxlevel; level++) { nilfs_bmap_commit_end_ptr(btree, &path[level].bp_oldreq, dat); path[level].bp_op(btree, path, level, NULL, NULL); } if (!nilfs_bmap_dirty(btree)) nilfs_bmap_set_dirty(btree); } static int nilfs_btree_delete(struct nilfs_bmap *btree, __u64 key) { struct nilfs_btree_path *path; struct nilfs_bmap_stats stats; struct inode *dat; int level, ret; path = nilfs_btree_alloc_path(); if (path == NULL) return -ENOMEM; ret = nilfs_btree_do_lookup(btree, path, key, NULL, NILFS_BTREE_LEVEL_NODE_MIN, 0); if (ret < 0) goto out; dat = NILFS_BMAP_USE_VBN(btree) ? nilfs_bmap_get_dat(btree) : NULL; ret = nilfs_btree_prepare_delete(btree, path, &level, &stats, dat); if (ret < 0) goto out; nilfs_btree_commit_delete(btree, path, level, dat); nilfs_inode_sub_blocks(btree->b_inode, stats.bs_nblocks); out: nilfs_btree_free_path(path); return ret; } static int nilfs_btree_seek_key(const struct nilfs_bmap *btree, __u64 start, __u64 *keyp) { struct nilfs_btree_path *path; const int minlevel = NILFS_BTREE_LEVEL_NODE_MIN; int ret; path = nilfs_btree_alloc_path(); if (!path) return -ENOMEM; ret = nilfs_btree_do_lookup(btree, path, start, NULL, minlevel, 0); if (!ret) *keyp = start; else if (ret == -ENOENT) ret = nilfs_btree_get_next_key(btree, path, minlevel, keyp); nilfs_btree_free_path(path); return ret; } static int nilfs_btree_last_key(const struct nilfs_bmap *btree, __u64 *keyp) { struct nilfs_btree_path *path; int ret; path = nilfs_btree_alloc_path(); if (path == NULL) return -ENOMEM; ret = nilfs_btree_do_lookup_last(btree, path, keyp, NULL); nilfs_btree_free_path(path); return ret; } static int nilfs_btree_check_delete(struct nilfs_bmap *btree, __u64 key) { struct buffer_head *bh; struct nilfs_btree_node *root, *node; __u64 maxkey, nextmaxkey; __u64 ptr; int nchildren, ret; root = nilfs_btree_get_root(btree); switch (nilfs_btree_height(btree)) { case 2: bh = NULL; node = root; break; case 3: nchildren = nilfs_btree_node_get_nchildren(root); if (nchildren > 1) return 0; ptr = nilfs_btree_node_get_ptr(root, nchildren - 1, NILFS_BTREE_ROOT_NCHILDREN_MAX); ret = nilfs_btree_get_block(btree, ptr, &bh); if (ret < 0) return ret; node = (struct nilfs_btree_node *)bh->b_data; break; default: return 0; } nchildren = nilfs_btree_node_get_nchildren(node); maxkey = nilfs_btree_node_get_key(node, nchildren - 1); nextmaxkey = (nchildren > 1) ? nilfs_btree_node_get_key(node, nchildren - 2) : 0; brelse(bh); return (maxkey == key) && (nextmaxkey < NILFS_BMAP_LARGE_LOW); } static int nilfs_btree_gather_data(struct nilfs_bmap *btree, __u64 *keys, __u64 *ptrs, int nitems) { struct buffer_head *bh; struct nilfs_btree_node *node, *root; __le64 *dkeys; __le64 *dptrs; __u64 ptr; int nchildren, ncmax, i, ret; root = nilfs_btree_get_root(btree); switch (nilfs_btree_height(btree)) { case 2: bh = NULL; node = root; ncmax = NILFS_BTREE_ROOT_NCHILDREN_MAX; break; case 3: nchildren = nilfs_btree_node_get_nchildren(root); WARN_ON(nchildren > 1); ptr = nilfs_btree_node_get_ptr(root, nchildren - 1, NILFS_BTREE_ROOT_NCHILDREN_MAX); ret = nilfs_btree_get_block(btree, ptr, &bh); if (ret < 0) return ret; node = (struct nilfs_btree_node *)bh->b_data; ncmax = nilfs_btree_nchildren_per_block(btree); break; default: node = NULL; return -EINVAL; } nchildren = nilfs_btree_node_get_nchildren(node); if (nchildren < nitems) nitems = nchildren; dkeys = nilfs_btree_node_dkeys(node); dptrs = nilfs_btree_node_dptrs(node, ncmax); for (i = 0; i < nitems; i++) { keys[i] = le64_to_cpu(dkeys[i]); ptrs[i] = le64_to_cpu(dptrs[i]); } brelse(bh); return nitems; } static int nilfs_btree_prepare_convert_and_insert(struct nilfs_bmap *btree, __u64 key, union nilfs_bmap_ptr_req *dreq, union nilfs_bmap_ptr_req *nreq, struct buffer_head **bhp, struct nilfs_bmap_stats *stats) { struct buffer_head *bh; struct inode *dat = NULL; int ret; stats->bs_nblocks = 0; /* for data */ /* cannot find near ptr */ if (NILFS_BMAP_USE_VBN(btree)) { dreq->bpr_ptr = nilfs_btree_find_target_v(btree, NULL, key); dat = nilfs_bmap_get_dat(btree); } ret = nilfs_attach_btree_node_cache(&NILFS_BMAP_I(btree)->vfs_inode); if (ret < 0) return ret; ret = nilfs_bmap_prepare_alloc_ptr(btree, dreq, dat); if (ret < 0) return ret; *bhp = NULL; stats->bs_nblocks++; if (nreq != NULL) { nreq->bpr_ptr = dreq->bpr_ptr + 1; ret = nilfs_bmap_prepare_alloc_ptr(btree, nreq, dat); if (ret < 0) goto err_out_dreq; ret = nilfs_btree_get_new_block(btree, nreq->bpr_ptr, &bh); if (ret < 0) goto err_out_nreq; *bhp = bh; stats->bs_nblocks++; } /* success */ return 0; /* error */ err_out_nreq: nilfs_bmap_abort_alloc_ptr(btree, nreq, dat); err_out_dreq: nilfs_bmap_abort_alloc_ptr(btree, dreq, dat); stats->bs_nblocks = 0; return ret; } static void nilfs_btree_commit_convert_and_insert(struct nilfs_bmap *btree, __u64 key, __u64 ptr, const __u64 *keys, const __u64 *ptrs, int n, union nilfs_bmap_ptr_req *dreq, union nilfs_bmap_ptr_req *nreq, struct buffer_head *bh) { struct nilfs_btree_node *node; struct inode *dat; __u64 tmpptr; int ncblk; /* free resources */ if (btree->b_ops->bop_clear != NULL) btree->b_ops->bop_clear(btree); /* ptr must be a pointer to a buffer head. */ set_buffer_nilfs_volatile((struct buffer_head *)((unsigned long)ptr)); /* convert and insert */ dat = NILFS_BMAP_USE_VBN(btree) ? nilfs_bmap_get_dat(btree) : NULL; __nilfs_btree_init(btree); if (nreq != NULL) { nilfs_bmap_commit_alloc_ptr(btree, dreq, dat); nilfs_bmap_commit_alloc_ptr(btree, nreq, dat); /* create child node at level 1 */ node = (struct nilfs_btree_node *)bh->b_data; ncblk = nilfs_btree_nchildren_per_block(btree); nilfs_btree_node_init(node, 0, 1, n, ncblk, keys, ptrs); nilfs_btree_node_insert(node, n, key, dreq->bpr_ptr, ncblk); if (!buffer_dirty(bh)) mark_buffer_dirty(bh); if (!nilfs_bmap_dirty(btree)) nilfs_bmap_set_dirty(btree); brelse(bh); /* create root node at level 2 */ node = nilfs_btree_get_root(btree); tmpptr = nreq->bpr_ptr; nilfs_btree_node_init(node, NILFS_BTREE_NODE_ROOT, 2, 1, NILFS_BTREE_ROOT_NCHILDREN_MAX, &keys[0], &tmpptr); } else { nilfs_bmap_commit_alloc_ptr(btree, dreq, dat); /* create root node at level 1 */ node = nilfs_btree_get_root(btree); nilfs_btree_node_init(node, NILFS_BTREE_NODE_ROOT, 1, n, NILFS_BTREE_ROOT_NCHILDREN_MAX, keys, ptrs); nilfs_btree_node_insert(node, n, key, dreq->bpr_ptr, NILFS_BTREE_ROOT_NCHILDREN_MAX); if (!nilfs_bmap_dirty(btree)) nilfs_bmap_set_dirty(btree); } if (NILFS_BMAP_USE_VBN(btree)) nilfs_bmap_set_target_v(btree, key, dreq->bpr_ptr); } /** * nilfs_btree_convert_and_insert - Convert and insert entries into a B-tree * @btree: NILFS B-tree structure * @key: Key of the new entry to be inserted * @ptr: Pointer (block number) associated with the key to be inserted * @keys: Array of keys to be inserted in addition to @key * @ptrs: Array of pointers associated with @keys * @n: Number of keys and pointers in @keys and @ptrs * * This function is used to insert a new entry specified by @key and @ptr, * along with additional entries specified by @keys and @ptrs arrays, into a * NILFS B-tree. * It prepares the necessary changes by allocating the required blocks and any * necessary intermediate nodes. It converts configurations from other forms of * block mapping (the one that currently exists is direct mapping) to a B-tree. * * Return: 0 on success or a negative error code on failure. */ int nilfs_btree_convert_and_insert(struct nilfs_bmap *btree, __u64 key, __u64 ptr, const __u64 *keys, const __u64 *ptrs, int n) { struct buffer_head *bh = NULL; union nilfs_bmap_ptr_req dreq, nreq, *di, *ni; struct nilfs_bmap_stats stats; int ret; if (n + 1 <= NILFS_BTREE_ROOT_NCHILDREN_MAX) { di = &dreq; ni = NULL; } else if ((n + 1) <= NILFS_BTREE_NODE_NCHILDREN_MAX( nilfs_btree_node_size(btree))) { di = &dreq; ni = &nreq; } else { di = NULL; ni = NULL; BUG(); } ret = nilfs_btree_prepare_convert_and_insert(btree, key, di, ni, &bh, &stats); if (ret < 0) return ret; nilfs_btree_commit_convert_and_insert(btree, key, ptr, keys, ptrs, n, di, ni, bh); nilfs_inode_add_blocks(btree->b_inode, stats.bs_nblocks); return 0; } static int nilfs_btree_propagate_p(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, struct buffer_head *bh) { while ((++level < nilfs_btree_height(btree) - 1) && !buffer_dirty(path[level].bp_bh)) mark_buffer_dirty(path[level].bp_bh); return 0; } static int nilfs_btree_prepare_update_v(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, struct inode *dat) { struct nilfs_btree_node *parent; int ncmax, ret; parent = nilfs_btree_get_node(btree, path, level + 1, &ncmax); path[level].bp_oldreq.bpr_ptr = nilfs_btree_node_get_ptr(parent, path[level + 1].bp_index, ncmax); path[level].bp_newreq.bpr_ptr = path[level].bp_oldreq.bpr_ptr + 1; ret = nilfs_dat_prepare_update(dat, &path[level].bp_oldreq.bpr_req, &path[level].bp_newreq.bpr_req); if (ret < 0) return ret; if (buffer_nilfs_node(path[level].bp_bh)) { path[level].bp_ctxt.oldkey = path[level].bp_oldreq.bpr_ptr; path[level].bp_ctxt.newkey = path[level].bp_newreq.bpr_ptr; path[level].bp_ctxt.bh = path[level].bp_bh; ret = nilfs_btnode_prepare_change_key( NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); if (ret < 0) { nilfs_dat_abort_update(dat, &path[level].bp_oldreq.bpr_req, &path[level].bp_newreq.bpr_req); return ret; } } return 0; } static void nilfs_btree_commit_update_v(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, struct inode *dat) { struct nilfs_btree_node *parent; int ncmax; nilfs_dat_commit_update(dat, &path[level].bp_oldreq.bpr_req, &path[level].bp_newreq.bpr_req, btree->b_ptr_type == NILFS_BMAP_PTR_VS); if (buffer_nilfs_node(path[level].bp_bh)) { nilfs_btnode_commit_change_key( NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); path[level].bp_bh = path[level].bp_ctxt.bh; } set_buffer_nilfs_volatile(path[level].bp_bh); parent = nilfs_btree_get_node(btree, path, level + 1, &ncmax); nilfs_btree_node_set_ptr(parent, path[level + 1].bp_index, path[level].bp_newreq.bpr_ptr, ncmax); } static void nilfs_btree_abort_update_v(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, struct inode *dat) { nilfs_dat_abort_update(dat, &path[level].bp_oldreq.bpr_req, &path[level].bp_newreq.bpr_req); if (buffer_nilfs_node(path[level].bp_bh)) nilfs_btnode_abort_change_key( NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); } static int nilfs_btree_prepare_propagate_v(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int minlevel, int *maxlevelp, struct inode *dat) { int level, ret; level = minlevel; if (!buffer_nilfs_volatile(path[level].bp_bh)) { ret = nilfs_btree_prepare_update_v(btree, path, level, dat); if (ret < 0) return ret; } while ((++level < nilfs_btree_height(btree) - 1) && !buffer_dirty(path[level].bp_bh)) { WARN_ON(buffer_nilfs_volatile(path[level].bp_bh)); ret = nilfs_btree_prepare_update_v(btree, path, level, dat); if (ret < 0) goto out; } /* success */ *maxlevelp = level - 1; return 0; /* error */ out: while (--level > minlevel) nilfs_btree_abort_update_v(btree, path, level, dat); if (!buffer_nilfs_volatile(path[level].bp_bh)) nilfs_btree_abort_update_v(btree, path, level, dat); return ret; } static void nilfs_btree_commit_propagate_v(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int minlevel, int maxlevel, struct buffer_head *bh, struct inode *dat) { int level; if (!buffer_nilfs_volatile(path[minlevel].bp_bh)) nilfs_btree_commit_update_v(btree, path, minlevel, dat); for (level = minlevel + 1; level <= maxlevel; level++) nilfs_btree_commit_update_v(btree, path, level, dat); } static int nilfs_btree_propagate_v(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, struct buffer_head *bh) { int maxlevel = 0, ret; struct nilfs_btree_node *parent; struct inode *dat = nilfs_bmap_get_dat(btree); __u64 ptr; int ncmax; get_bh(bh); path[level].bp_bh = bh; ret = nilfs_btree_prepare_propagate_v(btree, path, level, &maxlevel, dat); if (ret < 0) goto out; if (buffer_nilfs_volatile(path[level].bp_bh)) { parent = nilfs_btree_get_node(btree, path, level + 1, &ncmax); ptr = nilfs_btree_node_get_ptr(parent, path[level + 1].bp_index, ncmax); ret = nilfs_dat_mark_dirty(dat, ptr); if (ret < 0) goto out; } nilfs_btree_commit_propagate_v(btree, path, level, maxlevel, bh, dat); out: brelse(path[level].bp_bh); path[level].bp_bh = NULL; return ret; } static int nilfs_btree_propagate(struct nilfs_bmap *btree, struct buffer_head *bh) { struct nilfs_btree_path *path; struct nilfs_btree_node *node; __u64 key; int level, ret; WARN_ON(!buffer_dirty(bh)); path = nilfs_btree_alloc_path(); if (path == NULL) return -ENOMEM; if (buffer_nilfs_node(bh)) { node = (struct nilfs_btree_node *)bh->b_data; key = nilfs_btree_node_get_key(node, 0); level = nilfs_btree_node_get_level(node); } else { key = nilfs_bmap_data_get_key(btree, bh); level = NILFS_BTREE_LEVEL_DATA; } ret = nilfs_btree_do_lookup(btree, path, key, NULL, level + 1, 0); if (ret < 0) { if (unlikely(ret == -ENOENT)) nilfs_crit(btree->b_inode->i_sb, "writing node/leaf block does not appear in b-tree (ino=%lu) at key=%llu, level=%d", btree->b_inode->i_ino, (unsigned long long)key, level); goto out; } ret = NILFS_BMAP_USE_VBN(btree) ? nilfs_btree_propagate_v(btree, path, level, bh) : nilfs_btree_propagate_p(btree, path, level, bh); out: nilfs_btree_free_path(path); return ret; } static int nilfs_btree_propagate_gc(struct nilfs_bmap *btree, struct buffer_head *bh) { return nilfs_dat_mark_dirty(nilfs_bmap_get_dat(btree), bh->b_blocknr); } static void nilfs_btree_add_dirty_buffer(struct nilfs_bmap *btree, struct list_head *lists, struct buffer_head *bh) { struct list_head *head; struct buffer_head *cbh; struct nilfs_btree_node *node, *cnode; __u64 key, ckey; int level; get_bh(bh); node = (struct nilfs_btree_node *)bh->b_data; key = nilfs_btree_node_get_key(node, 0); level = nilfs_btree_node_get_level(node); if (level < NILFS_BTREE_LEVEL_NODE_MIN || level >= NILFS_BTREE_LEVEL_MAX) { dump_stack(); nilfs_warn(btree->b_inode->i_sb, "invalid btree level: %d (key=%llu, ino=%lu, blocknr=%llu)", level, (unsigned long long)key, btree->b_inode->i_ino, (unsigned long long)bh->b_blocknr); return; } list_for_each(head, &lists[level]) { cbh = list_entry(head, struct buffer_head, b_assoc_buffers); cnode = (struct nilfs_btree_node *)cbh->b_data; ckey = nilfs_btree_node_get_key(cnode, 0); if (key < ckey) break; } list_add_tail(&bh->b_assoc_buffers, head); } static void nilfs_btree_lookup_dirty_buffers(struct nilfs_bmap *btree, struct list_head *listp) { struct inode *btnc_inode = NILFS_BMAP_I(btree)->i_assoc_inode; struct address_space *btcache = btnc_inode->i_mapping; struct list_head lists[NILFS_BTREE_LEVEL_MAX]; struct folio_batch fbatch; struct buffer_head *bh, *head; pgoff_t index = 0; int level, i; for (level = NILFS_BTREE_LEVEL_NODE_MIN; level < NILFS_BTREE_LEVEL_MAX; level++) INIT_LIST_HEAD(&lists[level]); folio_batch_init(&fbatch); while (filemap_get_folios_tag(btcache, &index, (pgoff_t)-1, PAGECACHE_TAG_DIRTY, &fbatch)) { for (i = 0; i < folio_batch_count(&fbatch); i++) { bh = head = folio_buffers(fbatch.folios[i]); do { if (buffer_dirty(bh)) nilfs_btree_add_dirty_buffer(btree, lists, bh); } while ((bh = bh->b_this_page) != head); } folio_batch_release(&fbatch); cond_resched(); } for (level = NILFS_BTREE_LEVEL_NODE_MIN; level < NILFS_BTREE_LEVEL_MAX; level++) list_splice_tail(&lists[level], listp); } static int nilfs_btree_assign_p(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, struct buffer_head **bh, sector_t blocknr, union nilfs_binfo *binfo) { struct nilfs_btree_node *parent; __u64 key; __u64 ptr; int ncmax, ret; parent = nilfs_btree_get_node(btree, path, level + 1, &ncmax); ptr = nilfs_btree_node_get_ptr(parent, path[level + 1].bp_index, ncmax); if (buffer_nilfs_node(*bh)) { path[level].bp_ctxt.oldkey = ptr; path[level].bp_ctxt.newkey = blocknr; path[level].bp_ctxt.bh = *bh; ret = nilfs_btnode_prepare_change_key( NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); if (ret < 0) return ret; nilfs_btnode_commit_change_key( NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); *bh = path[level].bp_ctxt.bh; } nilfs_btree_node_set_ptr(parent, path[level + 1].bp_index, blocknr, ncmax); key = nilfs_btree_node_get_key(parent, path[level + 1].bp_index); /* on-disk format */ binfo->bi_dat.bi_blkoff = cpu_to_le64(key); binfo->bi_dat.bi_level = level; memset(binfo->bi_dat.bi_pad, 0, sizeof(binfo->bi_dat.bi_pad)); return 0; } static int nilfs_btree_assign_v(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, struct buffer_head **bh, sector_t blocknr, union nilfs_binfo *binfo) { struct nilfs_btree_node *parent; struct inode *dat = nilfs_bmap_get_dat(btree); __u64 key; __u64 ptr; union nilfs_bmap_ptr_req req; int ncmax, ret; parent = nilfs_btree_get_node(btree, path, level + 1, &ncmax); ptr = nilfs_btree_node_get_ptr(parent, path[level + 1].bp_index, ncmax); req.bpr_ptr = ptr; ret = nilfs_dat_prepare_start(dat, &req.bpr_req); if (ret < 0) return ret; nilfs_dat_commit_start(dat, &req.bpr_req, blocknr); key = nilfs_btree_node_get_key(parent, path[level + 1].bp_index); /* on-disk format */ binfo->bi_v.bi_vblocknr = cpu_to_le64(ptr); binfo->bi_v.bi_blkoff = cpu_to_le64(key); return 0; } static int nilfs_btree_assign(struct nilfs_bmap *btree, struct buffer_head **bh, sector_t blocknr, union nilfs_binfo *binfo) { struct nilfs_btree_path *path; struct nilfs_btree_node *node; __u64 key; int level, ret; path = nilfs_btree_alloc_path(); if (path == NULL) return -ENOMEM; if (buffer_nilfs_node(*bh)) { node = (struct nilfs_btree_node *)(*bh)->b_data; key = nilfs_btree_node_get_key(node, 0); level = nilfs_btree_node_get_level(node); } else { key = nilfs_bmap_data_get_key(btree, *bh); level = NILFS_BTREE_LEVEL_DATA; } ret = nilfs_btree_do_lookup(btree, path, key, NULL, level + 1, 0); if (ret < 0) { WARN_ON(ret == -ENOENT); goto out; } ret = NILFS_BMAP_USE_VBN(btree) ? nilfs_btree_assign_v(btree, path, level, bh, blocknr, binfo) : nilfs_btree_assign_p(btree, path, level, bh, blocknr, binfo); out: nilfs_btree_free_path(path); return ret; } static int nilfs_btree_assign_gc(struct nilfs_bmap *btree, struct buffer_head **bh, sector_t blocknr, union nilfs_binfo *binfo) { struct nilfs_btree_node *node; __u64 key; int ret; ret = nilfs_dat_move(nilfs_bmap_get_dat(btree), (*bh)->b_blocknr, blocknr); if (ret < 0) return ret; if (buffer_nilfs_node(*bh)) { node = (struct nilfs_btree_node *)(*bh)->b_data; key = nilfs_btree_node_get_key(node, 0); } else key = nilfs_bmap_data_get_key(btree, *bh); /* on-disk format */ binfo->bi_v.bi_vblocknr = cpu_to_le64((*bh)->b_blocknr); binfo->bi_v.bi_blkoff = cpu_to_le64(key); return 0; } static int nilfs_btree_mark(struct nilfs_bmap *btree, __u64 key, int level) { struct buffer_head *bh; struct nilfs_btree_path *path; __u64 ptr; int ret; path = nilfs_btree_alloc_path(); if (path == NULL) return -ENOMEM; ret = nilfs_btree_do_lookup(btree, path, key, &ptr, level + 1, 0); if (ret < 0) { WARN_ON(ret == -ENOENT); goto out; } ret = nilfs_btree_get_block(btree, ptr, &bh); if (ret < 0) { WARN_ON(ret == -ENOENT); goto out; } if (!buffer_dirty(bh)) mark_buffer_dirty(bh); brelse(bh); if (!nilfs_bmap_dirty(btree)) nilfs_bmap_set_dirty(btree); out: nilfs_btree_free_path(path); return ret; } static const struct nilfs_bmap_operations nilfs_btree_ops = { .bop_lookup = nilfs_btree_lookup, .bop_lookup_contig = nilfs_btree_lookup_contig, .bop_insert = nilfs_btree_insert, .bop_delete = nilfs_btree_delete, .bop_clear = NULL, .bop_propagate = nilfs_btree_propagate, .bop_lookup_dirty_buffers = nilfs_btree_lookup_dirty_buffers, .bop_assign = nilfs_btree_assign, .bop_mark = nilfs_btree_mark, .bop_seek_key = nilfs_btree_seek_key, .bop_last_key = nilfs_btree_last_key, .bop_check_insert = NULL, .bop_check_delete = nilfs_btree_check_delete, .bop_gather_data = nilfs_btree_gather_data, }; static const struct nilfs_bmap_operations nilfs_btree_ops_gc = { .bop_lookup = NULL, .bop_lookup_contig = NULL, .bop_insert = NULL, .bop_delete = NULL, .bop_clear = NULL, .bop_propagate = nilfs_btree_propagate_gc, .bop_lookup_dirty_buffers = nilfs_btree_lookup_dirty_buffers, .bop_assign = nilfs_btree_assign_gc, .bop_mark = NULL, .bop_seek_key = NULL, .bop_last_key = NULL, .bop_check_insert = NULL, .bop_check_delete = NULL, .bop_gather_data = NULL, }; static void __nilfs_btree_init(struct nilfs_bmap *bmap) { bmap->b_ops = &nilfs_btree_ops; bmap->b_nchildren_per_block = NILFS_BTREE_NODE_NCHILDREN_MAX(nilfs_btree_node_size(bmap)); } int nilfs_btree_init(struct nilfs_bmap *bmap) { int ret = 0; __nilfs_btree_init(bmap); if (nilfs_btree_root_broken(nilfs_btree_get_root(bmap), bmap->b_inode)) ret = -EIO; else ret = nilfs_attach_btree_node_cache( &NILFS_BMAP_I(bmap)->vfs_inode); return ret; } void nilfs_btree_init_gc(struct nilfs_bmap *bmap) { bmap->b_ops = &nilfs_btree_ops_gc; bmap->b_nchildren_per_block = NILFS_BTREE_NODE_NCHILDREN_MAX(nilfs_btree_node_size(bmap)); } |
| 4 4 2 2 2 2 3 1 3 1 4 3 1 9 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 | // SPDX-License-Identifier: GPL-2.0-or-later /* * inode.c - basic inode and dentry operations. * * Based on sysfs: * sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel * * configfs Copyright (C) 2005 Oracle. All rights reserved. * * Please see Documentation/filesystems/configfs.rst for more * information. */ #undef DEBUG #include <linux/pagemap.h> #include <linux/namei.h> #include <linux/backing-dev.h> #include <linux/capability.h> #include <linux/sched.h> #include <linux/lockdep.h> #include <linux/slab.h> #include <linux/configfs.h> #include "configfs_internal.h" #ifdef CONFIG_LOCKDEP static struct lock_class_key default_group_class[MAX_LOCK_DEPTH]; #endif static const struct inode_operations configfs_inode_operations ={ .setattr = configfs_setattr, }; int configfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { struct inode * inode = d_inode(dentry); struct configfs_dirent * sd = dentry->d_fsdata; struct iattr * sd_iattr; unsigned int ia_valid = iattr->ia_valid; int error; if (!sd) return -EINVAL; sd_iattr = sd->s_iattr; if (!sd_iattr) { /* setting attributes for the first time, allocate now */ sd_iattr = kzalloc(sizeof(struct iattr), GFP_KERNEL); if (!sd_iattr) return -ENOMEM; /* assign default attributes */ sd_iattr->ia_mode = sd->s_mode; sd_iattr->ia_uid = GLOBAL_ROOT_UID; sd_iattr->ia_gid = GLOBAL_ROOT_GID; sd_iattr->ia_atime = sd_iattr->ia_mtime = sd_iattr->ia_ctime = current_time(inode); sd->s_iattr = sd_iattr; } /* attributes were changed atleast once in past */ error = simple_setattr(idmap, dentry, iattr); if (error) return error; if (ia_valid & ATTR_UID) sd_iattr->ia_uid = iattr->ia_uid; if (ia_valid & ATTR_GID) sd_iattr->ia_gid = iattr->ia_gid; if (ia_valid & ATTR_ATIME) sd_iattr->ia_atime = iattr->ia_atime; if (ia_valid & ATTR_MTIME) sd_iattr->ia_mtime = iattr->ia_mtime; if (ia_valid & ATTR_CTIME) sd_iattr->ia_ctime = iattr->ia_ctime; if (ia_valid & ATTR_MODE) { umode_t mode = iattr->ia_mode; if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID)) mode &= ~S_ISGID; sd_iattr->ia_mode = sd->s_mode = mode; } return error; } static inline void set_default_inode_attr(struct inode * inode, umode_t mode) { inode->i_mode = mode; simple_inode_init_ts(inode); } static inline void set_inode_attr(struct inode * inode, struct iattr * iattr) { inode->i_mode = iattr->ia_mode; inode->i_uid = iattr->ia_uid; inode->i_gid = iattr->ia_gid; inode_set_atime_to_ts(inode, iattr->ia_atime); inode_set_mtime_to_ts(inode, iattr->ia_mtime); inode_set_ctime_to_ts(inode, iattr->ia_ctime); } struct inode *configfs_new_inode(umode_t mode, struct configfs_dirent *sd, struct super_block *s) { struct inode * inode = new_inode(s); if (inode) { inode->i_ino = get_next_ino(); inode->i_mapping->a_ops = &ram_aops; inode->i_op = &configfs_inode_operations; if (sd->s_iattr) { /* sysfs_dirent has non-default attributes * get them for the new inode from persistent copy * in sysfs_dirent */ set_inode_attr(inode, sd->s_iattr); } else set_default_inode_attr(inode, mode); } return inode; } #ifdef CONFIG_LOCKDEP static void configfs_set_inode_lock_class(struct configfs_dirent *sd, struct inode *inode) { int depth = sd->s_depth; if (depth > 0) { if (depth <= ARRAY_SIZE(default_group_class)) { lockdep_set_class(&inode->i_rwsem, &default_group_class[depth - 1]); } else { /* * In practice the maximum level of locking depth is * already reached. Just inform about possible reasons. */ pr_info("Too many levels of inodes for the locking correctness validator.\n"); pr_info("Spurious warnings may appear.\n"); } } } #else /* CONFIG_LOCKDEP */ static void configfs_set_inode_lock_class(struct configfs_dirent *sd, struct inode *inode) { } #endif /* CONFIG_LOCKDEP */ struct inode *configfs_create(struct dentry *dentry, umode_t mode) { struct inode *inode = NULL; struct configfs_dirent *sd; struct inode *p_inode; if (!dentry) return ERR_PTR(-ENOENT); if (d_really_is_positive(dentry)) return ERR_PTR(-EEXIST); sd = dentry->d_fsdata; inode = configfs_new_inode(mode, sd, dentry->d_sb); if (!inode) return ERR_PTR(-ENOMEM); p_inode = d_inode(dentry->d_parent); inode_set_mtime_to_ts(p_inode, inode_set_ctime_current(p_inode)); configfs_set_inode_lock_class(sd, inode); return inode; } /* * Get the name for corresponding element represented by the given configfs_dirent */ const unsigned char * configfs_get_name(struct configfs_dirent *sd) { struct configfs_attribute *attr; BUG_ON(!sd || !sd->s_element); /* These always have a dentry, so use that */ if (sd->s_type & (CONFIGFS_DIR | CONFIGFS_ITEM_LINK)) return sd->s_dentry->d_name.name; if (sd->s_type & (CONFIGFS_ITEM_ATTR | CONFIGFS_ITEM_BIN_ATTR)) { attr = sd->s_element; return attr->ca_name; } return NULL; } /* * Unhashes the dentry corresponding to given configfs_dirent * Called with parent inode's i_mutex held. */ void configfs_drop_dentry(struct configfs_dirent * sd, struct dentry * parent) { struct dentry * dentry = sd->s_dentry; if (dentry) { spin_lock(&dentry->d_lock); if (simple_positive(dentry)) { dget_dlock(dentry); __d_drop(dentry); spin_unlock(&dentry->d_lock); simple_unlink(d_inode(parent), dentry); } else spin_unlock(&dentry->d_lock); } } void configfs_hash_and_remove(struct dentry * dir, const char * name) { struct configfs_dirent * sd; struct configfs_dirent * parent_sd = dir->d_fsdata; if (d_really_is_negative(dir)) /* no inode means this hasn't been made visible yet */ return; inode_lock(d_inode(dir)); list_for_each_entry(sd, &parent_sd->s_children, s_sibling) { if (!sd->s_element) continue; if (!strcmp(configfs_get_name(sd), name)) { spin_lock(&configfs_dirent_lock); list_del_init(&sd->s_sibling); spin_unlock(&configfs_dirent_lock); configfs_drop_dentry(sd, dir); configfs_put(sd); break; } } inode_unlock(d_inode(dir)); } |
| 6 6 1 6 6 5 6 6 5 1 6 6 6 6 6 13 13 7 7 7 4 4 4 4 6 6 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2002,2005 Silicon Graphics, Inc. * All Rights Reserved. */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_inode.h" #include "xfs_btree.h" #include "xfs_ialloc.h" #include "xfs_ialloc_btree.h" #include "xfs_iwalk.h" #include "xfs_itable.h" #include "xfs_error.h" #include "xfs_icache.h" #include "xfs_health.h" #include "xfs_trans.h" /* * Bulk Stat * ========= * * Use the inode walking functions to fill out struct xfs_bulkstat for every * allocated inode, then pass the stat information to some externally provided * iteration function. */ struct xfs_bstat_chunk { bulkstat_one_fmt_pf formatter; struct xfs_ibulk *breq; struct xfs_bulkstat *buf; }; /* * Fill out the bulkstat info for a single inode and report it somewhere. * * bc->breq->lastino is effectively the inode cursor as we walk through the * filesystem. Therefore, we update it any time we need to move the cursor * forward, regardless of whether or not we're sending any bstat information * back to userspace. If the inode is internal metadata or, has been freed * out from under us, we just simply keep going. * * However, if any other type of error happens we want to stop right where we * are so that userspace will call back with exact number of the bad inode and * we can send back an error code. * * Note that if the formatter tells us there's no space left in the buffer we * move the cursor forward and abort the walk. */ STATIC int xfs_bulkstat_one_int( struct xfs_mount *mp, struct mnt_idmap *idmap, struct xfs_trans *tp, xfs_ino_t ino, struct xfs_bstat_chunk *bc) { struct user_namespace *sb_userns = mp->m_super->s_user_ns; struct xfs_inode *ip; /* incore inode pointer */ struct inode *inode; struct xfs_bulkstat *buf = bc->buf; xfs_extnum_t nextents; int error = -EINVAL; vfsuid_t vfsuid; vfsgid_t vfsgid; if (xfs_internal_inum(mp, ino)) goto out_advance; error = xfs_iget(mp, tp, ino, (XFS_IGET_DONTCACHE | XFS_IGET_UNTRUSTED), XFS_ILOCK_SHARED, &ip); if (error == -ENOENT || error == -EINVAL) goto out_advance; if (error) goto out; /* Reload the incore unlinked list to avoid failure in inodegc. */ if (xfs_inode_unlinked_incomplete(ip)) { error = xfs_inode_reload_unlinked_bucket(tp, ip); if (error) { xfs_iunlock(ip, XFS_ILOCK_SHARED); xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); xfs_irele(ip); return error; } } ASSERT(ip != NULL); ASSERT(ip->i_imap.im_blkno != 0); inode = VFS_I(ip); vfsuid = i_uid_into_vfsuid(idmap, inode); vfsgid = i_gid_into_vfsgid(idmap, inode); /* If this is a private inode, don't leak its details to userspace. */ if (IS_PRIVATE(inode)) { xfs_iunlock(ip, XFS_ILOCK_SHARED); xfs_irele(ip); error = -EINVAL; goto out_advance; } /* xfs_iget returns the following without needing * further change. */ buf->bs_projectid = ip->i_projid; buf->bs_ino = ino; buf->bs_uid = from_kuid(sb_userns, vfsuid_into_kuid(vfsuid)); buf->bs_gid = from_kgid(sb_userns, vfsgid_into_kgid(vfsgid)); buf->bs_size = ip->i_disk_size; buf->bs_nlink = inode->i_nlink; buf->bs_atime = inode_get_atime_sec(inode); buf->bs_atime_nsec = inode_get_atime_nsec(inode); buf->bs_mtime = inode_get_mtime_sec(inode); buf->bs_mtime_nsec = inode_get_mtime_nsec(inode); buf->bs_ctime = inode_get_ctime_sec(inode); buf->bs_ctime_nsec = inode_get_ctime_nsec(inode); buf->bs_gen = inode->i_generation; buf->bs_mode = inode->i_mode; buf->bs_xflags = xfs_ip2xflags(ip); buf->bs_extsize_blks = ip->i_extsize; nextents = xfs_ifork_nextents(&ip->i_df); if (!(bc->breq->flags & XFS_IBULK_NREXT64)) buf->bs_extents = min(nextents, XFS_MAX_EXTCNT_DATA_FORK_SMALL); else buf->bs_extents64 = nextents; xfs_bulkstat_health(ip, buf); buf->bs_aextents = xfs_ifork_nextents(&ip->i_af); buf->bs_forkoff = xfs_inode_fork_boff(ip); buf->bs_version = XFS_BULKSTAT_VERSION_V5; if (xfs_has_v3inodes(mp)) { buf->bs_btime = ip->i_crtime.tv_sec; buf->bs_btime_nsec = ip->i_crtime.tv_nsec; if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) buf->bs_cowextsize_blks = ip->i_cowextsize; } switch (ip->i_df.if_format) { case XFS_DINODE_FMT_DEV: buf->bs_rdev = sysv_encode_dev(inode->i_rdev); buf->bs_blksize = BLKDEV_IOSIZE; buf->bs_blocks = 0; break; case XFS_DINODE_FMT_LOCAL: buf->bs_rdev = 0; buf->bs_blksize = mp->m_sb.sb_blocksize; buf->bs_blocks = 0; break; case XFS_DINODE_FMT_EXTENTS: case XFS_DINODE_FMT_BTREE: buf->bs_rdev = 0; buf->bs_blksize = mp->m_sb.sb_blocksize; buf->bs_blocks = ip->i_nblocks + ip->i_delayed_blks; break; } xfs_iunlock(ip, XFS_ILOCK_SHARED); xfs_irele(ip); error = bc->formatter(bc->breq, buf); if (error == -ECANCELED) goto out_advance; if (error) goto out; out_advance: /* * Advance the cursor to the inode that comes after the one we just * looked at. We want the caller to move along if the bulkstat * information was copied successfully; if we tried to grab the inode * but it's no longer allocated; or if it's internal metadata. */ bc->breq->startino = ino + 1; out: return error; } /* Bulkstat a single inode. */ int xfs_bulkstat_one( struct xfs_ibulk *breq, bulkstat_one_fmt_pf formatter) { struct xfs_bstat_chunk bc = { .formatter = formatter, .breq = breq, }; struct xfs_trans *tp; int error; if (breq->idmap != &nop_mnt_idmap) { xfs_warn_ratelimited(breq->mp, "bulkstat not supported inside of idmapped mounts."); return -EINVAL; } ASSERT(breq->icount == 1); bc.buf = kzalloc(sizeof(struct xfs_bulkstat), GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!bc.buf) return -ENOMEM; /* * Grab an empty transaction so that we can use its recursive buffer * locking abilities to detect cycles in the inobt without deadlocking. */ error = xfs_trans_alloc_empty(breq->mp, &tp); if (error) goto out; error = xfs_bulkstat_one_int(breq->mp, breq->idmap, tp, breq->startino, &bc); xfs_trans_cancel(tp); out: kfree(bc.buf); /* * If we reported one inode to userspace then we abort because we hit * the end of the buffer. Don't leak that back to userspace. */ if (error == -ECANCELED) error = 0; return error; } static int xfs_bulkstat_iwalk( struct xfs_mount *mp, struct xfs_trans *tp, xfs_ino_t ino, void *data) { struct xfs_bstat_chunk *bc = data; int error; error = xfs_bulkstat_one_int(mp, bc->breq->idmap, tp, ino, data); /* bulkstat just skips over missing inodes */ if (error == -ENOENT || error == -EINVAL) return 0; return error; } /* * Check the incoming lastino parameter. * * We allow any inode value that could map to physical space inside the * filesystem because if there are no inodes there, bulkstat moves on to the * next chunk. In other words, the magic agino value of zero takes us to the * first chunk in the AG, and an agino value past the end of the AG takes us to * the first chunk in the next AG. * * Therefore we can end early if the requested inode is beyond the end of the * filesystem or doesn't map properly. */ static inline bool xfs_bulkstat_already_done( struct xfs_mount *mp, xfs_ino_t startino) { xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, startino); xfs_agino_t agino = XFS_INO_TO_AGINO(mp, startino); return agno >= mp->m_sb.sb_agcount || startino != XFS_AGINO_TO_INO(mp, agno, agino); } /* Return stat information in bulk (by-inode) for the filesystem. */ int xfs_bulkstat( struct xfs_ibulk *breq, bulkstat_one_fmt_pf formatter) { struct xfs_bstat_chunk bc = { .formatter = formatter, .breq = breq, }; struct xfs_trans *tp; unsigned int iwalk_flags = 0; int error; if (breq->idmap != &nop_mnt_idmap) { xfs_warn_ratelimited(breq->mp, "bulkstat not supported inside of idmapped mounts."); return -EINVAL; } if (xfs_bulkstat_already_done(breq->mp, breq->startino)) return 0; bc.buf = kzalloc(sizeof(struct xfs_bulkstat), GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!bc.buf) return -ENOMEM; /* * Grab an empty transaction so that we can use its recursive buffer * locking abilities to detect cycles in the inobt without deadlocking. */ error = xfs_trans_alloc_empty(breq->mp, &tp); if (error) goto out; if (breq->flags & XFS_IBULK_SAME_AG) iwalk_flags |= XFS_IWALK_SAME_AG; error = xfs_iwalk(breq->mp, tp, breq->startino, iwalk_flags, xfs_bulkstat_iwalk, breq->icount, &bc); xfs_trans_cancel(tp); out: kfree(bc.buf); /* * We found some inodes, so clear the error status and return them. * The lastino pointer will point directly at the inode that triggered * any error that occurred, so on the next call the error will be * triggered again and propagated to userspace as there will be no * formatted inodes in the buffer. */ if (breq->ocount > 0) error = 0; return error; } /* Convert bulkstat (v5) to bstat (v1). */ void xfs_bulkstat_to_bstat( struct xfs_mount *mp, struct xfs_bstat *bs1, const struct xfs_bulkstat *bstat) { /* memset is needed here because of padding holes in the structure. */ memset(bs1, 0, sizeof(struct xfs_bstat)); bs1->bs_ino = bstat->bs_ino; bs1->bs_mode = bstat->bs_mode; bs1->bs_nlink = bstat->bs_nlink; bs1->bs_uid = bstat->bs_uid; bs1->bs_gid = bstat->bs_gid; bs1->bs_rdev = bstat->bs_rdev; bs1->bs_blksize = bstat->bs_blksize; bs1->bs_size = bstat->bs_size; bs1->bs_atime.tv_sec = bstat->bs_atime; bs1->bs_mtime.tv_sec = bstat->bs_mtime; bs1->bs_ctime.tv_sec = bstat->bs_ctime; bs1->bs_atime.tv_nsec = bstat->bs_atime_nsec; bs1->bs_mtime.tv_nsec = bstat->bs_mtime_nsec; bs1->bs_ctime.tv_nsec = bstat->bs_ctime_nsec; bs1->bs_blocks = bstat->bs_blocks; bs1->bs_xflags = bstat->bs_xflags; bs1->bs_extsize = XFS_FSB_TO_B(mp, bstat->bs_extsize_blks); bs1->bs_extents = bstat->bs_extents; bs1->bs_gen = bstat->bs_gen; bs1->bs_projid_lo = bstat->bs_projectid & 0xFFFF; bs1->bs_forkoff = bstat->bs_forkoff; bs1->bs_projid_hi = bstat->bs_projectid >> 16; bs1->bs_sick = bstat->bs_sick; bs1->bs_checked = bstat->bs_checked; bs1->bs_cowextsize = XFS_FSB_TO_B(mp, bstat->bs_cowextsize_blks); bs1->bs_dmevmask = 0; bs1->bs_dmstate = 0; bs1->bs_aextents = bstat->bs_aextents; } struct xfs_inumbers_chunk { inumbers_fmt_pf formatter; struct xfs_ibulk *breq; }; /* * INUMBERS * ======== * This is how we export inode btree records to userspace, so that XFS tools * can figure out where inodes are allocated. */ /* * Format the inode group structure and report it somewhere. * * Similar to xfs_bulkstat_one_int, lastino is the inode cursor as we walk * through the filesystem so we move it forward unless there was a runtime * error. If the formatter tells us the buffer is now full we also move the * cursor forward and abort the walk. */ STATIC int xfs_inumbers_walk( struct xfs_mount *mp, struct xfs_trans *tp, xfs_agnumber_t agno, const struct xfs_inobt_rec_incore *irec, void *data) { struct xfs_inumbers inogrp = { .xi_startino = XFS_AGINO_TO_INO(mp, agno, irec->ir_startino), .xi_alloccount = irec->ir_count - irec->ir_freecount, .xi_allocmask = ~irec->ir_free, .xi_version = XFS_INUMBERS_VERSION_V5, }; struct xfs_inumbers_chunk *ic = data; int error; error = ic->formatter(ic->breq, &inogrp); if (error && error != -ECANCELED) return error; ic->breq->startino = XFS_AGINO_TO_INO(mp, agno, irec->ir_startino) + XFS_INODES_PER_CHUNK; return error; } /* * Return inode number table for the filesystem. */ int xfs_inumbers( struct xfs_ibulk *breq, inumbers_fmt_pf formatter) { struct xfs_inumbers_chunk ic = { .formatter = formatter, .breq = breq, }; struct xfs_trans *tp; int error = 0; if (xfs_bulkstat_already_done(breq->mp, breq->startino)) return 0; /* * Grab an empty transaction so that we can use its recursive buffer * locking abilities to detect cycles in the inobt without deadlocking. */ error = xfs_trans_alloc_empty(breq->mp, &tp); if (error) goto out; error = xfs_inobt_walk(breq->mp, tp, breq->startino, breq->flags, xfs_inumbers_walk, breq->icount, &ic); xfs_trans_cancel(tp); out: /* * We found some inode groups, so clear the error status and return * them. The lastino pointer will point directly at the inode that * triggered any error that occurred, so on the next call the error * will be triggered again and propagated to userspace as there will be * no formatted inode groups in the buffer. */ if (breq->ocount > 0) error = 0; return error; } /* Convert an inumbers (v5) struct to a inogrp (v1) struct. */ void xfs_inumbers_to_inogrp( struct xfs_inogrp *ig1, const struct xfs_inumbers *ig) { /* memset is needed here because of padding holes in the structure. */ memset(ig1, 0, sizeof(struct xfs_inogrp)); ig1->xi_startino = ig->xi_startino; ig1->xi_alloccount = ig->xi_alloccount; ig1->xi_allocmask = ig->xi_allocmask; } |
| 2590 997 943 55 133 935 999 5 944 5 9 2595 1 53 5 5 4 945 2 2 995 942 942 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Definitions for the 'struct sk_buff' memory handlers. * * Authors: * Alan Cox, <gw4pts@gw4pts.ampr.org> * Florian La Roche, <rzsfl@rz.uni-sb.de> */ #ifndef _LINUX_SKBUFF_H #define _LINUX_SKBUFF_H #include <linux/kernel.h> #include <linux/compiler.h> #include <linux/time.h> #include <linux/bug.h> #include <linux/bvec.h> #include <linux/cache.h> #include <linux/rbtree.h> #include <linux/socket.h> #include <linux/refcount.h> #include <linux/atomic.h> #include <asm/types.h> #include <linux/spinlock.h> #include <net/checksum.h> #include <linux/rcupdate.h> #include <linux/dma-mapping.h> #include <linux/netdev_features.h> #include <net/flow_dissector.h> #include <linux/in6.h> #include <linux/if_packet.h> #include <linux/llist.h> #include <net/flow.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <linux/netfilter/nf_conntrack_common.h> #endif #include <net/net_debug.h> #include <net/dropreason-core.h> #include <net/netmem.h> /** * DOC: skb checksums * * The interface for checksum offload between the stack and networking drivers * is as follows... * * IP checksum related features * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * Drivers advertise checksum offload capabilities in the features of a device. * From the stack's point of view these are capabilities offered by the driver. * A driver typically only advertises features that it is capable of offloading * to its device. * * .. flat-table:: Checksum related device features * :widths: 1 10 * * * - %NETIF_F_HW_CSUM * - The driver (or its device) is able to compute one * IP (one's complement) checksum for any combination * of protocols or protocol layering. The checksum is * computed and set in a packet per the CHECKSUM_PARTIAL * interface (see below). * * * - %NETIF_F_IP_CSUM * - Driver (device) is only able to checksum plain * TCP or UDP packets over IPv4. These are specifically * unencapsulated packets of the form IPv4|TCP or * IPv4|UDP where the Protocol field in the IPv4 header * is TCP or UDP. The IPv4 header may contain IP options. * This feature cannot be set in features for a device * with NETIF_F_HW_CSUM also set. This feature is being * DEPRECATED (see below). * * * - %NETIF_F_IPV6_CSUM * - Driver (device) is only able to checksum plain * TCP or UDP packets over IPv6. These are specifically * unencapsulated packets of the form IPv6|TCP or * IPv6|UDP where the Next Header field in the IPv6 * header is either TCP or UDP. IPv6 extension headers * are not supported with this feature. This feature * cannot be set in features for a device with * NETIF_F_HW_CSUM also set. This feature is being * DEPRECATED (see below). * * * - %NETIF_F_RXCSUM * - Driver (device) performs receive checksum offload. * This flag is only used to disable the RX checksum * feature for a device. The stack will accept receive * checksum indication in packets received on a device * regardless of whether NETIF_F_RXCSUM is set. * * Checksumming of received packets by device * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * Indication of checksum verification is set in &sk_buff.ip_summed. * Possible values are: * * - %CHECKSUM_NONE * * Device did not checksum this packet e.g. due to lack of capabilities. * The packet contains full (though not verified) checksum in packet but * not in skb->csum. Thus, skb->csum is undefined in this case. * * - %CHECKSUM_UNNECESSARY * * The hardware you're dealing with doesn't calculate the full checksum * (as in %CHECKSUM_COMPLETE), but it does parse headers and verify checksums * for specific protocols. For such packets it will set %CHECKSUM_UNNECESSARY * if their checksums are okay. &sk_buff.csum is still undefined in this case * though. A driver or device must never modify the checksum field in the * packet even if checksum is verified. * * %CHECKSUM_UNNECESSARY is applicable to following protocols: * * - TCP: IPv6 and IPv4. * - UDP: IPv4 and IPv6. A device may apply CHECKSUM_UNNECESSARY to a * zero UDP checksum for either IPv4 or IPv6, the networking stack * may perform further validation in this case. * - GRE: only if the checksum is present in the header. * - SCTP: indicates the CRC in SCTP header has been validated. * - FCOE: indicates the CRC in FC frame has been validated. * * &sk_buff.csum_level indicates the number of consecutive checksums found in * the packet minus one that have been verified as %CHECKSUM_UNNECESSARY. * For instance if a device receives an IPv6->UDP->GRE->IPv4->TCP packet * and a device is able to verify the checksums for UDP (possibly zero), * GRE (checksum flag is set) and TCP, &sk_buff.csum_level would be set to * two. If the device were only able to verify the UDP checksum and not * GRE, either because it doesn't support GRE checksum or because GRE * checksum is bad, skb->csum_level would be set to zero (TCP checksum is * not considered in this case). * * - %CHECKSUM_COMPLETE * * This is the most generic way. The device supplied checksum of the _whole_ * packet as seen by netif_rx() and fills in &sk_buff.csum. This means the * hardware doesn't need to parse L3/L4 headers to implement this. * * Notes: * * - Even if device supports only some protocols, but is able to produce * skb->csum, it MUST use CHECKSUM_COMPLETE, not CHECKSUM_UNNECESSARY. * - CHECKSUM_COMPLETE is not applicable to SCTP and FCoE protocols. * * - %CHECKSUM_PARTIAL * * A checksum is set up to be offloaded to a device as described in the * output description for CHECKSUM_PARTIAL. This may occur on a packet * received directly from another Linux OS, e.g., a virtualized Linux kernel * on the same host, or it may be set in the input path in GRO or remote * checksum offload. For the purposes of checksum verification, the checksum * referred to by skb->csum_start + skb->csum_offset and any preceding * checksums in the packet are considered verified. Any checksums in the * packet that are after the checksum being offloaded are not considered to * be verified. * * Checksumming on transmit for non-GSO * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * The stack requests checksum offload in the &sk_buff.ip_summed for a packet. * Values are: * * - %CHECKSUM_PARTIAL * * The driver is required to checksum the packet as seen by hard_start_xmit() * from &sk_buff.csum_start up to the end, and to record/write the checksum at * offset &sk_buff.csum_start + &sk_buff.csum_offset. * A driver may verify that the * csum_start and csum_offset values are valid values given the length and * offset of the packet, but it should not attempt to validate that the * checksum refers to a legitimate transport layer checksum -- it is the * purview of the stack to validate that csum_start and csum_offset are set * correctly. * * When the stack requests checksum offload for a packet, the driver MUST * ensure that the checksum is set correctly. A driver can either offload the * checksum calculation to the device, or call skb_checksum_help (in the case * that the device does not support offload for a particular checksum). * * %NETIF_F_IP_CSUM and %NETIF_F_IPV6_CSUM are being deprecated in favor of * %NETIF_F_HW_CSUM. New devices should use %NETIF_F_HW_CSUM to indicate * checksum offload capability. * skb_csum_hwoffload_help() can be called to resolve %CHECKSUM_PARTIAL based * on network device checksumming capabilities: if a packet does not match * them, skb_checksum_help() or skb_crc32c_help() (depending on the value of * &sk_buff.csum_not_inet, see :ref:`crc`) * is called to resolve the checksum. * * - %CHECKSUM_NONE * * The skb was already checksummed by the protocol, or a checksum is not * required. * * - %CHECKSUM_UNNECESSARY * * This has the same meaning as CHECKSUM_NONE for checksum offload on * output. * * - %CHECKSUM_COMPLETE * * Not used in checksum output. If a driver observes a packet with this value * set in skbuff, it should treat the packet as if %CHECKSUM_NONE were set. * * .. _crc: * * Non-IP checksum (CRC) offloads * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * .. flat-table:: * :widths: 1 10 * * * - %NETIF_F_SCTP_CRC * - This feature indicates that a device is capable of * offloading the SCTP CRC in a packet. To perform this offload the stack * will set csum_start and csum_offset accordingly, set ip_summed to * %CHECKSUM_PARTIAL and set csum_not_inet to 1, to provide an indication * in the skbuff that the %CHECKSUM_PARTIAL refers to CRC32c. * A driver that supports both IP checksum offload and SCTP CRC32c offload * must verify which offload is configured for a packet by testing the * value of &sk_buff.csum_not_inet; skb_crc32c_csum_help() is provided to * resolve %CHECKSUM_PARTIAL on skbs where csum_not_inet is set to 1. * * * - %NETIF_F_FCOE_CRC * - This feature indicates that a device is capable of offloading the FCOE * CRC in a packet. To perform this offload the stack will set ip_summed * to %CHECKSUM_PARTIAL and set csum_start and csum_offset * accordingly. Note that there is no indication in the skbuff that the * %CHECKSUM_PARTIAL refers to an FCOE checksum, so a driver that supports * both IP checksum offload and FCOE CRC offload must verify which offload * is configured for a packet, presumably by inspecting packet headers. * * Checksumming on output with GSO * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * In the case of a GSO packet (skb_is_gso() is true), checksum offload * is implied by the SKB_GSO_* flags in gso_type. Most obviously, if the * gso_type is %SKB_GSO_TCPV4 or %SKB_GSO_TCPV6, TCP checksum offload as * part of the GSO operation is implied. If a checksum is being offloaded * with GSO then ip_summed is %CHECKSUM_PARTIAL, and both csum_start and * csum_offset are set to refer to the outermost checksum being offloaded * (two offloaded checksums are possible with UDP encapsulation). */ /* Don't change this without changing skb_csum_unnecessary! */ #define CHECKSUM_NONE 0 #define CHECKSUM_UNNECESSARY 1 #define CHECKSUM_COMPLETE 2 #define CHECKSUM_PARTIAL 3 /* Maximum value in skb->csum_level */ #define SKB_MAX_CSUM_LEVEL 3 #define SKB_DATA_ALIGN(X) ALIGN(X, SMP_CACHE_BYTES) #define SKB_WITH_OVERHEAD(X) \ ((X) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) /* For X bytes available in skb->head, what is the minimal * allocation needed, knowing struct skb_shared_info needs * to be aligned. */ #define SKB_HEAD_ALIGN(X) (SKB_DATA_ALIGN(X) + \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) #define SKB_MAX_ORDER(X, ORDER) \ SKB_WITH_OVERHEAD((PAGE_SIZE << (ORDER)) - (X)) #define SKB_MAX_HEAD(X) (SKB_MAX_ORDER((X), 0)) #define SKB_MAX_ALLOC (SKB_MAX_ORDER(0, 2)) /* return minimum truesize of one skb containing X bytes of data */ #define SKB_TRUESIZE(X) ((X) + \ SKB_DATA_ALIGN(sizeof(struct sk_buff)) + \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) struct ahash_request; struct net_device; struct scatterlist; struct pipe_inode_info; struct iov_iter; struct napi_struct; struct bpf_prog; union bpf_attr; struct skb_ext; struct ts_config; #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) struct nf_bridge_info { enum { BRNF_PROTO_UNCHANGED, BRNF_PROTO_8021Q, BRNF_PROTO_PPPOE } orig_proto:8; u8 pkt_otherhost:1; u8 in_prerouting:1; u8 bridged_dnat:1; u8 sabotage_in_done:1; __u16 frag_max_size; int physinif; /* always valid & non-NULL from FORWARD on, for physdev match */ struct net_device *physoutdev; union { /* prerouting: detect dnat in orig/reply direction */ __be32 ipv4_daddr; struct in6_addr ipv6_daddr; /* after prerouting + nat detected: store original source * mac since neigh resolution overwrites it, only used while * skb is out in neigh layer. */ char neigh_header[8]; }; }; #endif #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) /* Chain in tc_skb_ext will be used to share the tc chain with * ovs recirc_id. It will be set to the current chain by tc * and read by ovs to recirc_id. */ struct tc_skb_ext { union { u64 act_miss_cookie; __u32 chain; }; __u16 mru; __u16 zone; u8 post_ct:1; u8 post_ct_snat:1; u8 post_ct_dnat:1; u8 act_miss:1; /* Set if act_miss_cookie is used */ u8 l2_miss:1; /* Set by bridge upon FDB or MDB miss */ }; #endif struct sk_buff_head { /* These two members must be first to match sk_buff. */ struct_group_tagged(sk_buff_list, list, struct sk_buff *next; struct sk_buff *prev; ); __u32 qlen; spinlock_t lock; }; struct sk_buff; #ifndef CONFIG_MAX_SKB_FRAGS # define CONFIG_MAX_SKB_FRAGS 17 #endif #define MAX_SKB_FRAGS CONFIG_MAX_SKB_FRAGS /* Set skb_shinfo(skb)->gso_size to this in case you want skb_segment to * segment using its current segmentation instead. */ #define GSO_BY_FRAGS 0xFFFF typedef struct skb_frag { netmem_ref netmem; unsigned int len; unsigned int offset; } skb_frag_t; /** * skb_frag_size() - Returns the size of a skb fragment * @frag: skb fragment */ static inline unsigned int skb_frag_size(const skb_frag_t *frag) { return frag->len; } /** * skb_frag_size_set() - Sets the size of a skb fragment * @frag: skb fragment * @size: size of fragment */ static inline void skb_frag_size_set(skb_frag_t *frag, unsigned int size) { frag->len = size; } /** * skb_frag_size_add() - Increments the size of a skb fragment by @delta * @frag: skb fragment * @delta: value to add */ static inline void skb_frag_size_add(skb_frag_t *frag, int delta) { frag->len += delta; } /** * skb_frag_size_sub() - Decrements the size of a skb fragment by @delta * @frag: skb fragment * @delta: value to subtract */ static inline void skb_frag_size_sub(skb_frag_t *frag, int delta) { frag->len -= delta; } /** * skb_frag_must_loop - Test if %p is a high memory page * @p: fragment's page */ static inline bool skb_frag_must_loop(struct page *p) { #if defined(CONFIG_HIGHMEM) if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP) || PageHighMem(p)) return true; #endif return false; } /** * skb_frag_foreach_page - loop over pages in a fragment * * @f: skb frag to operate on * @f_off: offset from start of f->netmem * @f_len: length from f_off to loop over * @p: (temp var) current page * @p_off: (temp var) offset from start of current page, * non-zero only on first page. * @p_len: (temp var) length in current page, * < PAGE_SIZE only on first and last page. * @copied: (temp var) length so far, excluding current p_len. * * A fragment can hold a compound page, in which case per-page * operations, notably kmap_atomic, must be called for each * regular page. */ #define skb_frag_foreach_page(f, f_off, f_len, p, p_off, p_len, copied) \ for (p = skb_frag_page(f) + ((f_off) >> PAGE_SHIFT), \ p_off = (f_off) & (PAGE_SIZE - 1), \ p_len = skb_frag_must_loop(p) ? \ min_t(u32, f_len, PAGE_SIZE - p_off) : f_len, \ copied = 0; \ copied < f_len; \ copied += p_len, p++, p_off = 0, \ p_len = min_t(u32, f_len - copied, PAGE_SIZE)) \ /** * struct skb_shared_hwtstamps - hardware time stamps * @hwtstamp: hardware time stamp transformed into duration * since arbitrary point in time * @netdev_data: address/cookie of network device driver used as * reference to actual hardware time stamp * * Software time stamps generated by ktime_get_real() are stored in * skb->tstamp. * * hwtstamps can only be compared against other hwtstamps from * the same device. * * This structure is attached to packets as part of the * &skb_shared_info. Use skb_hwtstamps() to get a pointer. */ struct skb_shared_hwtstamps { union { ktime_t hwtstamp; void *netdev_data; }; }; /* Definitions for tx_flags in struct skb_shared_info */ enum { /* generate hardware time stamp */ SKBTX_HW_TSTAMP = 1 << 0, /* generate software time stamp when queueing packet to NIC */ SKBTX_SW_TSTAMP = 1 << 1, /* device driver is going to provide hardware time stamp */ SKBTX_IN_PROGRESS = 1 << 2, /* generate hardware time stamp based on cycles if supported */ SKBTX_HW_TSTAMP_USE_CYCLES = 1 << 3, /* generate wifi status information (where possible) */ SKBTX_WIFI_STATUS = 1 << 4, /* determine hardware time stamp based on time or cycles */ SKBTX_HW_TSTAMP_NETDEV = 1 << 5, /* generate software time stamp when entering packet scheduling */ SKBTX_SCHED_TSTAMP = 1 << 6, }; #define SKBTX_ANY_SW_TSTAMP (SKBTX_SW_TSTAMP | \ SKBTX_SCHED_TSTAMP) #define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | \ SKBTX_HW_TSTAMP_USE_CYCLES | \ SKBTX_ANY_SW_TSTAMP) /* Definitions for flags in struct skb_shared_info */ enum { /* use zcopy routines */ SKBFL_ZEROCOPY_ENABLE = BIT(0), /* This indicates at least one fragment might be overwritten * (as in vmsplice(), sendfile() ...) * If we need to compute a TX checksum, we'll need to copy * all frags to avoid possible bad checksum */ SKBFL_SHARED_FRAG = BIT(1), /* segment contains only zerocopy data and should not be * charged to the kernel memory. */ SKBFL_PURE_ZEROCOPY = BIT(2), SKBFL_DONT_ORPHAN = BIT(3), /* page references are managed by the ubuf_info, so it's safe to * use frags only up until ubuf_info is released */ SKBFL_MANAGED_FRAG_REFS = BIT(4), }; #define SKBFL_ZEROCOPY_FRAG (SKBFL_ZEROCOPY_ENABLE | SKBFL_SHARED_FRAG) #define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY | \ SKBFL_DONT_ORPHAN | SKBFL_MANAGED_FRAG_REFS) struct ubuf_info_ops { void (*complete)(struct sk_buff *, struct ubuf_info *, bool zerocopy_success); /* has to be compatible with skb_zcopy_set() */ int (*link_skb)(struct sk_buff *skb, struct ubuf_info *uarg); }; /* * The callback notifies userspace to release buffers when skb DMA is done in * lower device, the skb last reference should be 0 when calling this. * The zerocopy_success argument is true if zero copy transmit occurred, * false on data copy or out of memory error caused by data copy attempt. * The ctx field is used to track device context. * The desc field is used to track userspace buffer index. */ struct ubuf_info { const struct ubuf_info_ops *ops; refcount_t refcnt; u8 flags; }; struct ubuf_info_msgzc { struct ubuf_info ubuf; union { struct { unsigned long desc; void *ctx; }; struct { u32 id; u16 len; u16 zerocopy:1; u32 bytelen; }; }; struct mmpin { struct user_struct *user; unsigned int num_pg; } mmp; }; #define skb_uarg(SKB) ((struct ubuf_info *)(skb_shinfo(SKB)->destructor_arg)) #define uarg_to_msgzc(ubuf_ptr) container_of((ubuf_ptr), struct ubuf_info_msgzc, \ ubuf) int mm_account_pinned_pages(struct mmpin *mmp, size_t size); void mm_unaccount_pinned_pages(struct mmpin *mmp); /* Preserve some data across TX submission and completion. * * Note, this state is stored in the driver. Extending the layout * might need some special care. */ struct xsk_tx_metadata_compl { __u64 *tx_timestamp; }; /* This data is invariant across clones and lives at * the end of the header data, ie. at skb->end. */ struct skb_shared_info { __u8 flags; __u8 meta_len; __u8 nr_frags; __u8 tx_flags; unsigned short gso_size; /* Warning: this field is not always filled in (UFO)! */ unsigned short gso_segs; struct sk_buff *frag_list; union { struct skb_shared_hwtstamps hwtstamps; struct xsk_tx_metadata_compl xsk_meta; }; unsigned int gso_type; u32 tskey; /* * Warning : all fields before dataref are cleared in __alloc_skb() */ atomic_t dataref; unsigned int xdp_frags_size; /* Intermediate layers must ensure that destructor_arg * remains valid until skb destructor */ void * destructor_arg; /* must be last field, see pskb_expand_head() */ skb_frag_t frags[MAX_SKB_FRAGS]; }; /** * DOC: dataref and headerless skbs * * Transport layers send out clones of payload skbs they hold for * retransmissions. To allow lower layers of the stack to prepend their headers * we split &skb_shared_info.dataref into two halves. * The lower 16 bits count the overall number of references. * The higher 16 bits indicate how many of the references are payload-only. * skb_header_cloned() checks if skb is allowed to add / write the headers. * * The creator of the skb (e.g. TCP) marks its skb as &sk_buff.nohdr * (via __skb_header_release()). Any clone created from marked skb will get * &sk_buff.hdr_len populated with the available headroom. * If there's the only clone in existence it's able to modify the headroom * at will. The sequence of calls inside the transport layer is:: * * <alloc skb> * skb_reserve() * __skb_header_release() * skb_clone() * // send the clone down the stack * * This is not a very generic construct and it depends on the transport layers * doing the right thing. In practice there's usually only one payload-only skb. * Having multiple payload-only skbs with different lengths of hdr_len is not * possible. The payload-only skbs should never leave their owner. */ #define SKB_DATAREF_SHIFT 16 #define SKB_DATAREF_MASK ((1 << SKB_DATAREF_SHIFT) - 1) enum { SKB_FCLONE_UNAVAILABLE, /* skb has no fclone (from head_cache) */ SKB_FCLONE_ORIG, /* orig skb (from fclone_cache) */ SKB_FCLONE_CLONE, /* companion fclone skb (from fclone_cache) */ }; enum { SKB_GSO_TCPV4 = 1 << 0, /* This indicates the skb is from an untrusted source. */ SKB_GSO_DODGY = 1 << 1, /* This indicates the tcp segment has CWR set. */ SKB_GSO_TCP_ECN = 1 << 2, SKB_GSO_TCP_FIXEDID = 1 << 3, SKB_GSO_TCPV6 = 1 << 4, SKB_GSO_FCOE = 1 << 5, SKB_GSO_GRE = 1 << 6, SKB_GSO_GRE_CSUM = 1 << 7, SKB_GSO_IPXIP4 = 1 << 8, SKB_GSO_IPXIP6 = 1 << 9, SKB_GSO_UDP_TUNNEL = 1 << 10, SKB_GSO_UDP_TUNNEL_CSUM = 1 << 11, SKB_GSO_PARTIAL = 1 << 12, SKB_GSO_TUNNEL_REMCSUM = 1 << 13, SKB_GSO_SCTP = 1 << 14, SKB_GSO_ESP = 1 << 15, SKB_GSO_UDP = 1 << 16, SKB_GSO_UDP_L4 = 1 << 17, SKB_GSO_FRAGLIST = 1 << 18, }; #if BITS_PER_LONG > 32 #define NET_SKBUFF_DATA_USES_OFFSET 1 #endif #ifdef NET_SKBUFF_DATA_USES_OFFSET typedef unsigned int sk_buff_data_t; #else typedef unsigned char *sk_buff_data_t; #endif enum skb_tstamp_type { SKB_CLOCK_REALTIME, SKB_CLOCK_MONOTONIC, SKB_CLOCK_TAI, __SKB_CLOCK_MAX = SKB_CLOCK_TAI, }; /** * DOC: Basic sk_buff geometry * * struct sk_buff itself is a metadata structure and does not hold any packet * data. All the data is held in associated buffers. * * &sk_buff.head points to the main "head" buffer. The head buffer is divided * into two parts: * * - data buffer, containing headers and sometimes payload; * this is the part of the skb operated on by the common helpers * such as skb_put() or skb_pull(); * - shared info (struct skb_shared_info) which holds an array of pointers * to read-only data in the (page, offset, length) format. * * Optionally &skb_shared_info.frag_list may point to another skb. * * Basic diagram may look like this:: * * --------------- * | sk_buff | * --------------- * ,--------------------------- + head * / ,----------------- + data * / / ,----------- + tail * | | | , + end * | | | | * v v v v * ----------------------------------------------- * | headroom | data | tailroom | skb_shared_info | * ----------------------------------------------- * + [page frag] * + [page frag] * + [page frag] * + [page frag] --------- * + frag_list --> | sk_buff | * --------- * */ /** * struct sk_buff - socket buffer * @next: Next buffer in list * @prev: Previous buffer in list * @tstamp: Time we arrived/left * @skb_mstamp_ns: (aka @tstamp) earliest departure time; start point * for retransmit timer * @rbnode: RB tree node, alternative to next/prev for netem/tcp * @list: queue head * @ll_node: anchor in an llist (eg socket defer_list) * @sk: Socket we are owned by * @dev: Device we arrived on/are leaving by * @dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL * @cb: Control buffer. Free for use by every layer. Put private vars here * @_skb_refdst: destination entry (with norefcount bit) * @len: Length of actual data * @data_len: Data length * @mac_len: Length of link layer header * @hdr_len: writable header length of cloned skb * @csum: Checksum (must include start/offset pair) * @csum_start: Offset from skb->head where checksumming should start * @csum_offset: Offset from csum_start where checksum should be stored * @priority: Packet queueing priority * @ignore_df: allow local fragmentation * @cloned: Head may be cloned (check refcnt to be sure) * @ip_summed: Driver fed us an IP checksum * @nohdr: Payload reference only, must not modify header * @pkt_type: Packet class * @fclone: skbuff clone status * @ipvs_property: skbuff is owned by ipvs * @inner_protocol_type: whether the inner protocol is * ENCAP_TYPE_ETHER or ENCAP_TYPE_IPPROTO * @remcsum_offload: remote checksum offload is enabled * @offload_fwd_mark: Packet was L2-forwarded in hardware * @offload_l3_fwd_mark: Packet was L3-forwarded in hardware * @tc_skip_classify: do not classify packet. set by IFB device * @tc_at_ingress: used within tc_classify to distinguish in/egress * @redirected: packet was redirected by packet classifier * @from_ingress: packet was redirected from the ingress path * @nf_skip_egress: packet shall skip nf egress - see netfilter_netdev.h * @peeked: this packet has been seen already, so stats have been * done for it, don't do them again * @nf_trace: netfilter packet trace flag * @protocol: Packet protocol from driver * @destructor: Destruct function * @tcp_tsorted_anchor: list structure for TCP (tp->tsorted_sent_queue) * @_sk_redir: socket redirection information for skmsg * @_nfct: Associated connection, if any (with nfctinfo bits) * @skb_iif: ifindex of device we arrived on * @tc_index: Traffic control index * @hash: the packet hash * @queue_mapping: Queue mapping for multiqueue devices * @head_frag: skb was allocated from page fragments, * not allocated by kmalloc() or vmalloc(). * @pfmemalloc: skbuff was allocated from PFMEMALLOC reserves * @pp_recycle: mark the packet for recycling instead of freeing (implies * page_pool support on driver) * @active_extensions: active extensions (skb_ext_id types) * @ndisc_nodetype: router type (from link layer) * @ooo_okay: allow the mapping of a socket to a queue to be changed * @l4_hash: indicate hash is a canonical 4-tuple hash over transport * ports. * @sw_hash: indicates hash was computed in software stack * @wifi_acked_valid: wifi_acked was set * @wifi_acked: whether frame was acked on wifi or not * @no_fcs: Request NIC to treat last 4 bytes as Ethernet FCS * @encapsulation: indicates the inner headers in the skbuff are valid * @encap_hdr_csum: software checksum is needed * @csum_valid: checksum is already valid * @csum_not_inet: use CRC32c to resolve CHECKSUM_PARTIAL * @csum_complete_sw: checksum was completed by software * @csum_level: indicates the number of consecutive checksums found in * the packet minus one that have been verified as * CHECKSUM_UNNECESSARY (max 3) * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @slow_gro: state present at GRO time, slower prepare step required * @tstamp_type: When set, skb->tstamp has the * delivery_time clock base of skb->tstamp. * @napi_id: id of the NAPI struct this skb came from * @sender_cpu: (aka @napi_id) source CPU in XPS * @alloc_cpu: CPU which did the skb allocation. * @secmark: security marking * @mark: Generic packet mark * @reserved_tailroom: (aka @mark) number of bytes of free space available * at the tail of an sk_buff * @vlan_all: vlan fields (proto & tci) * @vlan_proto: vlan encapsulation protocol * @vlan_tci: vlan tag control information * @inner_protocol: Protocol (encapsulation) * @inner_ipproto: (aka @inner_protocol) stores ipproto when * skb->inner_protocol_type == ENCAP_TYPE_IPPROTO; * @inner_transport_header: Inner transport layer header (encapsulation) * @inner_network_header: Network layer header (encapsulation) * @inner_mac_header: Link layer header (encapsulation) * @transport_header: Transport layer header * @network_header: Network layer header * @mac_header: Link layer header * @kcov_handle: KCOV remote handle for remote coverage collection * @tail: Tail pointer * @end: End pointer * @head: Head of buffer * @data: Data head pointer * @truesize: Buffer size * @users: User count - see {datagram,tcp}.c * @extensions: allocated extensions, valid if active_extensions is nonzero */ struct sk_buff { union { struct { /* These two members must be first to match sk_buff_head. */ struct sk_buff *next; struct sk_buff *prev; union { struct net_device *dev; /* Some protocols might use this space to store information, * while device pointer would be NULL. * UDP receive path is one user. */ unsigned long dev_scratch; }; }; struct rb_node rbnode; /* used in netem, ip4 defrag, and tcp stack */ struct list_head list; struct llist_node ll_node; }; struct sock *sk; union { ktime_t tstamp; u64 skb_mstamp_ns; /* earliest departure time */ }; /* * This is the control buffer. It is free to use for every * layer. Please put your private variables there. If you * want to keep them across layers you have to do a skb_clone() * first. This is owned by whoever has the skb queued ATM. */ char cb[48] __aligned(8); union { struct { unsigned long _skb_refdst; void (*destructor)(struct sk_buff *skb); }; struct list_head tcp_tsorted_anchor; #ifdef CONFIG_NET_SOCK_MSG unsigned long _sk_redir; #endif }; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) unsigned long _nfct; #endif unsigned int len, data_len; __u16 mac_len, hdr_len; /* Following fields are _not_ copied in __copy_skb_header() * Note that queue_mapping is here mostly to fill a hole. */ __u16 queue_mapping; /* if you move cloned around you also must adapt those constants */ #ifdef __BIG_ENDIAN_BITFIELD #define CLONED_MASK (1 << 7) #else #define CLONED_MASK 1 #endif #define CLONED_OFFSET offsetof(struct sk_buff, __cloned_offset) /* private: */ __u8 __cloned_offset[0]; /* public: */ __u8 cloned:1, nohdr:1, fclone:2, peeked:1, head_frag:1, pfmemalloc:1, pp_recycle:1; /* page_pool recycle indicator */ #ifdef CONFIG_SKB_EXTENSIONS __u8 active_extensions; #endif /* Fields enclosed in headers group are copied * using a single memcpy() in __copy_skb_header() */ struct_group(headers, /* private: */ __u8 __pkt_type_offset[0]; /* public: */ __u8 pkt_type:3; /* see PKT_TYPE_MAX */ __u8 ignore_df:1; __u8 dst_pending_confirm:1; __u8 ip_summed:2; __u8 ooo_okay:1; /* private: */ __u8 __mono_tc_offset[0]; /* public: */ __u8 tstamp_type:2; /* See skb_tstamp_type */ #ifdef CONFIG_NET_XGRESS __u8 tc_at_ingress:1; /* See TC_AT_INGRESS_MASK */ __u8 tc_skip_classify:1; #endif __u8 remcsum_offload:1; __u8 csum_complete_sw:1; __u8 csum_level:2; __u8 inner_protocol_type:1; __u8 l4_hash:1; __u8 sw_hash:1; #ifdef CONFIG_WIRELESS __u8 wifi_acked_valid:1; __u8 wifi_acked:1; #endif __u8 no_fcs:1; /* Indicates the inner headers are valid in the skbuff. */ __u8 encapsulation:1; __u8 encap_hdr_csum:1; __u8 csum_valid:1; #ifdef CONFIG_IPV6_NDISC_NODETYPE __u8 ndisc_nodetype:2; #endif #if IS_ENABLED(CONFIG_IP_VS) __u8 ipvs_property:1; #endif #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) __u8 nf_trace:1; #endif #ifdef CONFIG_NET_SWITCHDEV __u8 offload_fwd_mark:1; __u8 offload_l3_fwd_mark:1; #endif __u8 redirected:1; #ifdef CONFIG_NET_REDIRECT __u8 from_ingress:1; #endif #ifdef CONFIG_NETFILTER_SKIP_EGRESS __u8 nf_skip_egress:1; #endif #ifdef CONFIG_SKB_DECRYPTED __u8 decrypted:1; #endif __u8 slow_gro:1; #if IS_ENABLED(CONFIG_IP_SCTP) __u8 csum_not_inet:1; #endif #if defined(CONFIG_NET_SCHED) || defined(CONFIG_NET_XGRESS) __u16 tc_index; /* traffic control index */ #endif u16 alloc_cpu; union { __wsum csum; struct { __u16 csum_start; __u16 csum_offset; }; }; __u32 priority; int skb_iif; __u32 hash; union { u32 vlan_all; struct { __be16 vlan_proto; __u16 vlan_tci; }; }; #if defined(CONFIG_NET_RX_BUSY_POLL) || defined(CONFIG_XPS) union { unsigned int napi_id; unsigned int sender_cpu; }; #endif #ifdef CONFIG_NETWORK_SECMARK __u32 secmark; #endif union { __u32 mark; __u32 reserved_tailroom; }; union { __be16 inner_protocol; __u8 inner_ipproto; }; __u16 inner_transport_header; __u16 inner_network_header; __u16 inner_mac_header; __be16 protocol; __u16 transport_header; __u16 network_header; __u16 mac_header; #ifdef CONFIG_KCOV u64 kcov_handle; #endif ); /* end headers group */ /* These elements must be at the end, see alloc_skb() for details. */ sk_buff_data_t tail; sk_buff_data_t end; unsigned char *head, *data; unsigned int truesize; refcount_t users; #ifdef CONFIG_SKB_EXTENSIONS /* only usable after checking ->active_extensions != 0 */ struct skb_ext *extensions; #endif }; /* if you move pkt_type around you also must adapt those constants */ #ifdef __BIG_ENDIAN_BITFIELD #define PKT_TYPE_MAX (7 << 5) #else #define PKT_TYPE_MAX 7 #endif #define PKT_TYPE_OFFSET offsetof(struct sk_buff, __pkt_type_offset) /* if you move tc_at_ingress or tstamp_type * around, you also must adapt these constants. */ #ifdef __BIG_ENDIAN_BITFIELD #define SKB_TSTAMP_TYPE_MASK (3 << 6) #define SKB_TSTAMP_TYPE_RSHIFT (6) #define TC_AT_INGRESS_MASK (1 << 5) #else #define SKB_TSTAMP_TYPE_MASK (3) #define TC_AT_INGRESS_MASK (1 << 2) #endif #define SKB_BF_MONO_TC_OFFSET offsetof(struct sk_buff, __mono_tc_offset) #ifdef __KERNEL__ /* * Handling routines are only of interest to the kernel */ #define SKB_ALLOC_FCLONE 0x01 #define SKB_ALLOC_RX 0x02 #define SKB_ALLOC_NAPI 0x04 /** * skb_pfmemalloc - Test if the skb was allocated from PFMEMALLOC reserves * @skb: buffer */ static inline bool skb_pfmemalloc(const struct sk_buff *skb) { return unlikely(skb->pfmemalloc); } /* * skb might have a dst pointer attached, refcounted or not. * _skb_refdst low order bit is set if refcount was _not_ taken */ #define SKB_DST_NOREF 1UL #define SKB_DST_PTRMASK ~(SKB_DST_NOREF) /** * skb_dst - returns skb dst_entry * @skb: buffer * * Returns skb dst_entry, regardless of reference taken or not. */ static inline struct dst_entry *skb_dst(const struct sk_buff *skb) { /* If refdst was not refcounted, check we still are in a * rcu_read_lock section */ WARN_ON((skb->_skb_refdst & SKB_DST_NOREF) && !rcu_read_lock_held() && !rcu_read_lock_bh_held()); return (struct dst_entry *)(skb->_skb_refdst & SKB_DST_PTRMASK); } /** * skb_dst_set - sets skb dst * @skb: buffer * @dst: dst entry * * Sets skb dst, assuming a reference was taken on dst and should * be released by skb_dst_drop() */ static inline void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst) { skb->slow_gro |= !!dst; skb->_skb_refdst = (unsigned long)dst; } /** * skb_dst_set_noref - sets skb dst, hopefully, without taking reference * @skb: buffer * @dst: dst entry * * Sets skb dst, assuming a reference was not taken on dst. * If dst entry is cached, we do not take reference and dst_release * will be avoided by refdst_drop. If dst entry is not cached, we take * reference, so that last dst_release can destroy the dst immediately. */ static inline void skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst) { WARN_ON(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); skb->slow_gro |= !!dst; skb->_skb_refdst = (unsigned long)dst | SKB_DST_NOREF; } /** * skb_dst_is_noref - Test if skb dst isn't refcounted * @skb: buffer */ static inline bool skb_dst_is_noref(const struct sk_buff *skb) { return (skb->_skb_refdst & SKB_DST_NOREF) && skb_dst(skb); } /* For mangling skb->pkt_type from user space side from applications * such as nft, tc, etc, we only allow a conservative subset of * possible pkt_types to be set. */ static inline bool skb_pkt_type_ok(u32 ptype) { return ptype <= PACKET_OTHERHOST; } /** * skb_napi_id - Returns the skb's NAPI id * @skb: buffer */ static inline unsigned int skb_napi_id(const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL return skb->napi_id; #else return 0; #endif } static inline bool skb_wifi_acked_valid(const struct sk_buff *skb) { #ifdef CONFIG_WIRELESS return skb->wifi_acked_valid; #else return 0; #endif } /** * skb_unref - decrement the skb's reference count * @skb: buffer * * Returns true if we can free the skb. */ static inline bool skb_unref(struct sk_buff *skb) { if (unlikely(!skb)) return false; if (likely(refcount_read(&skb->users) == 1)) smp_rmb(); else if (likely(!refcount_dec_and_test(&skb->users))) return false; return true; } static inline bool skb_data_unref(const struct sk_buff *skb, struct skb_shared_info *shinfo) { int bias; if (!skb->cloned) return true; bias = skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1; if (atomic_read(&shinfo->dataref) == bias) smp_rmb(); else if (atomic_sub_return(bias, &shinfo->dataref)) return false; return true; } void __fix_address sk_skb_reason_drop(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason reason); static inline void kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason) { sk_skb_reason_drop(NULL, skb, reason); } /** * kfree_skb - free an sk_buff with 'NOT_SPECIFIED' reason * @skb: buffer to free */ static inline void kfree_skb(struct sk_buff *skb) { kfree_skb_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED); } void skb_release_head_state(struct sk_buff *skb); void kfree_skb_list_reason(struct sk_buff *segs, enum skb_drop_reason reason); void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt); void skb_tx_error(struct sk_buff *skb); static inline void kfree_skb_list(struct sk_buff *segs) { kfree_skb_list_reason(segs, SKB_DROP_REASON_NOT_SPECIFIED); } #ifdef CONFIG_TRACEPOINTS void consume_skb(struct sk_buff *skb); #else static inline void consume_skb(struct sk_buff *skb) { return kfree_skb(skb); } #endif void __consume_stateless_skb(struct sk_buff *skb); void __kfree_skb(struct sk_buff *skb); void kfree_skb_partial(struct sk_buff *skb, bool head_stolen); bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, bool *fragstolen, int *delta_truesize); struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int flags, int node); struct sk_buff *__build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size); void skb_attempt_defer_free(struct sk_buff *skb); struct sk_buff *napi_build_skb(void *data, unsigned int frag_size); struct sk_buff *slab_build_skb(void *data); /** * alloc_skb - allocate a network buffer * @size: size to allocate * @priority: allocation mask * * This function is a convenient wrapper around __alloc_skb(). */ static inline struct sk_buff *alloc_skb(unsigned int size, gfp_t priority) { return __alloc_skb(size, priority, 0, NUMA_NO_NODE); } struct sk_buff *alloc_skb_with_frags(unsigned long header_len, unsigned long data_len, int max_page_order, int *errcode, gfp_t gfp_mask); struct sk_buff *alloc_skb_for_msg(struct sk_buff *first); /* Layout of fast clones : [skb1][skb2][fclone_ref] */ struct sk_buff_fclones { struct sk_buff skb1; struct sk_buff skb2; refcount_t fclone_ref; }; /** * skb_fclone_busy - check if fclone is busy * @sk: socket * @skb: buffer * * Returns true if skb is a fast clone, and its clone is not freed. * Some drivers call skb_orphan() in their ndo_start_xmit(), * so we also check that didn't happen. */ static inline bool skb_fclone_busy(const struct sock *sk, const struct sk_buff *skb) { const struct sk_buff_fclones *fclones; fclones = container_of(skb, struct sk_buff_fclones, skb1); return skb->fclone == SKB_FCLONE_ORIG && refcount_read(&fclones->fclone_ref) > 1 && READ_ONCE(fclones->skb2.sk) == sk; } /** * alloc_skb_fclone - allocate a network buffer from fclone cache * @size: size to allocate * @priority: allocation mask * * This function is a convenient wrapper around __alloc_skb(). */ static inline struct sk_buff *alloc_skb_fclone(unsigned int size, gfp_t priority) { return __alloc_skb(size, priority, SKB_ALLOC_FCLONE, NUMA_NO_NODE); } struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src); void skb_headers_offset_update(struct sk_buff *skb, int off); int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask); struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t priority); void skb_copy_header(struct sk_buff *new, const struct sk_buff *old); struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t priority); struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom, gfp_t gfp_mask, bool fclone); static inline struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask) { return __pskb_copy_fclone(skb, headroom, gfp_mask, false); } int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, gfp_t gfp_mask); struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom); struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom); struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, gfp_t priority); int __must_check skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, int offset, int len); int __must_check skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len); int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer); int __skb_pad(struct sk_buff *skb, int pad, bool free_on_error); /** * skb_pad - zero pad the tail of an skb * @skb: buffer to pad * @pad: space to pad * * Ensure that a buffer is followed by a padding area that is zero * filled. Used by network drivers which may DMA or transfer data * beyond the buffer end onto the wire. * * May return error in out of memory cases. The skb is freed on error. */ static inline int skb_pad(struct sk_buff *skb, int pad) { return __skb_pad(skb, pad, true); } #define dev_kfree_skb(a) consume_skb(a) int skb_append_pagefrags(struct sk_buff *skb, struct page *page, int offset, size_t size, size_t max_frags); struct skb_seq_state { __u32 lower_offset; __u32 upper_offset; __u32 frag_idx; __u32 stepped_offset; struct sk_buff *root_skb; struct sk_buff *cur_skb; __u8 *frag_data; __u32 frag_off; }; void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from, unsigned int to, struct skb_seq_state *st); unsigned int skb_seq_read(unsigned int consumed, const u8 **data, struct skb_seq_state *st); void skb_abort_seq_read(struct skb_seq_state *st); unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, unsigned int to, struct ts_config *config); /* * Packet hash types specify the type of hash in skb_set_hash. * * Hash types refer to the protocol layer addresses which are used to * construct a packet's hash. The hashes are used to differentiate or identify * flows of the protocol layer for the hash type. Hash types are either * layer-2 (L2), layer-3 (L3), or layer-4 (L4). * * Properties of hashes: * * 1) Two packets in different flows have different hash values * 2) Two packets in the same flow should have the same hash value * * A hash at a higher layer is considered to be more specific. A driver should * set the most specific hash possible. * * A driver cannot indicate a more specific hash than the layer at which a hash * was computed. For instance an L3 hash cannot be set as an L4 hash. * * A driver may indicate a hash level which is less specific than the * actual layer the hash was computed on. For instance, a hash computed * at L4 may be considered an L3 hash. This should only be done if the * driver can't unambiguously determine that the HW computed the hash at * the higher layer. Note that the "should" in the second property above * permits this. */ enum pkt_hash_types { PKT_HASH_TYPE_NONE, /* Undefined type */ PKT_HASH_TYPE_L2, /* Input: src_MAC, dest_MAC */ PKT_HASH_TYPE_L3, /* Input: src_IP, dst_IP */ PKT_HASH_TYPE_L4, /* Input: src_IP, dst_IP, src_port, dst_port */ }; static inline void skb_clear_hash(struct sk_buff *skb) { skb->hash = 0; skb->sw_hash = 0; skb->l4_hash = 0; } static inline void skb_clear_hash_if_not_l4(struct sk_buff *skb) { if (!skb->l4_hash) skb_clear_hash(skb); } static inline void __skb_set_hash(struct sk_buff *skb, __u32 hash, bool is_sw, bool is_l4) { skb->l4_hash = is_l4; skb->sw_hash = is_sw; skb->hash = hash; } static inline void skb_set_hash(struct sk_buff *skb, __u32 hash, enum pkt_hash_types type) { /* Used by drivers to set hash from HW */ __skb_set_hash(skb, hash, false, type == PKT_HASH_TYPE_L4); } static inline void __skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4) { __skb_set_hash(skb, hash, true, is_l4); } u32 __skb_get_hash_symmetric_net(const struct net *net, const struct sk_buff *skb); static inline u32 __skb_get_hash_symmetric(const struct sk_buff *skb) { return __skb_get_hash_symmetric_net(NULL, skb); } void __skb_get_hash_net(const struct net *net, struct sk_buff *skb); u32 skb_get_poff(const struct sk_buff *skb); u32 __skb_get_poff(const struct sk_buff *skb, const void *data, const struct flow_keys_basic *keys, int hlen); __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, const void *data, int hlen_proto); static inline __be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto) { return __skb_flow_get_ports(skb, thoff, ip_proto, NULL, 0); } void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, unsigned int key_count); struct bpf_flow_dissector; u32 bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, __be16 proto, int nhoff, int hlen, unsigned int flags); bool __skb_flow_dissect(const struct net *net, const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, __be16 proto, int nhoff, int hlen, unsigned int flags); static inline bool skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, unsigned int flags) { return __skb_flow_dissect(NULL, skb, flow_dissector, target_container, NULL, 0, 0, 0, flags); } static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb, struct flow_keys *flow, unsigned int flags) { memset(flow, 0, sizeof(*flow)); return __skb_flow_dissect(NULL, skb, &flow_keys_dissector, flow, NULL, 0, 0, 0, flags); } static inline bool skb_flow_dissect_flow_keys_basic(const struct net *net, const struct sk_buff *skb, struct flow_keys_basic *flow, const void *data, __be16 proto, int nhoff, int hlen, unsigned int flags) { memset(flow, 0, sizeof(*flow)); return __skb_flow_dissect(net, skb, &flow_keys_basic_dissector, flow, data, proto, nhoff, hlen, flags); } void skb_flow_dissect_meta(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); /* Gets a skb connection tracking info, ctinfo map should be a * map of mapsize to translate enum ip_conntrack_info states * to user states. */ void skb_flow_dissect_ct(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, u16 *ctinfo_map, size_t mapsize, bool post_ct, u16 zone); void skb_flow_dissect_tunnel_info(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); void skb_flow_dissect_hash(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); static inline __u32 skb_get_hash_net(const struct net *net, struct sk_buff *skb) { if (!skb->l4_hash && !skb->sw_hash) __skb_get_hash_net(net, skb); return skb->hash; } static inline __u32 skb_get_hash(struct sk_buff *skb) { if (!skb->l4_hash && !skb->sw_hash) __skb_get_hash_net(NULL, skb); return skb->hash; } static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 *fl6) { if (!skb->l4_hash && !skb->sw_hash) { struct flow_keys keys; __u32 hash = __get_hash_from_flowi6(fl6, &keys); __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); } return skb->hash; } __u32 skb_get_hash_perturb(const struct sk_buff *skb, const siphash_key_t *perturb); static inline __u32 skb_get_hash_raw(const struct sk_buff *skb) { return skb->hash; } static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) { to->hash = from->hash; to->sw_hash = from->sw_hash; to->l4_hash = from->l4_hash; }; static inline int skb_cmp_decrypted(const struct sk_buff *skb1, const struct sk_buff *skb2) { #ifdef CONFIG_SKB_DECRYPTED return skb2->decrypted - skb1->decrypted; #else return 0; #endif } static inline bool skb_is_decrypted(const struct sk_buff *skb) { #ifdef CONFIG_SKB_DECRYPTED return skb->decrypted; #else return false; #endif } static inline void skb_copy_decrypted(struct sk_buff *to, const struct sk_buff *from) { #ifdef CONFIG_SKB_DECRYPTED to->decrypted = from->decrypted; #endif } #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { return skb->head + skb->end; } static inline unsigned int skb_end_offset(const struct sk_buff *skb) { return skb->end; } static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) { skb->end = offset; } #else static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { return skb->end; } static inline unsigned int skb_end_offset(const struct sk_buff *skb) { return skb->end - skb->head; } static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) { skb->end = skb->head + offset; } #endif extern const struct ubuf_info_ops msg_zerocopy_ubuf_ops; struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg); void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, struct sk_buff *skb, struct iov_iter *from, size_t length); int zerocopy_fill_skb_from_iter(struct sk_buff *skb, struct iov_iter *from, size_t length); static inline int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len) { return __zerocopy_sg_from_iter(msg, skb->sk, skb, &msg->msg_iter, len); } int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, struct msghdr *msg, int len, struct ubuf_info *uarg); /* Internal */ #define skb_shinfo(SKB) ((struct skb_shared_info *)(skb_end_pointer(SKB))) static inline struct skb_shared_hwtstamps *skb_hwtstamps(struct sk_buff *skb) { return &skb_shinfo(skb)->hwtstamps; } static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb) { bool is_zcopy = skb && skb_shinfo(skb)->flags & SKBFL_ZEROCOPY_ENABLE; return is_zcopy ? skb_uarg(skb) : NULL; } static inline bool skb_zcopy_pure(const struct sk_buff *skb) { return skb_shinfo(skb)->flags & SKBFL_PURE_ZEROCOPY; } static inline bool skb_zcopy_managed(const struct sk_buff *skb) { return skb_shinfo(skb)->flags & SKBFL_MANAGED_FRAG_REFS; } static inline bool skb_pure_zcopy_same(const struct sk_buff *skb1, const struct sk_buff *skb2) { return skb_zcopy_pure(skb1) == skb_zcopy_pure(skb2); } static inline void net_zcopy_get(struct ubuf_info *uarg) { refcount_inc(&uarg->refcnt); } static inline void skb_zcopy_init(struct sk_buff *skb, struct ubuf_info *uarg) { skb_shinfo(skb)->destructor_arg = uarg; skb_shinfo(skb)->flags |= uarg->flags; } static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg, bool *have_ref) { if (skb && uarg && !skb_zcopy(skb)) { if (unlikely(have_ref && *have_ref)) *have_ref = false; else net_zcopy_get(uarg); skb_zcopy_init(skb, uarg); } } static inline void skb_zcopy_set_nouarg(struct sk_buff *skb, void *val) { skb_shinfo(skb)->destructor_arg = (void *)((uintptr_t) val | 0x1UL); skb_shinfo(skb)->flags |= SKBFL_ZEROCOPY_FRAG; } static inline bool skb_zcopy_is_nouarg(struct sk_buff *skb) { return (uintptr_t) skb_shinfo(skb)->destructor_arg & 0x1UL; } static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb) { return (void *)((uintptr_t) skb_shinfo(skb)->destructor_arg & ~0x1UL); } static inline void net_zcopy_put(struct ubuf_info *uarg) { if (uarg) uarg->ops->complete(NULL, uarg, true); } static inline void net_zcopy_put_abort(struct ubuf_info *uarg, bool have_uref) { if (uarg) { if (uarg->ops == &msg_zerocopy_ubuf_ops) msg_zerocopy_put_abort(uarg, have_uref); else if (have_uref) net_zcopy_put(uarg); } } /* Release a reference on a zerocopy structure */ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success) { struct ubuf_info *uarg = skb_zcopy(skb); if (uarg) { if (!skb_zcopy_is_nouarg(skb)) uarg->ops->complete(skb, uarg, zerocopy_success); skb_shinfo(skb)->flags &= ~SKBFL_ALL_ZEROCOPY; } } void __skb_zcopy_downgrade_managed(struct sk_buff *skb); static inline void skb_zcopy_downgrade_managed(struct sk_buff *skb) { if (unlikely(skb_zcopy_managed(skb))) __skb_zcopy_downgrade_managed(skb); } static inline void skb_mark_not_on_list(struct sk_buff *skb) { skb->next = NULL; } static inline void skb_poison_list(struct sk_buff *skb) { #ifdef CONFIG_DEBUG_NET skb->next = SKB_LIST_POISON_NEXT; #endif } /* Iterate through singly-linked GSO fragments of an skb. */ #define skb_list_walk_safe(first, skb, next_skb) \ for ((skb) = (first), (next_skb) = (skb) ? (skb)->next : NULL; (skb); \ (skb) = (next_skb), (next_skb) = (skb) ? (skb)->next : NULL) static inline void skb_list_del_init(struct sk_buff *skb) { __list_del_entry(&skb->list); skb_mark_not_on_list(skb); } /** * skb_queue_empty - check if a queue is empty * @list: queue head * * Returns true if the queue is empty, false otherwise. */ static inline int skb_queue_empty(const struct sk_buff_head *list) { return list->next == (const struct sk_buff *) list; } /** * skb_queue_empty_lockless - check if a queue is empty * @list: queue head * * Returns true if the queue is empty, false otherwise. * This variant can be used in lockless contexts. */ static inline bool skb_queue_empty_lockless(const struct sk_buff_head *list) { return READ_ONCE(list->next) == (const struct sk_buff *) list; } /** * skb_queue_is_last - check if skb is the last entry in the queue * @list: queue head * @skb: buffer * * Returns true if @skb is the last buffer on the list. */ static inline bool skb_queue_is_last(const struct sk_buff_head *list, const struct sk_buff *skb) { return skb->next == (const struct sk_buff *) list; } /** * skb_queue_is_first - check if skb is the first entry in the queue * @list: queue head * @skb: buffer * * Returns true if @skb is the first buffer on the list. */ static inline bool skb_queue_is_first(const struct sk_buff_head *list, const struct sk_buff *skb) { return skb->prev == (const struct sk_buff *) list; } /** * skb_queue_next - return the next packet in the queue * @list: queue head * @skb: current buffer * * Return the next packet in @list after @skb. It is only valid to * call this if skb_queue_is_last() evaluates to false. */ static inline struct sk_buff *skb_queue_next(const struct sk_buff_head *list, const struct sk_buff *skb) { /* This BUG_ON may seem severe, but if we just return then we * are going to dereference garbage. */ BUG_ON(skb_queue_is_last(list, skb)); return skb->next; } /** * skb_queue_prev - return the prev packet in the queue * @list: queue head * @skb: current buffer * * Return the prev packet in @list before @skb. It is only valid to * call this if skb_queue_is_first() evaluates to false. */ static inline struct sk_buff *skb_queue_prev(const struct sk_buff_head *list, const struct sk_buff *skb) { /* This BUG_ON may seem severe, but if we just return then we * are going to dereference garbage. */ BUG_ON(skb_queue_is_first(list, skb)); return skb->prev; } /** * skb_get - reference buffer * @skb: buffer to reference * * Makes another reference to a socket buffer and returns a pointer * to the buffer. */ static inline struct sk_buff *skb_get(struct sk_buff *skb) { refcount_inc(&skb->users); return skb; } /* * If users == 1, we are the only owner and can avoid redundant atomic changes. */ /** * skb_cloned - is the buffer a clone * @skb: buffer to check * * Returns true if the buffer was generated with skb_clone() and is * one of multiple shared copies of the buffer. Cloned buffers are * shared data so must not be written to under normal circumstances. */ static inline int skb_cloned(const struct sk_buff *skb) { return skb->cloned && (atomic_read(&skb_shinfo(skb)->dataref) & SKB_DATAREF_MASK) != 1; } static inline int skb_unclone(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) return pskb_expand_head(skb, 0, 0, pri); return 0; } /* This variant of skb_unclone() makes sure skb->truesize * and skb_end_offset() are not changed, whenever a new skb->head is needed. * * Indeed there is no guarantee that ksize(kmalloc(X)) == ksize(kmalloc(X)) * when various debugging features are in place. */ int __skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri); static inline int skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) return __skb_unclone_keeptruesize(skb, pri); return 0; } /** * skb_header_cloned - is the header a clone * @skb: buffer to check * * Returns true if modifying the header part of the buffer requires * the data to be copied. */ static inline int skb_header_cloned(const struct sk_buff *skb) { int dataref; if (!skb->cloned) return 0; dataref = atomic_read(&skb_shinfo(skb)->dataref); dataref = (dataref & SKB_DATAREF_MASK) - (dataref >> SKB_DATAREF_SHIFT); return dataref != 1; } static inline int skb_header_unclone(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_header_cloned(skb)) return pskb_expand_head(skb, 0, 0, pri); return 0; } /** * __skb_header_release() - allow clones to use the headroom * @skb: buffer to operate on * * See "DOC: dataref and headerless skbs". */ static inline void __skb_header_release(struct sk_buff *skb) { skb->nohdr = 1; atomic_set(&skb_shinfo(skb)->dataref, 1 + (1 << SKB_DATAREF_SHIFT)); } /** * skb_shared - is the buffer shared * @skb: buffer to check * * Returns true if more than one person has a reference to this * buffer. */ static inline int skb_shared(const struct sk_buff *skb) { return refcount_read(&skb->users) != 1; } /** * skb_share_check - check if buffer is shared and if so clone it * @skb: buffer to check * @pri: priority for memory allocation * * If the buffer is shared the buffer is cloned and the old copy * drops a reference. A new clone with a single reference is returned. * If the buffer is not shared the original buffer is returned. When * being called from interrupt status or with spinlocks held pri must * be GFP_ATOMIC. * * NULL is returned on a memory allocation failure. */ static inline struct sk_buff *skb_share_check(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_shared(skb)) { struct sk_buff *nskb = skb_clone(skb, pri); if (likely(nskb)) consume_skb(skb); else kfree_skb(skb); skb = nskb; } return skb; } /* * Copy shared buffers into a new sk_buff. We effectively do COW on * packets to handle cases where we have a local reader and forward * and a couple of other messy ones. The normal one is tcpdumping * a packet that's being forwarded. */ /** * skb_unshare - make a copy of a shared buffer * @skb: buffer to check * @pri: priority for memory allocation * * If the socket buffer is a clone then this function creates a new * copy of the data, drops a reference count on the old copy and returns * the new copy with the reference count at 1. If the buffer is not a clone * the original buffer is returned. When called with a spinlock held or * from interrupt state @pri must be %GFP_ATOMIC * * %NULL is returned on a memory allocation failure. */ static inline struct sk_buff *skb_unshare(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) { struct sk_buff *nskb = skb_copy(skb, pri); /* Free our shared copy */ if (likely(nskb)) consume_skb(skb); else kfree_skb(skb); skb = nskb; } return skb; } /** * skb_peek - peek at the head of an &sk_buff_head * @list_: list to peek at * * Peek an &sk_buff. Unlike most other operations you _MUST_ * be careful with this one. A peek leaves the buffer on the * list and someone else may run off with it. You must hold * the appropriate locks or have a private queue to do this. * * Returns %NULL for an empty list or a pointer to the head element. * The reference count is not incremented and the reference is therefore * volatile. Use with caution. */ static inline struct sk_buff *skb_peek(const struct sk_buff_head *list_) { struct sk_buff *skb = list_->next; if (skb == (struct sk_buff *)list_) skb = NULL; return skb; } /** * __skb_peek - peek at the head of a non-empty &sk_buff_head * @list_: list to peek at * * Like skb_peek(), but the caller knows that the list is not empty. */ static inline struct sk_buff *__skb_peek(const struct sk_buff_head *list_) { return list_->next; } /** * skb_peek_next - peek skb following the given one from a queue * @skb: skb to start from * @list_: list to peek at * * Returns %NULL when the end of the list is met or a pointer to the * next element. The reference count is not incremented and the * reference is therefore volatile. Use with caution. */ static inline struct sk_buff *skb_peek_next(struct sk_buff *skb, const struct sk_buff_head *list_) { struct sk_buff *next = skb->next; if (next == (struct sk_buff *)list_) next = NULL; return next; } /** * skb_peek_tail - peek at the tail of an &sk_buff_head * @list_: list to peek at * * Peek an &sk_buff. Unlike most other operations you _MUST_ * be careful with this one. A peek leaves the buffer on the * list and someone else may run off with it. You must hold * the appropriate locks or have a private queue to do this. * * Returns %NULL for an empty list or a pointer to the tail element. * The reference count is not incremented and the reference is therefore * volatile. Use with caution. */ static inline struct sk_buff *skb_peek_tail(const struct sk_buff_head *list_) { struct sk_buff *skb = READ_ONCE(list_->prev); if (skb == (struct sk_buff *)list_) skb = NULL; return skb; } /** * skb_queue_len - get queue length * @list_: list to measure * * Return the length of an &sk_buff queue. */ static inline __u32 skb_queue_len(const struct sk_buff_head *list_) { return list_->qlen; } /** * skb_queue_len_lockless - get queue length * @list_: list to measure * * Return the length of an &sk_buff queue. * This variant can be used in lockless contexts. */ static inline __u32 skb_queue_len_lockless(const struct sk_buff_head *list_) { return READ_ONCE(list_->qlen); } /** * __skb_queue_head_init - initialize non-spinlock portions of sk_buff_head * @list: queue to initialize * * This initializes only the list and queue length aspects of * an sk_buff_head object. This allows to initialize the list * aspects of an sk_buff_head without reinitializing things like * the spinlock. It can also be used for on-stack sk_buff_head * objects where the spinlock is known to not be used. */ static inline void __skb_queue_head_init(struct sk_buff_head *list) { list->prev = list->next = (struct sk_buff *)list; list->qlen = 0; } /* * This function creates a split out lock class for each invocation; * this is needed for now since a whole lot of users of the skb-queue * infrastructure in drivers have different locking usage (in hardirq) * than the networking core (in softirq only). In the long run either the * network layer or drivers should need annotation to consolidate the * main types of usage into 3 classes. */ static inline void skb_queue_head_init(struct sk_buff_head *list) { spin_lock_init(&list->lock); __skb_queue_head_init(list); } static inline void skb_queue_head_init_class(struct sk_buff_head *list, struct lock_class_key *class) { skb_queue_head_init(list); lockdep_set_class(&list->lock, class); } /* * Insert an sk_buff on a list. * * The "__skb_xxxx()" functions are the non-atomic ones that * can only be called with interrupts disabled. */ static inline void __skb_insert(struct sk_buff *newsk, struct sk_buff *prev, struct sk_buff *next, struct sk_buff_head *list) { /* See skb_queue_empty_lockless() and skb_peek_tail() * for the opposite READ_ONCE() */ WRITE_ONCE(newsk->next, next); WRITE_ONCE(newsk->prev, prev); WRITE_ONCE(((struct sk_buff_list *)next)->prev, newsk); WRITE_ONCE(((struct sk_buff_list *)prev)->next, newsk); WRITE_ONCE(list->qlen, list->qlen + 1); } static inline void __skb_queue_splice(const struct sk_buff_head *list, struct sk_buff *prev, struct sk_buff *next) { struct sk_buff *first = list->next; struct sk_buff *last = list->prev; WRITE_ONCE(first->prev, prev); WRITE_ONCE(prev->next, first); WRITE_ONCE(last->next, next); WRITE_ONCE(next->prev, last); } /** * skb_queue_splice - join two skb lists, this is designed for stacks * @list: the new list to add * @head: the place to add it in the first list */ static inline void skb_queue_splice(const struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, (struct sk_buff *) head, head->next); head->qlen += list->qlen; } } /** * skb_queue_splice_init - join two skb lists and reinitialise the emptied list * @list: the new list to add * @head: the place to add it in the first list * * The list at @list is reinitialised */ static inline void skb_queue_splice_init(struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, (struct sk_buff *) head, head->next); head->qlen += list->qlen; __skb_queue_head_init(list); } } /** * skb_queue_splice_tail - join two skb lists, each list being a queue * @list: the new list to add * @head: the place to add it in the first list */ static inline void skb_queue_splice_tail(const struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, head->prev, (struct sk_buff *) head); head->qlen += list->qlen; } } /** * skb_queue_splice_tail_init - join two skb lists and reinitialise the emptied list * @list: the new list to add * @head: the place to add it in the first list * * Each of the lists is a queue. * The list at @list is reinitialised */ static inline void skb_queue_splice_tail_init(struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, head->prev, (struct sk_buff *) head); head->qlen += list->qlen; __skb_queue_head_init(list); } } /** * __skb_queue_after - queue a buffer at the list head * @list: list to use * @prev: place after this buffer * @newsk: buffer to queue * * Queue a buffer int the middle of a list. This function takes no locks * and you must therefore hold required locks before calling it. * * A buffer cannot be placed on two lists at the same time. */ static inline void __skb_queue_after(struct sk_buff_head *list, struct sk_buff *prev, struct sk_buff *newsk) { __skb_insert(newsk, prev, ((struct sk_buff_list *)prev)->next, list); } void skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list); static inline void __skb_queue_before(struct sk_buff_head *list, struct sk_buff *next, struct sk_buff *newsk) { __skb_insert(newsk, ((struct sk_buff_list *)next)->prev, next, list); } /** * __skb_queue_head - queue a buffer at the list head * @list: list to use * @newsk: buffer to queue * * Queue a buffer at the start of a list. This function takes no locks * and you must therefore hold required locks before calling it. * * A buffer cannot be placed on two lists at the same time. */ static inline void __skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk) { __skb_queue_after(list, (struct sk_buff *)list, newsk); } void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk); /** * __skb_queue_tail - queue a buffer at the list tail * @list: list to use * @newsk: buffer to queue * * Queue a buffer at the end of a list. This function takes no locks * and you must therefore hold required locks before calling it. * * A buffer cannot be placed on two lists at the same time. */ static inline void __skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk) { __skb_queue_before(list, (struct sk_buff *)list, newsk); } void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk); /* * remove sk_buff from list. _Must_ be called atomically, and with * the list known.. */ void skb_unlink(struct sk_buff *skb, struct sk_buff_head *list); static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) { struct sk_buff *next, *prev; WRITE_ONCE(list->qlen, list->qlen - 1); next = skb->next; prev = skb->prev; skb->next = skb->prev = NULL; WRITE_ONCE(next->prev, prev); WRITE_ONCE(prev->next, next); } /** * __skb_dequeue - remove from the head of the queue * @list: list to dequeue from * * Remove the head of the list. This function does not take any locks * so must be used with appropriate locks held only. The head item is * returned or %NULL if the list is empty. */ static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list) { struct sk_buff *skb = skb_peek(list); if (skb) __skb_unlink(skb, list); return skb; } struct sk_buff *skb_dequeue(struct sk_buff_head *list); /** * __skb_dequeue_tail - remove from the tail of the queue * @list: list to dequeue from * * Remove the tail of the list. This function does not take any locks * so must be used with appropriate locks held only. The tail item is * returned or %NULL if the list is empty. */ static inline struct sk_buff *__skb_dequeue_tail(struct sk_buff_head *list) { struct sk_buff *skb = skb_peek_tail(list); if (skb) __skb_unlink(skb, list); return skb; } struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list); static inline bool skb_is_nonlinear(const struct sk_buff *skb) { return skb->data_len; } static inline unsigned int skb_headlen(const struct sk_buff *skb) { return skb->len - skb->data_len; } static inline unsigned int __skb_pagelen(const struct sk_buff *skb) { unsigned int i, len = 0; for (i = skb_shinfo(skb)->nr_frags - 1; (int)i >= 0; i--) len += skb_frag_size(&skb_shinfo(skb)->frags[i]); return len; } static inline unsigned int skb_pagelen(const struct sk_buff *skb) { return skb_headlen(skb) + __skb_pagelen(skb); } static inline void skb_frag_fill_netmem_desc(skb_frag_t *frag, netmem_ref netmem, int off, int size) { frag->netmem = netmem; frag->offset = off; skb_frag_size_set(frag, size); } static inline void skb_frag_fill_page_desc(skb_frag_t *frag, struct page *page, int off, int size) { skb_frag_fill_netmem_desc(frag, page_to_netmem(page), off, size); } static inline void __skb_fill_netmem_desc_noacc(struct skb_shared_info *shinfo, int i, netmem_ref netmem, int off, int size) { skb_frag_t *frag = &shinfo->frags[i]; skb_frag_fill_netmem_desc(frag, netmem, off, size); } static inline void __skb_fill_page_desc_noacc(struct skb_shared_info *shinfo, int i, struct page *page, int off, int size) { __skb_fill_netmem_desc_noacc(shinfo, i, page_to_netmem(page), off, size); } /** * skb_len_add - adds a number to len fields of skb * @skb: buffer to add len to * @delta: number of bytes to add */ static inline void skb_len_add(struct sk_buff *skb, int delta) { skb->len += delta; skb->data_len += delta; skb->truesize += delta; } /** * __skb_fill_netmem_desc - initialise a fragment in an skb * @skb: buffer containing fragment to be initialised * @i: fragment index to initialise * @netmem: the netmem to use for this fragment * @off: the offset to the data with @page * @size: the length of the data * * Initialises the @i'th fragment of @skb to point to &size bytes at * offset @off within @page. * * Does not take any additional reference on the fragment. */ static inline void __skb_fill_netmem_desc(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size) { struct page *page = netmem_to_page(netmem); __skb_fill_netmem_desc_noacc(skb_shinfo(skb), i, netmem, off, size); /* Propagate page pfmemalloc to the skb if we can. The problem is * that not all callers have unique ownership of the page but rely * on page_is_pfmemalloc doing the right thing(tm). */ page = compound_head(page); if (page_is_pfmemalloc(page)) skb->pfmemalloc = true; } static inline void __skb_fill_page_desc(struct sk_buff *skb, int i, struct page *page, int off, int size) { __skb_fill_netmem_desc(skb, i, page_to_netmem(page), off, size); } static inline void skb_fill_netmem_desc(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size) { __skb_fill_netmem_desc(skb, i, netmem, off, size); skb_shinfo(skb)->nr_frags = i + 1; } /** * skb_fill_page_desc - initialise a paged fragment in an skb * @skb: buffer containing fragment to be initialised * @i: paged fragment index to initialise * @page: the page to use for this fragment * @off: the offset to the data with @page * @size: the length of the data * * As per __skb_fill_page_desc() -- initialises the @i'th fragment of * @skb to point to @size bytes at offset @off within @page. In * addition updates @skb such that @i is the last fragment. * * Does not take any additional reference on the fragment. */ static inline void skb_fill_page_desc(struct sk_buff *skb, int i, struct page *page, int off, int size) { skb_fill_netmem_desc(skb, i, page_to_netmem(page), off, size); } /** * skb_fill_page_desc_noacc - initialise a paged fragment in an skb * @skb: buffer containing fragment to be initialised * @i: paged fragment index to initialise * @page: the page to use for this fragment * @off: the offset to the data with @page * @size: the length of the data * * Variant of skb_fill_page_desc() which does not deal with * pfmemalloc, if page is not owned by us. */ static inline void skb_fill_page_desc_noacc(struct sk_buff *skb, int i, struct page *page, int off, int size) { struct skb_shared_info *shinfo = skb_shinfo(skb); __skb_fill_page_desc_noacc(shinfo, i, page, off, size); shinfo->nr_frags = i + 1; } void skb_add_rx_frag_netmem(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size, unsigned int truesize); static inline void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off, int size, unsigned int truesize) { skb_add_rx_frag_netmem(skb, i, page_to_netmem(page), off, size, truesize); } void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size, unsigned int truesize); #define SKB_LINEAR_ASSERT(skb) BUG_ON(skb_is_nonlinear(skb)) #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_tail_pointer(const struct sk_buff *skb) { return skb->head + skb->tail; } static inline void skb_reset_tail_pointer(struct sk_buff *skb) { skb->tail = skb->data - skb->head; } static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset) { skb_reset_tail_pointer(skb); skb->tail += offset; } #else /* NET_SKBUFF_DATA_USES_OFFSET */ static inline unsigned char *skb_tail_pointer(const struct sk_buff *skb) { return skb->tail; } static inline void skb_reset_tail_pointer(struct sk_buff *skb) { skb->tail = skb->data; } static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset) { skb->tail = skb->data + offset; } #endif /* NET_SKBUFF_DATA_USES_OFFSET */ static inline void skb_assert_len(struct sk_buff *skb) { #ifdef CONFIG_DEBUG_NET if (WARN_ONCE(!skb->len, "%s\n", __func__)) DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false); #endif /* CONFIG_DEBUG_NET */ } /* * Add data to an sk_buff */ void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len); void *skb_put(struct sk_buff *skb, unsigned int len); static inline void *__skb_put(struct sk_buff *skb, unsigned int len) { void *tmp = skb_tail_pointer(skb); SKB_LINEAR_ASSERT(skb); skb->tail += len; skb->len += len; return tmp; } static inline void *__skb_put_zero(struct sk_buff *skb, unsigned int len) { void *tmp = __skb_put(skb, len); memset(tmp, 0, len); return tmp; } static inline void *__skb_put_data(struct sk_buff *skb, const void *data, unsigned int len) { void *tmp = __skb_put(skb, len); memcpy(tmp, data, len); return tmp; } static inline void __skb_put_u8(struct sk_buff *skb, u8 val) { *(u8 *)__skb_put(skb, 1) = val; } static inline void *skb_put_zero(struct sk_buff *skb, unsigned int len) { void *tmp = skb_put(skb, len); memset(tmp, 0, len); return tmp; } static inline void *skb_put_data(struct sk_buff *skb, const void *data, unsigned int len) { void *tmp = skb_put(skb, len); memcpy(tmp, data, len); return tmp; } static inline void skb_put_u8(struct sk_buff *skb, u8 val) { *(u8 *)skb_put(skb, 1) = val; } void *skb_push(struct sk_buff *skb, unsigned int len); static inline void *__skb_push(struct sk_buff *skb, unsigned int len) { DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); skb->data -= len; skb->len += len; return skb->data; } void *skb_pull(struct sk_buff *skb, unsigned int len); static inline void *__skb_pull(struct sk_buff *skb, unsigned int len) { DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); skb->len -= len; if (unlikely(skb->len < skb->data_len)) { #if defined(CONFIG_DEBUG_NET) skb->len += len; pr_err("__skb_pull(len=%u)\n", len); skb_dump(KERN_ERR, skb, false); #endif BUG(); } return skb->data += len; } static inline void *skb_pull_inline(struct sk_buff *skb, unsigned int len) { return unlikely(len > skb->len) ? NULL : __skb_pull(skb, len); } void *skb_pull_data(struct sk_buff *skb, size_t len); void *__pskb_pull_tail(struct sk_buff *skb, int delta); static inline enum skb_drop_reason pskb_may_pull_reason(struct sk_buff *skb, unsigned int len) { DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); if (likely(len <= skb_headlen(skb))) return SKB_NOT_DROPPED_YET; if (unlikely(len > skb->len)) return SKB_DROP_REASON_PKT_TOO_SMALL; if (unlikely(!__pskb_pull_tail(skb, len - skb_headlen(skb)))) return SKB_DROP_REASON_NOMEM; return SKB_NOT_DROPPED_YET; } static inline bool pskb_may_pull(struct sk_buff *skb, unsigned int len) { return pskb_may_pull_reason(skb, len) == SKB_NOT_DROPPED_YET; } static inline void *pskb_pull(struct sk_buff *skb, unsigned int len) { if (!pskb_may_pull(skb, len)) return NULL; skb->len -= len; return skb->data += len; } void skb_condense(struct sk_buff *skb); /** * skb_headroom - bytes at buffer head * @skb: buffer to check * * Return the number of bytes of free space at the head of an &sk_buff. */ static inline unsigned int skb_headroom(const struct sk_buff *skb) { return skb->data - skb->head; } /** * skb_tailroom - bytes at buffer end * @skb: buffer to check * * Return the number of bytes of free space at the tail of an sk_buff */ static inline int skb_tailroom(const struct sk_buff *skb) { return skb_is_nonlinear(skb) ? 0 : skb->end - skb->tail; } /** * skb_availroom - bytes at buffer end * @skb: buffer to check * * Return the number of bytes of free space at the tail of an sk_buff * allocated by sk_stream_alloc() */ static inline int skb_availroom(const struct sk_buff *skb) { if (skb_is_nonlinear(skb)) return 0; return skb->end - skb->tail - skb->reserved_tailroom; } /** * skb_reserve - adjust headroom * @skb: buffer to alter * @len: bytes to move * * Increase the headroom of an empty &sk_buff by reducing the tail * room. This is only allowed for an empty buffer. */ static inline void skb_reserve(struct sk_buff *skb, int len) { skb->data += len; skb->tail += len; } /** * skb_tailroom_reserve - adjust reserved_tailroom * @skb: buffer to alter * @mtu: maximum amount of headlen permitted * @needed_tailroom: minimum amount of reserved_tailroom * * Set reserved_tailroom so that headlen can be as large as possible but * not larger than mtu and tailroom cannot be smaller than * needed_tailroom. * The required headroom should already have been reserved before using * this function. */ static inline void skb_tailroom_reserve(struct sk_buff *skb, unsigned int mtu, unsigned int needed_tailroom) { SKB_LINEAR_ASSERT(skb); if (mtu < skb_tailroom(skb) - needed_tailroom) /* use at most mtu */ skb->reserved_tailroom = skb_tailroom(skb) - mtu; else /* use up to all available space */ skb->reserved_tailroom = needed_tailroom; } #define ENCAP_TYPE_ETHER 0 #define ENCAP_TYPE_IPPROTO 1 static inline void skb_set_inner_protocol(struct sk_buff *skb, __be16 protocol) { skb->inner_protocol = protocol; skb->inner_protocol_type = ENCAP_TYPE_ETHER; } static inline void skb_set_inner_ipproto(struct sk_buff *skb, __u8 ipproto) { skb->inner_ipproto = ipproto; skb->inner_protocol_type = ENCAP_TYPE_IPPROTO; } static inline void skb_reset_inner_headers(struct sk_buff *skb) { skb->inner_mac_header = skb->mac_header; skb->inner_network_header = skb->network_header; skb->inner_transport_header = skb->transport_header; } static inline void skb_reset_mac_len(struct sk_buff *skb) { skb->mac_len = skb->network_header - skb->mac_header; } static inline unsigned char *skb_inner_transport_header(const struct sk_buff *skb) { return skb->head + skb->inner_transport_header; } static inline int skb_inner_transport_offset(const struct sk_buff *skb) { return skb_inner_transport_header(skb) - skb->data; } static inline void skb_reset_inner_transport_header(struct sk_buff *skb) { skb->inner_transport_header = skb->data - skb->head; } static inline void skb_set_inner_transport_header(struct sk_buff *skb, const int offset) { skb_reset_inner_transport_header(skb); skb->inner_transport_header += offset; } static inline unsigned char *skb_inner_network_header(const struct sk_buff *skb) { return skb->head + skb->inner_network_header; } static inline void skb_reset_inner_network_header(struct sk_buff *skb) { skb->inner_network_header = skb->data - skb->head; } static inline void skb_set_inner_network_header(struct sk_buff *skb, const int offset) { skb_reset_inner_network_header(skb); skb->inner_network_header += offset; } static inline bool skb_inner_network_header_was_set(const struct sk_buff *skb) { return skb->inner_network_header > 0; } static inline unsigned char *skb_inner_mac_header(const struct sk_buff *skb) { return skb->head + skb->inner_mac_header; } static inline void skb_reset_inner_mac_header(struct sk_buff *skb) { skb->inner_mac_header = skb->data - skb->head; } static inline void skb_set_inner_mac_header(struct sk_buff *skb, const int offset) { skb_reset_inner_mac_header(skb); skb->inner_mac_header += offset; } static inline bool skb_transport_header_was_set(const struct sk_buff *skb) { return skb->transport_header != (typeof(skb->transport_header))~0U; } static inline unsigned char *skb_transport_header(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb)); return skb->head + skb->transport_header; } static inline void skb_reset_transport_header(struct sk_buff *skb) { skb->transport_header = skb->data - skb->head; } static inline void skb_set_transport_header(struct sk_buff *skb, const int offset) { skb_reset_transport_header(skb); skb->transport_header += offset; } static inline unsigned char *skb_network_header(const struct sk_buff *skb) { return skb->head + skb->network_header; } static inline void skb_reset_network_header(struct sk_buff *skb) { skb->network_header = skb->data - skb->head; } static inline void skb_set_network_header(struct sk_buff *skb, const int offset) { skb_reset_network_header(skb); skb->network_header += offset; } static inline int skb_mac_header_was_set(const struct sk_buff *skb) { return skb->mac_header != (typeof(skb->mac_header))~0U; } static inline unsigned char *skb_mac_header(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_mac_header_was_set(skb)); return skb->head + skb->mac_header; } static inline int skb_mac_offset(const struct sk_buff *skb) { return skb_mac_header(skb) - skb->data; } static inline u32 skb_mac_header_len(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_mac_header_was_set(skb)); return skb->network_header - skb->mac_header; } static inline void skb_unset_mac_header(struct sk_buff *skb) { skb->mac_header = (typeof(skb->mac_header))~0U; } static inline void skb_reset_mac_header(struct sk_buff *skb) { skb->mac_header = skb->data - skb->head; } static inline void skb_set_mac_header(struct sk_buff *skb, const int offset) { skb_reset_mac_header(skb); skb->mac_header += offset; } static inline void skb_pop_mac_header(struct sk_buff *skb) { skb->mac_header = skb->network_header; } static inline void skb_probe_transport_header(struct sk_buff *skb) { struct flow_keys_basic keys; if (skb_transport_header_was_set(skb)) return; if (skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, NULL, 0, 0, 0, 0)) skb_set_transport_header(skb, keys.control.thoff); } static inline void skb_mac_header_rebuild(struct sk_buff *skb) { if (skb_mac_header_was_set(skb)) { const unsigned char *old_mac = skb_mac_header(skb); skb_set_mac_header(skb, -skb->mac_len); memmove(skb_mac_header(skb), old_mac, skb->mac_len); } } /* Move the full mac header up to current network_header. * Leaves skb->data pointing at offset skb->mac_len into the mac_header. * Must be provided the complete mac header length. */ static inline void skb_mac_header_rebuild_full(struct sk_buff *skb, u32 full_mac_len) { if (skb_mac_header_was_set(skb)) { const unsigned char *old_mac = skb_mac_header(skb); skb_set_mac_header(skb, -full_mac_len); memmove(skb_mac_header(skb), old_mac, full_mac_len); __skb_push(skb, full_mac_len - skb->mac_len); } } static inline int skb_checksum_start_offset(const struct sk_buff *skb) { return skb->csum_start - skb_headroom(skb); } static inline unsigned char *skb_checksum_start(const struct sk_buff *skb) { return skb->head + skb->csum_start; } static inline int skb_transport_offset(const struct sk_buff *skb) { return skb_transport_header(skb) - skb->data; } static inline u32 skb_network_header_len(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb)); return skb->transport_header - skb->network_header; } static inline u32 skb_inner_network_header_len(const struct sk_buff *skb) { return skb->inner_transport_header - skb->inner_network_header; } static inline int skb_network_offset(const struct sk_buff *skb) { return skb_network_header(skb) - skb->data; } static inline int skb_inner_network_offset(const struct sk_buff *skb) { return skb_inner_network_header(skb) - skb->data; } static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len) { return pskb_may_pull(skb, skb_network_offset(skb) + len); } /* * CPUs often take a performance hit when accessing unaligned memory * locations. The actual performance hit varies, it can be small if the * hardware handles it or large if we have to take an exception and fix it * in software. * * Since an ethernet header is 14 bytes network drivers often end up with * the IP header at an unaligned offset. The IP header can be aligned by * shifting the start of the packet by 2 bytes. Drivers should do this * with: * * skb_reserve(skb, NET_IP_ALIGN); * * The downside to this alignment of the IP header is that the DMA is now * unaligned. On some architectures the cost of an unaligned DMA is high * and this cost outweighs the gains made by aligning the IP header. * * Since this trade off varies between architectures, we allow NET_IP_ALIGN * to be overridden. */ #ifndef NET_IP_ALIGN #define NET_IP_ALIGN 2 #endif /* * The networking layer reserves some headroom in skb data (via * dev_alloc_skb). This is used to avoid having to reallocate skb data when * the header has to grow. In the default case, if the header has to grow * 32 bytes or less we avoid the reallocation. * * Unfortunately this headroom changes the DMA alignment of the resulting * network packet. As for NET_IP_ALIGN, this unaligned DMA is expensive * on some architectures. An architecture can override this value, * perhaps setting it to a cacheline in size (since that will maintain * cacheline alignment of the DMA). It must be a power of 2. * * Various parts of the networking layer expect at least 32 bytes of * headroom, you should not reduce this. * * Using max(32, L1_CACHE_BYTES) makes sense (especially with RPS) * to reduce average number of cache lines per packet. * get_rps_cpu() for example only access one 64 bytes aligned block : * NET_IP_ALIGN(2) + ethernet_header(14) + IP_header(20/40) + ports(8) */ #ifndef NET_SKB_PAD #define NET_SKB_PAD max(32, L1_CACHE_BYTES) #endif int ___pskb_trim(struct sk_buff *skb, unsigned int len); static inline void __skb_set_length(struct sk_buff *skb, unsigned int len) { if (WARN_ON(skb_is_nonlinear(skb))) return; skb->len = len; skb_set_tail_pointer(skb, len); } static inline void __skb_trim(struct sk_buff *skb, unsigned int len) { __skb_set_length(skb, len); } void skb_trim(struct sk_buff *skb, unsigned int len); static inline int __pskb_trim(struct sk_buff *skb, unsigned int len) { if (skb->data_len) return ___pskb_trim(skb, len); __skb_trim(skb, len); return 0; } static inline int pskb_trim(struct sk_buff *skb, unsigned int len) { return (len < skb->len) ? __pskb_trim(skb, len) : 0; } /** * pskb_trim_unique - remove end from a paged unique (not cloned) buffer * @skb: buffer to alter * @len: new length * * This is identical to pskb_trim except that the caller knows that * the skb is not cloned so we should never get an error due to out- * of-memory. */ static inline void pskb_trim_unique(struct sk_buff *skb, unsigned int len) { int err = pskb_trim(skb, len); BUG_ON(err); } static inline int __skb_grow(struct sk_buff *skb, unsigned int len) { unsigned int diff = len - skb->len; if (skb_tailroom(skb) < diff) { int ret = pskb_expand_head(skb, 0, diff - skb_tailroom(skb), GFP_ATOMIC); if (ret) return ret; } __skb_set_length(skb, len); return 0; } /** * skb_orphan - orphan a buffer * @skb: buffer to orphan * * If a buffer currently has an owner then we call the owner's * destructor function and make the @skb unowned. The buffer continues * to exist but is no longer charged to its former owner. */ static inline void skb_orphan(struct sk_buff *skb) { if (skb->destructor) { skb->destructor(skb); skb->destructor = NULL; skb->sk = NULL; } else { BUG_ON(skb->sk); } } /** * skb_orphan_frags - orphan the frags contained in a buffer * @skb: buffer to orphan frags from * @gfp_mask: allocation mask for replacement pages * * For each frag in the SKB which needs a destructor (i.e. has an * owner) create a copy of that frag and release the original * page by calling the destructor. */ static inline int skb_orphan_frags(struct sk_buff *skb, gfp_t gfp_mask) { if (likely(!skb_zcopy(skb))) return 0; if (skb_shinfo(skb)->flags & SKBFL_DONT_ORPHAN) return 0; return skb_copy_ubufs(skb, gfp_mask); } /* Frags must be orphaned, even if refcounted, if skb might loop to rx path */ static inline int skb_orphan_frags_rx(struct sk_buff *skb, gfp_t gfp_mask) { if (likely(!skb_zcopy(skb))) return 0; return skb_copy_ubufs(skb, gfp_mask); } /** * __skb_queue_purge_reason - empty a list * @list: list to empty * @reason: drop reason * * Delete all buffers on an &sk_buff list. Each buffer is removed from * the list and one reference dropped. This function does not take the * list lock and the caller must hold the relevant locks to use it. */ static inline void __skb_queue_purge_reason(struct sk_buff_head *list, enum skb_drop_reason reason) { struct sk_buff *skb; while ((skb = __skb_dequeue(list)) != NULL) kfree_skb_reason(skb, reason); } static inline void __skb_queue_purge(struct sk_buff_head *list) { __skb_queue_purge_reason(list, SKB_DROP_REASON_QUEUE_PURGE); } void skb_queue_purge_reason(struct sk_buff_head *list, enum skb_drop_reason reason); static inline void skb_queue_purge(struct sk_buff_head *list) { skb_queue_purge_reason(list, SKB_DROP_REASON_QUEUE_PURGE); } unsigned int skb_rbtree_purge(struct rb_root *root); void skb_errqueue_purge(struct sk_buff_head *list); void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask); /** * netdev_alloc_frag - allocate a page fragment * @fragsz: fragment size * * Allocates a frag from a page for receive buffer. * Uses GFP_ATOMIC allocations. */ static inline void *netdev_alloc_frag(unsigned int fragsz) { return __netdev_alloc_frag_align(fragsz, ~0u); } static inline void *netdev_alloc_frag_align(unsigned int fragsz, unsigned int align) { WARN_ON_ONCE(!is_power_of_2(align)); return __netdev_alloc_frag_align(fragsz, -align); } struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int length, gfp_t gfp_mask); /** * netdev_alloc_skb - allocate an skbuff for rx on a specific device * @dev: network device to receive on * @length: length to allocate * * Allocate a new &sk_buff and assign it a usage count of one. The * buffer has unspecified headroom built in. Users should allocate * the headroom they think they need without accounting for the * built in space. The built in space is used for optimisations. * * %NULL is returned if there is no free memory. Although this function * allocates memory it can be called from an interrupt. */ static inline struct sk_buff *netdev_alloc_skb(struct net_device *dev, unsigned int length) { return __netdev_alloc_skb(dev, length, GFP_ATOMIC); } /* legacy helper around __netdev_alloc_skb() */ static inline struct sk_buff *__dev_alloc_skb(unsigned int length, gfp_t gfp_mask) { return __netdev_alloc_skb(NULL, length, gfp_mask); } /* legacy helper around netdev_alloc_skb() */ static inline struct sk_buff *dev_alloc_skb(unsigned int length) { return netdev_alloc_skb(NULL, length); } static inline struct sk_buff *__netdev_alloc_skb_ip_align(struct net_device *dev, unsigned int length, gfp_t gfp) { struct sk_buff *skb = __netdev_alloc_skb(dev, length + NET_IP_ALIGN, gfp); if (NET_IP_ALIGN && skb) skb_reserve(skb, NET_IP_ALIGN); return skb; } static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev, unsigned int length) { return __netdev_alloc_skb_ip_align(dev, length, GFP_ATOMIC); } static inline void skb_free_frag(void *addr) { page_frag_free(addr); } void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask); static inline void *napi_alloc_frag(unsigned int fragsz) { return __napi_alloc_frag_align(fragsz, ~0u); } static inline void *napi_alloc_frag_align(unsigned int fragsz, unsigned int align) { WARN_ON_ONCE(!is_power_of_2(align)); return __napi_alloc_frag_align(fragsz, -align); } struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int length); void napi_consume_skb(struct sk_buff *skb, int budget); void napi_skb_free_stolen_head(struct sk_buff *skb); void __napi_kfree_skb(struct sk_buff *skb, enum skb_drop_reason reason); /** * __dev_alloc_pages - allocate page for network Rx * @gfp_mask: allocation priority. Set __GFP_NOMEMALLOC if not for network Rx * @order: size of the allocation * * Allocate a new page. * * %NULL is returned if there is no free memory. */ static inline struct page *__dev_alloc_pages_noprof(gfp_t gfp_mask, unsigned int order) { /* This piece of code contains several assumptions. * 1. This is for device Rx, therefore a cold page is preferred. * 2. The expectation is the user wants a compound page. * 3. If requesting a order 0 page it will not be compound * due to the check to see if order has a value in prep_new_page * 4. __GFP_MEMALLOC is ignored if __GFP_NOMEMALLOC is set due to * code in gfp_to_alloc_flags that should be enforcing this. */ gfp_mask |= __GFP_COMP | __GFP_MEMALLOC; return alloc_pages_node_noprof(NUMA_NO_NODE, gfp_mask, order); } #define __dev_alloc_pages(...) alloc_hooks(__dev_alloc_pages_noprof(__VA_ARGS__)) /* * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). */ #define dev_alloc_pages(_order) __dev_alloc_pages(GFP_ATOMIC | __GFP_NOWARN, _order) /** * __dev_alloc_page - allocate a page for network Rx * @gfp_mask: allocation priority. Set __GFP_NOMEMALLOC if not for network Rx * * Allocate a new page. * * %NULL is returned if there is no free memory. */ static inline struct page *__dev_alloc_page_noprof(gfp_t gfp_mask) { return __dev_alloc_pages_noprof(gfp_mask, 0); } #define __dev_alloc_page(...) alloc_hooks(__dev_alloc_page_noprof(__VA_ARGS__)) /* * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). */ #define dev_alloc_page() dev_alloc_pages(0) /** * dev_page_is_reusable - check whether a page can be reused for network Rx * @page: the page to test * * A page shouldn't be considered for reusing/recycling if it was allocated * under memory pressure or at a distant memory node. * * Returns false if this page should be returned to page allocator, true * otherwise. */ static inline bool dev_page_is_reusable(const struct page *page) { return likely(page_to_nid(page) == numa_mem_id() && !page_is_pfmemalloc(page)); } /** * skb_propagate_pfmemalloc - Propagate pfmemalloc if skb is allocated after RX page * @page: The page that was allocated from skb_alloc_page * @skb: The skb that may need pfmemalloc set */ static inline void skb_propagate_pfmemalloc(const struct page *page, struct sk_buff *skb) { if (page_is_pfmemalloc(page)) skb->pfmemalloc = true; } /** * skb_frag_off() - Returns the offset of a skb fragment * @frag: the paged fragment */ static inline unsigned int skb_frag_off(const skb_frag_t *frag) { return frag->offset; } /** * skb_frag_off_add() - Increments the offset of a skb fragment by @delta * @frag: skb fragment * @delta: value to add */ static inline void skb_frag_off_add(skb_frag_t *frag, int delta) { frag->offset += delta; } /** * skb_frag_off_set() - Sets the offset of a skb fragment * @frag: skb fragment * @offset: offset of fragment */ static inline void skb_frag_off_set(skb_frag_t *frag, unsigned int offset) { frag->offset = offset; } /** * skb_frag_off_copy() - Sets the offset of a skb fragment from another fragment * @fragto: skb fragment where offset is set * @fragfrom: skb fragment offset is copied from */ static inline void skb_frag_off_copy(skb_frag_t *fragto, const skb_frag_t *fragfrom) { fragto->offset = fragfrom->offset; } /** * skb_frag_page - retrieve the page referred to by a paged fragment * @frag: the paged fragment * * Returns the &struct page associated with @frag. */ static inline struct page *skb_frag_page(const skb_frag_t *frag) { return netmem_to_page(frag->netmem); } int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, unsigned int headroom); int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, struct bpf_prog *prog); /** * skb_frag_address - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer * * Returns the address of the data within @frag. The page must already * be mapped. */ static inline void *skb_frag_address(const skb_frag_t *frag) { return page_address(skb_frag_page(frag)) + skb_frag_off(frag); } /** * skb_frag_address_safe - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer * * Returns the address of the data within @frag. Checks that the page * is mapped and returns %NULL otherwise. */ static inline void *skb_frag_address_safe(const skb_frag_t *frag) { void *ptr = page_address(skb_frag_page(frag)); if (unlikely(!ptr)) return NULL; return ptr + skb_frag_off(frag); } /** * skb_frag_page_copy() - sets the page in a fragment from another fragment * @fragto: skb fragment where page is set * @fragfrom: skb fragment page is copied from */ static inline void skb_frag_page_copy(skb_frag_t *fragto, const skb_frag_t *fragfrom) { fragto->netmem = fragfrom->netmem; } bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio); /** * skb_frag_dma_map - maps a paged fragment via the DMA API * @dev: the device to map the fragment to * @frag: the paged fragment to map * @offset: the offset within the fragment (starting at the * fragment's own offset) * @size: the number of bytes to map * @dir: the direction of the mapping (``PCI_DMA_*``) * * Maps the page associated with @frag to @device. */ static inline dma_addr_t skb_frag_dma_map(struct device *dev, const skb_frag_t *frag, size_t offset, size_t size, enum dma_data_direction dir) { return dma_map_page(dev, skb_frag_page(frag), skb_frag_off(frag) + offset, size, dir); } static inline struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask) { return __pskb_copy(skb, skb_headroom(skb), gfp_mask); } static inline struct sk_buff *pskb_copy_for_clone(struct sk_buff *skb, gfp_t gfp_mask) { return __pskb_copy_fclone(skb, skb_headroom(skb), gfp_mask, true); } /** * skb_clone_writable - is the header of a clone writable * @skb: buffer to check * @len: length up to which to write * * Returns true if modifying the header part of the cloned buffer * does not requires the data to be copied. */ static inline int skb_clone_writable(const struct sk_buff *skb, unsigned int len) { return !skb_header_cloned(skb) && skb_headroom(skb) + len <= skb->hdr_len; } static inline int skb_try_make_writable(struct sk_buff *skb, unsigned int write_len) { return skb_cloned(skb) && !skb_clone_writable(skb, write_len) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC); } static inline int __skb_cow(struct sk_buff *skb, unsigned int headroom, int cloned) { int delta = 0; if (headroom > skb_headroom(skb)) delta = headroom - skb_headroom(skb); if (delta || cloned) return pskb_expand_head(skb, ALIGN(delta, NET_SKB_PAD), 0, GFP_ATOMIC); return 0; } /** * skb_cow - copy header of skb when it is required * @skb: buffer to cow * @headroom: needed headroom * * If the skb passed lacks sufficient headroom or its data part * is shared, data is reallocated. If reallocation fails, an error * is returned and original skb is not changed. * * The result is skb with writable area skb->head...skb->tail * and at least @headroom of space at head. */ static inline int skb_cow(struct sk_buff *skb, unsigned int headroom) { return __skb_cow(skb, headroom, skb_cloned(skb)); } /** * skb_cow_head - skb_cow but only making the head writable * @skb: buffer to cow * @headroom: needed headroom * * This function is identical to skb_cow except that we replace the * skb_cloned check by skb_header_cloned. It should be used when * you only need to push on some header and do not need to modify * the data. */ static inline int skb_cow_head(struct sk_buff *skb, unsigned int headroom) { return __skb_cow(skb, headroom, skb_header_cloned(skb)); } /** * skb_padto - pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error. */ static inline int skb_padto(struct sk_buff *skb, unsigned int len) { unsigned int size = skb->len; if (likely(size >= len)) return 0; return skb_pad(skb, len - size); } /** * __skb_put_padto - increase size and pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length * @free_on_error: free buffer on error * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error if @free_on_error is true. */ static inline int __must_check __skb_put_padto(struct sk_buff *skb, unsigned int len, bool free_on_error) { unsigned int size = skb->len; if (unlikely(size < len)) { len -= size; if (__skb_pad(skb, len, free_on_error)) return -ENOMEM; __skb_put(skb, len); } return 0; } /** * skb_put_padto - increase size and pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error. */ static inline int __must_check skb_put_padto(struct sk_buff *skb, unsigned int len) { return __skb_put_padto(skb, len, true); } bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i) __must_check; static inline int skb_add_data(struct sk_buff *skb, struct iov_iter *from, int copy) { const int off = skb->len; if (skb->ip_summed == CHECKSUM_NONE) { __wsum csum = 0; if (csum_and_copy_from_iter_full(skb_put(skb, copy), copy, &csum, from)) { skb->csum = csum_block_add(skb->csum, csum, off); return 0; } } else if (copy_from_iter_full(skb_put(skb, copy), copy, from)) return 0; __skb_trim(skb, off); return -EFAULT; } static inline bool skb_can_coalesce(struct sk_buff *skb, int i, const struct page *page, int off) { if (skb_zcopy(skb)) return false; if (i) { const skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1]; return page == skb_frag_page(frag) && off == skb_frag_off(frag) + skb_frag_size(frag); } return false; } static inline int __skb_linearize(struct sk_buff *skb) { return __pskb_pull_tail(skb, skb->data_len) ? 0 : -ENOMEM; } /** * skb_linearize - convert paged skb to linear one * @skb: buffer to linarize * * If there is no free memory -ENOMEM is returned, otherwise zero * is returned and the old skb data released. */ static inline int skb_linearize(struct sk_buff *skb) { return skb_is_nonlinear(skb) ? __skb_linearize(skb) : 0; } /** * skb_has_shared_frag - can any frag be overwritten * @skb: buffer to test * * Return true if the skb has at least one frag that might be modified * by an external entity (as in vmsplice()/sendfile()) */ static inline bool skb_has_shared_frag(const struct sk_buff *skb) { return skb_is_nonlinear(skb) && skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG; } /** * skb_linearize_cow - make sure skb is linear and writable * @skb: buffer to process * * If there is no free memory -ENOMEM is returned, otherwise zero * is returned and the old skb data released. */ static inline int skb_linearize_cow(struct sk_buff *skb) { return skb_is_nonlinear(skb) || skb_cloned(skb) ? __skb_linearize(skb) : 0; } static __always_inline void __skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len, unsigned int off) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_block_sub(skb->csum, csum_partial(start, len, 0), off); else if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start_offset(skb) < 0) skb->ip_summed = CHECKSUM_NONE; } /** * skb_postpull_rcsum - update checksum for received skb after pull * @skb: buffer to update * @start: start of data before pull * @len: length of data pulled * * After doing a pull on a received packet, you need to call this to * update the CHECKSUM_COMPLETE checksum, or set ip_summed to * CHECKSUM_NONE so that it can be recomputed from scratch. */ static inline void skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = wsum_negate(csum_partial(start, len, wsum_negate(skb->csum))); else if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start_offset(skb) < 0) skb->ip_summed = CHECKSUM_NONE; } static __always_inline void __skb_postpush_rcsum(struct sk_buff *skb, const void *start, unsigned int len, unsigned int off) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_block_add(skb->csum, csum_partial(start, len, 0), off); } /** * skb_postpush_rcsum - update checksum for received skb after push * @skb: buffer to update * @start: start of data after push * @len: length of data pushed * * After doing a push on a received packet, you need to call this to * update the CHECKSUM_COMPLETE checksum. */ static inline void skb_postpush_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { __skb_postpush_rcsum(skb, start, len, 0); } void *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); /** * skb_push_rcsum - push skb and update receive checksum * @skb: buffer to update * @len: length of data pulled * * This function performs an skb_push on the packet and updates * the CHECKSUM_COMPLETE checksum. It should be used on * receive path processing instead of skb_push unless you know * that the checksum difference is zero (e.g., a valid IP header) * or you are setting ip_summed to CHECKSUM_NONE. */ static inline void *skb_push_rcsum(struct sk_buff *skb, unsigned int len) { skb_push(skb, len); skb_postpush_rcsum(skb, skb->data, len); return skb->data; } int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len); /** * pskb_trim_rcsum - trim received skb and update checksum * @skb: buffer to trim * @len: new length * * This is exactly the same as pskb_trim except that it ensures the * checksum of received packets are still valid after the operation. * It can change skb pointers. */ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) { if (likely(len >= skb->len)) return 0; return pskb_trim_rcsum_slow(skb, len); } static inline int __skb_trim_rcsum(struct sk_buff *skb, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; __skb_trim(skb, len); return 0; } static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; return __skb_grow(skb, len); } #define rb_to_skb(rb) rb_entry_safe(rb, struct sk_buff, rbnode) #define skb_rb_first(root) rb_to_skb(rb_first(root)) #define skb_rb_last(root) rb_to_skb(rb_last(root)) #define skb_rb_next(skb) rb_to_skb(rb_next(&(skb)->rbnode)) #define skb_rb_prev(skb) rb_to_skb(rb_prev(&(skb)->rbnode)) #define skb_queue_walk(queue, skb) \ for (skb = (queue)->next; \ skb != (struct sk_buff *)(queue); \ skb = skb->next) #define skb_queue_walk_safe(queue, skb, tmp) \ for (skb = (queue)->next, tmp = skb->next; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->next) #define skb_queue_walk_from(queue, skb) \ for (; skb != (struct sk_buff *)(queue); \ skb = skb->next) #define skb_rbtree_walk(skb, root) \ for (skb = skb_rb_first(root); skb != NULL; \ skb = skb_rb_next(skb)) #define skb_rbtree_walk_from(skb) \ for (; skb != NULL; \ skb = skb_rb_next(skb)) #define skb_rbtree_walk_from_safe(skb, tmp) \ for (; tmp = skb ? skb_rb_next(skb) : NULL, (skb != NULL); \ skb = tmp) #define skb_queue_walk_from_safe(queue, skb, tmp) \ for (tmp = skb->next; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->next) #define skb_queue_reverse_walk(queue, skb) \ for (skb = (queue)->prev; \ skb != (struct sk_buff *)(queue); \ skb = skb->prev) #define skb_queue_reverse_walk_safe(queue, skb, tmp) \ for (skb = (queue)->prev, tmp = skb->prev; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->prev) #define skb_queue_reverse_walk_from_safe(queue, skb, tmp) \ for (tmp = skb->prev; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->prev) static inline bool skb_has_frag_list(const struct sk_buff *skb) { return skb_shinfo(skb)->frag_list != NULL; } static inline void skb_frag_list_init(struct sk_buff *skb) { skb_shinfo(skb)->frag_list = NULL; } #define skb_walk_frags(skb, iter) \ for (iter = skb_shinfo(skb)->frag_list; iter; iter = iter->next) int __skb_wait_for_more_packets(struct sock *sk, struct sk_buff_head *queue, int *err, long *timeo_p, const struct sk_buff *skb); struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, struct sk_buff_head *queue, unsigned int flags, int *off, int *err, struct sk_buff **last); struct sk_buff *__skb_try_recv_datagram(struct sock *sk, struct sk_buff_head *queue, unsigned int flags, int *off, int *err, struct sk_buff **last); struct sk_buff *__skb_recv_datagram(struct sock *sk, struct sk_buff_head *sk_queue, unsigned int flags, int *off, int *err); struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags, int *err); __poll_t datagram_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int skb_copy_datagram_iter(const struct sk_buff *from, int offset, struct iov_iter *to, int size); static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset, struct msghdr *msg, int size) { return skb_copy_datagram_iter(from, offset, &msg->msg_iter, size); } int skb_copy_and_csum_datagram_msg(struct sk_buff *skb, int hlen, struct msghdr *msg); int skb_copy_and_hash_datagram_iter(const struct sk_buff *skb, int offset, struct iov_iter *to, int len, struct ahash_request *hash); int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset, struct iov_iter *from, int len); int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm); void skb_free_datagram(struct sock *sk, struct sk_buff *skb); int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags); int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len); int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len); __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, int len); int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int len, unsigned int flags); int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset, int len); int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); unsigned int skb_zerocopy_headlen(const struct sk_buff *from); int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen); void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len); int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen); void skb_scrub_packet(struct sk_buff *skb, bool xnet); struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features); struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features, unsigned int offset); struct sk_buff *skb_vlan_untag(struct sk_buff *skb); int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len); int skb_ensure_writable_head_tail(struct sk_buff *skb, struct net_device *dev); int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); int skb_eth_pop(struct sk_buff *skb); int skb_eth_push(struct sk_buff *skb, const unsigned char *dst, const unsigned char *src); int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, int mac_len, bool ethernet); int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, bool ethernet); int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse); int skb_mpls_dec_ttl(struct sk_buff *skb); struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy, gfp_t gfp); static inline int memcpy_from_msg(void *data, struct msghdr *msg, int len) { return copy_from_iter_full(data, len, &msg->msg_iter) ? 0 : -EFAULT; } static inline int memcpy_to_msg(struct msghdr *msg, void *data, int len) { return copy_to_iter(data, len, &msg->msg_iter) == len ? 0 : -EFAULT; } struct skb_checksum_ops { __wsum (*update)(const void *mem, int len, __wsum wsum); __wsum (*combine)(__wsum csum, __wsum csum2, int offset, int len); }; extern const struct skb_checksum_ops *crc32c_csum_stub __read_mostly; __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum, const struct skb_checksum_ops *ops); __wsum skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum); static inline void * __must_check __skb_header_pointer(const struct sk_buff *skb, int offset, int len, const void *data, int hlen, void *buffer) { if (likely(hlen - offset >= len)) return (void *)data + offset; if (!skb || unlikely(skb_copy_bits(skb, offset, buffer, len) < 0)) return NULL; return buffer; } static inline void * __must_check skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) { return __skb_header_pointer(skb, offset, len, skb->data, skb_headlen(skb), buffer); } static inline void * __must_check skb_pointer_if_linear(const struct sk_buff *skb, int offset, int len) { if (likely(skb_headlen(skb) - offset >= len)) return skb->data + offset; return NULL; } /** * skb_needs_linearize - check if we need to linearize a given skb * depending on the given device features. * @skb: socket buffer to check * @features: net device features * * Returns true if either: * 1. skb has frag_list and the device doesn't support FRAGLIST, or * 2. skb is fragmented and the device does not support SG. */ static inline bool skb_needs_linearize(struct sk_buff *skb, netdev_features_t features) { return skb_is_nonlinear(skb) && ((skb_has_frag_list(skb) && !(features & NETIF_F_FRAGLIST)) || (skb_shinfo(skb)->nr_frags && !(features & NETIF_F_SG))); } static inline void skb_copy_from_linear_data(const struct sk_buff *skb, void *to, const unsigned int len) { memcpy(to, skb->data, len); } static inline void skb_copy_from_linear_data_offset(const struct sk_buff *skb, const int offset, void *to, const unsigned int len) { memcpy(to, skb->data + offset, len); } static inline void skb_copy_to_linear_data(struct sk_buff *skb, const void *from, const unsigned int len) { memcpy(skb->data, from, len); } static inline void skb_copy_to_linear_data_offset(struct sk_buff *skb, const int offset, const void *from, const unsigned int len) { memcpy(skb->data + offset, from, len); } void skb_init(void); static inline ktime_t skb_get_ktime(const struct sk_buff *skb) { return skb->tstamp; } /** * skb_get_timestamp - get timestamp from a skb * @skb: skb to get stamp from * @stamp: pointer to struct __kernel_old_timeval to store stamp in * * Timestamps are stored in the skb as offsets to a base timestamp. * This function converts the offset back to a struct timeval and stores * it in stamp. */ static inline void skb_get_timestamp(const struct sk_buff *skb, struct __kernel_old_timeval *stamp) { *stamp = ns_to_kernel_old_timeval(skb->tstamp); } static inline void skb_get_new_timestamp(const struct sk_buff *skb, struct __kernel_sock_timeval *stamp) { struct timespec64 ts = ktime_to_timespec64(skb->tstamp); stamp->tv_sec = ts.tv_sec; stamp->tv_usec = ts.tv_nsec / 1000; } static inline void skb_get_timestampns(const struct sk_buff *skb, struct __kernel_old_timespec *stamp) { struct timespec64 ts = ktime_to_timespec64(skb->tstamp); stamp->tv_sec = ts.tv_sec; stamp->tv_nsec = ts.tv_nsec; } static inline void skb_get_new_timestampns(const struct sk_buff *skb, struct __kernel_timespec *stamp) { struct timespec64 ts = ktime_to_timespec64(skb->tstamp); stamp->tv_sec = ts.tv_sec; stamp->tv_nsec = ts.tv_nsec; } static inline void __net_timestamp(struct sk_buff *skb) { skb->tstamp = ktime_get_real(); skb->tstamp_type = SKB_CLOCK_REALTIME; } static inline ktime_t net_timedelta(ktime_t t) { return ktime_sub(ktime_get_real(), t); } static inline void skb_set_delivery_time(struct sk_buff *skb, ktime_t kt, u8 tstamp_type) { skb->tstamp = kt; if (kt) skb->tstamp_type = tstamp_type; else skb->tstamp_type = SKB_CLOCK_REALTIME; } static inline void skb_set_delivery_type_by_clockid(struct sk_buff *skb, ktime_t kt, clockid_t clockid) { u8 tstamp_type = SKB_CLOCK_REALTIME; switch (clockid) { case CLOCK_REALTIME: break; case CLOCK_MONOTONIC: tstamp_type = SKB_CLOCK_MONOTONIC; break; case CLOCK_TAI: tstamp_type = SKB_CLOCK_TAI; break; default: WARN_ON_ONCE(1); kt = 0; } skb_set_delivery_time(skb, kt, tstamp_type); } DECLARE_STATIC_KEY_FALSE(netstamp_needed_key); /* It is used in the ingress path to clear the delivery_time. * If needed, set the skb->tstamp to the (rcv) timestamp. */ static inline void skb_clear_delivery_time(struct sk_buff *skb) { if (skb->tstamp_type) { skb->tstamp_type = SKB_CLOCK_REALTIME; if (static_branch_unlikely(&netstamp_needed_key)) skb->tstamp = ktime_get_real(); else skb->tstamp = 0; } } static inline void skb_clear_tstamp(struct sk_buff *skb) { if (skb->tstamp_type) return; skb->tstamp = 0; } static inline ktime_t skb_tstamp(const struct sk_buff *skb) { if (skb->tstamp_type) return 0; return skb->tstamp; } static inline ktime_t skb_tstamp_cond(const struct sk_buff *skb, bool cond) { if (skb->tstamp_type != SKB_CLOCK_MONOTONIC && skb->tstamp) return skb->tstamp; if (static_branch_unlikely(&netstamp_needed_key) || cond) return ktime_get_real(); return 0; } static inline u8 skb_metadata_len(const struct sk_buff *skb) { return skb_shinfo(skb)->meta_len; } static inline void *skb_metadata_end(const struct sk_buff *skb) { return skb_mac_header(skb); } static inline bool __skb_metadata_differs(const struct sk_buff *skb_a, const struct sk_buff *skb_b, u8 meta_len) { const void *a = skb_metadata_end(skb_a); const void *b = skb_metadata_end(skb_b); u64 diffs = 0; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) || BITS_PER_LONG != 64) goto slow; /* Using more efficient variant than plain call to memcmp(). */ switch (meta_len) { #define __it(x, op) (x -= sizeof(u##op)) #define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op)) case 32: diffs |= __it_diff(a, b, 64); fallthrough; case 24: diffs |= __it_diff(a, b, 64); fallthrough; case 16: diffs |= __it_diff(a, b, 64); fallthrough; case 8: diffs |= __it_diff(a, b, 64); break; case 28: diffs |= __it_diff(a, b, 64); fallthrough; case 20: diffs |= __it_diff(a, b, 64); fallthrough; case 12: diffs |= __it_diff(a, b, 64); fallthrough; case 4: diffs |= __it_diff(a, b, 32); break; default: slow: return memcmp(a - meta_len, b - meta_len, meta_len); } return diffs; } static inline bool skb_metadata_differs(const struct sk_buff *skb_a, const struct sk_buff *skb_b) { u8 len_a = skb_metadata_len(skb_a); u8 len_b = skb_metadata_len(skb_b); if (!(len_a | len_b)) return false; return len_a != len_b ? true : __skb_metadata_differs(skb_a, skb_b, len_a); } static inline void skb_metadata_set(struct sk_buff *skb, u8 meta_len) { skb_shinfo(skb)->meta_len = meta_len; } static inline void skb_metadata_clear(struct sk_buff *skb) { skb_metadata_set(skb, 0); } struct sk_buff *skb_clone_sk(struct sk_buff *skb); #ifdef CONFIG_NETWORK_PHY_TIMESTAMPING void skb_clone_tx_timestamp(struct sk_buff *skb); bool skb_defer_rx_timestamp(struct sk_buff *skb); #else /* CONFIG_NETWORK_PHY_TIMESTAMPING */ static inline void skb_clone_tx_timestamp(struct sk_buff *skb) { } static inline bool skb_defer_rx_timestamp(struct sk_buff *skb) { return false; } #endif /* !CONFIG_NETWORK_PHY_TIMESTAMPING */ /** * skb_complete_tx_timestamp() - deliver cloned skb with tx timestamps * * PHY drivers may accept clones of transmitted packets for * timestamping via their phy_driver.txtstamp method. These drivers * must call this function to return the skb back to the stack with a * timestamp. * * @skb: clone of the original outgoing packet * @hwtstamps: hardware time stamps * */ void skb_complete_tx_timestamp(struct sk_buff *skb, struct skb_shared_hwtstamps *hwtstamps); void __skb_tstamp_tx(struct sk_buff *orig_skb, const struct sk_buff *ack_skb, struct skb_shared_hwtstamps *hwtstamps, struct sock *sk, int tstype); /** * skb_tstamp_tx - queue clone of skb with send time stamps * @orig_skb: the original outgoing packet * @hwtstamps: hardware time stamps, may be NULL if not available * * If the skb has a socket associated, then this function clones the * skb (thus sharing the actual data and optional structures), stores * the optional hardware time stamping information (if non NULL) or * generates a software time stamp (otherwise), then queues the clone * to the error queue of the socket. Errors are silently ignored. */ void skb_tstamp_tx(struct sk_buff *orig_skb, struct skb_shared_hwtstamps *hwtstamps); /** * skb_tx_timestamp() - Driver hook for transmit timestamping * * Ethernet MAC Drivers should call this function in their hard_xmit() * function immediately before giving the sk_buff to the MAC hardware. * * Specifically, one should make absolutely sure that this function is * called before TX completion of this packet can trigger. Otherwise * the packet could potentially already be freed. * * @skb: A socket buffer. */ static inline void skb_tx_timestamp(struct sk_buff *skb) { skb_clone_tx_timestamp(skb); if (skb_shinfo(skb)->tx_flags & SKBTX_SW_TSTAMP) skb_tstamp_tx(skb, NULL); } /** * skb_complete_wifi_ack - deliver skb with wifi status * * @skb: the original outgoing packet * @acked: ack status * */ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked); __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len); __sum16 __skb_checksum_complete(struct sk_buff *skb); static inline int skb_csum_unnecessary(const struct sk_buff *skb) { return ((skb->ip_summed == CHECKSUM_UNNECESSARY) || skb->csum_valid || (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start_offset(skb) >= 0)); } /** * skb_checksum_complete - Calculate checksum of an entire packet * @skb: packet to process * * This function calculates the checksum over the entire packet plus * the value of skb->csum. The latter can be used to supply the * checksum of a pseudo header as used by TCP/UDP. It returns the * checksum. * * For protocols that contain complete checksums such as ICMP/TCP/UDP, * this function can be used to verify that checksum on received * packets. In that case the function should return zero if the * checksum is correct. In particular, this function will return zero * if skb->ip_summed is CHECKSUM_UNNECESSARY which indicates that the * hardware has already verified the correctness of the checksum. */ static inline __sum16 skb_checksum_complete(struct sk_buff *skb) { return skb_csum_unnecessary(skb) ? 0 : __skb_checksum_complete(skb); } static inline void __skb_decr_checksum_unnecessary(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_UNNECESSARY) { if (skb->csum_level == 0) skb->ip_summed = CHECKSUM_NONE; else skb->csum_level--; } } static inline void __skb_incr_checksum_unnecessary(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_UNNECESSARY) { if (skb->csum_level < SKB_MAX_CSUM_LEVEL) skb->csum_level++; } else if (skb->ip_summed == CHECKSUM_NONE) { skb->ip_summed = CHECKSUM_UNNECESSARY; skb->csum_level = 0; } } static inline void __skb_reset_checksum_unnecessary(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_UNNECESSARY) { skb->ip_summed = CHECKSUM_NONE; skb->csum_level = 0; } } /* Check if we need to perform checksum complete validation. * * Returns true if checksum complete is needed, false otherwise * (either checksum is unnecessary or zero checksum is allowed). */ static inline bool __skb_checksum_validate_needed(struct sk_buff *skb, bool zero_okay, __sum16 check) { if (skb_csum_unnecessary(skb) || (zero_okay && !check)) { skb->csum_valid = 1; __skb_decr_checksum_unnecessary(skb); return false; } return true; } /* For small packets <= CHECKSUM_BREAK perform checksum complete directly * in checksum_init. */ #define CHECKSUM_BREAK 76 /* Unset checksum-complete * * Unset checksum complete can be done when packet is being modified * (uncompressed for instance) and checksum-complete value is * invalidated. */ static inline void skb_checksum_complete_unset(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; } /* Validate (init) checksum based on checksum complete. * * Return values: * 0: checksum is validated or try to in skb_checksum_complete. In the latter * case the ip_summed will not be CHECKSUM_UNNECESSARY and the pseudo * checksum is stored in skb->csum for use in __skb_checksum_complete * non-zero: value of invalid checksum * */ static inline __sum16 __skb_checksum_validate_complete(struct sk_buff *skb, bool complete, __wsum psum) { if (skb->ip_summed == CHECKSUM_COMPLETE) { if (!csum_fold(csum_add(psum, skb->csum))) { skb->csum_valid = 1; return 0; } } skb->csum = psum; if (complete || skb->len <= CHECKSUM_BREAK) { __sum16 csum; csum = __skb_checksum_complete(skb); skb->csum_valid = !csum; return csum; } return 0; } static inline __wsum null_compute_pseudo(struct sk_buff *skb, int proto) { return 0; } /* Perform checksum validate (init). Note that this is a macro since we only * want to calculate the pseudo header which is an input function if necessary. * First we try to validate without any computation (checksum unnecessary) and * then calculate based on checksum complete calling the function to compute * pseudo header. * * Return values: * 0: checksum is validated or try to in skb_checksum_complete * non-zero: value of invalid checksum */ #define __skb_checksum_validate(skb, proto, complete, \ zero_okay, check, compute_pseudo) \ ({ \ __sum16 __ret = 0; \ skb->csum_valid = 0; \ if (__skb_checksum_validate_needed(skb, zero_okay, check)) \ __ret = __skb_checksum_validate_complete(skb, \ complete, compute_pseudo(skb, proto)); \ __ret; \ }) #define skb_checksum_init(skb, proto, compute_pseudo) \ __skb_checksum_validate(skb, proto, false, false, 0, compute_pseudo) #define skb_checksum_init_zero_check(skb, proto, check, compute_pseudo) \ __skb_checksum_validate(skb, proto, false, true, check, compute_pseudo) #define skb_checksum_validate(skb, proto, compute_pseudo) \ __skb_checksum_validate(skb, proto, true, false, 0, compute_pseudo) #define skb_checksum_validate_zero_check(skb, proto, check, \ compute_pseudo) \ __skb_checksum_validate(skb, proto, true, true, check, compute_pseudo) #define skb_checksum_simple_validate(skb) \ __skb_checksum_validate(skb, 0, true, false, 0, null_compute_pseudo) static inline bool __skb_checksum_convert_check(struct sk_buff *skb) { return (skb->ip_summed == CHECKSUM_NONE && skb->csum_valid); } static inline void __skb_checksum_convert(struct sk_buff *skb, __wsum pseudo) { skb->csum = ~pseudo; skb->ip_summed = CHECKSUM_COMPLETE; } #define skb_checksum_try_convert(skb, proto, compute_pseudo) \ do { \ if (__skb_checksum_convert_check(skb)) \ __skb_checksum_convert(skb, compute_pseudo(skb, proto)); \ } while (0) static inline void skb_remcsum_adjust_partial(struct sk_buff *skb, void *ptr, u16 start, u16 offset) { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = ((unsigned char *)ptr + start) - skb->head; skb->csum_offset = offset - start; } /* Update skbuf and packet to reflect the remote checksum offload operation. * When called, ptr indicates the starting point for skb->csum when * ip_summed is CHECKSUM_COMPLETE. If we need create checksum complete * here, skb_postpull_rcsum is done so skb->csum start is ptr. */ static inline void skb_remcsum_process(struct sk_buff *skb, void *ptr, int start, int offset, bool nopartial) { __wsum delta; if (!nopartial) { skb_remcsum_adjust_partial(skb, ptr, start, offset); return; } if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) { __skb_checksum_complete(skb); skb_postpull_rcsum(skb, skb->data, ptr - (void *)skb->data); } delta = remcsum_adjust(ptr, skb->csum, start, offset); /* Adjust skb->csum since we changed the packet */ skb->csum = csum_add(skb->csum, delta); } static inline struct nf_conntrack *skb_nfct(const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) return (void *)(skb->_nfct & NFCT_PTRMASK); #else return NULL; #endif } static inline unsigned long skb_get_nfct(const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) return skb->_nfct; #else return 0UL; #endif } static inline void skb_set_nfct(struct sk_buff *skb, unsigned long nfct) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) skb->slow_gro |= !!nfct; skb->_nfct = nfct; #endif } #ifdef CONFIG_SKB_EXTENSIONS enum skb_ext_id { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) SKB_EXT_BRIDGE_NF, #endif #ifdef CONFIG_XFRM SKB_EXT_SEC_PATH, #endif #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) TC_SKB_EXT, #endif #if IS_ENABLED(CONFIG_MPTCP) SKB_EXT_MPTCP, #endif #if IS_ENABLED(CONFIG_MCTP_FLOWS) SKB_EXT_MCTP, #endif SKB_EXT_NUM, /* must be last */ }; /** * struct skb_ext - sk_buff extensions * @refcnt: 1 on allocation, deallocated on 0 * @offset: offset to add to @data to obtain extension address * @chunks: size currently allocated, stored in SKB_EXT_ALIGN_SHIFT units * @data: start of extension data, variable sized * * Note: offsets/lengths are stored in chunks of 8 bytes, this allows * to use 'u8' types while allowing up to 2kb worth of extension data. */ struct skb_ext { refcount_t refcnt; u8 offset[SKB_EXT_NUM]; /* in chunks of 8 bytes */ u8 chunks; /* same */ char data[] __aligned(8); }; struct skb_ext *__skb_ext_alloc(gfp_t flags); void *__skb_ext_set(struct sk_buff *skb, enum skb_ext_id id, struct skb_ext *ext); void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id); void __skb_ext_del(struct sk_buff *skb, enum skb_ext_id id); void __skb_ext_put(struct skb_ext *ext); static inline void skb_ext_put(struct sk_buff *skb) { if (skb->active_extensions) __skb_ext_put(skb->extensions); } static inline void __skb_ext_copy(struct sk_buff *dst, const struct sk_buff *src) { dst->active_extensions = src->active_extensions; if (src->active_extensions) { struct skb_ext *ext = src->extensions; refcount_inc(&ext->refcnt); dst->extensions = ext; } } static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *src) { skb_ext_put(dst); __skb_ext_copy(dst, src); } static inline bool __skb_ext_exist(const struct skb_ext *ext, enum skb_ext_id i) { return !!ext->offset[i]; } static inline bool skb_ext_exist(const struct sk_buff *skb, enum skb_ext_id id) { return skb->active_extensions & (1 << id); } static inline void skb_ext_del(struct sk_buff *skb, enum skb_ext_id id) { if (skb_ext_exist(skb, id)) __skb_ext_del(skb, id); } static inline void *skb_ext_find(const struct sk_buff *skb, enum skb_ext_id id) { if (skb_ext_exist(skb, id)) { struct skb_ext *ext = skb->extensions; return (void *)ext + (ext->offset[id] << 3); } return NULL; } static inline void skb_ext_reset(struct sk_buff *skb) { if (unlikely(skb->active_extensions)) { __skb_ext_put(skb->extensions); skb->active_extensions = 0; } } static inline bool skb_has_extensions(struct sk_buff *skb) { return unlikely(skb->active_extensions); } #else static inline void skb_ext_put(struct sk_buff *skb) {} static inline void skb_ext_reset(struct sk_buff *skb) {} static inline void skb_ext_del(struct sk_buff *skb, int unused) {} static inline void __skb_ext_copy(struct sk_buff *d, const struct sk_buff *s) {} static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *s) {} static inline bool skb_has_extensions(struct sk_buff *skb) { return false; } #endif /* CONFIG_SKB_EXTENSIONS */ static inline void nf_reset_ct(struct sk_buff *skb) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) nf_conntrack_put(skb_nfct(skb)); skb->_nfct = 0; #endif } static inline void nf_reset_trace(struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) skb->nf_trace = 0; #endif } static inline void ipvs_reset(struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IP_VS) skb->ipvs_property = 0; #endif } /* Note: This doesn't put any conntrack info in dst. */ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src, bool copy) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) dst->_nfct = src->_nfct; nf_conntrack_get(skb_nfct(src)); #endif #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) if (copy) dst->nf_trace = src->nf_trace; #endif } static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) nf_conntrack_put(skb_nfct(dst)); #endif dst->slow_gro = src->slow_gro; __nf_copy(dst, src, true); } #ifdef CONFIG_NETWORK_SECMARK static inline void skb_copy_secmark(struct sk_buff *to, const struct sk_buff *from) { to->secmark = from->secmark; } static inline void skb_init_secmark(struct sk_buff *skb) { skb->secmark = 0; } #else static inline void skb_copy_secmark(struct sk_buff *to, const struct sk_buff *from) { } static inline void skb_init_secmark(struct sk_buff *skb) { } #endif static inline int secpath_exists(const struct sk_buff *skb) { #ifdef CONFIG_XFRM return skb_ext_exist(skb, SKB_EXT_SEC_PATH); #else return 0; #endif } static inline bool skb_irq_freeable(const struct sk_buff *skb) { return !skb->destructor && !secpath_exists(skb) && !skb_nfct(skb) && !skb->_skb_refdst && !skb_has_frag_list(skb); } static inline void skb_set_queue_mapping(struct sk_buff *skb, u16 queue_mapping) { skb->queue_mapping = queue_mapping; } static inline u16 skb_get_queue_mapping(const struct sk_buff *skb) { return skb->queue_mapping; } static inline void skb_copy_queue_mapping(struct sk_buff *to, const struct sk_buff *from) { to->queue_mapping = from->queue_mapping; } static inline void skb_record_rx_queue(struct sk_buff *skb, u16 rx_queue) { skb->queue_mapping = rx_queue + 1; } static inline u16 skb_get_rx_queue(const struct sk_buff *skb) { return skb->queue_mapping - 1; } static inline bool skb_rx_queue_recorded(const struct sk_buff *skb) { return skb->queue_mapping != 0; } static inline void skb_set_dst_pending_confirm(struct sk_buff *skb, u32 val) { skb->dst_pending_confirm = val; } static inline bool skb_get_dst_pending_confirm(const struct sk_buff *skb) { return skb->dst_pending_confirm != 0; } static inline struct sec_path *skb_sec_path(const struct sk_buff *skb) { #ifdef CONFIG_XFRM return skb_ext_find(skb, SKB_EXT_SEC_PATH); #else return NULL; #endif } static inline bool skb_is_gso(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_size; } /* Note: Should be called only if skb_is_gso(skb) is true */ static inline bool skb_is_gso_v6(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6; } /* Note: Should be called only if skb_is_gso(skb) is true */ static inline bool skb_is_gso_sctp(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_type & SKB_GSO_SCTP; } /* Note: Should be called only if skb_is_gso(skb) is true */ static inline bool skb_is_gso_tcp(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6); } static inline void skb_gso_reset(struct sk_buff *skb) { skb_shinfo(skb)->gso_size = 0; skb_shinfo(skb)->gso_segs = 0; skb_shinfo(skb)->gso_type = 0; } static inline void skb_increase_gso_size(struct skb_shared_info *shinfo, u16 increment) { if (WARN_ON_ONCE(shinfo->gso_size == GSO_BY_FRAGS)) return; shinfo->gso_size += increment; } static inline void skb_decrease_gso_size(struct skb_shared_info *shinfo, u16 decrement) { if (WARN_ON_ONCE(shinfo->gso_size == GSO_BY_FRAGS)) return; shinfo->gso_size -= decrement; } void __skb_warn_lro_forwarding(const struct sk_buff *skb); static inline bool skb_warn_if_lro(const struct sk_buff *skb) { /* LRO sets gso_size but not gso_type, whereas if GSO is really * wanted then gso_type will be set. */ const struct skb_shared_info *shinfo = skb_shinfo(skb); if (skb_is_nonlinear(skb) && shinfo->gso_size != 0 && unlikely(shinfo->gso_type == 0)) { __skb_warn_lro_forwarding(skb); return true; } return false; } static inline void skb_forward_csum(struct sk_buff *skb) { /* Unfortunately we don't support this one. Any brave souls? */ if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; } /** * skb_checksum_none_assert - make sure skb ip_summed is CHECKSUM_NONE * @skb: skb to check * * fresh skbs have their ip_summed set to CHECKSUM_NONE. * Instead of forcing ip_summed to CHECKSUM_NONE, we can * use this helper, to document places where we make this assertion. */ static inline void skb_checksum_none_assert(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(skb->ip_summed != CHECKSUM_NONE); } bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off); int skb_checksum_setup(struct sk_buff *skb, bool recalculate); struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb, unsigned int transport_len, __sum16(*skb_chkf)(struct sk_buff *skb)); /** * skb_head_is_locked - Determine if the skb->head is locked down * @skb: skb to check * * The head on skbs build around a head frag can be removed if they are * not cloned. This function returns true if the skb head is locked down * due to either being allocated via kmalloc, or by being a clone with * multiple references to the head. */ static inline bool skb_head_is_locked(const struct sk_buff *skb) { return !skb->head_frag || skb_cloned(skb); } /* Local Checksum Offload. * Compute outer checksum based on the assumption that the * inner checksum will be offloaded later. * See Documentation/networking/checksum-offloads.rst for * explanation of how this works. * Fill in outer checksum adjustment (e.g. with sum of outer * pseudo-header) before calling. * Also ensure that inner checksum is in linear data area. */ static inline __wsum lco_csum(struct sk_buff *skb) { unsigned char *csum_start = skb_checksum_start(skb); unsigned char *l4_hdr = skb_transport_header(skb); __wsum partial; /* Start with complement of inner checksum adjustment */ partial = ~csum_unfold(*(__force __sum16 *)(csum_start + skb->csum_offset)); /* Add in checksum of our headers (incl. outer checksum * adjustment filled in by caller) and return result. */ return csum_partial(l4_hdr, csum_start - l4_hdr, partial); } static inline bool skb_is_redirected(const struct sk_buff *skb) { return skb->redirected; } static inline void skb_set_redirected(struct sk_buff *skb, bool from_ingress) { skb->redirected = 1; #ifdef CONFIG_NET_REDIRECT skb->from_ingress = from_ingress; if (skb->from_ingress) skb_clear_tstamp(skb); #endif } static inline void skb_reset_redirect(struct sk_buff *skb) { skb->redirected = 0; } static inline void skb_set_redirected_noclear(struct sk_buff *skb, bool from_ingress) { skb->redirected = 1; #ifdef CONFIG_NET_REDIRECT skb->from_ingress = from_ingress; #endif } static inline bool skb_csum_is_sctp(struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IP_SCTP) return skb->csum_not_inet; #else return 0; #endif } static inline void skb_reset_csum_not_inet(struct sk_buff *skb) { skb->ip_summed = CHECKSUM_NONE; #if IS_ENABLED(CONFIG_IP_SCTP) skb->csum_not_inet = 0; #endif } static inline void skb_set_kcov_handle(struct sk_buff *skb, const u64 kcov_handle) { #ifdef CONFIG_KCOV skb->kcov_handle = kcov_handle; #endif } static inline u64 skb_get_kcov_handle(struct sk_buff *skb) { #ifdef CONFIG_KCOV return skb->kcov_handle; #else return 0; #endif } static inline void skb_mark_for_recycle(struct sk_buff *skb) { #ifdef CONFIG_PAGE_POOL skb->pp_recycle = 1; #endif } ssize_t skb_splice_from_iter(struct sk_buff *skb, struct iov_iter *iter, ssize_t maxsize, gfp_t gfp); #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PSI_H #define _LINUX_PSI_H #include <linux/jump_label.h> #include <linux/psi_types.h> #include <linux/sched.h> #include <linux/poll.h> #include <linux/cgroup-defs.h> #include <linux/cgroup.h> struct seq_file; struct css_set; #ifdef CONFIG_PSI extern struct static_key_false psi_disabled; extern struct psi_group psi_system; void psi_init(void); void psi_memstall_enter(unsigned long *flags); void psi_memstall_leave(unsigned long *flags); int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res); struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf, enum psi_res res, struct file *file, struct kernfs_open_file *of); void psi_trigger_destroy(struct psi_trigger *t); __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, poll_table *wait); #ifdef CONFIG_CGROUPS static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) { return cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi; } int psi_cgroup_alloc(struct cgroup *cgrp); void psi_cgroup_free(struct cgroup *cgrp); void cgroup_move_task(struct task_struct *p, struct css_set *to); void psi_cgroup_restart(struct psi_group *group); #endif #else /* CONFIG_PSI */ static inline void psi_init(void) {} static inline void psi_memstall_enter(unsigned long *flags) {} static inline void psi_memstall_leave(unsigned long *flags) {} #ifdef CONFIG_CGROUPS static inline int psi_cgroup_alloc(struct cgroup *cgrp) { return 0; } static inline void psi_cgroup_free(struct cgroup *cgrp) { } static inline void cgroup_move_task(struct task_struct *p, struct css_set *to) { rcu_assign_pointer(p->cgroups, to); } static inline void psi_cgroup_restart(struct psi_group *group) {} #endif #endif /* CONFIG_PSI */ #endif /* _LINUX_PSI_H */ |
| 1 1 1 4 19 19 9 9 11466 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2012-2014 Andy Lutomirski <luto@amacapital.net> * * Based on the original implementation which is: * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE * Copyright 2003 Andi Kleen, SuSE Labs. * * Parts of the original code have been moved to arch/x86/vdso/vma.c * * This file implements vsyscall emulation. vsyscalls are a legacy ABI: * Userspace can request certain kernel services by calling fixed * addresses. This concept is problematic: * * - It interferes with ASLR. * - It's awkward to write code that lives in kernel addresses but is * callable by userspace at fixed addresses. * - The whole concept is impossible for 32-bit compat userspace. * - UML cannot easily virtualize a vsyscall. * * As of mid-2014, I believe that there is no new userspace code that * will use a vsyscall if the vDSO is present. I hope that there will * soon be no new userspace code that will ever use a vsyscall. * * The code in this file emulates vsyscalls when notified of a page * fault to a vsyscall address. */ #include <linux/kernel.h> #include <linux/timer.h> #include <linux/sched/signal.h> #include <linux/mm_types.h> #include <linux/syscalls.h> #include <linux/ratelimit.h> #include <asm/vsyscall.h> #include <asm/unistd.h> #include <asm/fixmap.h> #include <asm/traps.h> #include <asm/paravirt.h> #define CREATE_TRACE_POINTS #include "vsyscall_trace.h" static enum { EMULATE, XONLY, NONE } vsyscall_mode __ro_after_init = #ifdef CONFIG_LEGACY_VSYSCALL_NONE NONE; #elif defined(CONFIG_LEGACY_VSYSCALL_XONLY) XONLY; #else #error VSYSCALL config is broken #endif static int __init vsyscall_setup(char *str) { if (str) { if (!strcmp("emulate", str)) vsyscall_mode = EMULATE; else if (!strcmp("xonly", str)) vsyscall_mode = XONLY; else if (!strcmp("none", str)) vsyscall_mode = NONE; else return -EINVAL; return 0; } return -EINVAL; } early_param("vsyscall", vsyscall_setup); static void warn_bad_vsyscall(const char *level, struct pt_regs *regs, const char *message) { if (!show_unhandled_signals) return; printk_ratelimited("%s%s[%d] %s ip:%lx cs:%x sp:%lx ax:%lx si:%lx di:%lx\n", level, current->comm, task_pid_nr(current), message, regs->ip, regs->cs, regs->sp, regs->ax, regs->si, regs->di); } static int addr_to_vsyscall_nr(unsigned long addr) { int nr; if ((addr & ~0xC00UL) != VSYSCALL_ADDR) return -EINVAL; nr = (addr & 0xC00UL) >> 10; if (nr >= 3) return -EINVAL; return nr; } static bool write_ok_or_segv(unsigned long ptr, size_t size) { if (!access_ok((void __user *)ptr, size)) { struct thread_struct *thread = ¤t->thread; thread->error_code = X86_PF_USER | X86_PF_WRITE; thread->cr2 = ptr; thread->trap_nr = X86_TRAP_PF; force_sig_fault(SIGSEGV, SEGV_MAPERR, (void __user *)ptr); return false; } else { return true; } } bool emulate_vsyscall(unsigned long error_code, struct pt_regs *regs, unsigned long address) { unsigned long caller; int vsyscall_nr, syscall_nr, tmp; long ret; unsigned long orig_dx; /* Write faults or kernel-privilege faults never get fixed up. */ if ((error_code & (X86_PF_WRITE | X86_PF_USER)) != X86_PF_USER) return false; if (!(error_code & X86_PF_INSTR)) { /* Failed vsyscall read */ if (vsyscall_mode == EMULATE) return false; /* * User code tried and failed to read the vsyscall page. */ warn_bad_vsyscall(KERN_INFO, regs, "vsyscall read attempt denied -- look up the vsyscall kernel parameter if you need a workaround"); return false; } /* * No point in checking CS -- the only way to get here is a user mode * trap to a high address, which means that we're in 64-bit user code. */ WARN_ON_ONCE(address != regs->ip); if (vsyscall_mode == NONE) { warn_bad_vsyscall(KERN_INFO, regs, "vsyscall attempted with vsyscall=none"); return false; } vsyscall_nr = addr_to_vsyscall_nr(address); trace_emulate_vsyscall(vsyscall_nr); if (vsyscall_nr < 0) { warn_bad_vsyscall(KERN_WARNING, regs, "misaligned vsyscall (exploit attempt or buggy program) -- look up the vsyscall kernel parameter if you need a workaround"); goto sigsegv; } if (get_user(caller, (unsigned long __user *)regs->sp) != 0) { warn_bad_vsyscall(KERN_WARNING, regs, "vsyscall with bad stack (exploit attempt?)"); goto sigsegv; } /* * Check for access_ok violations and find the syscall nr. * * NULL is a valid user pointer (in the access_ok sense) on 32-bit and * 64-bit, so we don't need to special-case it here. For all the * vsyscalls, NULL means "don't write anything" not "write it at * address 0". */ switch (vsyscall_nr) { case 0: if (!write_ok_or_segv(regs->di, sizeof(struct __kernel_old_timeval)) || !write_ok_or_segv(regs->si, sizeof(struct timezone))) { ret = -EFAULT; goto check_fault; } syscall_nr = __NR_gettimeofday; break; case 1: if (!write_ok_or_segv(regs->di, sizeof(__kernel_old_time_t))) { ret = -EFAULT; goto check_fault; } syscall_nr = __NR_time; break; case 2: if (!write_ok_or_segv(regs->di, sizeof(unsigned)) || !write_ok_or_segv(regs->si, sizeof(unsigned))) { ret = -EFAULT; goto check_fault; } syscall_nr = __NR_getcpu; break; } /* * Handle seccomp. regs->ip must be the original value. * See seccomp_send_sigsys and Documentation/userspace-api/seccomp_filter.rst. * * We could optimize the seccomp disabled case, but performance * here doesn't matter. */ regs->orig_ax = syscall_nr; regs->ax = -ENOSYS; tmp = secure_computing(); if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) { warn_bad_vsyscall(KERN_DEBUG, regs, "seccomp tried to change syscall nr or ip"); force_exit_sig(SIGSYS); return true; } regs->orig_ax = -1; if (tmp) goto do_ret; /* skip requested */ /* * With a real vsyscall, page faults cause SIGSEGV. */ ret = -EFAULT; switch (vsyscall_nr) { case 0: /* this decodes regs->di and regs->si on its own */ ret = __x64_sys_gettimeofday(regs); break; case 1: /* this decodes regs->di on its own */ ret = __x64_sys_time(regs); break; case 2: /* while we could clobber regs->dx, we didn't in the past... */ orig_dx = regs->dx; regs->dx = 0; /* this decodes regs->di, regs->si and regs->dx on its own */ ret = __x64_sys_getcpu(regs); regs->dx = orig_dx; break; } check_fault: if (ret == -EFAULT) { /* Bad news -- userspace fed a bad pointer to a vsyscall. */ warn_bad_vsyscall(KERN_INFO, regs, "vsyscall fault (exploit attempt?)"); goto sigsegv; } regs->ax = ret; do_ret: /* Emulate a ret instruction. */ regs->ip = caller; regs->sp += 8; return true; sigsegv: force_sig(SIGSEGV); return true; } /* * A pseudo VMA to allow ptrace access for the vsyscall page. This only * covers the 64bit vsyscall page now. 32bit has a real VMA now and does * not need special handling anymore: */ static const char *gate_vma_name(struct vm_area_struct *vma) { return "[vsyscall]"; } static const struct vm_operations_struct gate_vma_ops = { .name = gate_vma_name, }; static struct vm_area_struct gate_vma __ro_after_init = { .vm_start = VSYSCALL_ADDR, .vm_end = VSYSCALL_ADDR + PAGE_SIZE, .vm_page_prot = PAGE_READONLY_EXEC, .vm_flags = VM_READ | VM_EXEC, .vm_ops = &gate_vma_ops, }; struct vm_area_struct *get_gate_vma(struct mm_struct *mm) { #ifdef CONFIG_COMPAT if (!mm || !test_bit(MM_CONTEXT_HAS_VSYSCALL, &mm->context.flags)) return NULL; #endif if (vsyscall_mode == NONE) return NULL; return &gate_vma; } int in_gate_area(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma = get_gate_vma(mm); if (!vma) return 0; return (addr >= vma->vm_start) && (addr < vma->vm_end); } /* * Use this when you have no reliable mm, typically from interrupt * context. It is less reliable than using a task's mm and may give * false positives. */ int in_gate_area_no_mm(unsigned long addr) { return vsyscall_mode != NONE && (addr & PAGE_MASK) == VSYSCALL_ADDR; } /* * The VSYSCALL page is the only user-accessible page in the kernel address * range. Normally, the kernel page tables can have _PAGE_USER clear, but * the tables covering VSYSCALL_ADDR need _PAGE_USER set if vsyscalls * are enabled. * * Some day we may create a "minimal" vsyscall mode in which we emulate * vsyscalls but leave the page not present. If so, we skip calling * this. */ void __init set_vsyscall_pgtable_user_bits(pgd_t *root) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgd = pgd_offset_pgd(root, VSYSCALL_ADDR); set_pgd(pgd, __pgd(pgd_val(*pgd) | _PAGE_USER)); p4d = p4d_offset(pgd, VSYSCALL_ADDR); #if CONFIG_PGTABLE_LEVELS >= 5 set_p4d(p4d, __p4d(p4d_val(*p4d) | _PAGE_USER)); #endif pud = pud_offset(p4d, VSYSCALL_ADDR); set_pud(pud, __pud(pud_val(*pud) | _PAGE_USER)); pmd = pmd_offset(pud, VSYSCALL_ADDR); set_pmd(pmd, __pmd(pmd_val(*pmd) | _PAGE_USER)); } void __init map_vsyscall(void) { extern char __vsyscall_page; unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page); /* * For full emulation, the page needs to exist for real. In * execute-only mode, there is no PTE at all backing the vsyscall * page. */ if (vsyscall_mode == EMULATE) { __set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall, PAGE_KERNEL_VVAR); set_vsyscall_pgtable_user_bits(swapper_pg_dir); } if (vsyscall_mode == XONLY) vm_flags_init(&gate_vma, VM_EXEC); BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) != (unsigned long)VSYSCALL_ADDR); } |
| 2 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/power/user.c * * This file provides the user space interface for software suspend/resume. * * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl> */ #include <linux/suspend.h> #include <linux/reboot.h> #include <linux/string.h> #include <linux/device.h> #include <linux/miscdevice.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/pm.h> #include <linux/fs.h> #include <linux/compat.h> #include <linux/console.h> #include <linux/cpu.h> #include <linux/freezer.h> #include <linux/uaccess.h> #include "power.h" static bool need_wait; static struct snapshot_data { struct snapshot_handle handle; int swap; int mode; bool frozen; bool ready; bool platform_support; bool free_bitmaps; dev_t dev; } snapshot_state; int is_hibernate_resume_dev(dev_t dev) { return hibernation_available() && snapshot_state.dev == dev; } static int snapshot_open(struct inode *inode, struct file *filp) { struct snapshot_data *data; unsigned int sleep_flags; int error; if (!hibernation_available()) return -EPERM; sleep_flags = lock_system_sleep(); if (!hibernate_acquire()) { error = -EBUSY; goto Unlock; } if ((filp->f_flags & O_ACCMODE) == O_RDWR) { hibernate_release(); error = -ENOSYS; goto Unlock; } nonseekable_open(inode, filp); data = &snapshot_state; filp->private_data = data; memset(&data->handle, 0, sizeof(struct snapshot_handle)); if ((filp->f_flags & O_ACCMODE) == O_RDONLY) { /* Hibernating. The image device should be accessible. */ data->swap = swap_type_of(swsusp_resume_device, 0); data->mode = O_RDONLY; data->free_bitmaps = false; error = pm_notifier_call_chain_robust(PM_HIBERNATION_PREPARE, PM_POST_HIBERNATION); } else { /* * Resuming. We may need to wait for the image device to * appear. */ need_wait = true; data->swap = -1; data->mode = O_WRONLY; error = pm_notifier_call_chain_robust(PM_RESTORE_PREPARE, PM_POST_RESTORE); if (!error) { error = create_basic_memory_bitmaps(); data->free_bitmaps = !error; } } if (error) hibernate_release(); data->frozen = false; data->ready = false; data->platform_support = false; data->dev = 0; Unlock: unlock_system_sleep(sleep_flags); return error; } static int snapshot_release(struct inode *inode, struct file *filp) { struct snapshot_data *data; unsigned int sleep_flags; sleep_flags = lock_system_sleep(); swsusp_free(); data = filp->private_data; data->dev = 0; free_all_swap_pages(data->swap); if (data->frozen) { pm_restore_gfp_mask(); free_basic_memory_bitmaps(); thaw_processes(); } else if (data->free_bitmaps) { free_basic_memory_bitmaps(); } pm_notifier_call_chain(data->mode == O_RDONLY ? PM_POST_HIBERNATION : PM_POST_RESTORE); hibernate_release(); unlock_system_sleep(sleep_flags); return 0; } static ssize_t snapshot_read(struct file *filp, char __user *buf, size_t count, loff_t *offp) { loff_t pg_offp = *offp & ~PAGE_MASK; struct snapshot_data *data; unsigned int sleep_flags; ssize_t res; sleep_flags = lock_system_sleep(); data = filp->private_data; if (!data->ready) { res = -ENODATA; goto Unlock; } if (!pg_offp) { /* on page boundary? */ res = snapshot_read_next(&data->handle); if (res <= 0) goto Unlock; } else { res = PAGE_SIZE - pg_offp; } res = simple_read_from_buffer(buf, count, &pg_offp, data_of(data->handle), res); if (res > 0) *offp += res; Unlock: unlock_system_sleep(sleep_flags); return res; } static ssize_t snapshot_write(struct file *filp, const char __user *buf, size_t count, loff_t *offp) { loff_t pg_offp = *offp & ~PAGE_MASK; struct snapshot_data *data; unsigned long sleep_flags; ssize_t res; if (need_wait) { wait_for_device_probe(); need_wait = false; } sleep_flags = lock_system_sleep(); data = filp->private_data; if (!pg_offp) { res = snapshot_write_next(&data->handle); if (res <= 0) goto unlock; } else { res = PAGE_SIZE; } if (!data_of(data->handle)) { res = -EINVAL; goto unlock; } res = simple_write_to_buffer(data_of(data->handle), res, &pg_offp, buf, count); if (res > 0) *offp += res; unlock: unlock_system_sleep(sleep_flags); return res; } struct compat_resume_swap_area { compat_loff_t offset; u32 dev; } __packed; static int snapshot_set_swap_area(struct snapshot_data *data, void __user *argp) { sector_t offset; dev_t swdev; if (swsusp_swap_in_use()) return -EPERM; if (in_compat_syscall()) { struct compat_resume_swap_area swap_area; if (copy_from_user(&swap_area, argp, sizeof(swap_area))) return -EFAULT; swdev = new_decode_dev(swap_area.dev); offset = swap_area.offset; } else { struct resume_swap_area swap_area; if (copy_from_user(&swap_area, argp, sizeof(swap_area))) return -EFAULT; swdev = new_decode_dev(swap_area.dev); offset = swap_area.offset; } /* * User space encodes device types as two-byte values, * so we need to recode them */ data->swap = swap_type_of(swdev, offset); if (data->swap < 0) return swdev ? -ENODEV : -EINVAL; data->dev = swdev; return 0; } static long snapshot_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { int error = 0; struct snapshot_data *data; loff_t size; sector_t offset; if (need_wait) { wait_for_device_probe(); need_wait = false; } if (_IOC_TYPE(cmd) != SNAPSHOT_IOC_MAGIC) return -ENOTTY; if (_IOC_NR(cmd) > SNAPSHOT_IOC_MAXNR) return -ENOTTY; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!mutex_trylock(&system_transition_mutex)) return -EBUSY; lock_device_hotplug(); data = filp->private_data; switch (cmd) { case SNAPSHOT_FREEZE: if (data->frozen) break; ksys_sync_helper(); error = freeze_processes(); if (error) break; error = create_basic_memory_bitmaps(); if (error) thaw_processes(); else data->frozen = true; break; case SNAPSHOT_UNFREEZE: if (!data->frozen || data->ready) break; pm_restore_gfp_mask(); free_basic_memory_bitmaps(); data->free_bitmaps = false; thaw_processes(); data->frozen = false; break; case SNAPSHOT_CREATE_IMAGE: if (data->mode != O_RDONLY || !data->frozen || data->ready) { error = -EPERM; break; } pm_restore_gfp_mask(); error = hibernation_snapshot(data->platform_support); if (!error) { error = put_user(in_suspend, (int __user *)arg); data->ready = !freezer_test_done && !error; freezer_test_done = false; } break; case SNAPSHOT_ATOMIC_RESTORE: error = snapshot_write_finalize(&data->handle); if (error) break; if (data->mode != O_WRONLY || !data->frozen || !snapshot_image_loaded(&data->handle)) { error = -EPERM; break; } error = hibernation_restore(data->platform_support); break; case SNAPSHOT_FREE: swsusp_free(); memset(&data->handle, 0, sizeof(struct snapshot_handle)); data->ready = false; /* * It is necessary to thaw kernel threads here, because * SNAPSHOT_CREATE_IMAGE may be invoked directly after * SNAPSHOT_FREE. In that case, if kernel threads were not * thawed, the preallocation of memory carried out by * hibernation_snapshot() might run into problems (i.e. it * might fail or even deadlock). */ thaw_kernel_threads(); break; case SNAPSHOT_PREF_IMAGE_SIZE: image_size = arg; break; case SNAPSHOT_GET_IMAGE_SIZE: if (!data->ready) { error = -ENODATA; break; } size = snapshot_get_image_size(); size <<= PAGE_SHIFT; error = put_user(size, (loff_t __user *)arg); break; case SNAPSHOT_AVAIL_SWAP_SIZE: size = count_swap_pages(data->swap, 1); size <<= PAGE_SHIFT; error = put_user(size, (loff_t __user *)arg); break; case SNAPSHOT_ALLOC_SWAP_PAGE: if (data->swap < 0 || data->swap >= MAX_SWAPFILES) { error = -ENODEV; break; } offset = alloc_swapdev_block(data->swap); if (offset) { offset <<= PAGE_SHIFT; error = put_user(offset, (loff_t __user *)arg); } else { error = -ENOSPC; } break; case SNAPSHOT_FREE_SWAP_PAGES: if (data->swap < 0 || data->swap >= MAX_SWAPFILES) { error = -ENODEV; break; } free_all_swap_pages(data->swap); break; case SNAPSHOT_S2RAM: if (!data->frozen) { error = -EPERM; break; } /* * Tasks are frozen and the notifiers have been called with * PM_HIBERNATION_PREPARE */ error = suspend_devices_and_enter(PM_SUSPEND_MEM); data->ready = false; break; case SNAPSHOT_PLATFORM_SUPPORT: data->platform_support = !!arg; break; case SNAPSHOT_POWER_OFF: if (data->platform_support) error = hibernation_platform_enter(); break; case SNAPSHOT_SET_SWAP_AREA: error = snapshot_set_swap_area(data, (void __user *)arg); break; default: error = -ENOTTY; } unlock_device_hotplug(); mutex_unlock(&system_transition_mutex); return error; } #ifdef CONFIG_COMPAT static long snapshot_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { BUILD_BUG_ON(sizeof(loff_t) != sizeof(compat_loff_t)); switch (cmd) { case SNAPSHOT_GET_IMAGE_SIZE: case SNAPSHOT_AVAIL_SWAP_SIZE: case SNAPSHOT_ALLOC_SWAP_PAGE: case SNAPSHOT_CREATE_IMAGE: case SNAPSHOT_SET_SWAP_AREA: return snapshot_ioctl(file, cmd, (unsigned long) compat_ptr(arg)); default: return snapshot_ioctl(file, cmd, arg); } } #endif /* CONFIG_COMPAT */ static const struct file_operations snapshot_fops = { .open = snapshot_open, .release = snapshot_release, .read = snapshot_read, .write = snapshot_write, .llseek = no_llseek, .unlocked_ioctl = snapshot_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = snapshot_compat_ioctl, #endif }; static struct miscdevice snapshot_device = { .minor = SNAPSHOT_MINOR, .name = "snapshot", .fops = &snapshot_fops, }; static int __init snapshot_device_init(void) { return misc_register(&snapshot_device); }; device_initcall(snapshot_device_init); |
| 2 157 151 152 124 8 2 6 2 4 156 18 138 44 44 39 39 39 34 34 3 31 6 6 6 61 44 5 12 12 12 56 56 154 153 128 57 5 52 34 2 32 32 92 1 91 81 39 34 34 34 3 3 3 2 1 3 5 3 3 5 5 5 3 3 2 8 3 5 31 10 19 2 1 1 78 78 6 2 74 3 30 63 2 32 32 32 27 15 11 11 23 9 23 7 16 4 4 4 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 | // SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/inline.c * Copyright (c) 2013, Intel Corporation * Authors: Huajun Li <huajun.li@intel.com> * Haicheng Li <haicheng.li@intel.com> */ #include <linux/fs.h> #include <linux/f2fs_fs.h> #include <linux/fiemap.h> #include "f2fs.h" #include "node.h" #include <trace/events/f2fs.h> static bool support_inline_data(struct inode *inode) { if (f2fs_used_in_atomic_write(inode)) return false; if (!S_ISREG(inode->i_mode) && !S_ISLNK(inode->i_mode)) return false; if (i_size_read(inode) > MAX_INLINE_DATA(inode)) return false; return true; } bool f2fs_may_inline_data(struct inode *inode) { if (!support_inline_data(inode)) return false; return !f2fs_post_read_required(inode); } static bool inode_has_blocks(struct inode *inode, struct page *ipage) { struct f2fs_inode *ri = F2FS_INODE(ipage); int i; if (F2FS_HAS_BLOCKS(inode)) return true; for (i = 0; i < DEF_NIDS_PER_INODE; i++) { if (ri->i_nid[i]) return true; } return false; } bool f2fs_sanity_check_inline_data(struct inode *inode, struct page *ipage) { if (!f2fs_has_inline_data(inode)) return false; if (inode_has_blocks(inode, ipage)) return false; if (!support_inline_data(inode)) return true; /* * used by sanity_check_inode(), when disk layout fields has not * been synchronized to inmem fields. */ return (S_ISREG(inode->i_mode) && (file_is_encrypt(inode) || file_is_verity(inode) || (F2FS_I(inode)->i_flags & F2FS_COMPR_FL))); } bool f2fs_may_inline_dentry(struct inode *inode) { if (!test_opt(F2FS_I_SB(inode), INLINE_DENTRY)) return false; if (!S_ISDIR(inode->i_mode)) return false; return true; } void f2fs_do_read_inline_data(struct folio *folio, struct page *ipage) { struct inode *inode = folio_file_mapping(folio)->host; if (folio_test_uptodate(folio)) return; f2fs_bug_on(F2FS_I_SB(inode), folio_index(folio)); folio_zero_segment(folio, MAX_INLINE_DATA(inode), folio_size(folio)); /* Copy the whole inline data block */ memcpy_to_folio(folio, 0, inline_data_addr(inode, ipage), MAX_INLINE_DATA(inode)); if (!folio_test_uptodate(folio)) folio_mark_uptodate(folio); } void f2fs_truncate_inline_inode(struct inode *inode, struct page *ipage, u64 from) { void *addr; if (from >= MAX_INLINE_DATA(inode)) return; addr = inline_data_addr(inode, ipage); f2fs_wait_on_page_writeback(ipage, NODE, true, true); memset(addr + from, 0, MAX_INLINE_DATA(inode) - from); set_page_dirty(ipage); if (from == 0) clear_inode_flag(inode, FI_DATA_EXIST); } int f2fs_read_inline_data(struct inode *inode, struct folio *folio) { struct page *ipage; ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino); if (IS_ERR(ipage)) { folio_unlock(folio); return PTR_ERR(ipage); } if (!f2fs_has_inline_data(inode)) { f2fs_put_page(ipage, 1); return -EAGAIN; } if (folio_index(folio)) folio_zero_segment(folio, 0, folio_size(folio)); else f2fs_do_read_inline_data(folio, ipage); if (!folio_test_uptodate(folio)) folio_mark_uptodate(folio); f2fs_put_page(ipage, 1); folio_unlock(folio); return 0; } int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page) { struct f2fs_io_info fio = { .sbi = F2FS_I_SB(dn->inode), .ino = dn->inode->i_ino, .type = DATA, .op = REQ_OP_WRITE, .op_flags = REQ_SYNC | REQ_PRIO, .page = page, .encrypted_page = NULL, .io_type = FS_DATA_IO, }; struct node_info ni; int dirty, err; if (!f2fs_exist_data(dn->inode)) goto clear_out; err = f2fs_reserve_block(dn, 0); if (err) return err; err = f2fs_get_node_info(fio.sbi, dn->nid, &ni, false); if (err) { f2fs_truncate_data_blocks_range(dn, 1); f2fs_put_dnode(dn); return err; } fio.version = ni.version; if (unlikely(dn->data_blkaddr != NEW_ADDR)) { f2fs_put_dnode(dn); set_sbi_flag(fio.sbi, SBI_NEED_FSCK); f2fs_warn(fio.sbi, "%s: corrupted inline inode ino=%lx, i_addr[0]:0x%x, run fsck to fix.", __func__, dn->inode->i_ino, dn->data_blkaddr); f2fs_handle_error(fio.sbi, ERROR_INVALID_BLKADDR); return -EFSCORRUPTED; } f2fs_bug_on(F2FS_P_SB(page), folio_test_writeback(page_folio(page))); f2fs_do_read_inline_data(page_folio(page), dn->inode_page); set_page_dirty(page); /* clear dirty state */ dirty = clear_page_dirty_for_io(page); /* write data page to try to make data consistent */ set_page_writeback(page); fio.old_blkaddr = dn->data_blkaddr; set_inode_flag(dn->inode, FI_HOT_DATA); f2fs_outplace_write_data(dn, &fio); f2fs_wait_on_page_writeback(page, DATA, true, true); if (dirty) { inode_dec_dirty_pages(dn->inode); f2fs_remove_dirty_inode(dn->inode); } /* this converted inline_data should be recovered. */ set_inode_flag(dn->inode, FI_APPEND_WRITE); /* clear inline data and flag after data writeback */ f2fs_truncate_inline_inode(dn->inode, dn->inode_page, 0); clear_page_private_inline(dn->inode_page); clear_out: stat_dec_inline_inode(dn->inode); clear_inode_flag(dn->inode, FI_INLINE_DATA); f2fs_put_dnode(dn); return 0; } int f2fs_convert_inline_inode(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct dnode_of_data dn; struct page *ipage, *page; int err = 0; if (f2fs_hw_is_readonly(sbi) || f2fs_readonly(sbi->sb)) return -EROFS; if (!f2fs_has_inline_data(inode)) return 0; err = f2fs_dquot_initialize(inode); if (err) return err; page = f2fs_grab_cache_page(inode->i_mapping, 0, false); if (!page) return -ENOMEM; f2fs_lock_op(sbi); ipage = f2fs_get_node_page(sbi, inode->i_ino); if (IS_ERR(ipage)) { err = PTR_ERR(ipage); goto out; } set_new_dnode(&dn, inode, ipage, ipage, 0); if (f2fs_has_inline_data(inode)) err = f2fs_convert_inline_page(&dn, page); f2fs_put_dnode(&dn); out: f2fs_unlock_op(sbi); f2fs_put_page(page, 1); if (!err) f2fs_balance_fs(sbi, dn.node_changed); return err; } int f2fs_write_inline_data(struct inode *inode, struct page *page) { struct dnode_of_data dn; int err; set_new_dnode(&dn, inode, NULL, NULL, 0); err = f2fs_get_dnode_of_data(&dn, 0, LOOKUP_NODE); if (err) return err; if (!f2fs_has_inline_data(inode)) { f2fs_put_dnode(&dn); return -EAGAIN; } f2fs_bug_on(F2FS_I_SB(inode), page->index); f2fs_wait_on_page_writeback(dn.inode_page, NODE, true, true); memcpy_from_page(inline_data_addr(inode, dn.inode_page), page, 0, MAX_INLINE_DATA(inode)); set_page_dirty(dn.inode_page); f2fs_clear_page_cache_dirty_tag(page); set_inode_flag(inode, FI_APPEND_WRITE); set_inode_flag(inode, FI_DATA_EXIST); clear_page_private_inline(dn.inode_page); f2fs_put_dnode(&dn); return 0; } int f2fs_recover_inline_data(struct inode *inode, struct page *npage) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode *ri = NULL; void *src_addr, *dst_addr; struct page *ipage; /* * The inline_data recovery policy is as follows. * [prev.] [next] of inline_data flag * o o -> recover inline_data * o x -> remove inline_data, and then recover data blocks * x o -> remove data blocks, and then recover inline_data * x x -> recover data blocks */ if (IS_INODE(npage)) ri = F2FS_INODE(npage); if (f2fs_has_inline_data(inode) && ri && (ri->i_inline & F2FS_INLINE_DATA)) { process_inline: ipage = f2fs_get_node_page(sbi, inode->i_ino); if (IS_ERR(ipage)) return PTR_ERR(ipage); f2fs_wait_on_page_writeback(ipage, NODE, true, true); src_addr = inline_data_addr(inode, npage); dst_addr = inline_data_addr(inode, ipage); memcpy(dst_addr, src_addr, MAX_INLINE_DATA(inode)); set_inode_flag(inode, FI_INLINE_DATA); set_inode_flag(inode, FI_DATA_EXIST); set_page_dirty(ipage); f2fs_put_page(ipage, 1); return 1; } if (f2fs_has_inline_data(inode)) { ipage = f2fs_get_node_page(sbi, inode->i_ino); if (IS_ERR(ipage)) return PTR_ERR(ipage); f2fs_truncate_inline_inode(inode, ipage, 0); stat_dec_inline_inode(inode); clear_inode_flag(inode, FI_INLINE_DATA); f2fs_put_page(ipage, 1); } else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) { int ret; ret = f2fs_truncate_blocks(inode, 0, false); if (ret) return ret; stat_inc_inline_inode(inode); goto process_inline; } return 0; } struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir, const struct f2fs_filename *fname, struct page **res_page) { struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb); struct f2fs_dir_entry *de; struct f2fs_dentry_ptr d; struct page *ipage; void *inline_dentry; ipage = f2fs_get_node_page(sbi, dir->i_ino); if (IS_ERR(ipage)) { *res_page = ipage; return NULL; } inline_dentry = inline_data_addr(dir, ipage); make_dentry_ptr_inline(dir, &d, inline_dentry); de = f2fs_find_target_dentry(&d, fname, NULL); unlock_page(ipage); if (IS_ERR(de)) { *res_page = ERR_CAST(de); de = NULL; } if (de) *res_page = ipage; else f2fs_put_page(ipage, 0); return de; } int f2fs_make_empty_inline_dir(struct inode *inode, struct inode *parent, struct page *ipage) { struct f2fs_dentry_ptr d; void *inline_dentry; inline_dentry = inline_data_addr(inode, ipage); make_dentry_ptr_inline(inode, &d, inline_dentry); f2fs_do_make_empty_dir(inode, parent, &d); set_page_dirty(ipage); /* update i_size to MAX_INLINE_DATA */ if (i_size_read(inode) < MAX_INLINE_DATA(inode)) f2fs_i_size_write(inode, MAX_INLINE_DATA(inode)); return 0; } /* * NOTE: ipage is grabbed by caller, but if any error occurs, we should * release ipage in this function. */ static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage, void *inline_dentry) { struct page *page; struct dnode_of_data dn; struct f2fs_dentry_block *dentry_blk; struct f2fs_dentry_ptr src, dst; int err; page = f2fs_grab_cache_page(dir->i_mapping, 0, true); if (!page) { f2fs_put_page(ipage, 1); return -ENOMEM; } set_new_dnode(&dn, dir, ipage, NULL, 0); err = f2fs_reserve_block(&dn, 0); if (err) goto out; if (unlikely(dn.data_blkaddr != NEW_ADDR)) { f2fs_put_dnode(&dn); set_sbi_flag(F2FS_P_SB(page), SBI_NEED_FSCK); f2fs_warn(F2FS_P_SB(page), "%s: corrupted inline inode ino=%lx, i_addr[0]:0x%x, run fsck to fix.", __func__, dir->i_ino, dn.data_blkaddr); f2fs_handle_error(F2FS_P_SB(page), ERROR_INVALID_BLKADDR); err = -EFSCORRUPTED; goto out; } f2fs_wait_on_page_writeback(page, DATA, true, true); dentry_blk = page_address(page); /* * Start by zeroing the full block, to ensure that all unused space is * zeroed and no uninitialized memory is leaked to disk. */ memset(dentry_blk, 0, F2FS_BLKSIZE); make_dentry_ptr_inline(dir, &src, inline_dentry); make_dentry_ptr_block(dir, &dst, dentry_blk); /* copy data from inline dentry block to new dentry block */ memcpy(dst.bitmap, src.bitmap, src.nr_bitmap); memcpy(dst.dentry, src.dentry, SIZE_OF_DIR_ENTRY * src.max); memcpy(dst.filename, src.filename, src.max * F2FS_SLOT_LEN); if (!PageUptodate(page)) SetPageUptodate(page); set_page_dirty(page); /* clear inline dir and flag after data writeback */ f2fs_truncate_inline_inode(dir, ipage, 0); stat_dec_inline_dir(dir); clear_inode_flag(dir, FI_INLINE_DENTRY); /* * should retrieve reserved space which was used to keep * inline_dentry's structure for backward compatibility. */ if (!f2fs_sb_has_flexible_inline_xattr(F2FS_I_SB(dir)) && !f2fs_has_inline_xattr(dir)) F2FS_I(dir)->i_inline_xattr_size = 0; f2fs_i_depth_write(dir, 1); if (i_size_read(dir) < PAGE_SIZE) f2fs_i_size_write(dir, PAGE_SIZE); out: f2fs_put_page(page, 1); return err; } static int f2fs_add_inline_entries(struct inode *dir, void *inline_dentry) { struct f2fs_dentry_ptr d; unsigned long bit_pos = 0; int err = 0; make_dentry_ptr_inline(dir, &d, inline_dentry); while (bit_pos < d.max) { struct f2fs_dir_entry *de; struct f2fs_filename fname; nid_t ino; umode_t fake_mode; if (!test_bit_le(bit_pos, d.bitmap)) { bit_pos++; continue; } de = &d.dentry[bit_pos]; if (unlikely(!de->name_len)) { bit_pos++; continue; } /* * We only need the disk_name and hash to move the dentry. * We don't need the original or casefolded filenames. */ memset(&fname, 0, sizeof(fname)); fname.disk_name.name = d.filename[bit_pos]; fname.disk_name.len = le16_to_cpu(de->name_len); fname.hash = de->hash_code; ino = le32_to_cpu(de->ino); fake_mode = fs_ftype_to_dtype(de->file_type) << S_DT_SHIFT; err = f2fs_add_regular_entry(dir, &fname, NULL, ino, fake_mode); if (err) goto punch_dentry_pages; bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len)); } return 0; punch_dentry_pages: truncate_inode_pages(&dir->i_data, 0); f2fs_truncate_blocks(dir, 0, false); f2fs_remove_dirty_inode(dir); return err; } static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage, void *inline_dentry) { void *backup_dentry; int err; backup_dentry = f2fs_kmalloc(F2FS_I_SB(dir), MAX_INLINE_DATA(dir), GFP_F2FS_ZERO); if (!backup_dentry) { f2fs_put_page(ipage, 1); return -ENOMEM; } memcpy(backup_dentry, inline_dentry, MAX_INLINE_DATA(dir)); f2fs_truncate_inline_inode(dir, ipage, 0); unlock_page(ipage); err = f2fs_add_inline_entries(dir, backup_dentry); if (err) goto recover; lock_page(ipage); stat_dec_inline_dir(dir); clear_inode_flag(dir, FI_INLINE_DENTRY); /* * should retrieve reserved space which was used to keep * inline_dentry's structure for backward compatibility. */ if (!f2fs_sb_has_flexible_inline_xattr(F2FS_I_SB(dir)) && !f2fs_has_inline_xattr(dir)) F2FS_I(dir)->i_inline_xattr_size = 0; kfree(backup_dentry); return 0; recover: lock_page(ipage); f2fs_wait_on_page_writeback(ipage, NODE, true, true); memcpy(inline_dentry, backup_dentry, MAX_INLINE_DATA(dir)); f2fs_i_depth_write(dir, 0); f2fs_i_size_write(dir, MAX_INLINE_DATA(dir)); set_page_dirty(ipage); f2fs_put_page(ipage, 1); kfree(backup_dentry); return err; } static int do_convert_inline_dir(struct inode *dir, struct page *ipage, void *inline_dentry) { if (!F2FS_I(dir)->i_dir_level) return f2fs_move_inline_dirents(dir, ipage, inline_dentry); else return f2fs_move_rehashed_dirents(dir, ipage, inline_dentry); } int f2fs_try_convert_inline_dir(struct inode *dir, struct dentry *dentry) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); struct page *ipage; struct f2fs_filename fname; void *inline_dentry = NULL; int err = 0; if (!f2fs_has_inline_dentry(dir)) return 0; f2fs_lock_op(sbi); err = f2fs_setup_filename(dir, &dentry->d_name, 0, &fname); if (err) goto out; ipage = f2fs_get_node_page(sbi, dir->i_ino); if (IS_ERR(ipage)) { err = PTR_ERR(ipage); goto out_fname; } if (f2fs_has_enough_room(dir, ipage, &fname)) { f2fs_put_page(ipage, 1); goto out_fname; } inline_dentry = inline_data_addr(dir, ipage); err = do_convert_inline_dir(dir, ipage, inline_dentry); if (!err) f2fs_put_page(ipage, 1); out_fname: f2fs_free_filename(&fname); out: f2fs_unlock_op(sbi); return err; } int f2fs_add_inline_entry(struct inode *dir, const struct f2fs_filename *fname, struct inode *inode, nid_t ino, umode_t mode) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); struct page *ipage; unsigned int bit_pos; void *inline_dentry = NULL; struct f2fs_dentry_ptr d; int slots = GET_DENTRY_SLOTS(fname->disk_name.len); struct page *page = NULL; int err = 0; ipage = f2fs_get_node_page(sbi, dir->i_ino); if (IS_ERR(ipage)) return PTR_ERR(ipage); inline_dentry = inline_data_addr(dir, ipage); make_dentry_ptr_inline(dir, &d, inline_dentry); bit_pos = f2fs_room_for_filename(d.bitmap, slots, d.max); if (bit_pos >= d.max) { err = do_convert_inline_dir(dir, ipage, inline_dentry); if (err) return err; err = -EAGAIN; goto out; } if (inode) { f2fs_down_write_nested(&F2FS_I(inode)->i_sem, SINGLE_DEPTH_NESTING); page = f2fs_init_inode_metadata(inode, dir, fname, ipage); if (IS_ERR(page)) { err = PTR_ERR(page); goto fail; } } f2fs_wait_on_page_writeback(ipage, NODE, true, true); f2fs_update_dentry(ino, mode, &d, &fname->disk_name, fname->hash, bit_pos); set_page_dirty(ipage); /* we don't need to mark_inode_dirty now */ if (inode) { f2fs_i_pino_write(inode, dir->i_ino); /* synchronize inode page's data from inode cache */ if (is_inode_flag_set(inode, FI_NEW_INODE)) f2fs_update_inode(inode, page); f2fs_put_page(page, 1); } f2fs_update_parent_metadata(dir, inode, 0); fail: if (inode) f2fs_up_write(&F2FS_I(inode)->i_sem); out: f2fs_put_page(ipage, 1); return err; } void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page, struct inode *dir, struct inode *inode) { struct f2fs_dentry_ptr d; void *inline_dentry; int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len)); unsigned int bit_pos; int i; lock_page(page); f2fs_wait_on_page_writeback(page, NODE, true, true); inline_dentry = inline_data_addr(dir, page); make_dentry_ptr_inline(dir, &d, inline_dentry); bit_pos = dentry - d.dentry; for (i = 0; i < slots; i++) __clear_bit_le(bit_pos + i, d.bitmap); set_page_dirty(page); f2fs_put_page(page, 1); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); f2fs_mark_inode_dirty_sync(dir, false); if (inode) f2fs_drop_nlink(dir, inode); } bool f2fs_empty_inline_dir(struct inode *dir) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); struct page *ipage; unsigned int bit_pos = 2; void *inline_dentry; struct f2fs_dentry_ptr d; ipage = f2fs_get_node_page(sbi, dir->i_ino); if (IS_ERR(ipage)) return false; inline_dentry = inline_data_addr(dir, ipage); make_dentry_ptr_inline(dir, &d, inline_dentry); bit_pos = find_next_bit_le(d.bitmap, d.max, bit_pos); f2fs_put_page(ipage, 1); if (bit_pos < d.max) return false; return true; } int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx, struct fscrypt_str *fstr) { struct inode *inode = file_inode(file); struct page *ipage = NULL; struct f2fs_dentry_ptr d; void *inline_dentry = NULL; int err; make_dentry_ptr_inline(inode, &d, inline_dentry); if (ctx->pos == d.max) return 0; ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino); if (IS_ERR(ipage)) return PTR_ERR(ipage); /* * f2fs_readdir was protected by inode.i_rwsem, it is safe to access * ipage without page's lock held. */ unlock_page(ipage); inline_dentry = inline_data_addr(inode, ipage); make_dentry_ptr_inline(inode, &d, inline_dentry); err = f2fs_fill_dentries(ctx, &d, 0, fstr); if (!err) ctx->pos = d.max; f2fs_put_page(ipage, 0); return err < 0 ? err : 0; } int f2fs_inline_data_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len) { __u64 byteaddr, ilen; __u32 flags = FIEMAP_EXTENT_DATA_INLINE | FIEMAP_EXTENT_NOT_ALIGNED | FIEMAP_EXTENT_LAST; struct node_info ni; struct page *ipage; int err = 0; ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino); if (IS_ERR(ipage)) return PTR_ERR(ipage); if ((S_ISREG(inode->i_mode) || S_ISLNK(inode->i_mode)) && !f2fs_has_inline_data(inode)) { err = -EAGAIN; goto out; } if (S_ISDIR(inode->i_mode) && !f2fs_has_inline_dentry(inode)) { err = -EAGAIN; goto out; } ilen = min_t(size_t, MAX_INLINE_DATA(inode), i_size_read(inode)); if (start >= ilen) goto out; if (start + len < ilen) ilen = start + len; ilen -= start; err = f2fs_get_node_info(F2FS_I_SB(inode), inode->i_ino, &ni, false); if (err) goto out; byteaddr = (__u64)ni.blk_addr << inode->i_sb->s_blocksize_bits; byteaddr += (char *)inline_data_addr(inode, ipage) - (char *)F2FS_INODE(ipage); err = fiemap_fill_next_extent(fieinfo, start, byteaddr, ilen, flags); trace_f2fs_fiemap(inode, start, byteaddr, ilen, flags, err); out: f2fs_put_page(ipage, 1); return err; } |
| 193 192 180 99 147 147 255 255 255 252 114 59 114 11 104 112 112 184 22 18 94 99 24 83 97 109 111 70 46 70 1 69 34 34 27 79 80 34 173 179 13 253 252 85 167 167 30 145 166 26 7 7 7 8 8 8 7 15 15 180 149 178 176 15 128 98 177 176 177 176 178 149 149 25 180 8 8 2 196 196 197 196 4 14 19 151 20 211 213 50 47 6 146 17 197 8 219 218 221 8 9 19 194 195 172 172 150 185 18 7 7 167 184 220 2 2 2 2 2 1 1 26 25 187 8 30 166 8 174 26 51 144 38 26 26 12 18 183 188 187 29 29 3 29 28 29 4 15 17 28 11 11 11 11 11 2 2 2 2 922 20 325 913 893 59 7 6 7 7 7 7 7 7 187 179 9 2 7 7 9 293 294 295 8 8 254 252 21 8 230 216 16 163 242 32 242 241 241 241 265 263 13 13 12 12 16 13 268 139 287 287 287 94 186 284 287 287 96 187 286 96 187 284 1 287 137 37 157 97 96 189 187 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/errno.h> #include <linux/err.h> #include <linux/spinlock.h> #include <linux/mm.h> #include <linux/memfd.h> #include <linux/memremap.h> #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/secretmem.h> #include <linux/sched/signal.h> #include <linux/rwsem.h> #include <linux/hugetlb.h> #include <linux/migrate.h> #include <linux/mm_inline.h> #include <linux/pagevec.h> #include <linux/sched/mm.h> #include <linux/shmem_fs.h> #include <asm/mmu_context.h> #include <asm/tlbflush.h> #include "internal.h" struct follow_page_context { struct dev_pagemap *pgmap; unsigned int page_mask; }; static inline void sanity_check_pinned_pages(struct page **pages, unsigned long npages) { if (!IS_ENABLED(CONFIG_DEBUG_VM)) return; /* * We only pin anonymous pages if they are exclusive. Once pinned, we * can no longer turn them possibly shared and PageAnonExclusive() will * stick around until the page is freed. * * We'd like to verify that our pinned anonymous pages are still mapped * exclusively. The issue with anon THP is that we don't know how * they are/were mapped when pinning them. However, for anon * THP we can assume that either the given page (PTE-mapped THP) or * the head page (PMD-mapped THP) should be PageAnonExclusive(). If * neither is the case, there is certainly something wrong. */ for (; npages; npages--, pages++) { struct page *page = *pages; struct folio *folio = page_folio(page); if (is_zero_page(page) || !folio_test_anon(folio)) continue; if (!folio_test_large(folio) || folio_test_hugetlb(folio)) VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page), page); else /* Either a PTE-mapped or a PMD-mapped THP. */ VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page) && !PageAnonExclusive(page), page); } } /* * Return the folio with ref appropriately incremented, * or NULL if that failed. */ static inline struct folio *try_get_folio(struct page *page, int refs) { struct folio *folio; retry: folio = page_folio(page); if (WARN_ON_ONCE(folio_ref_count(folio) < 0)) return NULL; if (unlikely(!folio_ref_try_add(folio, refs))) return NULL; /* * At this point we have a stable reference to the folio; but it * could be that between calling page_folio() and the refcount * increment, the folio was split, in which case we'd end up * holding a reference on a folio that has nothing to do with the page * we were given anymore. * So now that the folio is stable, recheck that the page still * belongs to this folio. */ if (unlikely(page_folio(page) != folio)) { if (!put_devmap_managed_folio_refs(folio, refs)) folio_put_refs(folio, refs); goto retry; } return folio; } static void gup_put_folio(struct folio *folio, int refs, unsigned int flags) { if (flags & FOLL_PIN) { if (is_zero_folio(folio)) return; node_stat_mod_folio(folio, NR_FOLL_PIN_RELEASED, refs); if (folio_test_large(folio)) atomic_sub(refs, &folio->_pincount); else refs *= GUP_PIN_COUNTING_BIAS; } if (!put_devmap_managed_folio_refs(folio, refs)) folio_put_refs(folio, refs); } /** * try_grab_folio() - add a folio's refcount by a flag-dependent amount * @folio: pointer to folio to be grabbed * @refs: the value to (effectively) add to the folio's refcount * @flags: gup flags: these are the FOLL_* flag values * * This might not do anything at all, depending on the flags argument. * * "grab" names in this file mean, "look at flags to decide whether to use * FOLL_PIN or FOLL_GET behavior, when incrementing the folio's refcount. * * Either FOLL_PIN or FOLL_GET (or neither) may be set, but not both at the same * time. * * Return: 0 for success, or if no action was required (if neither FOLL_PIN * nor FOLL_GET was set, nothing is done). A negative error code for failure: * * -ENOMEM FOLL_GET or FOLL_PIN was set, but the folio could not * be grabbed. * * It is called when we have a stable reference for the folio, typically in * GUP slow path. */ int __must_check try_grab_folio(struct folio *folio, int refs, unsigned int flags) { if (WARN_ON_ONCE(folio_ref_count(folio) <= 0)) return -ENOMEM; if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(&folio->page))) return -EREMOTEIO; if (flags & FOLL_GET) folio_ref_add(folio, refs); else if (flags & FOLL_PIN) { /* * Don't take a pin on the zero page - it's not going anywhere * and it is used in a *lot* of places. */ if (is_zero_folio(folio)) return 0; /* * Increment the normal page refcount field at least once, * so that the page really is pinned. */ if (folio_test_large(folio)) { folio_ref_add(folio, refs); atomic_add(refs, &folio->_pincount); } else { folio_ref_add(folio, refs * GUP_PIN_COUNTING_BIAS); } node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs); } return 0; } /** * unpin_user_page() - release a dma-pinned page * @page: pointer to page to be released * * Pages that were pinned via pin_user_pages*() must be released via either * unpin_user_page(), or one of the unpin_user_pages*() routines. This is so * that such pages can be separately tracked and uniquely handled. In * particular, interactions with RDMA and filesystems need special handling. */ void unpin_user_page(struct page *page) { sanity_check_pinned_pages(&page, 1); gup_put_folio(page_folio(page), 1, FOLL_PIN); } EXPORT_SYMBOL(unpin_user_page); /** * unpin_folio() - release a dma-pinned folio * @folio: pointer to folio to be released * * Folios that were pinned via memfd_pin_folios() or other similar routines * must be released either using unpin_folio() or unpin_folios(). */ void unpin_folio(struct folio *folio) { gup_put_folio(folio, 1, FOLL_PIN); } EXPORT_SYMBOL_GPL(unpin_folio); /** * folio_add_pin - Try to get an additional pin on a pinned folio * @folio: The folio to be pinned * * Get an additional pin on a folio we already have a pin on. Makes no change * if the folio is a zero_page. */ void folio_add_pin(struct folio *folio) { if (is_zero_folio(folio)) return; /* * Similar to try_grab_folio(): be sure to *also* increment the normal * page refcount field at least once, so that the page really is * pinned. */ if (folio_test_large(folio)) { WARN_ON_ONCE(atomic_read(&folio->_pincount) < 1); folio_ref_inc(folio); atomic_inc(&folio->_pincount); } else { WARN_ON_ONCE(folio_ref_count(folio) < GUP_PIN_COUNTING_BIAS); folio_ref_add(folio, GUP_PIN_COUNTING_BIAS); } } static inline struct folio *gup_folio_range_next(struct page *start, unsigned long npages, unsigned long i, unsigned int *ntails) { struct page *next = nth_page(start, i); struct folio *folio = page_folio(next); unsigned int nr = 1; if (folio_test_large(folio)) nr = min_t(unsigned int, npages - i, folio_nr_pages(folio) - folio_page_idx(folio, next)); *ntails = nr; return folio; } static inline struct folio *gup_folio_next(struct page **list, unsigned long npages, unsigned long i, unsigned int *ntails) { struct folio *folio = page_folio(list[i]); unsigned int nr; for (nr = i + 1; nr < npages; nr++) { if (page_folio(list[nr]) != folio) break; } *ntails = nr - i; return folio; } /** * unpin_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages * @pages: array of pages to be maybe marked dirty, and definitely released. * @npages: number of pages in the @pages array. * @make_dirty: whether to mark the pages dirty * * "gup-pinned page" refers to a page that has had one of the get_user_pages() * variants called on that page. * * For each page in the @pages array, make that page (or its head page, if a * compound page) dirty, if @make_dirty is true, and if the page was previously * listed as clean. In any case, releases all pages using unpin_user_page(), * possibly via unpin_user_pages(), for the non-dirty case. * * Please see the unpin_user_page() documentation for details. * * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is * required, then the caller should a) verify that this is really correct, * because _lock() is usually required, and b) hand code it: * set_page_dirty_lock(), unpin_user_page(). * */ void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, bool make_dirty) { unsigned long i; struct folio *folio; unsigned int nr; if (!make_dirty) { unpin_user_pages(pages, npages); return; } sanity_check_pinned_pages(pages, npages); for (i = 0; i < npages; i += nr) { folio = gup_folio_next(pages, npages, i, &nr); /* * Checking PageDirty at this point may race with * clear_page_dirty_for_io(), but that's OK. Two key * cases: * * 1) This code sees the page as already dirty, so it * skips the call to set_page_dirty(). That could happen * because clear_page_dirty_for_io() called * folio_mkclean(), followed by set_page_dirty(). * However, now the page is going to get written back, * which meets the original intention of setting it * dirty, so all is well: clear_page_dirty_for_io() goes * on to call TestClearPageDirty(), and write the page * back. * * 2) This code sees the page as clean, so it calls * set_page_dirty(). The page stays dirty, despite being * written back, so it gets written back again in the * next writeback cycle. This is harmless. */ if (!folio_test_dirty(folio)) { folio_lock(folio); folio_mark_dirty(folio); folio_unlock(folio); } gup_put_folio(folio, nr, FOLL_PIN); } } EXPORT_SYMBOL(unpin_user_pages_dirty_lock); /** * unpin_user_page_range_dirty_lock() - release and optionally dirty * gup-pinned page range * * @page: the starting page of a range maybe marked dirty, and definitely released. * @npages: number of consecutive pages to release. * @make_dirty: whether to mark the pages dirty * * "gup-pinned page range" refers to a range of pages that has had one of the * pin_user_pages() variants called on that page. * * For the page ranges defined by [page .. page+npages], make that range (or * its head pages, if a compound page) dirty, if @make_dirty is true, and if the * page range was previously listed as clean. * * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is * required, then the caller should a) verify that this is really correct, * because _lock() is usually required, and b) hand code it: * set_page_dirty_lock(), unpin_user_page(). * */ void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages, bool make_dirty) { unsigned long i; struct folio *folio; unsigned int nr; for (i = 0; i < npages; i += nr) { folio = gup_folio_range_next(page, npages, i, &nr); if (make_dirty && !folio_test_dirty(folio)) { folio_lock(folio); folio_mark_dirty(folio); folio_unlock(folio); } gup_put_folio(folio, nr, FOLL_PIN); } } EXPORT_SYMBOL(unpin_user_page_range_dirty_lock); static void gup_fast_unpin_user_pages(struct page **pages, unsigned long npages) { unsigned long i; struct folio *folio; unsigned int nr; /* * Don't perform any sanity checks because we might have raced with * fork() and some anonymous pages might now actually be shared -- * which is why we're unpinning after all. */ for (i = 0; i < npages; i += nr) { folio = gup_folio_next(pages, npages, i, &nr); gup_put_folio(folio, nr, FOLL_PIN); } } /** * unpin_user_pages() - release an array of gup-pinned pages. * @pages: array of pages to be marked dirty and released. * @npages: number of pages in the @pages array. * * For each page in the @pages array, release the page using unpin_user_page(). * * Please see the unpin_user_page() documentation for details. */ void unpin_user_pages(struct page **pages, unsigned long npages) { unsigned long i; struct folio *folio; unsigned int nr; /* * If this WARN_ON() fires, then the system *might* be leaking pages (by * leaving them pinned), but probably not. More likely, gup/pup returned * a hard -ERRNO error to the caller, who erroneously passed it here. */ if (WARN_ON(IS_ERR_VALUE(npages))) return; sanity_check_pinned_pages(pages, npages); for (i = 0; i < npages; i += nr) { folio = gup_folio_next(pages, npages, i, &nr); gup_put_folio(folio, nr, FOLL_PIN); } } EXPORT_SYMBOL(unpin_user_pages); /** * unpin_folios() - release an array of gup-pinned folios. * @folios: array of folios to be marked dirty and released. * @nfolios: number of folios in the @folios array. * * For each folio in the @folios array, release the folio using gup_put_folio. * * Please see the unpin_folio() documentation for details. */ void unpin_folios(struct folio **folios, unsigned long nfolios) { unsigned long i = 0, j; /* * If this WARN_ON() fires, then the system *might* be leaking folios * (by leaving them pinned), but probably not. More likely, gup/pup * returned a hard -ERRNO error to the caller, who erroneously passed * it here. */ if (WARN_ON(IS_ERR_VALUE(nfolios))) return; while (i < nfolios) { for (j = i + 1; j < nfolios; j++) if (folios[i] != folios[j]) break; if (folios[i]) gup_put_folio(folios[i], j - i, FOLL_PIN); i = j; } } EXPORT_SYMBOL_GPL(unpin_folios); /* * Set the MMF_HAS_PINNED if not set yet; after set it'll be there for the mm's * lifecycle. Avoid setting the bit unless necessary, or it might cause write * cache bouncing on large SMP machines for concurrent pinned gups. */ static inline void mm_set_has_pinned_flag(unsigned long *mm_flags) { if (!test_bit(MMF_HAS_PINNED, mm_flags)) set_bit(MMF_HAS_PINNED, mm_flags); } #ifdef CONFIG_MMU #ifdef CONFIG_HAVE_GUP_FAST static int record_subpages(struct page *page, unsigned long sz, unsigned long addr, unsigned long end, struct page **pages) { struct page *start_page; int nr; start_page = nth_page(page, (addr & (sz - 1)) >> PAGE_SHIFT); for (nr = 0; addr != end; nr++, addr += PAGE_SIZE) pages[nr] = nth_page(start_page, nr); return nr; } /** * try_grab_folio_fast() - Attempt to get or pin a folio in fast path. * @page: pointer to page to be grabbed * @refs: the value to (effectively) add to the folio's refcount * @flags: gup flags: these are the FOLL_* flag values. * * "grab" names in this file mean, "look at flags to decide whether to use * FOLL_PIN or FOLL_GET behavior, when incrementing the folio's refcount. * * Either FOLL_PIN or FOLL_GET (or neither) must be set, but not both at the * same time. (That's true throughout the get_user_pages*() and * pin_user_pages*() APIs.) Cases: * * FOLL_GET: folio's refcount will be incremented by @refs. * * FOLL_PIN on large folios: folio's refcount will be incremented by * @refs, and its pincount will be incremented by @refs. * * FOLL_PIN on single-page folios: folio's refcount will be incremented by * @refs * GUP_PIN_COUNTING_BIAS. * * Return: The folio containing @page (with refcount appropriately * incremented) for success, or NULL upon failure. If neither FOLL_GET * nor FOLL_PIN was set, that's considered failure, and furthermore, * a likely bug in the caller, so a warning is also emitted. * * It uses add ref unless zero to elevate the folio refcount and must be called * in fast path only. */ static struct folio *try_grab_folio_fast(struct page *page, int refs, unsigned int flags) { struct folio *folio; /* Raise warn if it is not called in fast GUP */ VM_WARN_ON_ONCE(!irqs_disabled()); if (WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == 0)) return NULL; if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page))) return NULL; if (flags & FOLL_GET) return try_get_folio(page, refs); /* FOLL_PIN is set */ /* * Don't take a pin on the zero page - it's not going anywhere * and it is used in a *lot* of places. */ if (is_zero_page(page)) return page_folio(page); folio = try_get_folio(page, refs); if (!folio) return NULL; /* * Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a * right zone, so fail and let the caller fall back to the slow * path. */ if (unlikely((flags & FOLL_LONGTERM) && !folio_is_longterm_pinnable(folio))) { if (!put_devmap_managed_folio_refs(folio, refs)) folio_put_refs(folio, refs); return NULL; } /* * When pinning a large folio, use an exact count to track it. * * However, be sure to *also* increment the normal folio * refcount field at least once, so that the folio really * is pinned. That's why the refcount from the earlier * try_get_folio() is left intact. */ if (folio_test_large(folio)) atomic_add(refs, &folio->_pincount); else folio_ref_add(folio, refs * (GUP_PIN_COUNTING_BIAS - 1)); /* * Adjust the pincount before re-checking the PTE for changes. * This is essentially a smp_mb() and is paired with a memory * barrier in folio_try_share_anon_rmap_*(). */ smp_mb__after_atomic(); node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs); return folio; } #endif /* CONFIG_HAVE_GUP_FAST */ static struct page *no_page_table(struct vm_area_struct *vma, unsigned int flags, unsigned long address) { if (!(flags & FOLL_DUMP)) return NULL; /* * When core dumping, we don't want to allocate unnecessary pages or * page tables. Return error instead of NULL to skip handle_mm_fault, * then get_dump_page() will return NULL to leave a hole in the dump. * But we can only make this optimization where a hole would surely * be zero-filled if handle_mm_fault() actually did handle it. */ if (is_vm_hugetlb_page(vma)) { struct hstate *h = hstate_vma(vma); if (!hugetlbfs_pagecache_present(h, vma, address)) return ERR_PTR(-EFAULT); } else if ((vma_is_anonymous(vma) || !vma->vm_ops->fault)) { return ERR_PTR(-EFAULT); } return NULL; } #ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES static struct page *follow_huge_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pudp, int flags, struct follow_page_context *ctx) { struct mm_struct *mm = vma->vm_mm; struct page *page; pud_t pud = *pudp; unsigned long pfn = pud_pfn(pud); int ret; assert_spin_locked(pud_lockptr(mm, pudp)); if ((flags & FOLL_WRITE) && !pud_write(pud)) return NULL; if (!pud_present(pud)) return NULL; pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT; if (IS_ENABLED(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) && pud_devmap(pud)) { /* * device mapped pages can only be returned if the caller * will manage the page reference count. * * At least one of FOLL_GET | FOLL_PIN must be set, so * assert that here: */ if (!(flags & (FOLL_GET | FOLL_PIN))) return ERR_PTR(-EEXIST); if (flags & FOLL_TOUCH) touch_pud(vma, addr, pudp, flags & FOLL_WRITE); ctx->pgmap = get_dev_pagemap(pfn, ctx->pgmap); if (!ctx->pgmap) return ERR_PTR(-EFAULT); } page = pfn_to_page(pfn); if (!pud_devmap(pud) && !pud_write(pud) && gup_must_unshare(vma, flags, page)) return ERR_PTR(-EMLINK); ret = try_grab_folio(page_folio(page), 1, flags); if (ret) page = ERR_PTR(ret); else ctx->page_mask = HPAGE_PUD_NR - 1; return page; } /* FOLL_FORCE can write to even unwritable PMDs in COW mappings. */ static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page, struct vm_area_struct *vma, unsigned int flags) { /* If the pmd is writable, we can write to the page. */ if (pmd_write(pmd)) return true; /* Maybe FOLL_FORCE is set to override it? */ if (!(flags & FOLL_FORCE)) return false; /* But FOLL_FORCE has no effect on shared mappings */ if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED)) return false; /* ... or read-only private ones */ if (!(vma->vm_flags & VM_MAYWRITE)) return false; /* ... or already writable ones that just need to take a write fault */ if (vma->vm_flags & VM_WRITE) return false; /* * See can_change_pte_writable(): we broke COW and could map the page * writable if we have an exclusive anonymous page ... */ if (!page || !PageAnon(page) || !PageAnonExclusive(page)) return false; /* ... and a write-fault isn't required for other reasons. */ if (pmd_needs_soft_dirty_wp(vma, pmd)) return false; return !userfaultfd_huge_pmd_wp(vma, pmd); } static struct page *follow_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, unsigned int flags, struct follow_page_context *ctx) { struct mm_struct *mm = vma->vm_mm; pmd_t pmdval = *pmd; struct page *page; int ret; assert_spin_locked(pmd_lockptr(mm, pmd)); page = pmd_page(pmdval); if ((flags & FOLL_WRITE) && !can_follow_write_pmd(pmdval, page, vma, flags)) return NULL; /* Avoid dumping huge zero page */ if ((flags & FOLL_DUMP) && is_huge_zero_pmd(pmdval)) return ERR_PTR(-EFAULT); if (pmd_protnone(*pmd) && !gup_can_follow_protnone(vma, flags)) return NULL; if (!pmd_write(pmdval) && gup_must_unshare(vma, flags, page)) return ERR_PTR(-EMLINK); VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && !PageAnonExclusive(page), page); ret = try_grab_folio(page_folio(page), 1, flags); if (ret) return ERR_PTR(ret); #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (pmd_trans_huge(pmdval) && (flags & FOLL_TOUCH)) touch_pmd(vma, addr, pmd, flags & FOLL_WRITE); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; ctx->page_mask = HPAGE_PMD_NR - 1; return page; } #else /* CONFIG_PGTABLE_HAS_HUGE_LEAVES */ static struct page *follow_huge_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pudp, int flags, struct follow_page_context *ctx) { return NULL; } static struct page *follow_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, unsigned int flags, struct follow_page_context *ctx) { return NULL; } #endif /* CONFIG_PGTABLE_HAS_HUGE_LEAVES */ static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address, pte_t *pte, unsigned int flags) { if (flags & FOLL_TOUCH) { pte_t orig_entry = ptep_get(pte); pte_t entry = orig_entry; if (flags & FOLL_WRITE) entry = pte_mkdirty(entry); entry = pte_mkyoung(entry); if (!pte_same(orig_entry, entry)) { set_pte_at(vma->vm_mm, address, pte, entry); update_mmu_cache(vma, address, pte); } } /* Proper page table entry exists, but no corresponding struct page */ return -EEXIST; } /* FOLL_FORCE can write to even unwritable PTEs in COW mappings. */ static inline bool can_follow_write_pte(pte_t pte, struct page *page, struct vm_area_struct *vma, unsigned int flags) { /* If the pte is writable, we can write to the page. */ if (pte_write(pte)) return true; /* Maybe FOLL_FORCE is set to override it? */ if (!(flags & FOLL_FORCE)) return false; /* But FOLL_FORCE has no effect on shared mappings */ if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED)) return false; /* ... or read-only private ones */ if (!(vma->vm_flags & VM_MAYWRITE)) return false; /* ... or already writable ones that just need to take a write fault */ if (vma->vm_flags & VM_WRITE) return false; /* * See can_change_pte_writable(): we broke COW and could map the page * writable if we have an exclusive anonymous page ... */ if (!page || !PageAnon(page) || !PageAnonExclusive(page)) return false; /* ... and a write-fault isn't required for other reasons. */ if (pte_needs_soft_dirty_wp(vma, pte)) return false; return !userfaultfd_pte_wp(vma, pte); } static struct page *follow_page_pte(struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, unsigned int flags, struct dev_pagemap **pgmap) { struct mm_struct *mm = vma->vm_mm; struct page *page; spinlock_t *ptl; pte_t *ptep, pte; int ret; /* FOLL_GET and FOLL_PIN are mutually exclusive. */ if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == (FOLL_PIN | FOLL_GET))) return ERR_PTR(-EINVAL); ptep = pte_offset_map_lock(mm, pmd, address, &ptl); if (!ptep) return no_page_table(vma, flags, address); pte = ptep_get(ptep); if (!pte_present(pte)) goto no_page; if (pte_protnone(pte) && !gup_can_follow_protnone(vma, flags)) goto no_page; page = vm_normal_page(vma, address, pte); /* * We only care about anon pages in can_follow_write_pte() and don't * have to worry about pte_devmap() because they are never anon. */ if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, page, vma, flags)) { page = NULL; goto out; } if (!page && pte_devmap(pte) && (flags & (FOLL_GET | FOLL_PIN))) { /* * Only return device mapping pages in the FOLL_GET or FOLL_PIN * case since they are only valid while holding the pgmap * reference. */ *pgmap = get_dev_pagemap(pte_pfn(pte), *pgmap); if (*pgmap) page = pte_page(pte); else goto no_page; } else if (unlikely(!page)) { if (flags & FOLL_DUMP) { /* Avoid special (like zero) pages in core dumps */ page = ERR_PTR(-EFAULT); goto out; } if (is_zero_pfn(pte_pfn(pte))) { page = pte_page(pte); } else { ret = follow_pfn_pte(vma, address, ptep, flags); page = ERR_PTR(ret); goto out; } } if (!pte_write(pte) && gup_must_unshare(vma, flags, page)) { page = ERR_PTR(-EMLINK); goto out; } VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && !PageAnonExclusive(page), page); /* try_grab_folio() does nothing unless FOLL_GET or FOLL_PIN is set. */ ret = try_grab_folio(page_folio(page), 1, flags); if (unlikely(ret)) { page = ERR_PTR(ret); goto out; } /* * We need to make the page accessible if and only if we are going * to access its content (the FOLL_PIN case). Please see * Documentation/core-api/pin_user_pages.rst for details. */ if (flags & FOLL_PIN) { ret = arch_make_page_accessible(page); if (ret) { unpin_user_page(page); page = ERR_PTR(ret); goto out; } } if (flags & FOLL_TOUCH) { if ((flags & FOLL_WRITE) && !pte_dirty(pte) && !PageDirty(page)) set_page_dirty(page); /* * pte_mkyoung() would be more correct here, but atomic care * is needed to avoid losing the dirty bit: it is easier to use * mark_page_accessed(). */ mark_page_accessed(page); } out: pte_unmap_unlock(ptep, ptl); return page; no_page: pte_unmap_unlock(ptep, ptl); if (!pte_none(pte)) return NULL; return no_page_table(vma, flags, address); } static struct page *follow_pmd_mask(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, unsigned int flags, struct follow_page_context *ctx) { pmd_t *pmd, pmdval; spinlock_t *ptl; struct page *page; struct mm_struct *mm = vma->vm_mm; pmd = pmd_offset(pudp, address); pmdval = pmdp_get_lockless(pmd); if (pmd_none(pmdval)) return no_page_table(vma, flags, address); if (!pmd_present(pmdval)) return no_page_table(vma, flags, address); if (pmd_devmap(pmdval)) { ptl = pmd_lock(mm, pmd); page = follow_devmap_pmd(vma, address, pmd, flags, &ctx->pgmap); spin_unlock(ptl); if (page) return page; return no_page_table(vma, flags, address); } if (likely(!pmd_leaf(pmdval))) return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); if (pmd_protnone(pmdval) && !gup_can_follow_protnone(vma, flags)) return no_page_table(vma, flags, address); ptl = pmd_lock(mm, pmd); pmdval = *pmd; if (unlikely(!pmd_present(pmdval))) { spin_unlock(ptl); return no_page_table(vma, flags, address); } if (unlikely(!pmd_leaf(pmdval))) { spin_unlock(ptl); return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); } if (pmd_trans_huge(pmdval) && (flags & FOLL_SPLIT_PMD)) { spin_unlock(ptl); split_huge_pmd(vma, pmd, address); /* If pmd was left empty, stuff a page table in there quickly */ return pte_alloc(mm, pmd) ? ERR_PTR(-ENOMEM) : follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); } page = follow_huge_pmd(vma, address, pmd, flags, ctx); spin_unlock(ptl); return page; } static struct page *follow_pud_mask(struct vm_area_struct *vma, unsigned long address, p4d_t *p4dp, unsigned int flags, struct follow_page_context *ctx) { pud_t *pudp, pud; spinlock_t *ptl; struct page *page; struct mm_struct *mm = vma->vm_mm; pudp = pud_offset(p4dp, address); pud = READ_ONCE(*pudp); if (!pud_present(pud)) return no_page_table(vma, flags, address); if (pud_leaf(pud)) { ptl = pud_lock(mm, pudp); page = follow_huge_pud(vma, address, pudp, flags, ctx); spin_unlock(ptl); if (page) return page; return no_page_table(vma, flags, address); } if (unlikely(pud_bad(pud))) return no_page_table(vma, flags, address); return follow_pmd_mask(vma, address, pudp, flags, ctx); } static struct page *follow_p4d_mask(struct vm_area_struct *vma, unsigned long address, pgd_t *pgdp, unsigned int flags, struct follow_page_context *ctx) { p4d_t *p4dp, p4d; p4dp = p4d_offset(pgdp, address); p4d = READ_ONCE(*p4dp); BUILD_BUG_ON(p4d_leaf(p4d)); if (!p4d_present(p4d) || p4d_bad(p4d)) return no_page_table(vma, flags, address); return follow_pud_mask(vma, address, p4dp, flags, ctx); } /** * follow_page_mask - look up a page descriptor from a user-virtual address * @vma: vm_area_struct mapping @address * @address: virtual address to look up * @flags: flags modifying lookup behaviour * @ctx: contains dev_pagemap for %ZONE_DEVICE memory pinning and a * pointer to output page_mask * * @flags can have FOLL_ flags set, defined in <linux/mm.h> * * When getting pages from ZONE_DEVICE memory, the @ctx->pgmap caches * the device's dev_pagemap metadata to avoid repeating expensive lookups. * * When getting an anonymous page and the caller has to trigger unsharing * of a shared anonymous page first, -EMLINK is returned. The caller should * trigger a fault with FAULT_FLAG_UNSHARE set. Note that unsharing is only * relevant with FOLL_PIN and !FOLL_WRITE. * * On output, the @ctx->page_mask is set according to the size of the page. * * Return: the mapped (struct page *), %NULL if no mapping exists, or * an error pointer if there is a mapping to something not represented * by a page descriptor (see also vm_normal_page()). */ static struct page *follow_page_mask(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct follow_page_context *ctx) { pgd_t *pgd; struct mm_struct *mm = vma->vm_mm; struct page *page; vma_pgtable_walk_begin(vma); ctx->page_mask = 0; pgd = pgd_offset(mm, address); if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) page = no_page_table(vma, flags, address); else page = follow_p4d_mask(vma, address, pgd, flags, ctx); vma_pgtable_walk_end(vma); return page; } struct page *follow_page(struct vm_area_struct *vma, unsigned long address, unsigned int foll_flags) { struct follow_page_context ctx = { NULL }; struct page *page; if (vma_is_secretmem(vma)) return NULL; if (WARN_ON_ONCE(foll_flags & FOLL_PIN)) return NULL; /* * We never set FOLL_HONOR_NUMA_FAULT because callers don't expect * to fail on PROT_NONE-mapped pages. */ page = follow_page_mask(vma, address, foll_flags, &ctx); if (ctx.pgmap) put_dev_pagemap(ctx.pgmap); return page; } static int get_gate_page(struct mm_struct *mm, unsigned long address, unsigned int gup_flags, struct vm_area_struct **vma, struct page **page) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; pte_t entry; int ret = -EFAULT; /* user gate pages are read-only */ if (gup_flags & FOLL_WRITE) return -EFAULT; if (address > TASK_SIZE) pgd = pgd_offset_k(address); else pgd = pgd_offset_gate(mm, address); if (pgd_none(*pgd)) return -EFAULT; p4d = p4d_offset(pgd, address); if (p4d_none(*p4d)) return -EFAULT; pud = pud_offset(p4d, address); if (pud_none(*pud)) return -EFAULT; pmd = pmd_offset(pud, address); if (!pmd_present(*pmd)) return -EFAULT; pte = pte_offset_map(pmd, address); if (!pte) return -EFAULT; entry = ptep_get(pte); if (pte_none(entry)) goto unmap; *vma = get_gate_vma(mm); if (!page) goto out; *page = vm_normal_page(*vma, address, entry); if (!*page) { if ((gup_flags & FOLL_DUMP) || !is_zero_pfn(pte_pfn(entry))) goto unmap; *page = pte_page(entry); } ret = try_grab_folio(page_folio(*page), 1, gup_flags); if (unlikely(ret)) goto unmap; out: ret = 0; unmap: pte_unmap(pte); return ret; } /* * mmap_lock must be held on entry. If @flags has FOLL_UNLOCKABLE but not * FOLL_NOWAIT, the mmap_lock may be released. If it is, *@locked will be set * to 0 and -EBUSY returned. */ static int faultin_page(struct vm_area_struct *vma, unsigned long address, unsigned int *flags, bool unshare, int *locked) { unsigned int fault_flags = 0; vm_fault_t ret; if (*flags & FOLL_NOFAULT) return -EFAULT; if (*flags & FOLL_WRITE) fault_flags |= FAULT_FLAG_WRITE; if (*flags & FOLL_REMOTE) fault_flags |= FAULT_FLAG_REMOTE; if (*flags & FOLL_UNLOCKABLE) { fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; /* * FAULT_FLAG_INTERRUPTIBLE is opt-in. GUP callers must set * FOLL_INTERRUPTIBLE to enable FAULT_FLAG_INTERRUPTIBLE. * That's because some callers may not be prepared to * handle early exits caused by non-fatal signals. */ if (*flags & FOLL_INTERRUPTIBLE) fault_flags |= FAULT_FLAG_INTERRUPTIBLE; } if (*flags & FOLL_NOWAIT) fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT; if (*flags & FOLL_TRIED) { /* * Note: FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_TRIED * can co-exist */ fault_flags |= FAULT_FLAG_TRIED; } if (unshare) { fault_flags |= FAULT_FLAG_UNSHARE; /* FAULT_FLAG_WRITE and FAULT_FLAG_UNSHARE are incompatible */ VM_BUG_ON(fault_flags & FAULT_FLAG_WRITE); } ret = handle_mm_fault(vma, address, fault_flags, NULL); if (ret & VM_FAULT_COMPLETED) { /* * With FAULT_FLAG_RETRY_NOWAIT we'll never release the * mmap lock in the page fault handler. Sanity check this. */ WARN_ON_ONCE(fault_flags & FAULT_FLAG_RETRY_NOWAIT); *locked = 0; /* * We should do the same as VM_FAULT_RETRY, but let's not * return -EBUSY since that's not reflecting the reality of * what has happened - we've just fully completed a page * fault, with the mmap lock released. Use -EAGAIN to show * that we want to take the mmap lock _again_. */ return -EAGAIN; } if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, *flags); if (err) return err; BUG(); } if (ret & VM_FAULT_RETRY) { if (!(fault_flags & FAULT_FLAG_RETRY_NOWAIT)) *locked = 0; return -EBUSY; } return 0; } /* * Writing to file-backed mappings which require folio dirty tracking using GUP * is a fundamentally broken operation, as kernel write access to GUP mappings * do not adhere to the semantics expected by a file system. * * Consider the following scenario:- * * 1. A folio is written to via GUP which write-faults the memory, notifying * the file system and dirtying the folio. * 2. Later, writeback is triggered, resulting in the folio being cleaned and * the PTE being marked read-only. * 3. The GUP caller writes to the folio, as it is mapped read/write via the * direct mapping. * 4. The GUP caller, now done with the page, unpins it and sets it dirty * (though it does not have to). * * This results in both data being written to a folio without writenotify, and * the folio being dirtied unexpectedly (if the caller decides to do so). */ static bool writable_file_mapping_allowed(struct vm_area_struct *vma, unsigned long gup_flags) { /* * If we aren't pinning then no problematic write can occur. A long term * pin is the most egregious case so this is the case we disallow. */ if ((gup_flags & (FOLL_PIN | FOLL_LONGTERM)) != (FOLL_PIN | FOLL_LONGTERM)) return true; /* * If the VMA does not require dirty tracking then no problematic write * can occur either. */ return !vma_needs_dirty_tracking(vma); } static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) { vm_flags_t vm_flags = vma->vm_flags; int write = (gup_flags & FOLL_WRITE); int foreign = (gup_flags & FOLL_REMOTE); bool vma_anon = vma_is_anonymous(vma); if (vm_flags & (VM_IO | VM_PFNMAP)) return -EFAULT; if ((gup_flags & FOLL_ANON) && !vma_anon) return -EFAULT; if ((gup_flags & FOLL_LONGTERM) && vma_is_fsdax(vma)) return -EOPNOTSUPP; if (vma_is_secretmem(vma)) return -EFAULT; if (write) { if (!vma_anon && !writable_file_mapping_allowed(vma, gup_flags)) return -EFAULT; if (!(vm_flags & VM_WRITE) || (vm_flags & VM_SHADOW_STACK)) { if (!(gup_flags & FOLL_FORCE)) return -EFAULT; /* hugetlb does not support FOLL_FORCE|FOLL_WRITE. */ if (is_vm_hugetlb_page(vma)) return -EFAULT; /* * We used to let the write,force case do COW in a * VM_MAYWRITE VM_SHARED !VM_WRITE vma, so ptrace could * set a breakpoint in a read-only mapping of an * executable, without corrupting the file (yet only * when that file had been opened for writing!). * Anon pages in shared mappings are surprising: now * just reject it. */ if (!is_cow_mapping(vm_flags)) return -EFAULT; } } else if (!(vm_flags & VM_READ)) { if (!(gup_flags & FOLL_FORCE)) return -EFAULT; /* * Is there actually any vma we can reach here which does not * have VM_MAYREAD set? */ if (!(vm_flags & VM_MAYREAD)) return -EFAULT; } /* * gups are always data accesses, not instruction * fetches, so execute=false here */ if (!arch_vma_access_permitted(vma, write, false, foreign)) return -EFAULT; return 0; } /* * This is "vma_lookup()", but with a warning if we would have * historically expanded the stack in the GUP code. */ static struct vm_area_struct *gup_vma_lookup(struct mm_struct *mm, unsigned long addr) { #ifdef CONFIG_STACK_GROWSUP return vma_lookup(mm, addr); #else static volatile unsigned long next_warn; struct vm_area_struct *vma; unsigned long now, next; vma = find_vma(mm, addr); if (!vma || (addr >= vma->vm_start)) return vma; /* Only warn for half-way relevant accesses */ if (!(vma->vm_flags & VM_GROWSDOWN)) return NULL; if (vma->vm_start - addr > 65536) return NULL; /* Let's not warn more than once an hour.. */ now = jiffies; next = next_warn; if (next && time_before(now, next)) return NULL; next_warn = now + 60*60*HZ; /* Let people know things may have changed. */ pr_warn("GUP no longer grows the stack in %s (%d): %lx-%lx (%lx)\n", current->comm, task_pid_nr(current), vma->vm_start, vma->vm_end, addr); dump_stack(); return NULL; #endif } /** * __get_user_pages() - pin user pages in memory * @mm: mm_struct of target mm * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying pin behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. Or NULL, if caller * only intends to ensure the pages are faulted in. * @locked: whether we're still with the mmap_lock held * * Returns either number of pages pinned (which may be less than the * number requested), or an error. Details about the return value: * * -- If nr_pages is 0, returns 0. * -- If nr_pages is >0, but no pages were pinned, returns -errno. * -- If nr_pages is >0, and some pages were pinned, returns the number of * pages pinned. Again, this may be less than nr_pages. * -- 0 return value is possible when the fault would need to be retried. * * The caller is responsible for releasing returned @pages, via put_page(). * * Must be called with mmap_lock held. It may be released. See below. * * __get_user_pages walks a process's page tables and takes a reference to * each struct page that each user address corresponds to at a given * instant. That is, it takes the page that would be accessed if a user * thread accesses the given user virtual address at that instant. * * This does not guarantee that the page exists in the user mappings when * __get_user_pages returns, and there may even be a completely different * page there in some cases (eg. if mmapped pagecache has been invalidated * and subsequently re-faulted). However it does guarantee that the page * won't be freed completely. And mostly callers simply care that the page * contains data that was valid *at some point in time*. Typically, an IO * or similar operation cannot guarantee anything stronger anyway because * locks can't be held over the syscall boundary. * * If @gup_flags & FOLL_WRITE == 0, the page must not be written to. If * the page is written to, set_page_dirty (or set_page_dirty_lock, as * appropriate) must be called after the page is finished with, and * before put_page is called. * * If FOLL_UNLOCKABLE is set without FOLL_NOWAIT then the mmap_lock may * be released. If this happens *@locked will be set to 0 on return. * * A caller using such a combination of @gup_flags must therefore hold the * mmap_lock for reading only, and recognize when it's been released. Otherwise, * it must be held for either reading or writing and will not be released. * * In most cases, get_user_pages or get_user_pages_fast should be used * instead of __get_user_pages. __get_user_pages should be used only if * you need some special @gup_flags. */ static long __get_user_pages(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked) { long ret = 0, i = 0; struct vm_area_struct *vma = NULL; struct follow_page_context ctx = { NULL }; if (!nr_pages) return 0; start = untagged_addr_remote(mm, start); VM_BUG_ON(!!pages != !!(gup_flags & (FOLL_GET | FOLL_PIN))); do { struct page *page; unsigned int foll_flags = gup_flags; unsigned int page_increm; /* first iteration or cross vma bound */ if (!vma || start >= vma->vm_end) { /* * MADV_POPULATE_(READ|WRITE) wants to handle VMA * lookups+error reporting differently. */ if (gup_flags & FOLL_MADV_POPULATE) { vma = vma_lookup(mm, start); if (!vma) { ret = -ENOMEM; goto out; } if (check_vma_flags(vma, gup_flags)) { ret = -EINVAL; goto out; } goto retry; } vma = gup_vma_lookup(mm, start); if (!vma && in_gate_area(mm, start)) { ret = get_gate_page(mm, start & PAGE_MASK, gup_flags, &vma, pages ? &page : NULL); if (ret) goto out; ctx.page_mask = 0; goto next_page; } if (!vma) { ret = -EFAULT; goto out; } ret = check_vma_flags(vma, gup_flags); if (ret) goto out; } retry: /* * If we have a pending SIGKILL, don't keep faulting pages and * potentially allocating memory. */ if (fatal_signal_pending(current)) { ret = -EINTR; goto out; } cond_resched(); page = follow_page_mask(vma, start, foll_flags, &ctx); if (!page || PTR_ERR(page) == -EMLINK) { ret = faultin_page(vma, start, &foll_flags, PTR_ERR(page) == -EMLINK, locked); switch (ret) { case 0: goto retry; case -EBUSY: case -EAGAIN: ret = 0; fallthrough; case -EFAULT: case -ENOMEM: case -EHWPOISON: goto out; } BUG(); } else if (PTR_ERR(page) == -EEXIST) { /* * Proper page table entry exists, but no corresponding * struct page. If the caller expects **pages to be * filled in, bail out now, because that can't be done * for this page. */ if (pages) { ret = PTR_ERR(page); goto out; } } else if (IS_ERR(page)) { ret = PTR_ERR(page); goto out; } next_page: page_increm = 1 + (~(start >> PAGE_SHIFT) & ctx.page_mask); if (page_increm > nr_pages) page_increm = nr_pages; if (pages) { struct page *subpage; unsigned int j; /* * This must be a large folio (and doesn't need to * be the whole folio; it can be part of it), do * the refcount work for all the subpages too. * * NOTE: here the page may not be the head page * e.g. when start addr is not thp-size aligned. * try_grab_folio() should have taken care of tail * pages. */ if (page_increm > 1) { struct folio *folio = page_folio(page); /* * Since we already hold refcount on the * large folio, this should never fail. */ if (try_grab_folio(folio, page_increm - 1, foll_flags)) { /* * Release the 1st page ref if the * folio is problematic, fail hard. */ gup_put_folio(folio, 1, foll_flags); ret = -EFAULT; goto out; } } for (j = 0; j < page_increm; j++) { subpage = nth_page(page, j); pages[i + j] = subpage; flush_anon_page(vma, subpage, start + j * PAGE_SIZE); flush_dcache_page(subpage); } } i += page_increm; start += page_increm * PAGE_SIZE; nr_pages -= page_increm; } while (nr_pages); out: if (ctx.pgmap) put_dev_pagemap(ctx.pgmap); return i ? i : ret; } static bool vma_permits_fault(struct vm_area_struct *vma, unsigned int fault_flags) { bool write = !!(fault_flags & FAULT_FLAG_WRITE); bool foreign = !!(fault_flags & FAULT_FLAG_REMOTE); vm_flags_t vm_flags = write ? VM_WRITE : VM_READ; if (!(vm_flags & vma->vm_flags)) return false; /* * The architecture might have a hardware protection * mechanism other than read/write that can deny access. * * gup always represents data access, not instruction * fetches, so execute=false here: */ if (!arch_vma_access_permitted(vma, write, false, foreign)) return false; return true; } /** * fixup_user_fault() - manually resolve a user page fault * @mm: mm_struct of target mm * @address: user address * @fault_flags:flags to pass down to handle_mm_fault() * @unlocked: did we unlock the mmap_lock while retrying, maybe NULL if caller * does not allow retry. If NULL, the caller must guarantee * that fault_flags does not contain FAULT_FLAG_ALLOW_RETRY. * * This is meant to be called in the specific scenario where for locking reasons * we try to access user memory in atomic context (within a pagefault_disable() * section), this returns -EFAULT, and we want to resolve the user fault before * trying again. * * Typically this is meant to be used by the futex code. * * The main difference with get_user_pages() is that this function will * unconditionally call handle_mm_fault() which will in turn perform all the * necessary SW fixup of the dirty and young bits in the PTE, while * get_user_pages() only guarantees to update these in the struct page. * * This is important for some architectures where those bits also gate the * access permission to the page because they are maintained in software. On * such architectures, gup() will not be enough to make a subsequent access * succeed. * * This function will not return with an unlocked mmap_lock. So it has not the * same semantics wrt the @mm->mmap_lock as does filemap_fault(). */ int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked) { struct vm_area_struct *vma; vm_fault_t ret; address = untagged_addr_remote(mm, address); if (unlocked) fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; retry: vma = gup_vma_lookup(mm, address); if (!vma) return -EFAULT; if (!vma_permits_fault(vma, fault_flags)) return -EFAULT; if ((fault_flags & FAULT_FLAG_KILLABLE) && fatal_signal_pending(current)) return -EINTR; ret = handle_mm_fault(vma, address, fault_flags, NULL); if (ret & VM_FAULT_COMPLETED) { /* * NOTE: it's a pity that we need to retake the lock here * to pair with the unlock() in the callers. Ideally we * could tell the callers so they do not need to unlock. */ mmap_read_lock(mm); *unlocked = true; return 0; } if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, 0); if (err) return err; BUG(); } if (ret & VM_FAULT_RETRY) { mmap_read_lock(mm); *unlocked = true; fault_flags |= FAULT_FLAG_TRIED; goto retry; } return 0; } EXPORT_SYMBOL_GPL(fixup_user_fault); /* * GUP always responds to fatal signals. When FOLL_INTERRUPTIBLE is * specified, it'll also respond to generic signals. The caller of GUP * that has FOLL_INTERRUPTIBLE should take care of the GUP interruption. */ static bool gup_signal_pending(unsigned int flags) { if (fatal_signal_pending(current)) return true; if (!(flags & FOLL_INTERRUPTIBLE)) return false; return signal_pending(current); } /* * Locking: (*locked == 1) means that the mmap_lock has already been acquired by * the caller. This function may drop the mmap_lock. If it does so, then it will * set (*locked = 0). * * (*locked == 0) means that the caller expects this function to acquire and * drop the mmap_lock. Therefore, the value of *locked will still be zero when * the function returns, even though it may have changed temporarily during * function execution. * * Please note that this function, unlike __get_user_pages(), will not return 0 * for nr_pages > 0, unless FOLL_NOWAIT is used. */ static __always_inline long __get_user_pages_locked(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, int *locked, unsigned int flags) { long ret, pages_done; bool must_unlock = false; if (!nr_pages) return 0; /* * The internal caller expects GUP to manage the lock internally and the * lock must be released when this returns. */ if (!*locked) { if (mmap_read_lock_killable(mm)) return -EAGAIN; must_unlock = true; *locked = 1; } else mmap_assert_locked(mm); if (flags & FOLL_PIN) mm_set_has_pinned_flag(&mm->flags); /* * FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior * is to set FOLL_GET if the caller wants pages[] filled in (but has * carelessly failed to specify FOLL_GET), so keep doing that, but only * for FOLL_GET, not for the newer FOLL_PIN. * * FOLL_PIN always expects pages to be non-null, but no need to assert * that here, as any failures will be obvious enough. */ if (pages && !(flags & FOLL_PIN)) flags |= FOLL_GET; pages_done = 0; for (;;) { ret = __get_user_pages(mm, start, nr_pages, flags, pages, locked); if (!(flags & FOLL_UNLOCKABLE)) { /* VM_FAULT_RETRY couldn't trigger, bypass */ pages_done = ret; break; } /* VM_FAULT_RETRY or VM_FAULT_COMPLETED cannot return errors */ if (!*locked) { BUG_ON(ret < 0); BUG_ON(ret >= nr_pages); } if (ret > 0) { nr_pages -= ret; pages_done += ret; if (!nr_pages) break; } if (*locked) { /* * VM_FAULT_RETRY didn't trigger or it was a * FOLL_NOWAIT. */ if (!pages_done) pages_done = ret; break; } /* * VM_FAULT_RETRY triggered, so seek to the faulting offset. * For the prefault case (!pages) we only update counts. */ if (likely(pages)) pages += ret; start += ret << PAGE_SHIFT; /* The lock was temporarily dropped, so we must unlock later */ must_unlock = true; retry: /* * Repeat on the address that fired VM_FAULT_RETRY * with both FAULT_FLAG_ALLOW_RETRY and * FAULT_FLAG_TRIED. Note that GUP can be interrupted * by fatal signals of even common signals, depending on * the caller's request. So we need to check it before we * start trying again otherwise it can loop forever. */ if (gup_signal_pending(flags)) { if (!pages_done) pages_done = -EINTR; break; } ret = mmap_read_lock_killable(mm); if (ret) { BUG_ON(ret > 0); if (!pages_done) pages_done = ret; break; } *locked = 1; ret = __get_user_pages(mm, start, 1, flags | FOLL_TRIED, pages, locked); if (!*locked) { /* Continue to retry until we succeeded */ BUG_ON(ret != 0); goto retry; } if (ret != 1) { BUG_ON(ret > 1); if (!pages_done) pages_done = ret; break; } nr_pages--; pages_done++; if (!nr_pages) break; if (likely(pages)) pages++; start += PAGE_SIZE; } if (must_unlock && *locked) { /* * We either temporarily dropped the lock, or the caller * requested that we both acquire and drop the lock. Either way, * we must now unlock, and notify the caller of that state. */ mmap_read_unlock(mm); *locked = 0; } /* * Failing to pin anything implies something has gone wrong (except when * FOLL_NOWAIT is specified). */ if (WARN_ON_ONCE(pages_done == 0 && !(flags & FOLL_NOWAIT))) return -EFAULT; return pages_done; } /** * populate_vma_page_range() - populate a range of pages in the vma. * @vma: target vma * @start: start address * @end: end address * @locked: whether the mmap_lock is still held * * This takes care of mlocking the pages too if VM_LOCKED is set. * * Return either number of pages pinned in the vma, or a negative error * code on error. * * vma->vm_mm->mmap_lock must be held. * * If @locked is NULL, it may be held for read or write and will * be unperturbed. * * If @locked is non-NULL, it must held for read only and may be * released. If it's released, *@locked will be set to 0. */ long populate_vma_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, int *locked) { struct mm_struct *mm = vma->vm_mm; unsigned long nr_pages = (end - start) / PAGE_SIZE; int local_locked = 1; int gup_flags; long ret; VM_BUG_ON(!PAGE_ALIGNED(start)); VM_BUG_ON(!PAGE_ALIGNED(end)); VM_BUG_ON_VMA(start < vma->vm_start, vma); VM_BUG_ON_VMA(end > vma->vm_end, vma); mmap_assert_locked(mm); /* * Rightly or wrongly, the VM_LOCKONFAULT case has never used * faultin_page() to break COW, so it has no work to do here. */ if (vma->vm_flags & VM_LOCKONFAULT) return nr_pages; /* ... similarly, we've never faulted in PROT_NONE pages */ if (!vma_is_accessible(vma)) return -EFAULT; gup_flags = FOLL_TOUCH; /* * We want to touch writable mappings with a write fault in order * to break COW, except for shared mappings because these don't COW * and we would not want to dirty them for nothing. * * Otherwise, do a read fault, and use FOLL_FORCE in case it's not * readable (ie write-only or executable). */ if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE) gup_flags |= FOLL_WRITE; else gup_flags |= FOLL_FORCE; if (locked) gup_flags |= FOLL_UNLOCKABLE; /* * We made sure addr is within a VMA, so the following will * not result in a stack expansion that recurses back here. */ ret = __get_user_pages(mm, start, nr_pages, gup_flags, NULL, locked ? locked : &local_locked); lru_add_drain(); return ret; } /* * faultin_page_range() - populate (prefault) page tables inside the * given range readable/writable * * This takes care of mlocking the pages, too, if VM_LOCKED is set. * * @mm: the mm to populate page tables in * @start: start address * @end: end address * @write: whether to prefault readable or writable * @locked: whether the mmap_lock is still held * * Returns either number of processed pages in the MM, or a negative error * code on error (see __get_user_pages()). Note that this function reports * errors related to VMAs, such as incompatible mappings, as expected by * MADV_POPULATE_(READ|WRITE). * * The range must be page-aligned. * * mm->mmap_lock must be held. If it's released, *@locked will be set to 0. */ long faultin_page_range(struct mm_struct *mm, unsigned long start, unsigned long end, bool write, int *locked) { unsigned long nr_pages = (end - start) / PAGE_SIZE; int gup_flags; long ret; VM_BUG_ON(!PAGE_ALIGNED(start)); VM_BUG_ON(!PAGE_ALIGNED(end)); mmap_assert_locked(mm); /* * FOLL_TOUCH: Mark page accessed and thereby young; will also mark * the page dirty with FOLL_WRITE -- which doesn't make a * difference with !FOLL_FORCE, because the page is writable * in the page table. * FOLL_HWPOISON: Return -EHWPOISON instead of -EFAULT when we hit * a poisoned page. * !FOLL_FORCE: Require proper access permissions. */ gup_flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_UNLOCKABLE | FOLL_MADV_POPULATE; if (write) gup_flags |= FOLL_WRITE; ret = __get_user_pages_locked(mm, start, nr_pages, NULL, locked, gup_flags); lru_add_drain(); return ret; } /* * __mm_populate - populate and/or mlock pages within a range of address space. * * This is used to implement mlock() and the MAP_POPULATE / MAP_LOCKED mmap * flags. VMAs must be already marked with the desired vm_flags, and * mmap_lock must not be held. */ int __mm_populate(unsigned long start, unsigned long len, int ignore_errors) { struct mm_struct *mm = current->mm; unsigned long end, nstart, nend; struct vm_area_struct *vma = NULL; int locked = 0; long ret = 0; end = start + len; for (nstart = start; nstart < end; nstart = nend) { /* * We want to fault in pages for [nstart; end) address range. * Find first corresponding VMA. */ if (!locked) { locked = 1; mmap_read_lock(mm); vma = find_vma_intersection(mm, nstart, end); } else if (nstart >= vma->vm_end) vma = find_vma_intersection(mm, vma->vm_end, end); if (!vma) break; /* * Set [nstart; nend) to intersection of desired address * range with the first VMA. Also, skip undesirable VMA types. */ nend = min(end, vma->vm_end); if (vma->vm_flags & (VM_IO | VM_PFNMAP)) continue; if (nstart < vma->vm_start) nstart = vma->vm_start; /* * Now fault in a range of pages. populate_vma_page_range() * double checks the vma flags, so that it won't mlock pages * if the vma was already munlocked. */ ret = populate_vma_page_range(vma, nstart, nend, &locked); if (ret < 0) { if (ignore_errors) { ret = 0; continue; /* continue at next VMA */ } break; } nend = nstart + ret * PAGE_SIZE; ret = 0; } if (locked) mmap_read_unlock(mm); return ret; /* 0 or negative error code */ } #else /* CONFIG_MMU */ static long __get_user_pages_locked(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, int *locked, unsigned int foll_flags) { struct vm_area_struct *vma; bool must_unlock = false; unsigned long vm_flags; long i; if (!nr_pages) return 0; /* * The internal caller expects GUP to manage the lock internally and the * lock must be released when this returns. */ if (!*locked) { if (mmap_read_lock_killable(mm)) return -EAGAIN; must_unlock = true; *locked = 1; } /* calculate required read or write permissions. * If FOLL_FORCE is set, we only require the "MAY" flags. */ vm_flags = (foll_flags & FOLL_WRITE) ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD); vm_flags &= (foll_flags & FOLL_FORCE) ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE); for (i = 0; i < nr_pages; i++) { vma = find_vma(mm, start); if (!vma) break; /* protect what we can, including chardevs */ if ((vma->vm_flags & (VM_IO | VM_PFNMAP)) || !(vm_flags & vma->vm_flags)) break; if (pages) { pages[i] = virt_to_page((void *)start); if (pages[i]) get_page(pages[i]); } start = (start + PAGE_SIZE) & PAGE_MASK; } if (must_unlock && *locked) { mmap_read_unlock(mm); *locked = 0; } return i ? : -EFAULT; } #endif /* !CONFIG_MMU */ /** * fault_in_writeable - fault in userspace address range for writing * @uaddr: start of address range * @size: size of address range * * Returns the number of bytes not faulted in (like copy_to_user() and * copy_from_user()). */ size_t fault_in_writeable(char __user *uaddr, size_t size) { char __user *start = uaddr, *end; if (unlikely(size == 0)) return 0; if (!user_write_access_begin(uaddr, size)) return size; if (!PAGE_ALIGNED(uaddr)) { unsafe_put_user(0, uaddr, out); uaddr = (char __user *)PAGE_ALIGN((unsigned long)uaddr); } end = (char __user *)PAGE_ALIGN((unsigned long)start + size); if (unlikely(end < start)) end = NULL; while (uaddr != end) { unsafe_put_user(0, uaddr, out); uaddr += PAGE_SIZE; } out: user_write_access_end(); if (size > uaddr - start) return size - (uaddr - start); return 0; } EXPORT_SYMBOL(fault_in_writeable); /** * fault_in_subpage_writeable - fault in an address range for writing * @uaddr: start of address range * @size: size of address range * * Fault in a user address range for writing while checking for permissions at * sub-page granularity (e.g. arm64 MTE). This function should be used when * the caller cannot guarantee forward progress of a copy_to_user() loop. * * Returns the number of bytes not faulted in (like copy_to_user() and * copy_from_user()). */ size_t fault_in_subpage_writeable(char __user *uaddr, size_t size) { size_t faulted_in; /* * Attempt faulting in at page granularity first for page table * permission checking. The arch-specific probe_subpage_writeable() * functions may not check for this. */ faulted_in = size - fault_in_writeable(uaddr, size); if (faulted_in) faulted_in -= probe_subpage_writeable(uaddr, faulted_in); return size - faulted_in; } EXPORT_SYMBOL(fault_in_subpage_writeable); /* * fault_in_safe_writeable - fault in an address range for writing * @uaddr: start of address range * @size: length of address range * * Faults in an address range for writing. This is primarily useful when we * already know that some or all of the pages in the address range aren't in * memory. * * Unlike fault_in_writeable(), this function is non-destructive. * * Note that we don't pin or otherwise hold the pages referenced that we fault * in. There's no guarantee that they'll stay in memory for any duration of * time. * * Returns the number of bytes not faulted in, like copy_to_user() and * copy_from_user(). */ size_t fault_in_safe_writeable(const char __user *uaddr, size_t size) { unsigned long start = (unsigned long)uaddr, end; struct mm_struct *mm = current->mm; bool unlocked = false; if (unlikely(size == 0)) return 0; end = PAGE_ALIGN(start + size); if (end < start) end = 0; mmap_read_lock(mm); do { if (fixup_user_fault(mm, start, FAULT_FLAG_WRITE, &unlocked)) break; start = (start + PAGE_SIZE) & PAGE_MASK; } while (start != end); mmap_read_unlock(mm); if (size > (unsigned long)uaddr - start) return size - ((unsigned long)uaddr - start); return 0; } EXPORT_SYMBOL(fault_in_safe_writeable); /** * fault_in_readable - fault in userspace address range for reading * @uaddr: start of user address range * @size: size of user address range * * Returns the number of bytes not faulted in (like copy_to_user() and * copy_from_user()). */ size_t fault_in_readable(const char __user *uaddr, size_t size) { const char __user *start = uaddr, *end; volatile char c; if (unlikely(size == 0)) return 0; if (!user_read_access_begin(uaddr, size)) return size; if (!PAGE_ALIGNED(uaddr)) { unsafe_get_user(c, uaddr, out); uaddr = (const char __user *)PAGE_ALIGN((unsigned long)uaddr); } end = (const char __user *)PAGE_ALIGN((unsigned long)start + size); if (unlikely(end < start)) end = NULL; while (uaddr != end) { unsafe_get_user(c, uaddr, out); uaddr += PAGE_SIZE; } out: user_read_access_end(); (void)c; if (size > uaddr - start) return size - (uaddr - start); return 0; } EXPORT_SYMBOL(fault_in_readable); /** * get_dump_page() - pin user page in memory while writing it to core dump * @addr: user address * * Returns struct page pointer of user page pinned for dump, * to be freed afterwards by put_page(). * * Returns NULL on any kind of failure - a hole must then be inserted into * the corefile, to preserve alignment with its headers; and also returns * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found - * allowing a hole to be left in the corefile to save disk space. * * Called without mmap_lock (takes and releases the mmap_lock by itself). */ #ifdef CONFIG_ELF_CORE struct page *get_dump_page(unsigned long addr) { struct page *page; int locked = 0; int ret; ret = __get_user_pages_locked(current->mm, addr, 1, &page, &locked, FOLL_FORCE | FOLL_DUMP | FOLL_GET); return (ret == 1) ? page : NULL; } #endif /* CONFIG_ELF_CORE */ #ifdef CONFIG_MIGRATION /* * Returns the number of collected folios. Return value is always >= 0. */ static unsigned long collect_longterm_unpinnable_folios( struct list_head *movable_folio_list, unsigned long nr_folios, struct folio **folios) { unsigned long i, collected = 0; struct folio *prev_folio = NULL; bool drain_allow = true; for (i = 0; i < nr_folios; i++) { struct folio *folio = folios[i]; if (folio == prev_folio) continue; prev_folio = folio; if (folio_is_longterm_pinnable(folio)) continue; collected++; if (folio_is_device_coherent(folio)) continue; if (folio_test_hugetlb(folio)) { isolate_hugetlb(folio, movable_folio_list); continue; } if (!folio_test_lru(folio) && drain_allow) { lru_add_drain_all(); drain_allow = false; } if (!folio_isolate_lru(folio)) continue; list_add_tail(&folio->lru, movable_folio_list); node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); } return collected; } /* * Unpins all folios and migrates device coherent folios and movable_folio_list. * Returns -EAGAIN if all folios were successfully migrated or -errno for * failure (or partial success). */ static int migrate_longterm_unpinnable_folios( struct list_head *movable_folio_list, unsigned long nr_folios, struct folio **folios) { int ret; unsigned long i; for (i = 0; i < nr_folios; i++) { struct folio *folio = folios[i]; if (folio_is_device_coherent(folio)) { /* * Migration will fail if the folio is pinned, so * convert the pin on the source folio to a normal * reference. */ folios[i] = NULL; folio_get(folio); gup_put_folio(folio, 1, FOLL_PIN); if (migrate_device_coherent_page(&folio->page)) { ret = -EBUSY; goto err; } continue; } /* * We can't migrate folios with unexpected references, so drop * the reference obtained by __get_user_pages_locked(). * Migrating folios have been added to movable_folio_list after * calling folio_isolate_lru() which takes a reference so the * folio won't be freed if it's migrating. */ unpin_folio(folios[i]); folios[i] = NULL; } if (!list_empty(movable_folio_list)) { struct migration_target_control mtc = { .nid = NUMA_NO_NODE, .gfp_mask = GFP_USER | __GFP_NOWARN, .reason = MR_LONGTERM_PIN, }; if (migrate_pages(movable_folio_list, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, MR_LONGTERM_PIN, NULL)) { ret = -ENOMEM; goto err; } } putback_movable_pages(movable_folio_list); return -EAGAIN; err: unpin_folios(folios, nr_folios); putback_movable_pages(movable_folio_list); return ret; } /* * Check whether all folios are *allowed* to be pinned indefinitely (longterm). * Rather confusingly, all folios in the range are required to be pinned via * FOLL_PIN, before calling this routine. * * If any folios in the range are not allowed to be pinned, then this routine * will migrate those folios away, unpin all the folios in the range and return * -EAGAIN. The caller should re-pin the entire range with FOLL_PIN and then * call this routine again. * * If an error other than -EAGAIN occurs, this indicates a migration failure. * The caller should give up, and propagate the error back up the call stack. * * If everything is OK and all folios in the range are allowed to be pinned, * then this routine leaves all folios pinned and returns zero for success. */ static long check_and_migrate_movable_folios(unsigned long nr_folios, struct folio **folios) { unsigned long collected; LIST_HEAD(movable_folio_list); collected = collect_longterm_unpinnable_folios(&movable_folio_list, nr_folios, folios); if (!collected) return 0; return migrate_longterm_unpinnable_folios(&movable_folio_list, nr_folios, folios); } /* * This routine just converts all the pages in the @pages array to folios and * calls check_and_migrate_movable_folios() to do the heavy lifting. * * Please see the check_and_migrate_movable_folios() documentation for details. */ static long check_and_migrate_movable_pages(unsigned long nr_pages, struct page **pages) { struct folio **folios; long i, ret; folios = kmalloc_array(nr_pages, sizeof(*folios), GFP_KERNEL); if (!folios) return -ENOMEM; for (i = 0; i < nr_pages; i++) folios[i] = page_folio(pages[i]); ret = check_and_migrate_movable_folios(nr_pages, folios); kfree(folios); return ret; } #else static long check_and_migrate_movable_pages(unsigned long nr_pages, struct page **pages) { return 0; } static long check_and_migrate_movable_folios(unsigned long nr_folios, struct folio **folios) { return 0; } #endif /* CONFIG_MIGRATION */ /* * __gup_longterm_locked() is a wrapper for __get_user_pages_locked which * allows us to process the FOLL_LONGTERM flag. */ static long __gup_longterm_locked(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, int *locked, unsigned int gup_flags) { unsigned int flags; long rc, nr_pinned_pages; if (!(gup_flags & FOLL_LONGTERM)) return __get_user_pages_locked(mm, start, nr_pages, pages, locked, gup_flags); flags = memalloc_pin_save(); do { nr_pinned_pages = __get_user_pages_locked(mm, start, nr_pages, pages, locked, gup_flags); if (nr_pinned_pages <= 0) { rc = nr_pinned_pages; break; } /* FOLL_LONGTERM implies FOLL_PIN */ rc = check_and_migrate_movable_pages(nr_pinned_pages, pages); } while (rc == -EAGAIN); memalloc_pin_restore(flags); return rc ? rc : nr_pinned_pages; } /* * Check that the given flags are valid for the exported gup/pup interface, and * update them with the required flags that the caller must have set. */ static bool is_valid_gup_args(struct page **pages, int *locked, unsigned int *gup_flags_p, unsigned int to_set) { unsigned int gup_flags = *gup_flags_p; /* * These flags not allowed to be specified externally to the gup * interfaces: * - FOLL_TOUCH/FOLL_PIN/FOLL_TRIED/FOLL_FAST_ONLY are internal only * - FOLL_REMOTE is internal only and used on follow_page() * - FOLL_UNLOCKABLE is internal only and used if locked is !NULL */ if (WARN_ON_ONCE(gup_flags & INTERNAL_GUP_FLAGS)) return false; gup_flags |= to_set; if (locked) { /* At the external interface locked must be set */ if (WARN_ON_ONCE(*locked != 1)) return false; gup_flags |= FOLL_UNLOCKABLE; } /* FOLL_GET and FOLL_PIN are mutually exclusive. */ if (WARN_ON_ONCE((gup_flags & (FOLL_PIN | FOLL_GET)) == (FOLL_PIN | FOLL_GET))) return false; /* LONGTERM can only be specified when pinning */ if (WARN_ON_ONCE(!(gup_flags & FOLL_PIN) && (gup_flags & FOLL_LONGTERM))) return false; /* Pages input must be given if using GET/PIN */ if (WARN_ON_ONCE((gup_flags & (FOLL_GET | FOLL_PIN)) && !pages)) return false; /* We want to allow the pgmap to be hot-unplugged at all times */ if (WARN_ON_ONCE((gup_flags & FOLL_LONGTERM) && (gup_flags & FOLL_PCI_P2PDMA))) return false; *gup_flags_p = gup_flags; return true; } #ifdef CONFIG_MMU /** * get_user_pages_remote() - pin user pages in memory * @mm: mm_struct of target mm * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying lookup behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. Or NULL, if caller * only intends to ensure the pages are faulted in. * @locked: pointer to lock flag indicating whether lock is held and * subsequently whether VM_FAULT_RETRY functionality can be * utilised. Lock must initially be held. * * Returns either number of pages pinned (which may be less than the * number requested), or an error. Details about the return value: * * -- If nr_pages is 0, returns 0. * -- If nr_pages is >0, but no pages were pinned, returns -errno. * -- If nr_pages is >0, and some pages were pinned, returns the number of * pages pinned. Again, this may be less than nr_pages. * * The caller is responsible for releasing returned @pages, via put_page(). * * Must be called with mmap_lock held for read or write. * * get_user_pages_remote walks a process's page tables and takes a reference * to each struct page that each user address corresponds to at a given * instant. That is, it takes the page that would be accessed if a user * thread accesses the given user virtual address at that instant. * * This does not guarantee that the page exists in the user mappings when * get_user_pages_remote returns, and there may even be a completely different * page there in some cases (eg. if mmapped pagecache has been invalidated * and subsequently re-faulted). However it does guarantee that the page * won't be freed completely. And mostly callers simply care that the page * contains data that was valid *at some point in time*. Typically, an IO * or similar operation cannot guarantee anything stronger anyway because * locks can't be held over the syscall boundary. * * If gup_flags & FOLL_WRITE == 0, the page must not be written to. If the page * is written to, set_page_dirty (or set_page_dirty_lock, as appropriate) must * be called after the page is finished with, and before put_page is called. * * get_user_pages_remote is typically used for fewer-copy IO operations, * to get a handle on the memory by some means other than accesses * via the user virtual addresses. The pages may be submitted for * DMA to devices or accessed via their kernel linear mapping (via the * kmap APIs). Care should be taken to use the correct cache flushing APIs. * * See also get_user_pages_fast, for performance critical applications. * * get_user_pages_remote should be phased out in favor of * get_user_pages_locked|unlocked or get_user_pages_fast. Nothing * should use get_user_pages_remote because it cannot pass * FAULT_FLAG_ALLOW_RETRY to handle_mm_fault. */ long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked) { int local_locked = 1; if (!is_valid_gup_args(pages, locked, &gup_flags, FOLL_TOUCH | FOLL_REMOTE)) return -EINVAL; return __get_user_pages_locked(mm, start, nr_pages, pages, locked ? locked : &local_locked, gup_flags); } EXPORT_SYMBOL(get_user_pages_remote); #else /* CONFIG_MMU */ long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked) { return 0; } #endif /* !CONFIG_MMU */ /** * get_user_pages() - pin user pages in memory * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying lookup behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. Or NULL, if caller * only intends to ensure the pages are faulted in. * * This is the same as get_user_pages_remote(), just with a less-flexible * calling convention where we assume that the mm being operated on belongs to * the current task, and doesn't allow passing of a locked parameter. We also * obviously don't pass FOLL_REMOTE in here. */ long get_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages) { int locked = 1; if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_TOUCH)) return -EINVAL; return __get_user_pages_locked(current->mm, start, nr_pages, pages, &locked, gup_flags); } EXPORT_SYMBOL(get_user_pages); /* * get_user_pages_unlocked() is suitable to replace the form: * * mmap_read_lock(mm); * get_user_pages(mm, ..., pages, NULL); * mmap_read_unlock(mm); * * with: * * get_user_pages_unlocked(mm, ..., pages); * * It is functionally equivalent to get_user_pages_fast so * get_user_pages_fast should be used instead if specific gup_flags * (e.g. FOLL_FORCE) are not required. */ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags) { int locked = 0; if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_TOUCH | FOLL_UNLOCKABLE)) return -EINVAL; return __get_user_pages_locked(current->mm, start, nr_pages, pages, &locked, gup_flags); } EXPORT_SYMBOL(get_user_pages_unlocked); /* * GUP-fast * * get_user_pages_fast attempts to pin user pages by walking the page * tables directly and avoids taking locks. Thus the walker needs to be * protected from page table pages being freed from under it, and should * block any THP splits. * * One way to achieve this is to have the walker disable interrupts, and * rely on IPIs from the TLB flushing code blocking before the page table * pages are freed. This is unsuitable for architectures that do not need * to broadcast an IPI when invalidating TLBs. * * Another way to achieve this is to batch up page table containing pages * belonging to more than one mm_user, then rcu_sched a callback to free those * pages. Disabling interrupts will allow the gup_fast() walker to both block * the rcu_sched callback, and an IPI that we broadcast for splitting THPs * (which is a relatively rare event). The code below adopts this strategy. * * Before activating this code, please be aware that the following assumptions * are currently made: * * *) Either MMU_GATHER_RCU_TABLE_FREE is enabled, and tlb_remove_table() is used to * free pages containing page tables or TLB flushing requires IPI broadcast. * * *) ptes can be read atomically by the architecture. * * *) access_ok is sufficient to validate userspace address ranges. * * The last two assumptions can be relaxed by the addition of helper functions. * * This code is based heavily on the PowerPC implementation by Nick Piggin. */ #ifdef CONFIG_HAVE_GUP_FAST /* * Used in the GUP-fast path to determine whether GUP is permitted to work on * a specific folio. * * This call assumes the caller has pinned the folio, that the lowest page table * level still points to this folio, and that interrupts have been disabled. * * GUP-fast must reject all secretmem folios. * * Writing to pinned file-backed dirty tracked folios is inherently problematic * (see comment describing the writable_file_mapping_allowed() function). We * therefore try to avoid the most egregious case of a long-term mapping doing * so. * * This function cannot be as thorough as that one as the VMA is not available * in the fast path, so instead we whitelist known good cases and if in doubt, * fall back to the slow path. */ static bool gup_fast_folio_allowed(struct folio *folio, unsigned int flags) { bool reject_file_backed = false; struct address_space *mapping; bool check_secretmem = false; unsigned long mapping_flags; /* * If we aren't pinning then no problematic write can occur. A long term * pin is the most egregious case so this is the one we disallow. */ if ((flags & (FOLL_PIN | FOLL_LONGTERM | FOLL_WRITE)) == (FOLL_PIN | FOLL_LONGTERM | FOLL_WRITE)) reject_file_backed = true; /* We hold a folio reference, so we can safely access folio fields. */ /* secretmem folios are always order-0 folios. */ if (IS_ENABLED(CONFIG_SECRETMEM) && !folio_test_large(folio)) check_secretmem = true; if (!reject_file_backed && !check_secretmem) return true; if (WARN_ON_ONCE(folio_test_slab(folio))) return false; /* hugetlb neither requires dirty-tracking nor can be secretmem. */ if (folio_test_hugetlb(folio)) return true; /* * GUP-fast disables IRQs. When IRQS are disabled, RCU grace periods * cannot proceed, which means no actions performed under RCU can * proceed either. * * inodes and thus their mappings are freed under RCU, which means the * mapping cannot be freed beneath us and thus we can safely dereference * it. */ lockdep_assert_irqs_disabled(); /* * However, there may be operations which _alter_ the mapping, so ensure * we read it once and only once. */ mapping = READ_ONCE(folio->mapping); /* * The mapping may have been truncated, in any case we cannot determine * if this mapping is safe - fall back to slow path to determine how to * proceed. */ if (!mapping) return false; /* Anonymous folios pose no problem. */ mapping_flags = (unsigned long)mapping & PAGE_MAPPING_FLAGS; if (mapping_flags) return mapping_flags & PAGE_MAPPING_ANON; /* * At this point, we know the mapping is non-null and points to an * address_space object. */ if (check_secretmem && secretmem_mapping(mapping)) return false; /* The only remaining allowed file system is shmem. */ return !reject_file_backed || shmem_mapping(mapping); } static void __maybe_unused gup_fast_undo_dev_pagemap(int *nr, int nr_start, unsigned int flags, struct page **pages) { while ((*nr) - nr_start) { struct folio *folio = page_folio(pages[--(*nr)]); folio_clear_referenced(folio); gup_put_folio(folio, 1, flags); } } #ifdef CONFIG_ARCH_HAS_PTE_SPECIAL /* * GUP-fast relies on pte change detection to avoid concurrent pgtable * operations. * * To pin the page, GUP-fast needs to do below in order: * (1) pin the page (by prefetching pte), then (2) check pte not changed. * * For the rest of pgtable operations where pgtable updates can be racy * with GUP-fast, we need to do (1) clear pte, then (2) check whether page * is pinned. * * Above will work for all pte-level operations, including THP split. * * For THP collapse, it's a bit more complicated because GUP-fast may be * walking a pgtable page that is being freed (pte is still valid but pmd * can be cleared already). To avoid race in such condition, we need to * also check pmd here to make sure pmd doesn't change (corresponds to * pmdp_collapse_flush() in the THP collapse code path). */ static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { struct dev_pagemap *pgmap = NULL; int nr_start = *nr, ret = 0; pte_t *ptep, *ptem; ptem = ptep = pte_offset_map(&pmd, addr); if (!ptep) return 0; do { pte_t pte = ptep_get_lockless(ptep); struct page *page; struct folio *folio; /* * Always fallback to ordinary GUP on PROT_NONE-mapped pages: * pte_access_permitted() better should reject these pages * either way: otherwise, GUP-fast might succeed in * cases where ordinary GUP would fail due to VMA access * permissions. */ if (pte_protnone(pte)) goto pte_unmap; if (!pte_access_permitted(pte, flags & FOLL_WRITE)) goto pte_unmap; if (pte_devmap(pte)) { if (unlikely(flags & FOLL_LONGTERM)) goto pte_unmap; pgmap = get_dev_pagemap(pte_pfn(pte), pgmap); if (unlikely(!pgmap)) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); goto pte_unmap; } } else if (pte_special(pte)) goto pte_unmap; VM_BUG_ON(!pfn_valid(pte_pfn(pte))); page = pte_page(pte); folio = try_grab_folio_fast(page, 1, flags); if (!folio) goto pte_unmap; if (unlikely(pmd_val(pmd) != pmd_val(*pmdp)) || unlikely(pte_val(pte) != pte_val(ptep_get(ptep)))) { gup_put_folio(folio, 1, flags); goto pte_unmap; } if (!gup_fast_folio_allowed(folio, flags)) { gup_put_folio(folio, 1, flags); goto pte_unmap; } if (!pte_write(pte) && gup_must_unshare(NULL, flags, page)) { gup_put_folio(folio, 1, flags); goto pte_unmap; } /* * We need to make the page accessible if and only if we are * going to access its content (the FOLL_PIN case). Please * see Documentation/core-api/pin_user_pages.rst for * details. */ if (flags & FOLL_PIN) { ret = arch_make_page_accessible(page); if (ret) { gup_put_folio(folio, 1, flags); goto pte_unmap; } } folio_set_referenced(folio); pages[*nr] = page; (*nr)++; } while (ptep++, addr += PAGE_SIZE, addr != end); ret = 1; pte_unmap: if (pgmap) put_dev_pagemap(pgmap); pte_unmap(ptem); return ret; } #else /* * If we can't determine whether or not a pte is special, then fail immediately * for ptes. Note, we can still pin HugeTLB and THP as these are guaranteed not * to be special. * * For a futex to be placed on a THP tail page, get_futex_key requires a * get_user_pages_fast_only implementation that can pin pages. Thus it's still * useful to have gup_fast_pmd_leaf even if we can't operate on ptes. */ static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { return 0; } #endif /* CONFIG_ARCH_HAS_PTE_SPECIAL */ #if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && defined(CONFIG_TRANSPARENT_HUGEPAGE) static int gup_fast_devmap_leaf(unsigned long pfn, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { int nr_start = *nr; struct dev_pagemap *pgmap = NULL; do { struct folio *folio; struct page *page = pfn_to_page(pfn); pgmap = get_dev_pagemap(pfn, pgmap); if (unlikely(!pgmap)) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); break; } if (!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page)) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); break; } folio = try_grab_folio_fast(page, 1, flags); if (!folio) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); break; } folio_set_referenced(folio); pages[*nr] = page; (*nr)++; pfn++; } while (addr += PAGE_SIZE, addr != end); put_dev_pagemap(pgmap); return addr == end; } static int gup_fast_devmap_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long fault_pfn; int nr_start = *nr; fault_pfn = pmd_pfn(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); if (!gup_fast_devmap_leaf(fault_pfn, addr, end, flags, pages, nr)) return 0; if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); return 0; } return 1; } static int gup_fast_devmap_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long fault_pfn; int nr_start = *nr; fault_pfn = pud_pfn(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); if (!gup_fast_devmap_leaf(fault_pfn, addr, end, flags, pages, nr)) return 0; if (unlikely(pud_val(orig) != pud_val(*pudp))) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); return 0; } return 1; } #else static int gup_fast_devmap_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { BUILD_BUG(); return 0; } static int gup_fast_devmap_pud_leaf(pud_t pud, pud_t *pudp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { BUILD_BUG(); return 0; } #endif static int gup_fast_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { struct page *page; struct folio *folio; int refs; if (!pmd_access_permitted(orig, flags & FOLL_WRITE)) return 0; if (pmd_devmap(orig)) { if (unlikely(flags & FOLL_LONGTERM)) return 0; return gup_fast_devmap_pmd_leaf(orig, pmdp, addr, end, flags, pages, nr); } page = pmd_page(orig); refs = record_subpages(page, PMD_SIZE, addr, end, pages + *nr); folio = try_grab_folio_fast(page, refs, flags); if (!folio) return 0; if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) { gup_put_folio(folio, refs, flags); return 0; } if (!gup_fast_folio_allowed(folio, flags)) { gup_put_folio(folio, refs, flags); return 0; } if (!pmd_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) { gup_put_folio(folio, refs, flags); return 0; } *nr += refs; folio_set_referenced(folio); return 1; } static int gup_fast_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { struct page *page; struct folio *folio; int refs; if (!pud_access_permitted(orig, flags & FOLL_WRITE)) return 0; if (pud_devmap(orig)) { if (unlikely(flags & FOLL_LONGTERM)) return 0; return gup_fast_devmap_pud_leaf(orig, pudp, addr, end, flags, pages, nr); } page = pud_page(orig); refs = record_subpages(page, PUD_SIZE, addr, end, pages + *nr); folio = try_grab_folio_fast(page, refs, flags); if (!folio) return 0; if (unlikely(pud_val(orig) != pud_val(*pudp))) { gup_put_folio(folio, refs, flags); return 0; } if (!gup_fast_folio_allowed(folio, flags)) { gup_put_folio(folio, refs, flags); return 0; } if (!pud_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) { gup_put_folio(folio, refs, flags); return 0; } *nr += refs; folio_set_referenced(folio); return 1; } static int gup_fast_pgd_leaf(pgd_t orig, pgd_t *pgdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { int refs; struct page *page; struct folio *folio; if (!pgd_access_permitted(orig, flags & FOLL_WRITE)) return 0; BUILD_BUG_ON(pgd_devmap(orig)); page = pgd_page(orig); refs = record_subpages(page, PGDIR_SIZE, addr, end, pages + *nr); folio = try_grab_folio_fast(page, refs, flags); if (!folio) return 0; if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) { gup_put_folio(folio, refs, flags); return 0; } if (!pgd_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) { gup_put_folio(folio, refs, flags); return 0; } if (!gup_fast_folio_allowed(folio, flags)) { gup_put_folio(folio, refs, flags); return 0; } *nr += refs; folio_set_referenced(folio); return 1; } static int gup_fast_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; pmd_t *pmdp; pmdp = pmd_offset_lockless(pudp, pud, addr); do { pmd_t pmd = pmdp_get_lockless(pmdp); next = pmd_addr_end(addr, end); if (!pmd_present(pmd)) return 0; if (unlikely(pmd_leaf(pmd))) { /* See gup_fast_pte_range() */ if (pmd_protnone(pmd)) return 0; if (!gup_fast_pmd_leaf(pmd, pmdp, addr, next, flags, pages, nr)) return 0; } else if (!gup_fast_pte_range(pmd, pmdp, addr, next, flags, pages, nr)) return 0; } while (pmdp++, addr = next, addr != end); return 1; } static int gup_fast_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; pud_t *pudp; pudp = pud_offset_lockless(p4dp, p4d, addr); do { pud_t pud = READ_ONCE(*pudp); next = pud_addr_end(addr, end); if (unlikely(!pud_present(pud))) return 0; if (unlikely(pud_leaf(pud))) { if (!gup_fast_pud_leaf(pud, pudp, addr, next, flags, pages, nr)) return 0; } else if (!gup_fast_pmd_range(pudp, pud, addr, next, flags, pages, nr)) return 0; } while (pudp++, addr = next, addr != end); return 1; } static int gup_fast_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; p4d_t *p4dp; p4dp = p4d_offset_lockless(pgdp, pgd, addr); do { p4d_t p4d = READ_ONCE(*p4dp); next = p4d_addr_end(addr, end); if (!p4d_present(p4d)) return 0; BUILD_BUG_ON(p4d_leaf(p4d)); if (!gup_fast_pud_range(p4dp, p4d, addr, next, flags, pages, nr)) return 0; } while (p4dp++, addr = next, addr != end); return 1; } static void gup_fast_pgd_range(unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; pgd_t *pgdp; pgdp = pgd_offset(current->mm, addr); do { pgd_t pgd = READ_ONCE(*pgdp); next = pgd_addr_end(addr, end); if (pgd_none(pgd)) return; if (unlikely(pgd_leaf(pgd))) { if (!gup_fast_pgd_leaf(pgd, pgdp, addr, next, flags, pages, nr)) return; } else if (!gup_fast_p4d_range(pgdp, pgd, addr, next, flags, pages, nr)) return; } while (pgdp++, addr = next, addr != end); } #else static inline void gup_fast_pgd_range(unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { } #endif /* CONFIG_HAVE_GUP_FAST */ #ifndef gup_fast_permitted /* * Check if it's allowed to use get_user_pages_fast_only() for the range, or * we need to fall back to the slow version: */ static bool gup_fast_permitted(unsigned long start, unsigned long end) { return true; } #endif static unsigned long gup_fast(unsigned long start, unsigned long end, unsigned int gup_flags, struct page **pages) { unsigned long flags; int nr_pinned = 0; unsigned seq; if (!IS_ENABLED(CONFIG_HAVE_GUP_FAST) || !gup_fast_permitted(start, end)) return 0; if (gup_flags & FOLL_PIN) { seq = raw_read_seqcount(¤t->mm->write_protect_seq); if (seq & 1) return 0; } /* * Disable interrupts. The nested form is used, in order to allow full, * general purpose use of this routine. * * With interrupts disabled, we block page table pages from being freed * from under us. See struct mmu_table_batch comments in * include/asm-generic/tlb.h for more details. * * We do not adopt an rcu_read_lock() here as we also want to block IPIs * that come from THPs splitting. */ local_irq_save(flags); gup_fast_pgd_range(start, end, gup_flags, pages, &nr_pinned); local_irq_restore(flags); /* * When pinning pages for DMA there could be a concurrent write protect * from fork() via copy_page_range(), in this case always fail GUP-fast. */ if (gup_flags & FOLL_PIN) { if (read_seqcount_retry(¤t->mm->write_protect_seq, seq)) { gup_fast_unpin_user_pages(pages, nr_pinned); return 0; } else { sanity_check_pinned_pages(pages, nr_pinned); } } return nr_pinned; } static int gup_fast_fallback(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages) { unsigned long len, end; unsigned long nr_pinned; int locked = 0; int ret; if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM | FOLL_FORCE | FOLL_PIN | FOLL_GET | FOLL_FAST_ONLY | FOLL_NOFAULT | FOLL_PCI_P2PDMA | FOLL_HONOR_NUMA_FAULT))) return -EINVAL; if (gup_flags & FOLL_PIN) mm_set_has_pinned_flag(¤t->mm->flags); if (!(gup_flags & FOLL_FAST_ONLY)) might_lock_read(¤t->mm->mmap_lock); start = untagged_addr(start) & PAGE_MASK; len = nr_pages << PAGE_SHIFT; if (check_add_overflow(start, len, &end)) return -EOVERFLOW; if (end > TASK_SIZE_MAX) return -EFAULT; if (unlikely(!access_ok((void __user *)start, len))) return -EFAULT; nr_pinned = gup_fast(start, end, gup_flags, pages); if (nr_pinned == nr_pages || gup_flags & FOLL_FAST_ONLY) return nr_pinned; /* Slow path: try to get the remaining pages with get_user_pages */ start += nr_pinned << PAGE_SHIFT; pages += nr_pinned; ret = __gup_longterm_locked(current->mm, start, nr_pages - nr_pinned, pages, &locked, gup_flags | FOLL_TOUCH | FOLL_UNLOCKABLE); if (ret < 0) { /* * The caller has to unpin the pages we already pinned so * returning -errno is not an option */ if (nr_pinned) return nr_pinned; return ret; } return ret + nr_pinned; } /** * get_user_pages_fast_only() - pin user pages in memory * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying pin behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * * Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to * the regular GUP. * * If the architecture does not support this function, simply return with no * pages pinned. * * Careful, careful! COW breaking can go either way, so a non-write * access can get ambiguous page results. If you call this function without * 'write' set, you'd better be sure that you're ok with that ambiguity. */ int get_user_pages_fast_only(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages) { /* * Internally (within mm/gup.c), gup fast variants must set FOLL_GET, * because gup fast is always a "pin with a +1 page refcount" request. * * FOLL_FAST_ONLY is required in order to match the API description of * this routine: no fall back to regular ("slow") GUP. */ if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_GET | FOLL_FAST_ONLY)) return -EINVAL; return gup_fast_fallback(start, nr_pages, gup_flags, pages); } EXPORT_SYMBOL_GPL(get_user_pages_fast_only); /** * get_user_pages_fast() - pin user pages in memory * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying pin behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * * Attempt to pin user pages in memory without taking mm->mmap_lock. * If not successful, it will fall back to taking the lock and * calling get_user_pages(). * * Returns number of pages pinned. This may be fewer than the number requested. * If nr_pages is 0 or negative, returns 0. If no pages were pinned, returns * -errno. */ int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages) { /* * The caller may or may not have explicitly set FOLL_GET; either way is * OK. However, internally (within mm/gup.c), gup fast variants must set * FOLL_GET, because gup fast is always a "pin with a +1 page refcount" * request. */ if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_GET)) return -EINVAL; return gup_fast_fallback(start, nr_pages, gup_flags, pages); } EXPORT_SYMBOL_GPL(get_user_pages_fast); /** * pin_user_pages_fast() - pin user pages in memory without taking locks * * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying pin behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * * Nearly the same as get_user_pages_fast(), except that FOLL_PIN is set. See * get_user_pages_fast() for documentation on the function arguments, because * the arguments here are identical. * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for further details. * * Note that if a zero_page is amongst the returned pages, it will not have * pins in it and unpin_user_page() will not remove pins from it. */ int pin_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages) { if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_PIN)) return -EINVAL; return gup_fast_fallback(start, nr_pages, gup_flags, pages); } EXPORT_SYMBOL_GPL(pin_user_pages_fast); /** * pin_user_pages_remote() - pin pages of a remote process * * @mm: mm_struct of target mm * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying lookup behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * @locked: pointer to lock flag indicating whether lock is held and * subsequently whether VM_FAULT_RETRY functionality can be * utilised. Lock must initially be held. * * Nearly the same as get_user_pages_remote(), except that FOLL_PIN is set. See * get_user_pages_remote() for documentation on the function arguments, because * the arguments here are identical. * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for details. * * Note that if a zero_page is amongst the returned pages, it will not have * pins in it and unpin_user_page*() will not remove pins from it. */ long pin_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked) { int local_locked = 1; if (!is_valid_gup_args(pages, locked, &gup_flags, FOLL_PIN | FOLL_TOUCH | FOLL_REMOTE)) return 0; return __gup_longterm_locked(mm, start, nr_pages, pages, locked ? locked : &local_locked, gup_flags); } EXPORT_SYMBOL(pin_user_pages_remote); /** * pin_user_pages() - pin user pages in memory for use by other devices * * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying lookup behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * * Nearly the same as get_user_pages(), except that FOLL_TOUCH is not set, and * FOLL_PIN is set. * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for details. * * Note that if a zero_page is amongst the returned pages, it will not have * pins in it and unpin_user_page*() will not remove pins from it. */ long pin_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages) { int locked = 1; if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_PIN)) return 0; return __gup_longterm_locked(current->mm, start, nr_pages, pages, &locked, gup_flags); } EXPORT_SYMBOL(pin_user_pages); /* * pin_user_pages_unlocked() is the FOLL_PIN variant of * get_user_pages_unlocked(). Behavior is the same, except that this one sets * FOLL_PIN and rejects FOLL_GET. * * Note that if a zero_page is amongst the returned pages, it will not have * pins in it and unpin_user_page*() will not remove pins from it. */ long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags) { int locked = 0; if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_PIN | FOLL_TOUCH | FOLL_UNLOCKABLE)) return 0; return __gup_longterm_locked(current->mm, start, nr_pages, pages, &locked, gup_flags); } EXPORT_SYMBOL(pin_user_pages_unlocked); /** * memfd_pin_folios() - pin folios associated with a memfd * @memfd: the memfd whose folios are to be pinned * @start: the first memfd offset * @end: the last memfd offset (inclusive) * @folios: array that receives pointers to the folios pinned * @max_folios: maximum number of entries in @folios * @offset: the offset into the first folio * * Attempt to pin folios associated with a memfd in the contiguous range * [start, end]. Given that a memfd is either backed by shmem or hugetlb, * the folios can either be found in the page cache or need to be allocated * if necessary. Once the folios are located, they are all pinned via * FOLL_PIN and @offset is populatedwith the offset into the first folio. * And, eventually, these pinned folios must be released either using * unpin_folios() or unpin_folio(). * * It must be noted that the folios may be pinned for an indefinite amount * of time. And, in most cases, the duration of time they may stay pinned * would be controlled by the userspace. This behavior is effectively the * same as using FOLL_LONGTERM with other GUP APIs. * * Returns number of folios pinned, which could be less than @max_folios * as it depends on the folio sizes that cover the range [start, end]. * If no folios were pinned, it returns -errno. */ long memfd_pin_folios(struct file *memfd, loff_t start, loff_t end, struct folio **folios, unsigned int max_folios, pgoff_t *offset) { unsigned int flags, nr_folios, nr_found; unsigned int i, pgshift = PAGE_SHIFT; pgoff_t start_idx, end_idx, next_idx; struct folio *folio = NULL; struct folio_batch fbatch; struct hstate *h; long ret = -EINVAL; if (start < 0 || start > end || !max_folios) return -EINVAL; if (!memfd) return -EINVAL; if (!shmem_file(memfd) && !is_file_hugepages(memfd)) return -EINVAL; if (end >= i_size_read(file_inode(memfd))) return -EINVAL; if (is_file_hugepages(memfd)) { h = hstate_file(memfd); pgshift = huge_page_shift(h); } flags = memalloc_pin_save(); do { nr_folios = 0; start_idx = start >> pgshift; end_idx = end >> pgshift; if (is_file_hugepages(memfd)) { start_idx <<= huge_page_order(h); end_idx <<= huge_page_order(h); } folio_batch_init(&fbatch); while (start_idx <= end_idx && nr_folios < max_folios) { /* * In most cases, we should be able to find the folios * in the page cache. If we cannot find them for some * reason, we try to allocate them and add them to the * page cache. */ nr_found = filemap_get_folios_contig(memfd->f_mapping, &start_idx, end_idx, &fbatch); if (folio) { folio_put(folio); folio = NULL; } next_idx = 0; for (i = 0; i < nr_found; i++) { /* * As there can be multiple entries for a * given folio in the batch returned by * filemap_get_folios_contig(), the below * check is to ensure that we pin and return a * unique set of folios between start and end. */ if (next_idx && next_idx != folio_index(fbatch.folios[i])) continue; folio = page_folio(&fbatch.folios[i]->page); if (try_grab_folio(folio, 1, FOLL_PIN)) { folio_batch_release(&fbatch); ret = -EINVAL; goto err; } if (nr_folios == 0) *offset = offset_in_folio(folio, start); folios[nr_folios] = folio; next_idx = folio_next_index(folio); if (++nr_folios == max_folios) break; } folio = NULL; folio_batch_release(&fbatch); if (!nr_found) { folio = memfd_alloc_folio(memfd, start_idx); if (IS_ERR(folio)) { ret = PTR_ERR(folio); if (ret != -EEXIST) goto err; } } } ret = check_and_migrate_movable_folios(nr_folios, folios); } while (ret == -EAGAIN); memalloc_pin_restore(flags); return ret ? ret : nr_folios; err: memalloc_pin_restore(flags); unpin_folios(folios, nr_folios); return ret; } EXPORT_SYMBOL_GPL(memfd_pin_folios); |
| 19 24 5 19 3 3 5 5 5 5 5 5 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/sysv/ialloc.c * * minix/bitmap.c * Copyright (C) 1991, 1992 Linus Torvalds * * ext/freelists.c * Copyright (C) 1992 Remy Card (card@masi.ibp.fr) * * xenix/alloc.c * Copyright (C) 1992 Doug Evans * * coh/alloc.c * Copyright (C) 1993 Pascal Haible, Bruno Haible * * sysv/ialloc.c * Copyright (C) 1993 Bruno Haible * * This file contains code for allocating/freeing inodes. */ #include <linux/kernel.h> #include <linux/stddef.h> #include <linux/sched.h> #include <linux/stat.h> #include <linux/string.h> #include <linux/buffer_head.h> #include <linux/writeback.h> #include "sysv.h" /* We don't trust the value of sb->sv_sbd2->s_tinode = *sb->sv_sb_total_free_inodes but we nevertheless keep it up to date. */ /* An inode on disk is considered free if both i_mode == 0 and i_nlink == 0. */ /* return &sb->sv_sb_fic_inodes[i] = &sbd->s_inode[i]; */ static inline sysv_ino_t * sv_sb_fic_inode(struct super_block * sb, unsigned int i) { struct sysv_sb_info *sbi = SYSV_SB(sb); if (sbi->s_bh1 == sbi->s_bh2) return &sbi->s_sb_fic_inodes[i]; else { /* 512 byte Xenix FS */ unsigned int offset = offsetof(struct xenix_super_block, s_inode[i]); if (offset < 512) return (sysv_ino_t*)(sbi->s_sbd1 + offset); else return (sysv_ino_t*)(sbi->s_sbd2 + offset); } } struct sysv_inode * sysv_raw_inode(struct super_block *sb, unsigned ino, struct buffer_head **bh) { struct sysv_sb_info *sbi = SYSV_SB(sb); struct sysv_inode *res; int block = sbi->s_firstinodezone + sbi->s_block_base; block += (ino-1) >> sbi->s_inodes_per_block_bits; *bh = sb_bread(sb, block); if (!*bh) return NULL; res = (struct sysv_inode *)(*bh)->b_data; return res + ((ino-1) & sbi->s_inodes_per_block_1); } static int refill_free_cache(struct super_block *sb) { struct sysv_sb_info *sbi = SYSV_SB(sb); struct buffer_head * bh; struct sysv_inode * raw_inode; int i = 0, ino; ino = SYSV_ROOT_INO+1; raw_inode = sysv_raw_inode(sb, ino, &bh); if (!raw_inode) goto out; while (ino <= sbi->s_ninodes) { if (raw_inode->i_mode == 0 && raw_inode->i_nlink == 0) { *sv_sb_fic_inode(sb,i++) = cpu_to_fs16(SYSV_SB(sb), ino); if (i == sbi->s_fic_size) break; } if ((ino++ & sbi->s_inodes_per_block_1) == 0) { brelse(bh); raw_inode = sysv_raw_inode(sb, ino, &bh); if (!raw_inode) goto out; } else raw_inode++; } brelse(bh); out: return i; } void sysv_free_inode(struct inode * inode) { struct super_block *sb = inode->i_sb; struct sysv_sb_info *sbi = SYSV_SB(sb); unsigned int ino; struct buffer_head * bh; struct sysv_inode * raw_inode; unsigned count; sb = inode->i_sb; ino = inode->i_ino; if (ino <= SYSV_ROOT_INO || ino > sbi->s_ninodes) { printk("sysv_free_inode: inode 0,1,2 or nonexistent inode\n"); return; } raw_inode = sysv_raw_inode(sb, ino, &bh); if (!raw_inode) { printk("sysv_free_inode: unable to read inode block on device " "%s\n", inode->i_sb->s_id); return; } mutex_lock(&sbi->s_lock); count = fs16_to_cpu(sbi, *sbi->s_sb_fic_count); if (count < sbi->s_fic_size) { *sv_sb_fic_inode(sb,count++) = cpu_to_fs16(sbi, ino); *sbi->s_sb_fic_count = cpu_to_fs16(sbi, count); } fs16_add(sbi, sbi->s_sb_total_free_inodes, 1); dirty_sb(sb); memset(raw_inode, 0, sizeof(struct sysv_inode)); mark_buffer_dirty(bh); mutex_unlock(&sbi->s_lock); brelse(bh); } struct inode * sysv_new_inode(const struct inode * dir, umode_t mode) { struct super_block *sb = dir->i_sb; struct sysv_sb_info *sbi = SYSV_SB(sb); struct inode *inode; sysv_ino_t ino; unsigned count; struct writeback_control wbc = { .sync_mode = WB_SYNC_NONE }; inode = new_inode(sb); if (!inode) return ERR_PTR(-ENOMEM); mutex_lock(&sbi->s_lock); count = fs16_to_cpu(sbi, *sbi->s_sb_fic_count); if (count == 0 || (*sv_sb_fic_inode(sb,count-1) == 0)) { count = refill_free_cache(sb); if (count == 0) { iput(inode); mutex_unlock(&sbi->s_lock); return ERR_PTR(-ENOSPC); } } /* Now count > 0. */ ino = *sv_sb_fic_inode(sb,--count); *sbi->s_sb_fic_count = cpu_to_fs16(sbi, count); fs16_add(sbi, sbi->s_sb_total_free_inodes, -1); dirty_sb(sb); inode_init_owner(&nop_mnt_idmap, inode, dir, mode); inode->i_ino = fs16_to_cpu(sbi, ino); simple_inode_init_ts(inode); inode->i_blocks = 0; memset(SYSV_I(inode)->i_data, 0, sizeof(SYSV_I(inode)->i_data)); SYSV_I(inode)->i_dir_start_lookup = 0; insert_inode_hash(inode); mark_inode_dirty(inode); sysv_write_inode(inode, &wbc); /* ensure inode not allocated again */ mark_inode_dirty(inode); /* cleared by sysv_write_inode() */ /* That's it. */ mutex_unlock(&sbi->s_lock); return inode; } unsigned long sysv_count_free_inodes(struct super_block * sb) { struct sysv_sb_info *sbi = SYSV_SB(sb); struct buffer_head * bh; struct sysv_inode * raw_inode; int ino, count, sb_count; mutex_lock(&sbi->s_lock); sb_count = fs16_to_cpu(sbi, *sbi->s_sb_total_free_inodes); if (0) goto trust_sb; /* this causes a lot of disk traffic ... */ count = 0; ino = SYSV_ROOT_INO+1; raw_inode = sysv_raw_inode(sb, ino, &bh); if (!raw_inode) goto Eio; while (ino <= sbi->s_ninodes) { if (raw_inode->i_mode == 0 && raw_inode->i_nlink == 0) count++; if ((ino++ & sbi->s_inodes_per_block_1) == 0) { brelse(bh); raw_inode = sysv_raw_inode(sb, ino, &bh); if (!raw_inode) goto Eio; } else raw_inode++; } brelse(bh); if (count != sb_count) goto Einval; out: mutex_unlock(&sbi->s_lock); return count; Einval: printk("sysv_count_free_inodes: " "free inode count was %d, correcting to %d\n", sb_count, count); if (!sb_rdonly(sb)) { *sbi->s_sb_total_free_inodes = cpu_to_fs16(SYSV_SB(sb), count); dirty_sb(sb); } goto out; Eio: printk("sysv_count_free_inodes: unable to read inode table\n"); trust_sb: count = sb_count; goto out; } |
| 218 177 147 11 343 344 121 295 294 42 249 89 3 270 269 191 192 89 28 269 269 2 262 151 233 2 132 2 11 369 157 333 10 4 6 4 7 247 127 52 2 3 2 3 6 6 6 6 6 6 6 6 6 227 5 129 145 227 226 6 219 36 227 78 227 226 6 225 227 4 4 4 4 4 4 2 2 1 2 2 1 1 1 2 2 2 2 2 4 4 4 89 90 90 31 31 90 13 24 68 14 4 44 50 371 371 156 334 334 2 184 294 112 112 70 60 185 85 139 39 185 185 185 306 306 293 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2017 Christoph Hellwig. */ #include "xfs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_bit.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_inode.h" #include "xfs_trace.h" /* * In-core extent record layout: * * +-------+----------------------------+ * | 00:53 | all 54 bits of startoff | * | 54:63 | low 10 bits of startblock | * +-------+----------------------------+ * | 00:20 | all 21 bits of length | * | 21 | unwritten extent bit | * | 22:63 | high 42 bits of startblock | * +-------+----------------------------+ */ #define XFS_IEXT_STARTOFF_MASK xfs_mask64lo(BMBT_STARTOFF_BITLEN) #define XFS_IEXT_LENGTH_MASK xfs_mask64lo(BMBT_BLOCKCOUNT_BITLEN) #define XFS_IEXT_STARTBLOCK_MASK xfs_mask64lo(BMBT_STARTBLOCK_BITLEN) struct xfs_iext_rec { uint64_t lo; uint64_t hi; }; /* * Given that the length can't be a zero, only an empty hi value indicates an * unused record. */ static bool xfs_iext_rec_is_empty(struct xfs_iext_rec *rec) { return rec->hi == 0; } static inline void xfs_iext_rec_clear(struct xfs_iext_rec *rec) { rec->lo = 0; rec->hi = 0; } static void xfs_iext_set( struct xfs_iext_rec *rec, struct xfs_bmbt_irec *irec) { ASSERT((irec->br_startoff & ~XFS_IEXT_STARTOFF_MASK) == 0); ASSERT((irec->br_blockcount & ~XFS_IEXT_LENGTH_MASK) == 0); ASSERT((irec->br_startblock & ~XFS_IEXT_STARTBLOCK_MASK) == 0); rec->lo = irec->br_startoff & XFS_IEXT_STARTOFF_MASK; rec->hi = irec->br_blockcount & XFS_IEXT_LENGTH_MASK; rec->lo |= (irec->br_startblock << 54); rec->hi |= ((irec->br_startblock & ~xfs_mask64lo(10)) << (22 - 10)); if (irec->br_state == XFS_EXT_UNWRITTEN) rec->hi |= (1 << 21); } static void xfs_iext_get( struct xfs_bmbt_irec *irec, struct xfs_iext_rec *rec) { irec->br_startoff = rec->lo & XFS_IEXT_STARTOFF_MASK; irec->br_blockcount = rec->hi & XFS_IEXT_LENGTH_MASK; irec->br_startblock = rec->lo >> 54; irec->br_startblock |= (rec->hi & xfs_mask64hi(42)) >> (22 - 10); if (rec->hi & (1 << 21)) irec->br_state = XFS_EXT_UNWRITTEN; else irec->br_state = XFS_EXT_NORM; } enum { NODE_SIZE = 256, KEYS_PER_NODE = NODE_SIZE / (sizeof(uint64_t) + sizeof(void *)), RECS_PER_LEAF = (NODE_SIZE - (2 * sizeof(struct xfs_iext_leaf *))) / sizeof(struct xfs_iext_rec), }; /* * In-core extent btree block layout: * * There are two types of blocks in the btree: leaf and inner (non-leaf) blocks. * * The leaf blocks are made up by %KEYS_PER_NODE extent records, which each * contain the startoffset, blockcount, startblock and unwritten extent flag. * See above for the exact format, followed by pointers to the previous and next * leaf blocks (if there are any). * * The inner (non-leaf) blocks first contain KEYS_PER_NODE lookup keys, followed * by an equal number of pointers to the btree blocks at the next lower level. * * +-------+-------+-------+-------+-------+----------+----------+ * Leaf: | rec 1 | rec 2 | rec 3 | rec 4 | rec N | prev-ptr | next-ptr | * +-------+-------+-------+-------+-------+----------+----------+ * * +-------+-------+-------+-------+-------+-------+------+-------+ * Inner: | key 1 | key 2 | key 3 | key N | ptr 1 | ptr 2 | ptr3 | ptr N | * +-------+-------+-------+-------+-------+-------+------+-------+ */ struct xfs_iext_node { uint64_t keys[KEYS_PER_NODE]; #define XFS_IEXT_KEY_INVALID (1ULL << 63) void *ptrs[KEYS_PER_NODE]; }; struct xfs_iext_leaf { struct xfs_iext_rec recs[RECS_PER_LEAF]; struct xfs_iext_leaf *prev; struct xfs_iext_leaf *next; }; inline xfs_extnum_t xfs_iext_count(struct xfs_ifork *ifp) { return ifp->if_bytes / sizeof(struct xfs_iext_rec); } static inline int xfs_iext_max_recs(struct xfs_ifork *ifp) { if (ifp->if_height == 1) return xfs_iext_count(ifp); return RECS_PER_LEAF; } static inline struct xfs_iext_rec *cur_rec(struct xfs_iext_cursor *cur) { return &cur->leaf->recs[cur->pos]; } static inline bool xfs_iext_valid(struct xfs_ifork *ifp, struct xfs_iext_cursor *cur) { if (!cur->leaf) return false; if (cur->pos < 0 || cur->pos >= xfs_iext_max_recs(ifp)) return false; if (xfs_iext_rec_is_empty(cur_rec(cur))) return false; return true; } static void * xfs_iext_find_first_leaf( struct xfs_ifork *ifp) { struct xfs_iext_node *node = ifp->if_data; int height; if (!ifp->if_height) return NULL; for (height = ifp->if_height; height > 1; height--) { node = node->ptrs[0]; ASSERT(node); } return node; } static void * xfs_iext_find_last_leaf( struct xfs_ifork *ifp) { struct xfs_iext_node *node = ifp->if_data; int height, i; if (!ifp->if_height) return NULL; for (height = ifp->if_height; height > 1; height--) { for (i = 1; i < KEYS_PER_NODE; i++) if (!node->ptrs[i]) break; node = node->ptrs[i - 1]; ASSERT(node); } return node; } void xfs_iext_first( struct xfs_ifork *ifp, struct xfs_iext_cursor *cur) { cur->pos = 0; cur->leaf = xfs_iext_find_first_leaf(ifp); } void xfs_iext_last( struct xfs_ifork *ifp, struct xfs_iext_cursor *cur) { int i; cur->leaf = xfs_iext_find_last_leaf(ifp); if (!cur->leaf) { cur->pos = 0; return; } for (i = 1; i < xfs_iext_max_recs(ifp); i++) { if (xfs_iext_rec_is_empty(&cur->leaf->recs[i])) break; } cur->pos = i - 1; } void xfs_iext_next( struct xfs_ifork *ifp, struct xfs_iext_cursor *cur) { if (!cur->leaf) { ASSERT(cur->pos <= 0 || cur->pos >= RECS_PER_LEAF); xfs_iext_first(ifp, cur); return; } ASSERT(cur->pos >= 0); ASSERT(cur->pos < xfs_iext_max_recs(ifp)); cur->pos++; if (ifp->if_height > 1 && !xfs_iext_valid(ifp, cur) && cur->leaf->next) { cur->leaf = cur->leaf->next; cur->pos = 0; } } void xfs_iext_prev( struct xfs_ifork *ifp, struct xfs_iext_cursor *cur) { if (!cur->leaf) { ASSERT(cur->pos <= 0 || cur->pos >= RECS_PER_LEAF); xfs_iext_last(ifp, cur); return; } ASSERT(cur->pos >= 0); ASSERT(cur->pos <= RECS_PER_LEAF); recurse: do { cur->pos--; if (xfs_iext_valid(ifp, cur)) return; } while (cur->pos > 0); if (ifp->if_height > 1 && cur->leaf->prev) { cur->leaf = cur->leaf->prev; cur->pos = RECS_PER_LEAF; goto recurse; } } static inline int xfs_iext_key_cmp( struct xfs_iext_node *node, int n, xfs_fileoff_t offset) { if (node->keys[n] > offset) return 1; if (node->keys[n] < offset) return -1; return 0; } static inline int xfs_iext_rec_cmp( struct xfs_iext_rec *rec, xfs_fileoff_t offset) { uint64_t rec_offset = rec->lo & XFS_IEXT_STARTOFF_MASK; uint32_t rec_len = rec->hi & XFS_IEXT_LENGTH_MASK; if (rec_offset > offset) return 1; if (rec_offset + rec_len <= offset) return -1; return 0; } static void * xfs_iext_find_level( struct xfs_ifork *ifp, xfs_fileoff_t offset, int level) { struct xfs_iext_node *node = ifp->if_data; int height, i; if (!ifp->if_height) return NULL; for (height = ifp->if_height; height > level; height--) { for (i = 1; i < KEYS_PER_NODE; i++) if (xfs_iext_key_cmp(node, i, offset) > 0) break; node = node->ptrs[i - 1]; if (!node) break; } return node; } static int xfs_iext_node_pos( struct xfs_iext_node *node, xfs_fileoff_t offset) { int i; for (i = 1; i < KEYS_PER_NODE; i++) { if (xfs_iext_key_cmp(node, i, offset) > 0) break; } return i - 1; } static int xfs_iext_node_insert_pos( struct xfs_iext_node *node, xfs_fileoff_t offset) { int i; for (i = 0; i < KEYS_PER_NODE; i++) { if (xfs_iext_key_cmp(node, i, offset) > 0) return i; } return KEYS_PER_NODE; } static int xfs_iext_node_nr_entries( struct xfs_iext_node *node, int start) { int i; for (i = start; i < KEYS_PER_NODE; i++) { if (node->keys[i] == XFS_IEXT_KEY_INVALID) break; } return i; } static int xfs_iext_leaf_nr_entries( struct xfs_ifork *ifp, struct xfs_iext_leaf *leaf, int start) { int i; for (i = start; i < xfs_iext_max_recs(ifp); i++) { if (xfs_iext_rec_is_empty(&leaf->recs[i])) break; } return i; } static inline uint64_t xfs_iext_leaf_key( struct xfs_iext_leaf *leaf, int n) { return leaf->recs[n].lo & XFS_IEXT_STARTOFF_MASK; } static inline void * xfs_iext_alloc_node( int size) { return kzalloc(size, GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); } static void xfs_iext_grow( struct xfs_ifork *ifp) { struct xfs_iext_node *node = xfs_iext_alloc_node(NODE_SIZE); int i; if (ifp->if_height == 1) { struct xfs_iext_leaf *prev = ifp->if_data; node->keys[0] = xfs_iext_leaf_key(prev, 0); node->ptrs[0] = prev; } else { struct xfs_iext_node *prev = ifp->if_data; ASSERT(ifp->if_height > 1); node->keys[0] = prev->keys[0]; node->ptrs[0] = prev; } for (i = 1; i < KEYS_PER_NODE; i++) node->keys[i] = XFS_IEXT_KEY_INVALID; ifp->if_data = node; ifp->if_height++; } static void xfs_iext_update_node( struct xfs_ifork *ifp, xfs_fileoff_t old_offset, xfs_fileoff_t new_offset, int level, void *ptr) { struct xfs_iext_node *node = ifp->if_data; int height, i; for (height = ifp->if_height; height > level; height--) { for (i = 0; i < KEYS_PER_NODE; i++) { if (i > 0 && xfs_iext_key_cmp(node, i, old_offset) > 0) break; if (node->keys[i] == old_offset) node->keys[i] = new_offset; } node = node->ptrs[i - 1]; ASSERT(node); } ASSERT(node == ptr); } static struct xfs_iext_node * xfs_iext_split_node( struct xfs_iext_node **nodep, int *pos, int *nr_entries) { struct xfs_iext_node *node = *nodep; struct xfs_iext_node *new = xfs_iext_alloc_node(NODE_SIZE); const int nr_move = KEYS_PER_NODE / 2; int nr_keep = nr_move + (KEYS_PER_NODE & 1); int i = 0; /* for sequential append operations just spill over into the new node */ if (*pos == KEYS_PER_NODE) { *nodep = new; *pos = 0; *nr_entries = 0; goto done; } for (i = 0; i < nr_move; i++) { new->keys[i] = node->keys[nr_keep + i]; new->ptrs[i] = node->ptrs[nr_keep + i]; node->keys[nr_keep + i] = XFS_IEXT_KEY_INVALID; node->ptrs[nr_keep + i] = NULL; } if (*pos >= nr_keep) { *nodep = new; *pos -= nr_keep; *nr_entries = nr_move; } else { *nr_entries = nr_keep; } done: for (; i < KEYS_PER_NODE; i++) new->keys[i] = XFS_IEXT_KEY_INVALID; return new; } static void xfs_iext_insert_node( struct xfs_ifork *ifp, uint64_t offset, void *ptr, int level) { struct xfs_iext_node *node, *new; int i, pos, nr_entries; again: if (ifp->if_height < level) xfs_iext_grow(ifp); new = NULL; node = xfs_iext_find_level(ifp, offset, level); pos = xfs_iext_node_insert_pos(node, offset); nr_entries = xfs_iext_node_nr_entries(node, pos); ASSERT(pos >= nr_entries || xfs_iext_key_cmp(node, pos, offset) != 0); ASSERT(nr_entries <= KEYS_PER_NODE); if (nr_entries == KEYS_PER_NODE) new = xfs_iext_split_node(&node, &pos, &nr_entries); /* * Update the pointers in higher levels if the first entry changes * in an existing node. */ if (node != new && pos == 0 && nr_entries > 0) xfs_iext_update_node(ifp, node->keys[0], offset, level, node); for (i = nr_entries; i > pos; i--) { node->keys[i] = node->keys[i - 1]; node->ptrs[i] = node->ptrs[i - 1]; } node->keys[pos] = offset; node->ptrs[pos] = ptr; if (new) { offset = new->keys[0]; ptr = new; level++; goto again; } } static struct xfs_iext_leaf * xfs_iext_split_leaf( struct xfs_iext_cursor *cur, int *nr_entries) { struct xfs_iext_leaf *leaf = cur->leaf; struct xfs_iext_leaf *new = xfs_iext_alloc_node(NODE_SIZE); const int nr_move = RECS_PER_LEAF / 2; int nr_keep = nr_move + (RECS_PER_LEAF & 1); int i; /* for sequential append operations just spill over into the new node */ if (cur->pos == RECS_PER_LEAF) { cur->leaf = new; cur->pos = 0; *nr_entries = 0; goto done; } for (i = 0; i < nr_move; i++) { new->recs[i] = leaf->recs[nr_keep + i]; xfs_iext_rec_clear(&leaf->recs[nr_keep + i]); } if (cur->pos >= nr_keep) { cur->leaf = new; cur->pos -= nr_keep; *nr_entries = nr_move; } else { *nr_entries = nr_keep; } done: if (leaf->next) leaf->next->prev = new; new->next = leaf->next; new->prev = leaf; leaf->next = new; return new; } static void xfs_iext_alloc_root( struct xfs_ifork *ifp, struct xfs_iext_cursor *cur) { ASSERT(ifp->if_bytes == 0); ifp->if_data = xfs_iext_alloc_node(sizeof(struct xfs_iext_rec)); ifp->if_height = 1; /* now that we have a node step into it */ cur->leaf = ifp->if_data; cur->pos = 0; } static void xfs_iext_realloc_root( struct xfs_ifork *ifp, struct xfs_iext_cursor *cur) { int64_t new_size = ifp->if_bytes + sizeof(struct xfs_iext_rec); void *new; /* account for the prev/next pointers */ if (new_size / sizeof(struct xfs_iext_rec) == RECS_PER_LEAF) new_size = NODE_SIZE; new = krealloc(ifp->if_data, new_size, GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); memset(new + ifp->if_bytes, 0, new_size - ifp->if_bytes); ifp->if_data = new; cur->leaf = new; } /* * Increment the sequence counter on extent tree changes. If we are on a COW * fork, this allows the writeback code to skip looking for a COW extent if the * COW fork hasn't changed. We use WRITE_ONCE here to ensure the update to the * sequence counter is seen before the modifications to the extent tree itself * take effect. */ static inline void xfs_iext_inc_seq(struct xfs_ifork *ifp) { WRITE_ONCE(ifp->if_seq, READ_ONCE(ifp->if_seq) + 1); } void xfs_iext_insert_raw( struct xfs_ifork *ifp, struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *irec) { xfs_fileoff_t offset = irec->br_startoff; struct xfs_iext_leaf *new = NULL; int nr_entries, i; xfs_iext_inc_seq(ifp); if (ifp->if_height == 0) xfs_iext_alloc_root(ifp, cur); else if (ifp->if_height == 1) xfs_iext_realloc_root(ifp, cur); nr_entries = xfs_iext_leaf_nr_entries(ifp, cur->leaf, cur->pos); ASSERT(nr_entries <= RECS_PER_LEAF); ASSERT(cur->pos >= nr_entries || xfs_iext_rec_cmp(cur_rec(cur), irec->br_startoff) != 0); if (nr_entries == RECS_PER_LEAF) new = xfs_iext_split_leaf(cur, &nr_entries); /* * Update the pointers in higher levels if the first entry changes * in an existing node. */ if (cur->leaf != new && cur->pos == 0 && nr_entries > 0) { xfs_iext_update_node(ifp, xfs_iext_leaf_key(cur->leaf, 0), offset, 1, cur->leaf); } for (i = nr_entries; i > cur->pos; i--) cur->leaf->recs[i] = cur->leaf->recs[i - 1]; xfs_iext_set(cur_rec(cur), irec); ifp->if_bytes += sizeof(struct xfs_iext_rec); if (new) xfs_iext_insert_node(ifp, xfs_iext_leaf_key(new, 0), new, 2); } void xfs_iext_insert( struct xfs_inode *ip, struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *irec, int state) { struct xfs_ifork *ifp = xfs_iext_state_to_fork(ip, state); xfs_iext_insert_raw(ifp, cur, irec); trace_xfs_iext_insert(ip, cur, state, _RET_IP_); } static struct xfs_iext_node * xfs_iext_rebalance_node( struct xfs_iext_node *parent, int *pos, struct xfs_iext_node *node, int nr_entries) { /* * If the neighbouring nodes are completely full, or have different * parents, we might never be able to merge our node, and will only * delete it once the number of entries hits zero. */ if (nr_entries == 0) return node; if (*pos > 0) { struct xfs_iext_node *prev = parent->ptrs[*pos - 1]; int nr_prev = xfs_iext_node_nr_entries(prev, 0), i; if (nr_prev + nr_entries <= KEYS_PER_NODE) { for (i = 0; i < nr_entries; i++) { prev->keys[nr_prev + i] = node->keys[i]; prev->ptrs[nr_prev + i] = node->ptrs[i]; } return node; } } if (*pos + 1 < xfs_iext_node_nr_entries(parent, *pos)) { struct xfs_iext_node *next = parent->ptrs[*pos + 1]; int nr_next = xfs_iext_node_nr_entries(next, 0), i; if (nr_entries + nr_next <= KEYS_PER_NODE) { /* * Merge the next node into this node so that we don't * have to do an additional update of the keys in the * higher levels. */ for (i = 0; i < nr_next; i++) { node->keys[nr_entries + i] = next->keys[i]; node->ptrs[nr_entries + i] = next->ptrs[i]; } ++*pos; return next; } } return NULL; } static void xfs_iext_remove_node( struct xfs_ifork *ifp, xfs_fileoff_t offset, void *victim) { struct xfs_iext_node *node, *parent; int level = 2, pos, nr_entries, i; ASSERT(level <= ifp->if_height); node = xfs_iext_find_level(ifp, offset, level); pos = xfs_iext_node_pos(node, offset); again: ASSERT(node->ptrs[pos]); ASSERT(node->ptrs[pos] == victim); kfree(victim); nr_entries = xfs_iext_node_nr_entries(node, pos) - 1; offset = node->keys[0]; for (i = pos; i < nr_entries; i++) { node->keys[i] = node->keys[i + 1]; node->ptrs[i] = node->ptrs[i + 1]; } node->keys[nr_entries] = XFS_IEXT_KEY_INVALID; node->ptrs[nr_entries] = NULL; if (pos == 0 && nr_entries > 0) { xfs_iext_update_node(ifp, offset, node->keys[0], level, node); offset = node->keys[0]; } if (nr_entries >= KEYS_PER_NODE / 2) return; if (level < ifp->if_height) { /* * If we aren't at the root yet try to find a neighbour node to * merge with (or delete the node if it is empty), and then * recurse up to the next level. */ level++; parent = xfs_iext_find_level(ifp, offset, level); pos = xfs_iext_node_pos(parent, offset); ASSERT(pos != KEYS_PER_NODE); ASSERT(parent->ptrs[pos] == node); node = xfs_iext_rebalance_node(parent, &pos, node, nr_entries); if (node) { victim = node; node = parent; goto again; } } else if (nr_entries == 1) { /* * If we are at the root and only one entry is left we can just * free this node and update the root pointer. */ ASSERT(node == ifp->if_data); ifp->if_data = node->ptrs[0]; ifp->if_height--; kfree(node); } } static void xfs_iext_rebalance_leaf( struct xfs_ifork *ifp, struct xfs_iext_cursor *cur, struct xfs_iext_leaf *leaf, xfs_fileoff_t offset, int nr_entries) { /* * If the neighbouring nodes are completely full we might never be able * to merge our node, and will only delete it once the number of * entries hits zero. */ if (nr_entries == 0) goto remove_node; if (leaf->prev) { int nr_prev = xfs_iext_leaf_nr_entries(ifp, leaf->prev, 0), i; if (nr_prev + nr_entries <= RECS_PER_LEAF) { for (i = 0; i < nr_entries; i++) leaf->prev->recs[nr_prev + i] = leaf->recs[i]; if (cur->leaf == leaf) { cur->leaf = leaf->prev; cur->pos += nr_prev; } goto remove_node; } } if (leaf->next) { int nr_next = xfs_iext_leaf_nr_entries(ifp, leaf->next, 0), i; if (nr_entries + nr_next <= RECS_PER_LEAF) { /* * Merge the next node into this node so that we don't * have to do an additional update of the keys in the * higher levels. */ for (i = 0; i < nr_next; i++) { leaf->recs[nr_entries + i] = leaf->next->recs[i]; } if (cur->leaf == leaf->next) { cur->leaf = leaf; cur->pos += nr_entries; } offset = xfs_iext_leaf_key(leaf->next, 0); leaf = leaf->next; goto remove_node; } } return; remove_node: if (leaf->prev) leaf->prev->next = leaf->next; if (leaf->next) leaf->next->prev = leaf->prev; xfs_iext_remove_node(ifp, offset, leaf); } static void xfs_iext_free_last_leaf( struct xfs_ifork *ifp) { ifp->if_height--; kfree(ifp->if_data); ifp->if_data = NULL; } void xfs_iext_remove( struct xfs_inode *ip, struct xfs_iext_cursor *cur, int state) { struct xfs_ifork *ifp = xfs_iext_state_to_fork(ip, state); struct xfs_iext_leaf *leaf = cur->leaf; xfs_fileoff_t offset = xfs_iext_leaf_key(leaf, 0); int i, nr_entries; trace_xfs_iext_remove(ip, cur, state, _RET_IP_); ASSERT(ifp->if_height > 0); ASSERT(ifp->if_data != NULL); ASSERT(xfs_iext_valid(ifp, cur)); xfs_iext_inc_seq(ifp); nr_entries = xfs_iext_leaf_nr_entries(ifp, leaf, cur->pos) - 1; for (i = cur->pos; i < nr_entries; i++) leaf->recs[i] = leaf->recs[i + 1]; xfs_iext_rec_clear(&leaf->recs[nr_entries]); ifp->if_bytes -= sizeof(struct xfs_iext_rec); if (cur->pos == 0 && nr_entries > 0) { xfs_iext_update_node(ifp, offset, xfs_iext_leaf_key(leaf, 0), 1, leaf); offset = xfs_iext_leaf_key(leaf, 0); } else if (cur->pos == nr_entries) { if (ifp->if_height > 1 && leaf->next) cur->leaf = leaf->next; else cur->leaf = NULL; cur->pos = 0; } if (nr_entries >= RECS_PER_LEAF / 2) return; if (ifp->if_height > 1) xfs_iext_rebalance_leaf(ifp, cur, leaf, offset, nr_entries); else if (nr_entries == 0) xfs_iext_free_last_leaf(ifp); } /* * Lookup the extent covering bno. * * If there is an extent covering bno return the extent index, and store the * expanded extent structure in *gotp, and the extent cursor in *cur. * If there is no extent covering bno, but there is an extent after it (e.g. * it lies in a hole) return that extent in *gotp and its cursor in *cur * instead. * If bno is beyond the last extent return false, and return an invalid * cursor value. */ bool xfs_iext_lookup_extent( struct xfs_inode *ip, struct xfs_ifork *ifp, xfs_fileoff_t offset, struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *gotp) { XFS_STATS_INC(ip->i_mount, xs_look_exlist); cur->leaf = xfs_iext_find_level(ifp, offset, 1); if (!cur->leaf) { cur->pos = 0; return false; } for (cur->pos = 0; cur->pos < xfs_iext_max_recs(ifp); cur->pos++) { struct xfs_iext_rec *rec = cur_rec(cur); if (xfs_iext_rec_is_empty(rec)) break; if (xfs_iext_rec_cmp(rec, offset) >= 0) goto found; } /* Try looking in the next node for an entry > offset */ if (ifp->if_height == 1 || !cur->leaf->next) return false; cur->leaf = cur->leaf->next; cur->pos = 0; if (!xfs_iext_valid(ifp, cur)) return false; found: xfs_iext_get(gotp, cur_rec(cur)); return true; } /* * Returns the last extent before end, and if this extent doesn't cover * end, update end to the end of the extent. */ bool xfs_iext_lookup_extent_before( struct xfs_inode *ip, struct xfs_ifork *ifp, xfs_fileoff_t *end, struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *gotp) { /* could be optimized to not even look up the next on a match.. */ if (xfs_iext_lookup_extent(ip, ifp, *end - 1, cur, gotp) && gotp->br_startoff <= *end - 1) return true; if (!xfs_iext_prev_extent(ifp, cur, gotp)) return false; *end = gotp->br_startoff + gotp->br_blockcount; return true; } void xfs_iext_update_extent( struct xfs_inode *ip, int state, struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *new) { struct xfs_ifork *ifp = xfs_iext_state_to_fork(ip, state); xfs_iext_inc_seq(ifp); if (cur->pos == 0) { struct xfs_bmbt_irec old; xfs_iext_get(&old, cur_rec(cur)); if (new->br_startoff != old.br_startoff) { xfs_iext_update_node(ifp, old.br_startoff, new->br_startoff, 1, cur->leaf); } } trace_xfs_bmap_pre_update(ip, cur, state, _RET_IP_); xfs_iext_set(cur_rec(cur), new); trace_xfs_bmap_post_update(ip, cur, state, _RET_IP_); } /* * Return true if the cursor points at an extent and return the extent structure * in gotp. Else return false. */ bool xfs_iext_get_extent( struct xfs_ifork *ifp, struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *gotp) { if (!xfs_iext_valid(ifp, cur)) return false; xfs_iext_get(gotp, cur_rec(cur)); return true; } /* * This is a recursive function, because of that we need to be extremely * careful with stack usage. */ static void xfs_iext_destroy_node( struct xfs_iext_node *node, int level) { int i; if (level > 1) { for (i = 0; i < KEYS_PER_NODE; i++) { if (node->keys[i] == XFS_IEXT_KEY_INVALID) break; xfs_iext_destroy_node(node->ptrs[i], level - 1); } } kfree(node); } void xfs_iext_destroy( struct xfs_ifork *ifp) { xfs_iext_destroy_node(ifp->if_data, ifp->if_height); ifp->if_bytes = 0; ifp->if_height = 0; ifp->if_data = NULL; } |
| 550 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 1994 Linus Torvalds * * Pentium III FXSR, SSE support * General FPU state handling cleanups * Gareth Hughes <gareth@valinux.com>, May 2000 * x86-64 work by Andi Kleen 2002 */ #ifndef _ASM_X86_FPU_API_H #define _ASM_X86_FPU_API_H #include <linux/bottom_half.h> #include <asm/fpu/types.h> /* * Use kernel_fpu_begin/end() if you intend to use FPU in kernel context. It * disables preemption so be careful if you intend to use it for long periods * of time. * If you intend to use the FPU in irq/softirq you need to check first with * irq_fpu_usable() if it is possible. */ /* Kernel FPU states to initialize in kernel_fpu_begin_mask() */ #define KFPU_387 _BITUL(0) /* 387 state will be initialized */ #define KFPU_MXCSR _BITUL(1) /* MXCSR will be initialized */ extern void kernel_fpu_begin_mask(unsigned int kfpu_mask); extern void kernel_fpu_end(void); extern bool irq_fpu_usable(void); extern void fpregs_mark_activate(void); /* Code that is unaware of kernel_fpu_begin_mask() can use this */ static inline void kernel_fpu_begin(void) { #ifdef CONFIG_X86_64 /* * Any 64-bit code that uses 387 instructions must explicitly request * KFPU_387. */ kernel_fpu_begin_mask(KFPU_MXCSR); #else /* * 32-bit kernel code may use 387 operations as well as SSE2, etc, * as long as it checks that the CPU has the required capability. */ kernel_fpu_begin_mask(KFPU_387 | KFPU_MXCSR); #endif } /* * Use fpregs_lock() while editing CPU's FPU registers or fpu->fpstate. * A context switch will (and softirq might) save CPU's FPU registers to * fpu->fpstate.regs and set TIF_NEED_FPU_LOAD leaving CPU's FPU registers in * a random state. * * local_bh_disable() protects against both preemption and soft interrupts * on !RT kernels. * * On RT kernels local_bh_disable() is not sufficient because it only * serializes soft interrupt related sections via a local lock, but stays * preemptible. Disabling preemption is the right choice here as bottom * half processing is always in thread context on RT kernels so it * implicitly prevents bottom half processing as well. * * Disabling preemption also serializes against kernel_fpu_begin(). */ static inline void fpregs_lock(void) { if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_bh_disable(); else preempt_disable(); } static inline void fpregs_unlock(void) { if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_bh_enable(); else preempt_enable(); } /* * FPU state gets lazily restored before returning to userspace. So when in the * kernel, the valid FPU state may be kept in the buffer. This function will force * restore all the fpu state to the registers early if needed, and lock them from * being automatically saved/restored. Then FPU state can be modified safely in the * registers, before unlocking with fpregs_unlock(). */ void fpregs_lock_and_load(void); #ifdef CONFIG_X86_DEBUG_FPU extern void fpregs_assert_state_consistent(void); #else static inline void fpregs_assert_state_consistent(void) { } #endif /* * Load the task FPU state before returning to userspace. */ extern void switch_fpu_return(void); /* * Query the presence of one or more xfeatures. Works on any legacy CPU as well. * * If 'feature_name' is set then put a human-readable description of * the feature there as well - this can be used to print error (or success) * messages. */ extern int cpu_has_xfeatures(u64 xfeatures_mask, const char **feature_name); /* Trap handling */ extern int fpu__exception_code(struct fpu *fpu, int trap_nr); extern void fpu_sync_fpstate(struct fpu *fpu); extern void fpu_reset_from_exception_fixup(void); /* Boot, hotplug and resume */ extern void fpu__init_cpu(void); extern void fpu__init_system(void); extern void fpu__init_check_bugs(void); extern void fpu__resume_cpu(void); #ifdef CONFIG_MATH_EMULATION extern void fpstate_init_soft(struct swregs_state *soft); #else static inline void fpstate_init_soft(struct swregs_state *soft) {} #endif /* State tracking */ DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); /* Process cleanup */ #ifdef CONFIG_X86_64 extern void fpstate_free(struct fpu *fpu); #else static inline void fpstate_free(struct fpu *fpu) { } #endif /* fpstate-related functions which are exported to KVM */ extern void fpstate_clear_xstate_component(struct fpstate *fps, unsigned int xfeature); extern u64 xstate_get_guest_group_perm(void); extern void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr); /* KVM specific functions */ extern bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu); extern void fpu_free_guest_fpstate(struct fpu_guest *gfpu); extern int fpu_swap_kvm_fpstate(struct fpu_guest *gfpu, bool enter_guest); extern int fpu_enable_guest_xfd_features(struct fpu_guest *guest_fpu, u64 xfeatures); #ifdef CONFIG_X86_64 extern void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd); extern void fpu_sync_guest_vmexit_xfd_state(void); #else static inline void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd) { } static inline void fpu_sync_guest_vmexit_xfd_state(void) { } #endif extern void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf, unsigned int size, u64 xfeatures, u32 pkru); extern int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf, u64 xcr0, u32 *vpkru); static inline void fpstate_set_confidential(struct fpu_guest *gfpu) { gfpu->fpstate->is_confidential = true; } static inline bool fpstate_is_confidential(struct fpu_guest *gfpu) { return gfpu->fpstate->is_confidential; } /* prctl */ extern long fpu_xstate_prctl(int option, unsigned long arg2); extern void fpu_idle_fpregs(void); #endif /* _ASM_X86_FPU_API_H */ |
| 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * include/net/l3mdev.h - L3 master device API * Copyright (c) 2015 Cumulus Networks * Copyright (c) 2015 David Ahern <dsa@cumulusnetworks.com> */ #ifndef _NET_L3MDEV_H_ #define _NET_L3MDEV_H_ #include <net/dst.h> #include <net/fib_rules.h> enum l3mdev_type { L3MDEV_TYPE_UNSPEC, L3MDEV_TYPE_VRF, __L3MDEV_TYPE_MAX }; #define L3MDEV_TYPE_MAX (__L3MDEV_TYPE_MAX - 1) typedef int (*lookup_by_table_id_t)(struct net *net, u32 table_d); /** * struct l3mdev_ops - l3mdev operations * * @l3mdev_fib_table: Get FIB table id to use for lookups * * @l3mdev_l3_rcv: Hook in L3 receive path * * @l3mdev_l3_out: Hook in L3 output path * * @l3mdev_link_scope_lookup: IPv6 lookup for linklocal and mcast destinations */ struct l3mdev_ops { u32 (*l3mdev_fib_table)(const struct net_device *dev); struct sk_buff * (*l3mdev_l3_rcv)(struct net_device *dev, struct sk_buff *skb, u16 proto); struct sk_buff * (*l3mdev_l3_out)(struct net_device *dev, struct sock *sk, struct sk_buff *skb, u16 proto); /* IPv6 ops */ struct dst_entry * (*l3mdev_link_scope_lookup)(const struct net_device *dev, struct flowi6 *fl6); }; #ifdef CONFIG_NET_L3_MASTER_DEV int l3mdev_table_lookup_register(enum l3mdev_type l3type, lookup_by_table_id_t fn); void l3mdev_table_lookup_unregister(enum l3mdev_type l3type, lookup_by_table_id_t fn); int l3mdev_ifindex_lookup_by_table_id(enum l3mdev_type l3type, struct net *net, u32 table_id); int l3mdev_fib_rule_match(struct net *net, struct flowi *fl, struct fib_lookup_arg *arg); void l3mdev_update_flow(struct net *net, struct flowi *fl); int l3mdev_master_ifindex_rcu(const struct net_device *dev); static inline int l3mdev_master_ifindex(struct net_device *dev) { int ifindex; rcu_read_lock(); ifindex = l3mdev_master_ifindex_rcu(dev); rcu_read_unlock(); return ifindex; } static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex) { struct net_device *dev; int rc = 0; if (likely(ifindex)) { rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); if (dev) rc = l3mdev_master_ifindex_rcu(dev); rcu_read_unlock(); } return rc; } static inline struct net_device *l3mdev_master_dev_rcu(const struct net_device *_dev) { /* netdev_master_upper_dev_get_rcu calls * list_first_or_null_rcu to walk the upper dev list. * list_first_or_null_rcu does not handle a const arg. We aren't * making changes, just want the master device from that list so * typecast to remove the const */ struct net_device *dev = (struct net_device *)_dev; struct net_device *master; if (!dev) return NULL; if (netif_is_l3_master(dev)) master = dev; else if (netif_is_l3_slave(dev)) master = netdev_master_upper_dev_get_rcu(dev); else master = NULL; return master; } int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex); static inline int l3mdev_master_upper_ifindex_by_index(struct net *net, int ifindex) { rcu_read_lock(); ifindex = l3mdev_master_upper_ifindex_by_index_rcu(net, ifindex); rcu_read_unlock(); return ifindex; } u32 l3mdev_fib_table_rcu(const struct net_device *dev); u32 l3mdev_fib_table_by_index(struct net *net, int ifindex); static inline u32 l3mdev_fib_table(const struct net_device *dev) { u32 tb_id; rcu_read_lock(); tb_id = l3mdev_fib_table_rcu(dev); rcu_read_unlock(); return tb_id; } static inline bool netif_index_is_l3_master(struct net *net, int ifindex) { struct net_device *dev; bool rc = false; if (ifindex == 0) return false; rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); if (dev) rc = netif_is_l3_master(dev); rcu_read_unlock(); return rc; } struct dst_entry *l3mdev_link_scope_lookup(struct net *net, struct flowi6 *fl6); static inline struct sk_buff *l3mdev_l3_rcv(struct sk_buff *skb, u16 proto) { struct net_device *master = NULL; if (netif_is_l3_slave(skb->dev)) master = netdev_master_upper_dev_get_rcu(skb->dev); else if (netif_is_l3_master(skb->dev) || netif_has_l3_rx_handler(skb->dev)) master = skb->dev; if (master && master->l3mdev_ops->l3mdev_l3_rcv) skb = master->l3mdev_ops->l3mdev_l3_rcv(master, skb, proto); return skb; } static inline struct sk_buff *l3mdev_ip_rcv(struct sk_buff *skb) { return l3mdev_l3_rcv(skb, AF_INET); } static inline struct sk_buff *l3mdev_ip6_rcv(struct sk_buff *skb) { return l3mdev_l3_rcv(skb, AF_INET6); } static inline struct sk_buff *l3mdev_l3_out(struct sock *sk, struct sk_buff *skb, u16 proto) { struct net_device *dev = skb_dst(skb)->dev; if (netif_is_l3_slave(dev)) { struct net_device *master; master = netdev_master_upper_dev_get_rcu(dev); if (master && master->l3mdev_ops->l3mdev_l3_out) skb = master->l3mdev_ops->l3mdev_l3_out(master, sk, skb, proto); } return skb; } static inline struct sk_buff *l3mdev_ip_out(struct sock *sk, struct sk_buff *skb) { return l3mdev_l3_out(sk, skb, AF_INET); } static inline struct sk_buff *l3mdev_ip6_out(struct sock *sk, struct sk_buff *skb) { return l3mdev_l3_out(sk, skb, AF_INET6); } #else static inline int l3mdev_master_ifindex_rcu(const struct net_device *dev) { return 0; } static inline int l3mdev_master_ifindex(struct net_device *dev) { return 0; } static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex) { return 0; } static inline int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex) { return 0; } static inline int l3mdev_master_upper_ifindex_by_index(struct net *net, int ifindex) { return 0; } static inline struct net_device *l3mdev_master_dev_rcu(const struct net_device *dev) { return NULL; } static inline u32 l3mdev_fib_table_rcu(const struct net_device *dev) { return 0; } static inline u32 l3mdev_fib_table(const struct net_device *dev) { return 0; } static inline u32 l3mdev_fib_table_by_index(struct net *net, int ifindex) { return 0; } static inline bool netif_index_is_l3_master(struct net *net, int ifindex) { return false; } static inline struct dst_entry *l3mdev_link_scope_lookup(struct net *net, struct flowi6 *fl6) { return NULL; } static inline struct sk_buff *l3mdev_ip_rcv(struct sk_buff *skb) { return skb; } static inline struct sk_buff *l3mdev_ip6_rcv(struct sk_buff *skb) { return skb; } static inline struct sk_buff *l3mdev_ip_out(struct sock *sk, struct sk_buff *skb) { return skb; } static inline struct sk_buff *l3mdev_ip6_out(struct sock *sk, struct sk_buff *skb) { return skb; } static inline int l3mdev_table_lookup_register(enum l3mdev_type l3type, lookup_by_table_id_t fn) { return -EOPNOTSUPP; } static inline void l3mdev_table_lookup_unregister(enum l3mdev_type l3type, lookup_by_table_id_t fn) { } static inline int l3mdev_ifindex_lookup_by_table_id(enum l3mdev_type l3type, struct net *net, u32 table_id) { return -ENODEV; } static inline int l3mdev_fib_rule_match(struct net *net, struct flowi *fl, struct fib_lookup_arg *arg) { return 1; } static inline void l3mdev_update_flow(struct net *net, struct flowi *fl) { } #endif #endif /* _NET_L3MDEV_H_ */ |
| 41 2 1 40 33 33 1 31 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 * Phillip Lougher <phillip@squashfs.org.uk> * * id.c */ /* * This file implements code to handle uids and gids. * * For space efficiency regular files store uid and gid indexes, which are * converted to 32-bit uids/gids using an id look up table. This table is * stored compressed into metadata blocks. A second index table is used to * locate these. This second index table for speed of access (and because it * is small) is read at mount time and cached in memory. */ #include <linux/fs.h> #include <linux/vfs.h> #include <linux/slab.h> #include "squashfs_fs.h" #include "squashfs_fs_sb.h" #include "squashfs.h" /* * Map uid/gid index into real 32-bit uid/gid using the id look up table */ int squashfs_get_id(struct super_block *sb, unsigned int index, unsigned int *id) { struct squashfs_sb_info *msblk = sb->s_fs_info; int block = SQUASHFS_ID_BLOCK(index); int offset = SQUASHFS_ID_BLOCK_OFFSET(index); u64 start_block; __le32 disk_id; int err; if (index >= msblk->ids) return -EINVAL; start_block = le64_to_cpu(msblk->id_table[block]); err = squashfs_read_metadata(sb, &disk_id, &start_block, &offset, sizeof(disk_id)); if (err < 0) return err; *id = le32_to_cpu(disk_id); return 0; } /* * Read uncompressed id lookup table indexes from disk into memory */ __le64 *squashfs_read_id_index_table(struct super_block *sb, u64 id_table_start, u64 next_table, unsigned short no_ids) { unsigned int length = SQUASHFS_ID_BLOCK_BYTES(no_ids); unsigned int indexes = SQUASHFS_ID_BLOCKS(no_ids); int n; __le64 *table; u64 start, end; TRACE("In read_id_index_table, length %d\n", length); /* Sanity check values */ /* there should always be at least one id */ if (no_ids == 0) return ERR_PTR(-EINVAL); /* * The computed size of the index table (length bytes) should exactly * match the table start and end points */ if (length != (next_table - id_table_start)) return ERR_PTR(-EINVAL); table = squashfs_read_table(sb, id_table_start, length); if (IS_ERR(table)) return table; /* * table[0], table[1], ... table[indexes - 1] store the locations * of the compressed id blocks. Each entry should be less than * the next (i.e. table[0] < table[1]), and the difference between them * should be SQUASHFS_METADATA_SIZE or less. table[indexes - 1] * should be less than id_table_start, and again the difference * should be SQUASHFS_METADATA_SIZE or less */ for (n = 0; n < (indexes - 1); n++) { start = le64_to_cpu(table[n]); end = le64_to_cpu(table[n + 1]); if (start >= end || (end - start) > (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } } start = le64_to_cpu(table[indexes - 1]); if (start >= id_table_start || (id_table_start - start) > (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } return table; } |
| 83 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * lzx_decompress.c - A decompressor for the LZX compression format, which can * be used in "System Compressed" files. This is based on the code from wimlib. * This code only supports a window size (dictionary size) of 32768 bytes, since * this is the only size used in System Compression. * * Copyright (C) 2015 Eric Biggers */ #include "decompress_common.h" #include "lib.h" /* Number of literal byte values */ #define LZX_NUM_CHARS 256 /* The smallest and largest allowed match lengths */ #define LZX_MIN_MATCH_LEN 2 #define LZX_MAX_MATCH_LEN 257 /* Number of distinct match lengths that can be represented */ #define LZX_NUM_LENS (LZX_MAX_MATCH_LEN - LZX_MIN_MATCH_LEN + 1) /* Number of match lengths for which no length symbol is required */ #define LZX_NUM_PRIMARY_LENS 7 #define LZX_NUM_LEN_HEADERS (LZX_NUM_PRIMARY_LENS + 1) /* Valid values of the 3-bit block type field */ #define LZX_BLOCKTYPE_VERBATIM 1 #define LZX_BLOCKTYPE_ALIGNED 2 #define LZX_BLOCKTYPE_UNCOMPRESSED 3 /* Number of offset slots for a window size of 32768 */ #define LZX_NUM_OFFSET_SLOTS 30 /* Number of symbols in the main code for a window size of 32768 */ #define LZX_MAINCODE_NUM_SYMBOLS \ (LZX_NUM_CHARS + (LZX_NUM_OFFSET_SLOTS * LZX_NUM_LEN_HEADERS)) /* Number of symbols in the length code */ #define LZX_LENCODE_NUM_SYMBOLS (LZX_NUM_LENS - LZX_NUM_PRIMARY_LENS) /* Number of symbols in the precode */ #define LZX_PRECODE_NUM_SYMBOLS 20 /* Number of bits in which each precode codeword length is represented */ #define LZX_PRECODE_ELEMENT_SIZE 4 /* Number of low-order bits of each match offset that are entropy-encoded in * aligned offset blocks */ #define LZX_NUM_ALIGNED_OFFSET_BITS 3 /* Number of symbols in the aligned offset code */ #define LZX_ALIGNEDCODE_NUM_SYMBOLS (1 << LZX_NUM_ALIGNED_OFFSET_BITS) /* Mask for the match offset bits that are entropy-encoded in aligned offset * blocks */ #define LZX_ALIGNED_OFFSET_BITMASK ((1 << LZX_NUM_ALIGNED_OFFSET_BITS) - 1) /* Number of bits in which each aligned offset codeword length is represented */ #define LZX_ALIGNEDCODE_ELEMENT_SIZE 3 /* Maximum lengths (in bits) of the codewords in each Huffman code */ #define LZX_MAX_MAIN_CODEWORD_LEN 16 #define LZX_MAX_LEN_CODEWORD_LEN 16 #define LZX_MAX_PRE_CODEWORD_LEN ((1 << LZX_PRECODE_ELEMENT_SIZE) - 1) #define LZX_MAX_ALIGNED_CODEWORD_LEN ((1 << LZX_ALIGNEDCODE_ELEMENT_SIZE) - 1) /* The default "filesize" value used in pre/post-processing. In the LZX format * used in cabinet files this value must be given to the decompressor, whereas * in the LZX format used in WIM files and system-compressed files this value is * fixed at 12000000. */ #define LZX_DEFAULT_FILESIZE 12000000 /* Assumed block size when the encoded block size begins with a 0 bit. */ #define LZX_DEFAULT_BLOCK_SIZE 32768 /* Number of offsets in the recent (or "repeat") offsets queue. */ #define LZX_NUM_RECENT_OFFSETS 3 /* These values are chosen for fast decompression. */ #define LZX_MAINCODE_TABLEBITS 11 #define LZX_LENCODE_TABLEBITS 10 #define LZX_PRECODE_TABLEBITS 6 #define LZX_ALIGNEDCODE_TABLEBITS 7 #define LZX_READ_LENS_MAX_OVERRUN 50 /* Mapping: offset slot => first match offset that uses that offset slot. */ static const u32 lzx_offset_slot_base[LZX_NUM_OFFSET_SLOTS + 1] = { 0, 1, 2, 3, 4, /* 0 --- 4 */ 6, 8, 12, 16, 24, /* 5 --- 9 */ 32, 48, 64, 96, 128, /* 10 --- 14 */ 192, 256, 384, 512, 768, /* 15 --- 19 */ 1024, 1536, 2048, 3072, 4096, /* 20 --- 24 */ 6144, 8192, 12288, 16384, 24576, /* 25 --- 29 */ 32768, /* extra */ }; /* Mapping: offset slot => how many extra bits must be read and added to the * corresponding offset slot base to decode the match offset. */ static const u8 lzx_extra_offset_bits[LZX_NUM_OFFSET_SLOTS] = { 0, 0, 0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8, 9, 9, 10, 10, 11, 11, 12, 12, 13, 13, }; /* Reusable heap-allocated memory for LZX decompression */ struct lzx_decompressor { /* Huffman decoding tables, and arrays that map symbols to codeword * lengths */ u16 maincode_decode_table[(1 << LZX_MAINCODE_TABLEBITS) + (LZX_MAINCODE_NUM_SYMBOLS * 2)]; u8 maincode_lens[LZX_MAINCODE_NUM_SYMBOLS + LZX_READ_LENS_MAX_OVERRUN]; u16 lencode_decode_table[(1 << LZX_LENCODE_TABLEBITS) + (LZX_LENCODE_NUM_SYMBOLS * 2)]; u8 lencode_lens[LZX_LENCODE_NUM_SYMBOLS + LZX_READ_LENS_MAX_OVERRUN]; u16 alignedcode_decode_table[(1 << LZX_ALIGNEDCODE_TABLEBITS) + (LZX_ALIGNEDCODE_NUM_SYMBOLS * 2)]; u8 alignedcode_lens[LZX_ALIGNEDCODE_NUM_SYMBOLS]; u16 precode_decode_table[(1 << LZX_PRECODE_TABLEBITS) + (LZX_PRECODE_NUM_SYMBOLS * 2)]; u8 precode_lens[LZX_PRECODE_NUM_SYMBOLS]; /* Temporary space for make_huffman_decode_table() */ u16 working_space[2 * (1 + LZX_MAX_MAIN_CODEWORD_LEN) + LZX_MAINCODE_NUM_SYMBOLS]; }; static void undo_e8_translation(void *target, s32 input_pos) { s32 abs_offset, rel_offset; abs_offset = get_unaligned_le32(target); if (abs_offset >= 0) { if (abs_offset < LZX_DEFAULT_FILESIZE) { /* "good translation" */ rel_offset = abs_offset - input_pos; put_unaligned_le32(rel_offset, target); } } else { if (abs_offset >= -input_pos) { /* "compensating translation" */ rel_offset = abs_offset + LZX_DEFAULT_FILESIZE; put_unaligned_le32(rel_offset, target); } } } /* * Undo the 'E8' preprocessing used in LZX. Before compression, the * uncompressed data was preprocessed by changing the targets of suspected x86 * CALL instructions from relative offsets to absolute offsets. After * match/literal decoding, the decompressor must undo the translation. */ static void lzx_postprocess(u8 *data, u32 size) { /* * A worthwhile optimization is to push the end-of-buffer check into the * relatively rare E8 case. This is possible if we replace the last six * bytes of data with E8 bytes; then we are guaranteed to hit an E8 byte * before reaching end-of-buffer. In addition, this scheme guarantees * that no translation can begin following an E8 byte in the last 10 * bytes because a 4-byte offset containing E8 as its high byte is a * large negative number that is not valid for translation. That is * exactly what we need. */ u8 *tail; u8 saved_bytes[6]; u8 *p; if (size <= 10) return; tail = &data[size - 6]; memcpy(saved_bytes, tail, 6); memset(tail, 0xE8, 6); p = data; for (;;) { while (*p != 0xE8) p++; if (p >= tail) break; undo_e8_translation(p + 1, p - data); p += 5; } memcpy(tail, saved_bytes, 6); } /* Read a Huffman-encoded symbol using the precode. */ static forceinline u32 read_presym(const struct lzx_decompressor *d, struct input_bitstream *is) { return read_huffsym(is, d->precode_decode_table, LZX_PRECODE_TABLEBITS, LZX_MAX_PRE_CODEWORD_LEN); } /* Read a Huffman-encoded symbol using the main code. */ static forceinline u32 read_mainsym(const struct lzx_decompressor *d, struct input_bitstream *is) { return read_huffsym(is, d->maincode_decode_table, LZX_MAINCODE_TABLEBITS, LZX_MAX_MAIN_CODEWORD_LEN); } /* Read a Huffman-encoded symbol using the length code. */ static forceinline u32 read_lensym(const struct lzx_decompressor *d, struct input_bitstream *is) { return read_huffsym(is, d->lencode_decode_table, LZX_LENCODE_TABLEBITS, LZX_MAX_LEN_CODEWORD_LEN); } /* Read a Huffman-encoded symbol using the aligned offset code. */ static forceinline u32 read_alignedsym(const struct lzx_decompressor *d, struct input_bitstream *is) { return read_huffsym(is, d->alignedcode_decode_table, LZX_ALIGNEDCODE_TABLEBITS, LZX_MAX_ALIGNED_CODEWORD_LEN); } /* * Read the precode from the compressed input bitstream, then use it to decode * @num_lens codeword length values. * * @is: The input bitstream. * * @lens: An array that contains the length values from the previous time * the codeword lengths for this Huffman code were read, or all 0's * if this is the first time. This array must have at least * (@num_lens + LZX_READ_LENS_MAX_OVERRUN) entries. * * @num_lens: Number of length values to decode. * * Returns 0 on success, or -1 if the data was invalid. */ static int lzx_read_codeword_lens(struct lzx_decompressor *d, struct input_bitstream *is, u8 *lens, u32 num_lens) { u8 *len_ptr = lens; u8 *lens_end = lens + num_lens; int i; /* Read the lengths of the precode codewords. These are given * explicitly. */ for (i = 0; i < LZX_PRECODE_NUM_SYMBOLS; i++) { d->precode_lens[i] = bitstream_read_bits(is, LZX_PRECODE_ELEMENT_SIZE); } /* Make the decoding table for the precode. */ if (make_huffman_decode_table(d->precode_decode_table, LZX_PRECODE_NUM_SYMBOLS, LZX_PRECODE_TABLEBITS, d->precode_lens, LZX_MAX_PRE_CODEWORD_LEN, d->working_space)) return -1; /* Decode the codeword lengths. */ do { u32 presym; u8 len; /* Read the next precode symbol. */ presym = read_presym(d, is); if (presym < 17) { /* Difference from old length */ len = *len_ptr - presym; if ((s8)len < 0) len += 17; *len_ptr++ = len; } else { /* Special RLE values */ u32 run_len; if (presym == 17) { /* Run of 0's */ run_len = 4 + bitstream_read_bits(is, 4); len = 0; } else if (presym == 18) { /* Longer run of 0's */ run_len = 20 + bitstream_read_bits(is, 5); len = 0; } else { /* Run of identical lengths */ run_len = 4 + bitstream_read_bits(is, 1); presym = read_presym(d, is); if (presym > 17) return -1; len = *len_ptr - presym; if ((s8)len < 0) len += 17; } do { *len_ptr++ = len; } while (--run_len); /* Worst case overrun is when presym == 18, * run_len == 20 + 31, and only 1 length was remaining. * So LZX_READ_LENS_MAX_OVERRUN == 50. * * Overrun while reading the first half of maincode_lens * can corrupt the previous values in the second half. * This doesn't really matter because the resulting * lengths will still be in range, and data that * generates overruns is invalid anyway. */ } } while (len_ptr < lens_end); return 0; } /* * Read the header of an LZX block and save the block type and (uncompressed) * size in *block_type_ret and *block_size_ret, respectively. * * If the block is compressed, also update the Huffman decode @tables with the * new Huffman codes. If the block is uncompressed, also update the match * offset @queue with the new match offsets. * * Return 0 on success, or -1 if the data was invalid. */ static int lzx_read_block_header(struct lzx_decompressor *d, struct input_bitstream *is, int *block_type_ret, u32 *block_size_ret, u32 recent_offsets[]) { int block_type; u32 block_size; int i; bitstream_ensure_bits(is, 4); /* The first three bits tell us what kind of block it is, and should be * one of the LZX_BLOCKTYPE_* values. */ block_type = bitstream_pop_bits(is, 3); /* Read the block size. */ if (bitstream_pop_bits(is, 1)) { block_size = LZX_DEFAULT_BLOCK_SIZE; } else { block_size = 0; block_size |= bitstream_read_bits(is, 8); block_size <<= 8; block_size |= bitstream_read_bits(is, 8); } switch (block_type) { case LZX_BLOCKTYPE_ALIGNED: /* Read the aligned offset code and prepare its decode table. */ for (i = 0; i < LZX_ALIGNEDCODE_NUM_SYMBOLS; i++) { d->alignedcode_lens[i] = bitstream_read_bits(is, LZX_ALIGNEDCODE_ELEMENT_SIZE); } if (make_huffman_decode_table(d->alignedcode_decode_table, LZX_ALIGNEDCODE_NUM_SYMBOLS, LZX_ALIGNEDCODE_TABLEBITS, d->alignedcode_lens, LZX_MAX_ALIGNED_CODEWORD_LEN, d->working_space)) return -1; /* Fall though, since the rest of the header for aligned offset * blocks is the same as that for verbatim blocks. */ fallthrough; case LZX_BLOCKTYPE_VERBATIM: /* Read the main code and prepare its decode table. * * Note that the codeword lengths in the main code are encoded * in two parts: one part for literal symbols, and one part for * match symbols. */ if (lzx_read_codeword_lens(d, is, d->maincode_lens, LZX_NUM_CHARS)) return -1; if (lzx_read_codeword_lens(d, is, d->maincode_lens + LZX_NUM_CHARS, LZX_MAINCODE_NUM_SYMBOLS - LZX_NUM_CHARS)) return -1; if (make_huffman_decode_table(d->maincode_decode_table, LZX_MAINCODE_NUM_SYMBOLS, LZX_MAINCODE_TABLEBITS, d->maincode_lens, LZX_MAX_MAIN_CODEWORD_LEN, d->working_space)) return -1; /* Read the length code and prepare its decode table. */ if (lzx_read_codeword_lens(d, is, d->lencode_lens, LZX_LENCODE_NUM_SYMBOLS)) return -1; if (make_huffman_decode_table(d->lencode_decode_table, LZX_LENCODE_NUM_SYMBOLS, LZX_LENCODE_TABLEBITS, d->lencode_lens, LZX_MAX_LEN_CODEWORD_LEN, d->working_space)) return -1; break; case LZX_BLOCKTYPE_UNCOMPRESSED: /* Before reading the three recent offsets from the uncompressed * block header, the stream must be aligned on a 16-bit * boundary. But if the stream is *already* aligned, then the * next 16 bits must be discarded. */ bitstream_ensure_bits(is, 1); bitstream_align(is); recent_offsets[0] = bitstream_read_u32(is); recent_offsets[1] = bitstream_read_u32(is); recent_offsets[2] = bitstream_read_u32(is); /* Offsets of 0 are invalid. */ if (recent_offsets[0] == 0 || recent_offsets[1] == 0 || recent_offsets[2] == 0) return -1; break; default: /* Unrecognized block type. */ return -1; } *block_type_ret = block_type; *block_size_ret = block_size; return 0; } /* Decompress a block of LZX-compressed data. */ static int lzx_decompress_block(const struct lzx_decompressor *d, struct input_bitstream *is, int block_type, u32 block_size, u8 * const out_begin, u8 *out_next, u32 recent_offsets[]) { u8 * const block_end = out_next + block_size; u32 ones_if_aligned = 0U - (block_type == LZX_BLOCKTYPE_ALIGNED); do { u32 mainsym; u32 match_len; u32 match_offset; u32 offset_slot; u32 num_extra_bits; mainsym = read_mainsym(d, is); if (mainsym < LZX_NUM_CHARS) { /* Literal */ *out_next++ = mainsym; continue; } /* Match */ /* Decode the length header and offset slot. */ mainsym -= LZX_NUM_CHARS; match_len = mainsym % LZX_NUM_LEN_HEADERS; offset_slot = mainsym / LZX_NUM_LEN_HEADERS; /* If needed, read a length symbol to decode the full length. */ if (match_len == LZX_NUM_PRIMARY_LENS) match_len += read_lensym(d, is); match_len += LZX_MIN_MATCH_LEN; if (offset_slot < LZX_NUM_RECENT_OFFSETS) { /* Repeat offset */ /* Note: This isn't a real LRU queue, since using the R2 * offset doesn't bump the R1 offset down to R2. This * quirk allows all 3 recent offsets to be handled by * the same code. (For R0, the swap is a no-op.) */ match_offset = recent_offsets[offset_slot]; recent_offsets[offset_slot] = recent_offsets[0]; recent_offsets[0] = match_offset; } else { /* Explicit offset */ /* Look up the number of extra bits that need to be read * to decode offsets with this offset slot. */ num_extra_bits = lzx_extra_offset_bits[offset_slot]; /* Start with the offset slot base value. */ match_offset = lzx_offset_slot_base[offset_slot]; /* In aligned offset blocks, the low-order 3 bits of * each offset are encoded using the aligned offset * code. Otherwise, all the extra bits are literal. */ if ((num_extra_bits & ones_if_aligned) >= LZX_NUM_ALIGNED_OFFSET_BITS) { match_offset += bitstream_read_bits(is, num_extra_bits - LZX_NUM_ALIGNED_OFFSET_BITS) << LZX_NUM_ALIGNED_OFFSET_BITS; match_offset += read_alignedsym(d, is); } else { match_offset += bitstream_read_bits(is, num_extra_bits); } /* Adjust the offset. */ match_offset -= (LZX_NUM_RECENT_OFFSETS - 1); /* Update the recent offsets. */ recent_offsets[2] = recent_offsets[1]; recent_offsets[1] = recent_offsets[0]; recent_offsets[0] = match_offset; } /* Validate the match, then copy it to the current position. */ if (match_len > (size_t)(block_end - out_next)) return -1; if (match_offset > (size_t)(out_next - out_begin)) return -1; out_next = lz_copy(out_next, match_len, match_offset, block_end, LZX_MIN_MATCH_LEN); } while (out_next != block_end); return 0; } /* * lzx_allocate_decompressor - Allocate an LZX decompressor * * Return the pointer to the decompressor on success, or return NULL and set * errno on failure. */ struct lzx_decompressor *lzx_allocate_decompressor(void) { return kmalloc(sizeof(struct lzx_decompressor), GFP_NOFS); } /* * lzx_decompress - Decompress a buffer of LZX-compressed data * * @decompressor: A decompressor allocated with lzx_allocate_decompressor() * @compressed_data: The buffer of data to decompress * @compressed_size: Number of bytes of compressed data * @uncompressed_data: The buffer in which to store the decompressed data * @uncompressed_size: The number of bytes the data decompresses into * * Return 0 on success, or return -1 and set errno on failure. */ int lzx_decompress(struct lzx_decompressor *decompressor, const void *compressed_data, size_t compressed_size, void *uncompressed_data, size_t uncompressed_size) { struct lzx_decompressor *d = decompressor; u8 * const out_begin = uncompressed_data; u8 *out_next = out_begin; u8 * const out_end = out_begin + uncompressed_size; struct input_bitstream is; u32 recent_offsets[LZX_NUM_RECENT_OFFSETS] = {1, 1, 1}; int e8_status = 0; init_input_bitstream(&is, compressed_data, compressed_size); /* Codeword lengths begin as all 0's for delta encoding purposes. */ memset(d->maincode_lens, 0, LZX_MAINCODE_NUM_SYMBOLS); memset(d->lencode_lens, 0, LZX_LENCODE_NUM_SYMBOLS); /* Decompress blocks until we have all the uncompressed data. */ while (out_next != out_end) { int block_type; u32 block_size; if (lzx_read_block_header(d, &is, &block_type, &block_size, recent_offsets)) goto invalid; if (block_size < 1 || block_size > (size_t)(out_end - out_next)) goto invalid; if (block_type != LZX_BLOCKTYPE_UNCOMPRESSED) { /* Compressed block */ if (lzx_decompress_block(d, &is, block_type, block_size, out_begin, out_next, recent_offsets)) goto invalid; e8_status |= d->maincode_lens[0xe8]; out_next += block_size; } else { /* Uncompressed block */ out_next = bitstream_read_bytes(&is, out_next, block_size); if (!out_next) goto invalid; if (block_size & 1) bitstream_read_byte(&is); e8_status = 1; } } /* Postprocess the data unless it cannot possibly contain 0xe8 bytes. */ if (e8_status) lzx_postprocess(uncompressed_data, uncompressed_size); return 0; invalid: return -1; } /* * lzx_free_decompressor - Free an LZX decompressor * * @decompressor: A decompressor that was allocated with * lzx_allocate_decompressor(), or NULL. */ void lzx_free_decompressor(struct lzx_decompressor *decompressor) { kfree(decompressor); } |
| 943 995 943 943 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * net/dst.h Protocol independent destination cache definitions. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * */ #ifndef _NET_DST_H #define _NET_DST_H #include <net/dst_ops.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/rcupdate.h> #include <linux/bug.h> #include <linux/jiffies.h> #include <linux/refcount.h> #include <linux/rcuref.h> #include <net/neighbour.h> #include <asm/processor.h> #include <linux/indirect_call_wrapper.h> struct sk_buff; struct dst_entry { struct net_device *dev; struct dst_ops *ops; unsigned long _metrics; unsigned long expires; #ifdef CONFIG_XFRM struct xfrm_state *xfrm; #else void *__pad1; #endif int (*input)(struct sk_buff *); int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); unsigned short flags; #define DST_NOXFRM 0x0002 #define DST_NOPOLICY 0x0004 #define DST_NOCOUNT 0x0008 #define DST_FAKE_RTABLE 0x0010 #define DST_XFRM_TUNNEL 0x0020 #define DST_XFRM_QUEUE 0x0040 #define DST_METADATA 0x0080 /* A non-zero value of dst->obsolete forces by-hand validation * of the route entry. Positive values are set by the generic * dst layer to indicate that the entry has been forcefully * destroyed. * * Negative values are used by the implementation layer code to * force invocation of the dst_ops->check() method. */ short obsolete; #define DST_OBSOLETE_NONE 0 #define DST_OBSOLETE_DEAD 2 #define DST_OBSOLETE_FORCE_CHK -1 #define DST_OBSOLETE_KILL -2 unsigned short header_len; /* more space at head required */ unsigned short trailer_len; /* space to reserve at tail */ /* * __rcuref wants to be on a different cache line from * input/output/ops or performance tanks badly */ #ifdef CONFIG_64BIT rcuref_t __rcuref; /* 64-bit offset 64 */ #endif int __use; unsigned long lastuse; struct rcu_head rcu_head; short error; short __pad; __u32 tclassid; #ifndef CONFIG_64BIT struct lwtunnel_state *lwtstate; rcuref_t __rcuref; /* 32-bit offset 64 */ #endif netdevice_tracker dev_tracker; /* * Used by rtable and rt6_info. Moves lwtstate into the next cache * line on 64bit so that lwtstate does not cause false sharing with * __rcuref under contention of __rcuref. This also puts the * frequently accessed members of rtable and rt6_info out of the * __rcuref cache line. */ struct list_head rt_uncached; struct uncached_list *rt_uncached_list; #ifdef CONFIG_64BIT struct lwtunnel_state *lwtstate; #endif }; struct dst_metrics { u32 metrics[RTAX_MAX]; refcount_t refcnt; } __aligned(4); /* Low pointer bits contain DST_METRICS_FLAGS */ extern const struct dst_metrics dst_default_metrics; u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old); #define DST_METRICS_READ_ONLY 0x1UL #define DST_METRICS_REFCOUNTED 0x2UL #define DST_METRICS_FLAGS 0x3UL #define __DST_METRICS_PTR(Y) \ ((u32 *)((Y) & ~DST_METRICS_FLAGS)) #define DST_METRICS_PTR(X) __DST_METRICS_PTR((X)->_metrics) static inline bool dst_metrics_read_only(const struct dst_entry *dst) { return dst->_metrics & DST_METRICS_READ_ONLY; } void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old); static inline void dst_destroy_metrics_generic(struct dst_entry *dst) { unsigned long val = dst->_metrics; if (!(val & DST_METRICS_READ_ONLY)) __dst_destroy_metrics_generic(dst, val); } static inline u32 *dst_metrics_write_ptr(struct dst_entry *dst) { unsigned long p = dst->_metrics; BUG_ON(!p); if (p & DST_METRICS_READ_ONLY) return dst->ops->cow_metrics(dst, p); return __DST_METRICS_PTR(p); } /* This may only be invoked before the entry has reached global * visibility. */ static inline void dst_init_metrics(struct dst_entry *dst, const u32 *src_metrics, bool read_only) { dst->_metrics = ((unsigned long) src_metrics) | (read_only ? DST_METRICS_READ_ONLY : 0); } static inline void dst_copy_metrics(struct dst_entry *dest, const struct dst_entry *src) { u32 *dst_metrics = dst_metrics_write_ptr(dest); if (dst_metrics) { u32 *src_metrics = DST_METRICS_PTR(src); memcpy(dst_metrics, src_metrics, RTAX_MAX * sizeof(u32)); } } static inline u32 *dst_metrics_ptr(struct dst_entry *dst) { return DST_METRICS_PTR(dst); } static inline u32 dst_metric_raw(const struct dst_entry *dst, const int metric) { u32 *p = DST_METRICS_PTR(dst); return p[metric-1]; } static inline u32 dst_metric(const struct dst_entry *dst, const int metric) { WARN_ON_ONCE(metric == RTAX_HOPLIMIT || metric == RTAX_ADVMSS || metric == RTAX_MTU); return dst_metric_raw(dst, metric); } static inline u32 dst_metric_advmss(const struct dst_entry *dst) { u32 advmss = dst_metric_raw(dst, RTAX_ADVMSS); if (!advmss) advmss = dst->ops->default_advmss(dst); return advmss; } static inline void dst_metric_set(struct dst_entry *dst, int metric, u32 val) { u32 *p = dst_metrics_write_ptr(dst); if (p) p[metric-1] = val; } /* Kernel-internal feature bits that are unallocated in user space. */ #define DST_FEATURE_ECN_CA (1U << 31) #define DST_FEATURE_MASK (DST_FEATURE_ECN_CA) #define DST_FEATURE_ECN_MASK (DST_FEATURE_ECN_CA | RTAX_FEATURE_ECN) static inline u32 dst_feature(const struct dst_entry *dst, u32 feature) { return dst_metric(dst, RTAX_FEATURES) & feature; } INDIRECT_CALLABLE_DECLARE(unsigned int ip6_mtu(const struct dst_entry *)); INDIRECT_CALLABLE_DECLARE(unsigned int ipv4_mtu(const struct dst_entry *)); static inline u32 dst_mtu(const struct dst_entry *dst) { return INDIRECT_CALL_INET(dst->ops->mtu, ip6_mtu, ipv4_mtu, dst); } /* RTT metrics are stored in milliseconds for user ABI, but used as jiffies */ static inline unsigned long dst_metric_rtt(const struct dst_entry *dst, int metric) { return msecs_to_jiffies(dst_metric(dst, metric)); } static inline int dst_metric_locked(const struct dst_entry *dst, int metric) { return dst_metric(dst, RTAX_LOCK) & (1 << metric); } static inline void dst_hold(struct dst_entry *dst) { /* * If your kernel compilation stops here, please check * the placement of __rcuref in struct dst_entry */ BUILD_BUG_ON(offsetof(struct dst_entry, __rcuref) & 63); WARN_ON(!rcuref_get(&dst->__rcuref)); } static inline void dst_use_noref(struct dst_entry *dst, unsigned long time) { if (unlikely(time != dst->lastuse)) { dst->__use++; dst->lastuse = time; } } static inline struct dst_entry *dst_clone(struct dst_entry *dst) { if (dst) dst_hold(dst); return dst; } void dst_release(struct dst_entry *dst); void dst_release_immediate(struct dst_entry *dst); static inline void refdst_drop(unsigned long refdst) { if (!(refdst & SKB_DST_NOREF)) dst_release((struct dst_entry *)(refdst & SKB_DST_PTRMASK)); } /** * skb_dst_drop - drops skb dst * @skb: buffer * * Drops dst reference count if a reference was taken. */ static inline void skb_dst_drop(struct sk_buff *skb) { if (skb->_skb_refdst) { refdst_drop(skb->_skb_refdst); skb->_skb_refdst = 0UL; } } static inline void __skb_dst_copy(struct sk_buff *nskb, unsigned long refdst) { nskb->slow_gro |= !!refdst; nskb->_skb_refdst = refdst; if (!(nskb->_skb_refdst & SKB_DST_NOREF)) dst_clone(skb_dst(nskb)); } static inline void skb_dst_copy(struct sk_buff *nskb, const struct sk_buff *oskb) { __skb_dst_copy(nskb, oskb->_skb_refdst); } /** * dst_hold_safe - Take a reference on a dst if possible * @dst: pointer to dst entry * * This helper returns false if it could not safely * take a reference on a dst. */ static inline bool dst_hold_safe(struct dst_entry *dst) { return rcuref_get(&dst->__rcuref); } /** * skb_dst_force - makes sure skb dst is refcounted * @skb: buffer * * If dst is not yet refcounted and not destroyed, grab a ref on it. * Returns true if dst is refcounted. */ static inline bool skb_dst_force(struct sk_buff *skb) { if (skb_dst_is_noref(skb)) { struct dst_entry *dst = skb_dst(skb); WARN_ON(!rcu_read_lock_held()); if (!dst_hold_safe(dst)) dst = NULL; skb->_skb_refdst = (unsigned long)dst; skb->slow_gro |= !!dst; } return skb->_skb_refdst != 0UL; } /** * __skb_tunnel_rx - prepare skb for rx reinsert * @skb: buffer * @dev: tunnel device * @net: netns for packet i/o * * After decapsulation, packet is going to re-enter (netif_rx()) our stack, * so make some cleanups. (no accounting done) */ static inline void __skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, struct net *net) { skb->dev = dev; /* * Clear hash so that we can recalulate the hash for the * encapsulated packet, unless we have already determine the hash * over the L4 4-tuple. */ skb_clear_hash_if_not_l4(skb); skb_set_queue_mapping(skb, 0); skb_scrub_packet(skb, !net_eq(net, dev_net(dev))); } /** * skb_tunnel_rx - prepare skb for rx reinsert * @skb: buffer * @dev: tunnel device * @net: netns for packet i/o * * After decapsulation, packet is going to re-enter (netif_rx()) our stack, * so make some cleanups, and perform accounting. * Note: this accounting is not SMP safe. */ static inline void skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, struct net *net) { DEV_STATS_INC(dev, rx_packets); DEV_STATS_ADD(dev, rx_bytes, skb->len); __skb_tunnel_rx(skb, dev, net); } static inline u32 dst_tclassid(const struct sk_buff *skb) { #ifdef CONFIG_IP_ROUTE_CLASSID const struct dst_entry *dst; dst = skb_dst(skb); if (dst) return dst->tclassid; #endif return 0; } int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb); static inline int dst_discard(struct sk_buff *skb) { return dst_discard_out(&init_net, skb->sk, skb); } void *dst_alloc(struct dst_ops *ops, struct net_device *dev, int initial_obsolete, unsigned short flags); void dst_init(struct dst_entry *dst, struct dst_ops *ops, struct net_device *dev, int initial_obsolete, unsigned short flags); void dst_dev_put(struct dst_entry *dst); static inline void dst_confirm(struct dst_entry *dst) { } static inline struct neighbour *dst_neigh_lookup(const struct dst_entry *dst, const void *daddr) { struct neighbour *n = dst->ops->neigh_lookup(dst, NULL, daddr); return IS_ERR(n) ? NULL : n; } static inline struct neighbour *dst_neigh_lookup_skb(const struct dst_entry *dst, struct sk_buff *skb) { struct neighbour *n; if (WARN_ON_ONCE(!dst->ops->neigh_lookup)) return NULL; n = dst->ops->neigh_lookup(dst, skb, NULL); return IS_ERR(n) ? NULL : n; } static inline void dst_confirm_neigh(const struct dst_entry *dst, const void *daddr) { if (dst->ops->confirm_neigh) dst->ops->confirm_neigh(dst, daddr); } static inline void dst_link_failure(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); if (dst && dst->ops && dst->ops->link_failure) dst->ops->link_failure(skb); } static inline void dst_set_expires(struct dst_entry *dst, int timeout) { unsigned long expires = jiffies + timeout; if (expires == 0) expires = 1; if (dst->expires == 0 || time_before(expires, dst->expires)) dst->expires = expires; } INDIRECT_CALLABLE_DECLARE(int ip6_output(struct net *, struct sock *, struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int ip_output(struct net *, struct sock *, struct sk_buff *)); /* Output packet to network from transport. */ static inline int dst_output(struct net *net, struct sock *sk, struct sk_buff *skb) { return INDIRECT_CALL_INET(skb_dst(skb)->output, ip6_output, ip_output, net, sk, skb); } INDIRECT_CALLABLE_DECLARE(int ip6_input(struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int ip_local_deliver(struct sk_buff *)); /* Input packet from network to transport. */ static inline int dst_input(struct sk_buff *skb) { return INDIRECT_CALL_INET(skb_dst(skb)->input, ip6_input, ip_local_deliver, skb); } INDIRECT_CALLABLE_DECLARE(struct dst_entry *ip6_dst_check(struct dst_entry *, u32)); INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *, u32)); static inline struct dst_entry *dst_check(struct dst_entry *dst, u32 cookie) { if (dst->obsolete) dst = INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check, ipv4_dst_check, dst, cookie); return dst; } /* Flags for xfrm_lookup flags argument. */ enum { XFRM_LOOKUP_ICMP = 1 << 0, XFRM_LOOKUP_QUEUE = 1 << 1, XFRM_LOOKUP_KEEP_DST_REF = 1 << 2, }; struct flowi; #ifndef CONFIG_XFRM static inline struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags) { return dst_orig; } static inline struct dst_entry * xfrm_lookup_with_ifid(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags, u32 if_id) { return dst_orig; } static inline struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags) { return dst_orig; } static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst) { return NULL; } #else struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags); struct dst_entry *xfrm_lookup_with_ifid(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags, u32 if_id); struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags); /* skb attached with this dst needs transformation if dst->xfrm is valid */ static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst) { return dst->xfrm; } #endif static inline void skb_dst_update_pmtu(struct sk_buff *skb, u32 mtu) { struct dst_entry *dst = skb_dst(skb); if (dst && dst->ops->update_pmtu) dst->ops->update_pmtu(dst, NULL, skb, mtu, true); } /* update dst pmtu but not do neighbor confirm */ static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu) { struct dst_entry *dst = skb_dst(skb); if (dst && dst->ops->update_pmtu) dst->ops->update_pmtu(dst, NULL, skb, mtu, false); } struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie); void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh); void dst_blackhole_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); u32 *dst_blackhole_cow_metrics(struct dst_entry *dst, unsigned long old); struct neighbour *dst_blackhole_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr); unsigned int dst_blackhole_mtu(const struct dst_entry *dst); #endif /* _NET_DST_H */ |
| 800 802 802 789 592 33 1 168 795 789 899 104 785 17 801 796 773 17 855 856 856 855 856 856 856 855 853 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2005,2006,2007,2008 IBM Corporation * * Authors: * Mimi Zohar <zohar@us.ibm.com> * Kylene Hall <kjhall@us.ibm.com> * * File: ima_crypto.c * Calculates md5/sha1 file hash, template hash, boot-aggreate hash */ #include <linux/kernel.h> #include <linux/moduleparam.h> #include <linux/ratelimit.h> #include <linux/file.h> #include <linux/crypto.h> #include <linux/scatterlist.h> #include <linux/err.h> #include <linux/slab.h> #include <crypto/hash.h> #include "ima.h" /* minimum file size for ahash use */ static unsigned long ima_ahash_minsize; module_param_named(ahash_minsize, ima_ahash_minsize, ulong, 0644); MODULE_PARM_DESC(ahash_minsize, "Minimum file size for ahash use"); /* default is 0 - 1 page. */ static int ima_maxorder; static unsigned int ima_bufsize = PAGE_SIZE; static int param_set_bufsize(const char *val, const struct kernel_param *kp) { unsigned long long size; int order; size = memparse(val, NULL); order = get_order(size); if (order > MAX_PAGE_ORDER) return -EINVAL; ima_maxorder = order; ima_bufsize = PAGE_SIZE << order; return 0; } static const struct kernel_param_ops param_ops_bufsize = { .set = param_set_bufsize, .get = param_get_uint, }; #define param_check_bufsize(name, p) __param_check(name, p, unsigned int) module_param_named(ahash_bufsize, ima_bufsize, bufsize, 0644); MODULE_PARM_DESC(ahash_bufsize, "Maximum ahash buffer size"); static struct crypto_shash *ima_shash_tfm; static struct crypto_ahash *ima_ahash_tfm; int ima_sha1_idx __ro_after_init; int ima_hash_algo_idx __ro_after_init; /* * Additional number of slots reserved, as needed, for SHA1 * and IMA default algo. */ int ima_extra_slots __ro_after_init; struct ima_algo_desc *ima_algo_array __ro_after_init; static int __init ima_init_ima_crypto(void) { long rc; ima_shash_tfm = crypto_alloc_shash(hash_algo_name[ima_hash_algo], 0, 0); if (IS_ERR(ima_shash_tfm)) { rc = PTR_ERR(ima_shash_tfm); pr_err("Can not allocate %s (reason: %ld)\n", hash_algo_name[ima_hash_algo], rc); return rc; } pr_info("Allocated hash algorithm: %s\n", hash_algo_name[ima_hash_algo]); return 0; } static struct crypto_shash *ima_alloc_tfm(enum hash_algo algo) { struct crypto_shash *tfm = ima_shash_tfm; int rc, i; if (algo < 0 || algo >= HASH_ALGO__LAST) algo = ima_hash_algo; if (algo == ima_hash_algo) return tfm; for (i = 0; i < NR_BANKS(ima_tpm_chip) + ima_extra_slots; i++) if (ima_algo_array[i].tfm && ima_algo_array[i].algo == algo) return ima_algo_array[i].tfm; tfm = crypto_alloc_shash(hash_algo_name[algo], 0, 0); if (IS_ERR(tfm)) { rc = PTR_ERR(tfm); pr_err("Can not allocate %s (reason: %d)\n", hash_algo_name[algo], rc); } return tfm; } int __init ima_init_crypto(void) { enum hash_algo algo; long rc; int i; rc = ima_init_ima_crypto(); if (rc) return rc; ima_sha1_idx = -1; ima_hash_algo_idx = -1; for (i = 0; i < NR_BANKS(ima_tpm_chip); i++) { algo = ima_tpm_chip->allocated_banks[i].crypto_id; if (algo == HASH_ALGO_SHA1) ima_sha1_idx = i; if (algo == ima_hash_algo) ima_hash_algo_idx = i; } if (ima_sha1_idx < 0) { ima_sha1_idx = NR_BANKS(ima_tpm_chip) + ima_extra_slots++; if (ima_hash_algo == HASH_ALGO_SHA1) ima_hash_algo_idx = ima_sha1_idx; } if (ima_hash_algo_idx < 0) ima_hash_algo_idx = NR_BANKS(ima_tpm_chip) + ima_extra_slots++; ima_algo_array = kcalloc(NR_BANKS(ima_tpm_chip) + ima_extra_slots, sizeof(*ima_algo_array), GFP_KERNEL); if (!ima_algo_array) { rc = -ENOMEM; goto out; } for (i = 0; i < NR_BANKS(ima_tpm_chip); i++) { algo = ima_tpm_chip->allocated_banks[i].crypto_id; ima_algo_array[i].algo = algo; /* unknown TPM algorithm */ if (algo == HASH_ALGO__LAST) continue; if (algo == ima_hash_algo) { ima_algo_array[i].tfm = ima_shash_tfm; continue; } ima_algo_array[i].tfm = ima_alloc_tfm(algo); if (IS_ERR(ima_algo_array[i].tfm)) { if (algo == HASH_ALGO_SHA1) { rc = PTR_ERR(ima_algo_array[i].tfm); ima_algo_array[i].tfm = NULL; goto out_array; } ima_algo_array[i].tfm = NULL; } } if (ima_sha1_idx >= NR_BANKS(ima_tpm_chip)) { if (ima_hash_algo == HASH_ALGO_SHA1) { ima_algo_array[ima_sha1_idx].tfm = ima_shash_tfm; } else { ima_algo_array[ima_sha1_idx].tfm = ima_alloc_tfm(HASH_ALGO_SHA1); if (IS_ERR(ima_algo_array[ima_sha1_idx].tfm)) { rc = PTR_ERR(ima_algo_array[ima_sha1_idx].tfm); goto out_array; } } ima_algo_array[ima_sha1_idx].algo = HASH_ALGO_SHA1; } if (ima_hash_algo_idx >= NR_BANKS(ima_tpm_chip) && ima_hash_algo_idx != ima_sha1_idx) { ima_algo_array[ima_hash_algo_idx].tfm = ima_shash_tfm; ima_algo_array[ima_hash_algo_idx].algo = ima_hash_algo; } return 0; out_array: for (i = 0; i < NR_BANKS(ima_tpm_chip) + ima_extra_slots; i++) { if (!ima_algo_array[i].tfm || ima_algo_array[i].tfm == ima_shash_tfm) continue; crypto_free_shash(ima_algo_array[i].tfm); } kfree(ima_algo_array); out: crypto_free_shash(ima_shash_tfm); return rc; } static void ima_free_tfm(struct crypto_shash *tfm) { int i; if (tfm == ima_shash_tfm) return; for (i = 0; i < NR_BANKS(ima_tpm_chip) + ima_extra_slots; i++) if (ima_algo_array[i].tfm == tfm) return; crypto_free_shash(tfm); } /** * ima_alloc_pages() - Allocate contiguous pages. * @max_size: Maximum amount of memory to allocate. * @allocated_size: Returned size of actual allocation. * @last_warn: Should the min_size allocation warn or not. * * Tries to do opportunistic allocation for memory first trying to allocate * max_size amount of memory and then splitting that until zero order is * reached. Allocation is tried without generating allocation warnings unless * last_warn is set. Last_warn set affects only last allocation of zero order. * * By default, ima_maxorder is 0 and it is equivalent to kmalloc(GFP_KERNEL) * * Return pointer to allocated memory, or NULL on failure. */ static void *ima_alloc_pages(loff_t max_size, size_t *allocated_size, int last_warn) { void *ptr; int order = ima_maxorder; gfp_t gfp_mask = __GFP_RECLAIM | __GFP_NOWARN | __GFP_NORETRY; if (order) order = min(get_order(max_size), order); for (; order; order--) { ptr = (void *)__get_free_pages(gfp_mask, order); if (ptr) { *allocated_size = PAGE_SIZE << order; return ptr; } } /* order is zero - one page */ gfp_mask = GFP_KERNEL; if (!last_warn) gfp_mask |= __GFP_NOWARN; ptr = (void *)__get_free_pages(gfp_mask, 0); if (ptr) { *allocated_size = PAGE_SIZE; return ptr; } *allocated_size = 0; return NULL; } /** * ima_free_pages() - Free pages allocated by ima_alloc_pages(). * @ptr: Pointer to allocated pages. * @size: Size of allocated buffer. */ static void ima_free_pages(void *ptr, size_t size) { if (!ptr) return; free_pages((unsigned long)ptr, get_order(size)); } static struct crypto_ahash *ima_alloc_atfm(enum hash_algo algo) { struct crypto_ahash *tfm = ima_ahash_tfm; int rc; if (algo < 0 || algo >= HASH_ALGO__LAST) algo = ima_hash_algo; if (algo != ima_hash_algo || !tfm) { tfm = crypto_alloc_ahash(hash_algo_name[algo], 0, 0); if (!IS_ERR(tfm)) { if (algo == ima_hash_algo) ima_ahash_tfm = tfm; } else { rc = PTR_ERR(tfm); pr_err("Can not allocate %s (reason: %d)\n", hash_algo_name[algo], rc); } } return tfm; } static void ima_free_atfm(struct crypto_ahash *tfm) { if (tfm != ima_ahash_tfm) crypto_free_ahash(tfm); } static inline int ahash_wait(int err, struct crypto_wait *wait) { err = crypto_wait_req(err, wait); if (err) pr_crit_ratelimited("ahash calculation failed: err: %d\n", err); return err; } static int ima_calc_file_hash_atfm(struct file *file, struct ima_digest_data *hash, struct crypto_ahash *tfm) { loff_t i_size, offset; char *rbuf[2] = { NULL, }; int rc, rbuf_len, active = 0, ahash_rc = 0; struct ahash_request *req; struct scatterlist sg[1]; struct crypto_wait wait; size_t rbuf_size[2]; hash->length = crypto_ahash_digestsize(tfm); req = ahash_request_alloc(tfm, GFP_KERNEL); if (!req) return -ENOMEM; crypto_init_wait(&wait); ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, crypto_req_done, &wait); rc = ahash_wait(crypto_ahash_init(req), &wait); if (rc) goto out1; i_size = i_size_read(file_inode(file)); if (i_size == 0) goto out2; /* * Try to allocate maximum size of memory. * Fail if even a single page cannot be allocated. */ rbuf[0] = ima_alloc_pages(i_size, &rbuf_size[0], 1); if (!rbuf[0]) { rc = -ENOMEM; goto out1; } /* Only allocate one buffer if that is enough. */ if (i_size > rbuf_size[0]) { /* * Try to allocate secondary buffer. If that fails fallback to * using single buffering. Use previous memory allocation size * as baseline for possible allocation size. */ rbuf[1] = ima_alloc_pages(i_size - rbuf_size[0], &rbuf_size[1], 0); } for (offset = 0; offset < i_size; offset += rbuf_len) { if (!rbuf[1] && offset) { /* Not using two buffers, and it is not the first * read/request, wait for the completion of the * previous ahash_update() request. */ rc = ahash_wait(ahash_rc, &wait); if (rc) goto out3; } /* read buffer */ rbuf_len = min_t(loff_t, i_size - offset, rbuf_size[active]); rc = integrity_kernel_read(file, offset, rbuf[active], rbuf_len); if (rc != rbuf_len) { if (rc >= 0) rc = -EINVAL; /* * Forward current rc, do not overwrite with return value * from ahash_wait() */ ahash_wait(ahash_rc, &wait); goto out3; } if (rbuf[1] && offset) { /* Using two buffers, and it is not the first * read/request, wait for the completion of the * previous ahash_update() request. */ rc = ahash_wait(ahash_rc, &wait); if (rc) goto out3; } sg_init_one(&sg[0], rbuf[active], rbuf_len); ahash_request_set_crypt(req, sg, NULL, rbuf_len); ahash_rc = crypto_ahash_update(req); if (rbuf[1]) active = !active; /* swap buffers, if we use two */ } /* wait for the last update request to complete */ rc = ahash_wait(ahash_rc, &wait); out3: ima_free_pages(rbuf[0], rbuf_size[0]); ima_free_pages(rbuf[1], rbuf_size[1]); out2: if (!rc) { ahash_request_set_crypt(req, NULL, hash->digest, 0); rc = ahash_wait(crypto_ahash_final(req), &wait); } out1: ahash_request_free(req); return rc; } static int ima_calc_file_ahash(struct file *file, struct ima_digest_data *hash) { struct crypto_ahash *tfm; int rc; tfm = ima_alloc_atfm(hash->algo); if (IS_ERR(tfm)) return PTR_ERR(tfm); rc = ima_calc_file_hash_atfm(file, hash, tfm); ima_free_atfm(tfm); return rc; } static int ima_calc_file_hash_tfm(struct file *file, struct ima_digest_data *hash, struct crypto_shash *tfm) { loff_t i_size, offset = 0; char *rbuf; int rc; SHASH_DESC_ON_STACK(shash, tfm); shash->tfm = tfm; hash->length = crypto_shash_digestsize(tfm); rc = crypto_shash_init(shash); if (rc != 0) return rc; i_size = i_size_read(file_inode(file)); if (i_size == 0) goto out; rbuf = kzalloc(PAGE_SIZE, GFP_KERNEL); if (!rbuf) return -ENOMEM; while (offset < i_size) { int rbuf_len; rbuf_len = integrity_kernel_read(file, offset, rbuf, PAGE_SIZE); if (rbuf_len < 0) { rc = rbuf_len; break; } if (rbuf_len == 0) { /* unexpected EOF */ rc = -EINVAL; break; } offset += rbuf_len; rc = crypto_shash_update(shash, rbuf, rbuf_len); if (rc) break; } kfree(rbuf); out: if (!rc) rc = crypto_shash_final(shash, hash->digest); return rc; } static int ima_calc_file_shash(struct file *file, struct ima_digest_data *hash) { struct crypto_shash *tfm; int rc; tfm = ima_alloc_tfm(hash->algo); if (IS_ERR(tfm)) return PTR_ERR(tfm); rc = ima_calc_file_hash_tfm(file, hash, tfm); ima_free_tfm(tfm); return rc; } /* * ima_calc_file_hash - calculate file hash * * Asynchronous hash (ahash) allows using HW acceleration for calculating * a hash. ahash performance varies for different data sizes on different * crypto accelerators. shash performance might be better for smaller files. * The 'ima.ahash_minsize' module parameter allows specifying the best * minimum file size for using ahash on the system. * * If the ima.ahash_minsize parameter is not specified, this function uses * shash for the hash calculation. If ahash fails, it falls back to using * shash. */ int ima_calc_file_hash(struct file *file, struct ima_digest_data *hash) { loff_t i_size; int rc; struct file *f = file; bool new_file_instance = false; /* * For consistency, fail file's opened with the O_DIRECT flag on * filesystems mounted with/without DAX option. */ if (file->f_flags & O_DIRECT) { hash->length = hash_digest_size[ima_hash_algo]; hash->algo = ima_hash_algo; return -EINVAL; } /* Open a new file instance in O_RDONLY if we cannot read */ if (!(file->f_mode & FMODE_READ)) { int flags = file->f_flags & ~(O_WRONLY | O_APPEND | O_TRUNC | O_CREAT | O_NOCTTY | O_EXCL); flags |= O_RDONLY; f = dentry_open(&file->f_path, flags, file->f_cred); if (IS_ERR(f)) return PTR_ERR(f); new_file_instance = true; } i_size = i_size_read(file_inode(f)); if (ima_ahash_minsize && i_size >= ima_ahash_minsize) { rc = ima_calc_file_ahash(f, hash); if (!rc) goto out; } rc = ima_calc_file_shash(f, hash); out: if (new_file_instance) fput(f); return rc; } /* * Calculate the hash of template data */ static int ima_calc_field_array_hash_tfm(struct ima_field_data *field_data, struct ima_template_entry *entry, int tfm_idx) { SHASH_DESC_ON_STACK(shash, ima_algo_array[tfm_idx].tfm); struct ima_template_desc *td = entry->template_desc; int num_fields = entry->template_desc->num_fields; int rc, i; shash->tfm = ima_algo_array[tfm_idx].tfm; rc = crypto_shash_init(shash); if (rc != 0) return rc; for (i = 0; i < num_fields; i++) { u8 buffer[IMA_EVENT_NAME_LEN_MAX + 1] = { 0 }; u8 *data_to_hash = field_data[i].data; u32 datalen = field_data[i].len; u32 datalen_to_hash = !ima_canonical_fmt ? datalen : (__force u32)cpu_to_le32(datalen); if (strcmp(td->name, IMA_TEMPLATE_IMA_NAME) != 0) { rc = crypto_shash_update(shash, (const u8 *) &datalen_to_hash, sizeof(datalen_to_hash)); if (rc) break; } else if (strcmp(td->fields[i]->field_id, "n") == 0) { memcpy(buffer, data_to_hash, datalen); data_to_hash = buffer; datalen = IMA_EVENT_NAME_LEN_MAX + 1; } rc = crypto_shash_update(shash, data_to_hash, datalen); if (rc) break; } if (!rc) rc = crypto_shash_final(shash, entry->digests[tfm_idx].digest); return rc; } int ima_calc_field_array_hash(struct ima_field_data *field_data, struct ima_template_entry *entry) { u16 alg_id; int rc, i; rc = ima_calc_field_array_hash_tfm(field_data, entry, ima_sha1_idx); if (rc) return rc; entry->digests[ima_sha1_idx].alg_id = TPM_ALG_SHA1; for (i = 0; i < NR_BANKS(ima_tpm_chip) + ima_extra_slots; i++) { if (i == ima_sha1_idx) continue; if (i < NR_BANKS(ima_tpm_chip)) { alg_id = ima_tpm_chip->allocated_banks[i].alg_id; entry->digests[i].alg_id = alg_id; } /* for unmapped TPM algorithms digest is still a padded SHA1 */ if (!ima_algo_array[i].tfm) { memcpy(entry->digests[i].digest, entry->digests[ima_sha1_idx].digest, TPM_DIGEST_SIZE); continue; } rc = ima_calc_field_array_hash_tfm(field_data, entry, i); if (rc) return rc; } return rc; } static int calc_buffer_ahash_atfm(const void *buf, loff_t len, struct ima_digest_data *hash, struct crypto_ahash *tfm) { struct ahash_request *req; struct scatterlist sg; struct crypto_wait wait; int rc, ahash_rc = 0; hash->length = crypto_ahash_digestsize(tfm); req = ahash_request_alloc(tfm, GFP_KERNEL); if (!req) return -ENOMEM; crypto_init_wait(&wait); ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, crypto_req_done, &wait); rc = ahash_wait(crypto_ahash_init(req), &wait); if (rc) goto out; sg_init_one(&sg, buf, len); ahash_request_set_crypt(req, &sg, NULL, len); ahash_rc = crypto_ahash_update(req); /* wait for the update request to complete */ rc = ahash_wait(ahash_rc, &wait); if (!rc) { ahash_request_set_crypt(req, NULL, hash->digest, 0); rc = ahash_wait(crypto_ahash_final(req), &wait); } out: ahash_request_free(req); return rc; } static int calc_buffer_ahash(const void *buf, loff_t len, struct ima_digest_data *hash) { struct crypto_ahash *tfm; int rc; tfm = ima_alloc_atfm(hash->algo); if (IS_ERR(tfm)) return PTR_ERR(tfm); rc = calc_buffer_ahash_atfm(buf, len, hash, tfm); ima_free_atfm(tfm); return rc; } static int calc_buffer_shash_tfm(const void *buf, loff_t size, struct ima_digest_data *hash, struct crypto_shash *tfm) { SHASH_DESC_ON_STACK(shash, tfm); unsigned int len; int rc; shash->tfm = tfm; hash->length = crypto_shash_digestsize(tfm); rc = crypto_shash_init(shash); if (rc != 0) return rc; while (size) { len = size < PAGE_SIZE ? size : PAGE_SIZE; rc = crypto_shash_update(shash, buf, len); if (rc) break; buf += len; size -= len; } if (!rc) rc = crypto_shash_final(shash, hash->digest); return rc; } static int calc_buffer_shash(const void *buf, loff_t len, struct ima_digest_data *hash) { struct crypto_shash *tfm; int rc; tfm = ima_alloc_tfm(hash->algo); if (IS_ERR(tfm)) return PTR_ERR(tfm); rc = calc_buffer_shash_tfm(buf, len, hash, tfm); ima_free_tfm(tfm); return rc; } int ima_calc_buffer_hash(const void *buf, loff_t len, struct ima_digest_data *hash) { int rc; if (ima_ahash_minsize && len >= ima_ahash_minsize) { rc = calc_buffer_ahash(buf, len, hash); if (!rc) return 0; } return calc_buffer_shash(buf, len, hash); } static void ima_pcrread(u32 idx, struct tpm_digest *d) { if (!ima_tpm_chip) return; if (tpm_pcr_read(ima_tpm_chip, idx, d) != 0) pr_err("Error Communicating to TPM chip\n"); } /* * The boot_aggregate is a cumulative hash over TPM registers 0 - 7. With * TPM 1.2 the boot_aggregate was based on reading the SHA1 PCRs, but with * TPM 2.0 hash agility, TPM chips could support multiple TPM PCR banks, * allowing firmware to configure and enable different banks. * * Knowing which TPM bank is read to calculate the boot_aggregate digest * needs to be conveyed to a verifier. For this reason, use the same * hash algorithm for reading the TPM PCRs as for calculating the boot * aggregate digest as stored in the measurement list. */ static int ima_calc_boot_aggregate_tfm(char *digest, u16 alg_id, struct crypto_shash *tfm) { struct tpm_digest d = { .alg_id = alg_id, .digest = {0} }; int rc; u32 i; SHASH_DESC_ON_STACK(shash, tfm); shash->tfm = tfm; pr_devel("calculating the boot-aggregate based on TPM bank: %04x\n", d.alg_id); rc = crypto_shash_init(shash); if (rc != 0) return rc; /* cumulative digest over TPM registers 0-7 */ for (i = TPM_PCR0; i < TPM_PCR8; i++) { ima_pcrread(i, &d); /* now accumulate with current aggregate */ rc = crypto_shash_update(shash, d.digest, crypto_shash_digestsize(tfm)); if (rc != 0) return rc; } /* * Extend cumulative digest over TPM registers 8-9, which contain * measurement for the kernel command line (reg. 8) and image (reg. 9) * in a typical PCR allocation. Registers 8-9 are only included in * non-SHA1 boot_aggregate digests to avoid ambiguity. */ if (alg_id != TPM_ALG_SHA1) { for (i = TPM_PCR8; i < TPM_PCR10; i++) { ima_pcrread(i, &d); rc = crypto_shash_update(shash, d.digest, crypto_shash_digestsize(tfm)); } } if (!rc) crypto_shash_final(shash, digest); return rc; } int ima_calc_boot_aggregate(struct ima_digest_data *hash) { struct crypto_shash *tfm; u16 crypto_id, alg_id; int rc, i, bank_idx = -1; for (i = 0; i < ima_tpm_chip->nr_allocated_banks; i++) { crypto_id = ima_tpm_chip->allocated_banks[i].crypto_id; if (crypto_id == hash->algo) { bank_idx = i; break; } if (crypto_id == HASH_ALGO_SHA256) bank_idx = i; if (bank_idx == -1 && crypto_id == HASH_ALGO_SHA1) bank_idx = i; } if (bank_idx == -1) { pr_err("No suitable TPM algorithm for boot aggregate\n"); return 0; } hash->algo = ima_tpm_chip->allocated_banks[bank_idx].crypto_id; tfm = ima_alloc_tfm(hash->algo); if (IS_ERR(tfm)) return PTR_ERR(tfm); hash->length = crypto_shash_digestsize(tfm); alg_id = ima_tpm_chip->allocated_banks[bank_idx].alg_id; rc = ima_calc_boot_aggregate_tfm(hash->digest, alg_id, tfm); ima_free_tfm(tfm); return rc; } |
| 2 2 768 4 4 4 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * linux/include/linux/jbd2.h * * Written by Stephen C. Tweedie <sct@redhat.com> * * Copyright 1998-2000 Red Hat, Inc --- All Rights Reserved * * Definitions for transaction data structures for the buffer cache * filesystem journaling support. */ #ifndef _LINUX_JBD2_H #define _LINUX_JBD2_H /* Allow this file to be included directly into e2fsprogs */ #ifndef __KERNEL__ #include "jfs_compat.h" #define JBD2_DEBUG #else #include <linux/types.h> #include <linux/buffer_head.h> #include <linux/journal-head.h> #include <linux/stddef.h> #include <linux/mutex.h> #include <linux/timer.h> #include <linux/slab.h> #include <linux/bit_spinlock.h> #include <linux/blkdev.h> #include <crypto/hash.h> #endif #define journal_oom_retry 1 /* * Define JBD2_PARANIOD_IOFAIL to cause a kernel BUG() if ext4 finds * certain classes of error which can occur due to failed IOs. Under * normal use we want ext4 to continue after such errors, because * hardware _can_ fail, but for debugging purposes when running tests on * known-good hardware we may want to trap these errors. */ #undef JBD2_PARANOID_IOFAIL /* * The default maximum commit age, in seconds. */ #define JBD2_DEFAULT_MAX_COMMIT_AGE 5 #ifdef CONFIG_JBD2_DEBUG /* * Define JBD2_EXPENSIVE_CHECKING to enable more expensive internal * consistency checks. By default we don't do this unless * CONFIG_JBD2_DEBUG is on. */ #define JBD2_EXPENSIVE_CHECKING void __jbd2_debug(int level, const char *file, const char *func, unsigned int line, const char *fmt, ...); #define jbd2_debug(n, fmt, a...) \ __jbd2_debug((n), __FILE__, __func__, __LINE__, (fmt), ##a) #else #define jbd2_debug(n, fmt, a...) no_printk(fmt, ##a) #endif extern void *jbd2_alloc(size_t size, gfp_t flags); extern void jbd2_free(void *ptr, size_t size); #define JBD2_MIN_JOURNAL_BLOCKS 1024 #define JBD2_DEFAULT_FAST_COMMIT_BLOCKS 256 #ifdef __KERNEL__ /** * typedef handle_t - The handle_t type represents a single atomic update being performed by some process. * * All filesystem modifications made by the process go * through this handle. Recursive operations (such as quota operations) * are gathered into a single update. * * The buffer credits field is used to account for journaled buffers * being modified by the running process. To ensure that there is * enough log space for all outstanding operations, we need to limit the * number of outstanding buffers possible at any time. When the * operation completes, any buffer credits not used are credited back to * the transaction, so that at all times we know how many buffers the * outstanding updates on a transaction might possibly touch. * * This is an opaque datatype. **/ typedef struct jbd2_journal_handle handle_t; /* Atomic operation type */ /** * typedef journal_t - The journal_t maintains all of the journaling state information for a single filesystem. * * journal_t is linked to from the fs superblock structure. * * We use the journal_t to keep track of all outstanding transaction * activity on the filesystem, and to manage the state of the log * writing process. * * This is an opaque datatype. **/ typedef struct journal_s journal_t; /* Journal control structure */ #endif /* * Internal structures used by the logging mechanism: */ #define JBD2_MAGIC_NUMBER 0xc03b3998U /* The first 4 bytes of /dev/random! */ /* * On-disk structures */ /* * Descriptor block types: */ #define JBD2_DESCRIPTOR_BLOCK 1 #define JBD2_COMMIT_BLOCK 2 #define JBD2_SUPERBLOCK_V1 3 #define JBD2_SUPERBLOCK_V2 4 #define JBD2_REVOKE_BLOCK 5 /* * Standard header for all descriptor blocks: */ typedef struct journal_header_s { __be32 h_magic; __be32 h_blocktype; __be32 h_sequence; } journal_header_t; /* * Checksum types. */ #define JBD2_CRC32_CHKSUM 1 #define JBD2_MD5_CHKSUM 2 #define JBD2_SHA1_CHKSUM 3 #define JBD2_CRC32C_CHKSUM 4 #define JBD2_CRC32_CHKSUM_SIZE 4 #define JBD2_CHECKSUM_BYTES (32 / sizeof(u32)) /* * Commit block header for storing transactional checksums: * * NOTE: If FEATURE_COMPAT_CHECKSUM (checksum v1) is set, the h_chksum* * fields are used to store a checksum of the descriptor and data blocks. * * If FEATURE_INCOMPAT_CSUM_V2 (checksum v2) is set, then the h_chksum * field is used to store crc32c(uuid+commit_block). Each journal metadata * block gets its own checksum, and data block checksums are stored in * journal_block_tag (in the descriptor). The other h_chksum* fields are * not used. * * If FEATURE_INCOMPAT_CSUM_V3 is set, the descriptor block uses * journal_block_tag3_t to store a full 32-bit checksum. Everything else * is the same as v2. * * Checksum v1, v2, and v3 are mutually exclusive features. */ struct commit_header { __be32 h_magic; __be32 h_blocktype; __be32 h_sequence; unsigned char h_chksum_type; unsigned char h_chksum_size; unsigned char h_padding[2]; __be32 h_chksum[JBD2_CHECKSUM_BYTES]; __be64 h_commit_sec; __be32 h_commit_nsec; }; /* * The block tag: used to describe a single buffer in the journal. * t_blocknr_high is only used if INCOMPAT_64BIT is set, so this * raw struct shouldn't be used for pointer math or sizeof() - use * journal_tag_bytes(journal) instead to compute this. */ typedef struct journal_block_tag3_s { __be32 t_blocknr; /* The on-disk block number */ __be32 t_flags; /* See below */ __be32 t_blocknr_high; /* most-significant high 32bits. */ __be32 t_checksum; /* crc32c(uuid+seq+block) */ } journal_block_tag3_t; typedef struct journal_block_tag_s { __be32 t_blocknr; /* The on-disk block number */ __be16 t_checksum; /* truncated crc32c(uuid+seq+block) */ __be16 t_flags; /* See below */ __be32 t_blocknr_high; /* most-significant high 32bits. */ } journal_block_tag_t; /* Tail of descriptor or revoke block, for checksumming */ struct jbd2_journal_block_tail { __be32 t_checksum; /* crc32c(uuid+descr_block) */ }; /* * The revoke descriptor: used on disk to describe a series of blocks to * be revoked from the log */ typedef struct jbd2_journal_revoke_header_s { journal_header_t r_header; __be32 r_count; /* Count of bytes used in the block */ } jbd2_journal_revoke_header_t; /* Definitions for the journal tag flags word: */ #define JBD2_FLAG_ESCAPE 1 /* on-disk block is escaped */ #define JBD2_FLAG_SAME_UUID 2 /* block has same uuid as previous */ #define JBD2_FLAG_DELETED 4 /* block deleted by this transaction */ #define JBD2_FLAG_LAST_TAG 8 /* last tag in this descriptor block */ /* * The journal superblock. All fields are in big-endian byte order. */ typedef struct journal_superblock_s { /* 0x0000 */ journal_header_t s_header; /* 0x000C */ /* Static information describing the journal */ __be32 s_blocksize; /* journal device blocksize */ __be32 s_maxlen; /* total blocks in journal file */ __be32 s_first; /* first block of log information */ /* 0x0018 */ /* Dynamic information describing the current state of the log */ __be32 s_sequence; /* first commit ID expected in log */ __be32 s_start; /* blocknr of start of log */ /* 0x0020 */ /* Error value, as set by jbd2_journal_abort(). */ __be32 s_errno; /* 0x0024 */ /* Remaining fields are only valid in a version-2 superblock */ __be32 s_feature_compat; /* compatible feature set */ __be32 s_feature_incompat; /* incompatible feature set */ __be32 s_feature_ro_compat; /* readonly-compatible feature set */ /* 0x0030 */ __u8 s_uuid[16]; /* 128-bit uuid for journal */ /* 0x0040 */ __be32 s_nr_users; /* Nr of filesystems sharing log */ __be32 s_dynsuper; /* Blocknr of dynamic superblock copy*/ /* 0x0048 */ __be32 s_max_transaction; /* Limit of journal blocks per trans.*/ __be32 s_max_trans_data; /* Limit of data blocks per trans. */ /* 0x0050 */ __u8 s_checksum_type; /* checksum type */ __u8 s_padding2[3]; /* 0x0054 */ __be32 s_num_fc_blks; /* Number of fast commit blocks */ __be32 s_head; /* blocknr of head of log, only uptodate * while the filesystem is clean */ /* 0x005C */ __u32 s_padding[40]; __be32 s_checksum; /* crc32c(superblock) */ /* 0x0100 */ __u8 s_users[16*48]; /* ids of all fs'es sharing the log */ /* 0x0400 */ } journal_superblock_t; #define JBD2_FEATURE_COMPAT_CHECKSUM 0x00000001 #define JBD2_FEATURE_INCOMPAT_REVOKE 0x00000001 #define JBD2_FEATURE_INCOMPAT_64BIT 0x00000002 #define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT 0x00000004 #define JBD2_FEATURE_INCOMPAT_CSUM_V2 0x00000008 #define JBD2_FEATURE_INCOMPAT_CSUM_V3 0x00000010 #define JBD2_FEATURE_INCOMPAT_FAST_COMMIT 0x00000020 /* See "journal feature predicate functions" below */ /* Features known to this kernel version: */ #define JBD2_KNOWN_COMPAT_FEATURES JBD2_FEATURE_COMPAT_CHECKSUM #define JBD2_KNOWN_ROCOMPAT_FEATURES 0 #define JBD2_KNOWN_INCOMPAT_FEATURES (JBD2_FEATURE_INCOMPAT_REVOKE | \ JBD2_FEATURE_INCOMPAT_64BIT | \ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | \ JBD2_FEATURE_INCOMPAT_CSUM_V2 | \ JBD2_FEATURE_INCOMPAT_CSUM_V3 | \ JBD2_FEATURE_INCOMPAT_FAST_COMMIT) #ifdef __KERNEL__ #include <linux/fs.h> #include <linux/sched.h> enum jbd_state_bits { BH_JBD /* Has an attached ext3 journal_head */ = BH_PrivateStart, BH_JWrite, /* Being written to log (@@@ DEBUGGING) */ BH_Freed, /* Has been freed (truncated) */ BH_Revoked, /* Has been revoked from the log */ BH_RevokeValid, /* Revoked flag is valid */ BH_JBDDirty, /* Is dirty but journaled */ BH_JournalHead, /* Pins bh->b_private and jh->b_bh */ BH_Shadow, /* IO on shadow buffer is running */ BH_Verified, /* Metadata block has been verified ok */ BH_JBDPrivateStart, /* First bit available for private use by FS */ }; BUFFER_FNS(JBD, jbd) BUFFER_FNS(JWrite, jwrite) BUFFER_FNS(JBDDirty, jbddirty) TAS_BUFFER_FNS(JBDDirty, jbddirty) BUFFER_FNS(Revoked, revoked) TAS_BUFFER_FNS(Revoked, revoked) BUFFER_FNS(RevokeValid, revokevalid) TAS_BUFFER_FNS(RevokeValid, revokevalid) BUFFER_FNS(Freed, freed) BUFFER_FNS(Shadow, shadow) BUFFER_FNS(Verified, verified) static inline struct buffer_head *jh2bh(struct journal_head *jh) { return jh->b_bh; } static inline struct journal_head *bh2jh(struct buffer_head *bh) { return bh->b_private; } static inline void jbd_lock_bh_journal_head(struct buffer_head *bh) { bit_spin_lock(BH_JournalHead, &bh->b_state); } static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) { bit_spin_unlock(BH_JournalHead, &bh->b_state); } #define J_ASSERT(assert) BUG_ON(!(assert)) #define J_ASSERT_BH(bh, expr) J_ASSERT(expr) #define J_ASSERT_JH(jh, expr) J_ASSERT(expr) #if defined(JBD2_PARANOID_IOFAIL) #define J_EXPECT(expr, why...) J_ASSERT(expr) #define J_EXPECT_BH(bh, expr, why...) J_ASSERT_BH(bh, expr) #define J_EXPECT_JH(jh, expr, why...) J_ASSERT_JH(jh, expr) #else #define __journal_expect(expr, why...) \ ({ \ int val = (expr); \ if (!val) { \ printk(KERN_ERR \ "JBD2 unexpected failure: %s: %s;\n", \ __func__, #expr); \ printk(KERN_ERR why "\n"); \ } \ val; \ }) #define J_EXPECT(expr, why...) __journal_expect(expr, ## why) #define J_EXPECT_BH(bh, expr, why...) __journal_expect(expr, ## why) #define J_EXPECT_JH(jh, expr, why...) __journal_expect(expr, ## why) #endif /* Flags in jbd_inode->i_flags */ #define __JI_COMMIT_RUNNING 0 #define __JI_WRITE_DATA 1 #define __JI_WAIT_DATA 2 /* * Commit of the inode data in progress. We use this flag to protect us from * concurrent deletion of inode. We cannot use reference to inode for this * since we cannot afford doing last iput() on behalf of kjournald */ #define JI_COMMIT_RUNNING (1 << __JI_COMMIT_RUNNING) /* Write allocated dirty buffers in this inode before commit */ #define JI_WRITE_DATA (1 << __JI_WRITE_DATA) /* Wait for outstanding data writes for this inode before commit */ #define JI_WAIT_DATA (1 << __JI_WAIT_DATA) /** * struct jbd2_inode - The jbd_inode type is the structure linking inodes in * ordered mode present in a transaction so that we can sync them during commit. */ struct jbd2_inode { /** * @i_transaction: * * Which transaction does this inode belong to? Either the running * transaction or the committing one. [j_list_lock] */ transaction_t *i_transaction; /** * @i_next_transaction: * * Pointer to the running transaction modifying inode's data in case * there is already a committing transaction touching it. [j_list_lock] */ transaction_t *i_next_transaction; /** * @i_list: List of inodes in the i_transaction [j_list_lock] */ struct list_head i_list; /** * @i_vfs_inode: * * VFS inode this inode belongs to [constant for lifetime of structure] */ struct inode *i_vfs_inode; /** * @i_flags: Flags of inode [j_list_lock] */ unsigned long i_flags; /** * @i_dirty_start: * * Offset in bytes where the dirty range for this inode starts. * [j_list_lock] */ loff_t i_dirty_start; /** * @i_dirty_end: * * Inclusive offset in bytes where the dirty range for this inode * ends. [j_list_lock] */ loff_t i_dirty_end; }; struct jbd2_revoke_table_s; /** * struct jbd2_journal_handle - The jbd2_journal_handle type is the concrete * type associated with handle_t. * @h_transaction: Which compound transaction is this update a part of? * @h_journal: Which journal handle belongs to - used iff h_reserved set. * @h_rsv_handle: Handle reserved for finishing the logical operation. * @h_total_credits: Number of remaining buffers we are allowed to add to * journal. These are dirty buffers and revoke descriptor blocks. * @h_revoke_credits: Number of remaining revoke records available for handle * @h_ref: Reference count on this handle. * @h_err: Field for caller's use to track errors through large fs operations. * @h_sync: Flag for sync-on-close. * @h_jdata: Flag to force data journaling. * @h_reserved: Flag for handle for reserved credits. * @h_aborted: Flag indicating fatal error on handle. * @h_type: For handle statistics. * @h_line_no: For handle statistics. * @h_start_jiffies: Handle Start time. * @h_requested_credits: Holds @h_total_credits after handle is started. * @h_revoke_credits_requested: Holds @h_revoke_credits after handle is started. * @saved_alloc_context: Saved context while transaction is open. **/ /* Docbook can't yet cope with the bit fields, but will leave the documentation * in so it can be fixed later. */ struct jbd2_journal_handle { union { transaction_t *h_transaction; /* Which journal handle belongs to - used iff h_reserved set */ journal_t *h_journal; }; handle_t *h_rsv_handle; int h_total_credits; int h_revoke_credits; int h_revoke_credits_requested; int h_ref; int h_err; /* Flags [no locking] */ unsigned int h_sync: 1; unsigned int h_jdata: 1; unsigned int h_reserved: 1; unsigned int h_aborted: 1; unsigned int h_type: 8; unsigned int h_line_no: 16; unsigned long h_start_jiffies; unsigned int h_requested_credits; unsigned int saved_alloc_context; }; /* * Some stats for checkpoint phase */ struct transaction_chp_stats_s { unsigned long cs_chp_time; __u32 cs_forced_to_close; __u32 cs_written; __u32 cs_dropped; }; /* The transaction_t type is the guts of the journaling mechanism. It * tracks a compound transaction through its various states: * * RUNNING: accepting new updates * LOCKED: Updates still running but we don't accept new ones * RUNDOWN: Updates are tidying up but have finished requesting * new buffers to modify (state not used for now) * FLUSH: All updates complete, but we are still writing to disk * COMMIT: All data on disk, writing commit record * FINISHED: We still have to keep the transaction for checkpointing. * * The transaction keeps track of all of the buffers modified by a * running transaction, and all of the buffers committed but not yet * flushed to home for finished transactions. * (Locking Documentation improved by LockDoc) */ /* * Lock ranking: * * j_list_lock * ->jbd_lock_bh_journal_head() (This is "innermost") * * j_state_lock * ->b_state_lock * * b_state_lock * ->j_list_lock * * j_state_lock * ->j_list_lock (journal_unmap_buffer) * */ struct transaction_s { /* Pointer to the journal for this transaction. [no locking] */ journal_t *t_journal; /* Sequence number for this transaction [no locking] */ tid_t t_tid; /* * Transaction's current state * [no locking - only kjournald2 alters this] * [j_list_lock] guards transition of a transaction into T_FINISHED * state and subsequent call of __jbd2_journal_drop_transaction() * FIXME: needs barriers * KLUDGE: [use j_state_lock] */ enum { T_RUNNING, T_LOCKED, T_SWITCH, T_FLUSH, T_COMMIT, T_COMMIT_DFLUSH, T_COMMIT_JFLUSH, T_COMMIT_CALLBACK, T_FINISHED } t_state; /* * Where in the log does this transaction's commit start? [no locking] */ unsigned long t_log_start; /* * Number of buffers on the t_buffers list [j_list_lock, no locks * needed for jbd2 thread] */ int t_nr_buffers; /* * Doubly-linked circular list of all buffers reserved but not yet * modified by this transaction [j_list_lock, no locks needed fo * jbd2 thread] */ struct journal_head *t_reserved_list; /* * Doubly-linked circular list of all metadata buffers owned by this * transaction [j_list_lock, no locks needed for jbd2 thread] */ struct journal_head *t_buffers; /* * Doubly-linked circular list of all forget buffers (superseded * buffers which we can un-checkpoint once this transaction commits) * [j_list_lock] */ struct journal_head *t_forget; /* * Doubly-linked circular list of all buffers still to be flushed before * this transaction can be checkpointed. [j_list_lock] */ struct journal_head *t_checkpoint_list; /* * Doubly-linked circular list of metadata buffers being * shadowed by log IO. The IO buffers on the iobuf list and * the shadow buffers on this list match each other one for * one at all times. [j_list_lock, no locks needed for jbd2 * thread] */ struct journal_head *t_shadow_list; /* * List of inodes associated with the transaction; e.g., ext4 uses * this to track inodes in data=ordered and data=journal mode that * need special handling on transaction commit; also used by ocfs2. * [j_list_lock] */ struct list_head t_inode_list; /* * Longest time some handle had to wait for running transaction */ unsigned long t_max_wait; /* * When transaction started */ unsigned long t_start; /* * When commit was requested [j_state_lock] */ unsigned long t_requested; /* * Checkpointing stats [j_list_lock] */ struct transaction_chp_stats_s t_chp_stats; /* * Number of outstanding updates running on this transaction * [none] */ atomic_t t_updates; /* * Number of blocks reserved for this transaction in the journal. * This is including all credits reserved when starting transaction * handles as well as all journal descriptor blocks needed for this * transaction. [none] */ atomic_t t_outstanding_credits; /* * Number of revoke records for this transaction added by already * stopped handles. [none] */ atomic_t t_outstanding_revokes; /* * How many handles used this transaction? [none] */ atomic_t t_handle_count; /* * Forward and backward links for the circular list of all transactions * awaiting checkpoint. [j_list_lock] */ transaction_t *t_cpnext, *t_cpprev; /* * When will the transaction expire (become due for commit), in jiffies? * [no locking] */ unsigned long t_expires; /* * When this transaction started, in nanoseconds [no locking] */ ktime_t t_start_time; /* * This transaction is being forced and some process is * waiting for it to finish. */ unsigned int t_synchronous_commit:1; /* Disk flush needs to be sent to fs partition [no locking] */ int t_need_data_flush; /* * For use by the filesystem to store fs-specific data * structures associated with the transaction */ struct list_head t_private_list; }; struct transaction_run_stats_s { unsigned long rs_wait; unsigned long rs_request_delay; unsigned long rs_running; unsigned long rs_locked; unsigned long rs_flushing; unsigned long rs_logging; __u32 rs_handle_count; __u32 rs_blocks; __u32 rs_blocks_logged; }; struct transaction_stats_s { unsigned long ts_tid; unsigned long ts_requested; struct transaction_run_stats_s run; }; static inline unsigned long jbd2_time_diff(unsigned long start, unsigned long end) { if (end >= start) return end - start; return end + (MAX_JIFFY_OFFSET - start); } #define JBD2_NR_BATCH 64 enum passtype {PASS_SCAN, PASS_REVOKE, PASS_REPLAY}; #define JBD2_FC_REPLAY_STOP 0 #define JBD2_FC_REPLAY_CONTINUE 1 /** * struct journal_s - The journal_s type is the concrete type associated with * journal_t. */ struct journal_s { /** * @j_flags: General journaling state flags [j_state_lock, * no lock for quick racy checks] */ unsigned long j_flags; /** * @j_errno: * * Is there an outstanding uncleared error on the journal (from a prior * abort)? [j_state_lock] */ int j_errno; /** * @j_abort_mutex: Lock the whole aborting procedure. */ struct mutex j_abort_mutex; /** * @j_sb_buffer: The first part of the superblock buffer. */ struct buffer_head *j_sb_buffer; /** * @j_superblock: The second part of the superblock buffer. */ journal_superblock_t *j_superblock; /** * @j_state_lock: Protect the various scalars in the journal. */ rwlock_t j_state_lock; /** * @j_barrier_count: * * Number of processes waiting to create a barrier lock [j_state_lock, * no lock for quick racy checks] */ int j_barrier_count; /** * @j_barrier: The barrier lock itself. */ struct mutex j_barrier; /** * @j_running_transaction: * * Transactions: The current running transaction... * [j_state_lock, no lock for quick racy checks] [caller holding * open handle] */ transaction_t *j_running_transaction; /** * @j_committing_transaction: * * the transaction we are pushing to disk * [j_state_lock] [caller holding open handle] */ transaction_t *j_committing_transaction; /** * @j_checkpoint_transactions: * * ... and a linked circular list of all transactions waiting for * checkpointing. [j_list_lock] */ transaction_t *j_checkpoint_transactions; /** * @j_wait_transaction_locked: * * Wait queue for waiting for a locked transaction to start committing, * or for a barrier lock to be released. */ wait_queue_head_t j_wait_transaction_locked; /** * @j_wait_done_commit: Wait queue for waiting for commit to complete. */ wait_queue_head_t j_wait_done_commit; /** * @j_wait_commit: Wait queue to trigger commit. */ wait_queue_head_t j_wait_commit; /** * @j_wait_updates: Wait queue to wait for updates to complete. */ wait_queue_head_t j_wait_updates; /** * @j_wait_reserved: * * Wait queue to wait for reserved buffer credits to drop. */ wait_queue_head_t j_wait_reserved; /** * @j_fc_wait: * * Wait queue to wait for completion of async fast commits. */ wait_queue_head_t j_fc_wait; /** * @j_checkpoint_mutex: * * Semaphore for locking against concurrent checkpoints. */ struct mutex j_checkpoint_mutex; /** * @j_chkpt_bhs: * * List of buffer heads used by the checkpoint routine. This * was moved from jbd2_log_do_checkpoint() to reduce stack * usage. Access to this array is controlled by the * @j_checkpoint_mutex. [j_checkpoint_mutex] */ struct buffer_head *j_chkpt_bhs[JBD2_NR_BATCH]; /** * @j_shrinker: * * Journal head shrinker, reclaim buffer's journal head which * has been written back. */ struct shrinker *j_shrinker; /** * @j_checkpoint_jh_count: * * Number of journal buffers on the checkpoint list. [j_list_lock] */ struct percpu_counter j_checkpoint_jh_count; /** * @j_shrink_transaction: * * Record next transaction will shrink on the checkpoint list. * [j_list_lock] */ transaction_t *j_shrink_transaction; /** * @j_head: * * Journal head: identifies the first unused block in the journal. * [j_state_lock] */ unsigned long j_head; /** * @j_tail: * * Journal tail: identifies the oldest still-used block in the journal. * [j_state_lock] */ unsigned long j_tail; /** * @j_free: * * Journal free: how many free blocks are there in the journal? * [j_state_lock] */ unsigned long j_free; /** * @j_first: * * The block number of the first usable block in the journal * [j_state_lock]. */ unsigned long j_first; /** * @j_last: * * The block number one beyond the last usable block in the journal * [j_state_lock]. */ unsigned long j_last; /** * @j_fc_first: * * The block number of the first fast commit block in the journal * [j_state_lock]. */ unsigned long j_fc_first; /** * @j_fc_off: * * Number of fast commit blocks currently allocated. Accessed only * during fast commit. Currently only process can do fast commit, so * this field is not protected by any lock. */ unsigned long j_fc_off; /** * @j_fc_last: * * The block number one beyond the last fast commit block in the journal * [j_state_lock]. */ unsigned long j_fc_last; /** * @j_dev: Device where we store the journal. */ struct block_device *j_dev; /** * @j_blocksize: Block size for the location where we store the journal. */ int j_blocksize; /** * @j_blk_offset: * * Starting block offset into the device where we store the journal. */ unsigned long long j_blk_offset; /** * @j_devname: Journal device name. */ char j_devname[BDEVNAME_SIZE+24]; /** * @j_fs_dev: * * Device which holds the client fs. For internal journal this will be * equal to j_dev. */ struct block_device *j_fs_dev; /** * @j_fs_dev_wb_err: * * Records the errseq of the client fs's backing block device. */ errseq_t j_fs_dev_wb_err; /** * @j_total_len: Total maximum capacity of the journal region on disk. */ unsigned int j_total_len; /** * @j_reserved_credits: * * Number of buffers reserved from the running transaction. */ atomic_t j_reserved_credits; /** * @j_list_lock: Protects the buffer lists and internal buffer state. */ spinlock_t j_list_lock; /** * @j_inode: * * Optional inode where we store the journal. If present, all * journal block numbers are mapped into this inode via bmap(). */ struct inode *j_inode; /** * @j_tail_sequence: * * Sequence number of the oldest transaction in the log [j_state_lock] */ tid_t j_tail_sequence; /** * @j_transaction_sequence: * * Sequence number of the next transaction to grant [j_state_lock] */ tid_t j_transaction_sequence; /** * @j_commit_sequence: * * Sequence number of the most recently committed transaction * [j_state_lock, no lock for quick racy checks] */ tid_t j_commit_sequence; /** * @j_commit_request: * * Sequence number of the most recent transaction wanting commit * [j_state_lock, no lock for quick racy checks] */ tid_t j_commit_request; /** * @j_uuid: * * Journal uuid: identifies the object (filesystem, LVM volume etc) * backed by this journal. This will eventually be replaced by an array * of uuids, allowing us to index multiple devices within a single * journal and to perform atomic updates across them. */ __u8 j_uuid[16]; /** * @j_task: Pointer to the current commit thread for this journal. */ struct task_struct *j_task; /** * @j_max_transaction_buffers: * * Maximum number of metadata buffers to allow in a single compound * commit transaction. */ int j_max_transaction_buffers; /** * @j_revoke_records_per_block: * * Number of revoke records that fit in one descriptor block. */ int j_revoke_records_per_block; /** * @j_transaction_overhead: * * Number of blocks each transaction needs for its own bookkeeping */ int j_transaction_overhead_buffers; /** * @j_commit_interval: * * What is the maximum transaction lifetime before we begin a commit? */ unsigned long j_commit_interval; /** * @j_commit_timer: The timer used to wakeup the commit thread. */ struct timer_list j_commit_timer; /** * @j_revoke_lock: Protect the revoke table. */ spinlock_t j_revoke_lock; /** * @j_revoke: * * The revoke table - maintains the list of revoked blocks in the * current transaction. */ struct jbd2_revoke_table_s *j_revoke; /** * @j_revoke_table: Alternate revoke tables for j_revoke. */ struct jbd2_revoke_table_s *j_revoke_table[2]; /** * @j_wbuf: Array of bhs for jbd2_journal_commit_transaction. */ struct buffer_head **j_wbuf; /** * @j_fc_wbuf: Array of fast commit bhs for fast commit. Accessed only * during a fast commit. Currently only process can do fast commit, so * this field is not protected by any lock. */ struct buffer_head **j_fc_wbuf; /** * @j_wbufsize: * * Size of @j_wbuf array. */ int j_wbufsize; /** * @j_fc_wbufsize: * * Size of @j_fc_wbuf array. */ int j_fc_wbufsize; /** * @j_last_sync_writer: * * The pid of the last person to run a synchronous operation * through the journal. */ pid_t j_last_sync_writer; /** * @j_average_commit_time: * * The average amount of time in nanoseconds it takes to commit a * transaction to disk. [j_state_lock] */ u64 j_average_commit_time; /** * @j_min_batch_time: * * Minimum time that we should wait for additional filesystem operations * to get batched into a synchronous handle in microseconds. */ u32 j_min_batch_time; /** * @j_max_batch_time: * * Maximum time that we should wait for additional filesystem operations * to get batched into a synchronous handle in microseconds. */ u32 j_max_batch_time; /** * @j_commit_callback: * * This function is called when a transaction is closed. */ void (*j_commit_callback)(journal_t *, transaction_t *); /** * @j_submit_inode_data_buffers: * * This function is called for all inodes associated with the * committing transaction marked with JI_WRITE_DATA flag * before we start to write out the transaction to the journal. */ int (*j_submit_inode_data_buffers) (struct jbd2_inode *); /** * @j_finish_inode_data_buffers: * * This function is called for all inodes associated with the * committing transaction marked with JI_WAIT_DATA flag * after we have written the transaction to the journal * but before we write out the commit block. */ int (*j_finish_inode_data_buffers) (struct jbd2_inode *); /* * Journal statistics */ /** * @j_history_lock: Protect the transactions statistics history. */ spinlock_t j_history_lock; /** * @j_proc_entry: procfs entry for the jbd statistics directory. */ struct proc_dir_entry *j_proc_entry; /** * @j_stats: Overall statistics. */ struct transaction_stats_s j_stats; /** * @j_failed_commit: Failed journal commit ID. */ unsigned int j_failed_commit; /** * @j_private: * * An opaque pointer to fs-private information. ext3 puts its * superblock pointer here. */ void *j_private; /** * @j_chksum_driver: * * Reference to checksum algorithm driver via cryptoapi. */ struct crypto_shash *j_chksum_driver; /** * @j_csum_seed: * * Precomputed journal UUID checksum for seeding other checksums. */ __u32 j_csum_seed; #ifdef CONFIG_DEBUG_LOCK_ALLOC /** * @j_trans_commit_map: * * Lockdep entity to track transaction commit dependencies. Handles * hold this "lock" for read, when we wait for commit, we acquire the * "lock" for writing. This matches the properties of jbd2 journalling * where the running transaction has to wait for all handles to be * dropped to commit that transaction and also acquiring a handle may * require transaction commit to finish. */ struct lockdep_map j_trans_commit_map; #endif /** * @j_fc_cleanup_callback: * * Clean-up after fast commit or full commit. JBD2 calls this function * after every commit operation. */ void (*j_fc_cleanup_callback)(struct journal_s *journal, int full, tid_t tid); /** * @j_fc_replay_callback: * * File-system specific function that performs replay of a fast * commit. JBD2 calls this function for each fast commit block found in * the journal. This function should return JBD2_FC_REPLAY_CONTINUE * to indicate that the block was processed correctly and more fast * commit replay should continue. Return value of JBD2_FC_REPLAY_STOP * indicates the end of replay (no more blocks remaining). A negative * return value indicates error. */ int (*j_fc_replay_callback)(struct journal_s *journal, struct buffer_head *bh, enum passtype pass, int off, tid_t expected_commit_id); /** * @j_bmap: * * Bmap function that should be used instead of the generic * VFS bmap function. */ int (*j_bmap)(struct journal_s *journal, sector_t *block); }; #define jbd2_might_wait_for_commit(j) \ do { \ rwsem_acquire(&j->j_trans_commit_map, 0, 0, _THIS_IP_); \ rwsem_release(&j->j_trans_commit_map, _THIS_IP_); \ } while (0) /* * We can support any known requested features iff the * superblock is not in version 1. Otherwise we fail to support any * extended sb features. */ static inline bool jbd2_format_support_feature(journal_t *j) { return j->j_superblock->s_header.h_blocktype != cpu_to_be32(JBD2_SUPERBLOCK_V1); } /* journal feature predicate functions */ #define JBD2_FEATURE_COMPAT_FUNCS(name, flagname) \ static inline bool jbd2_has_feature_##name(journal_t *j) \ { \ return (jbd2_format_support_feature(j) && \ ((j)->j_superblock->s_feature_compat & \ cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname)) != 0); \ } \ static inline void jbd2_set_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_compat |= \ cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname); \ } \ static inline void jbd2_clear_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_compat &= \ ~cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname); \ } #define JBD2_FEATURE_RO_COMPAT_FUNCS(name, flagname) \ static inline bool jbd2_has_feature_##name(journal_t *j) \ { \ return (jbd2_format_support_feature(j) && \ ((j)->j_superblock->s_feature_ro_compat & \ cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname)) != 0); \ } \ static inline void jbd2_set_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_ro_compat |= \ cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname); \ } \ static inline void jbd2_clear_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_ro_compat &= \ ~cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname); \ } #define JBD2_FEATURE_INCOMPAT_FUNCS(name, flagname) \ static inline bool jbd2_has_feature_##name(journal_t *j) \ { \ return (jbd2_format_support_feature(j) && \ ((j)->j_superblock->s_feature_incompat & \ cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname)) != 0); \ } \ static inline void jbd2_set_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_incompat |= \ cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname); \ } \ static inline void jbd2_clear_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_incompat &= \ ~cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname); \ } JBD2_FEATURE_COMPAT_FUNCS(checksum, CHECKSUM) JBD2_FEATURE_INCOMPAT_FUNCS(revoke, REVOKE) JBD2_FEATURE_INCOMPAT_FUNCS(64bit, 64BIT) JBD2_FEATURE_INCOMPAT_FUNCS(async_commit, ASYNC_COMMIT) JBD2_FEATURE_INCOMPAT_FUNCS(csum2, CSUM_V2) JBD2_FEATURE_INCOMPAT_FUNCS(csum3, CSUM_V3) JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit, FAST_COMMIT) /* Journal high priority write IO operation flags */ #define JBD2_JOURNAL_REQ_FLAGS (REQ_META | REQ_SYNC | REQ_IDLE) /* * Journal flag definitions */ #define JBD2_UNMOUNT 0x001 /* Journal thread is being destroyed */ #define JBD2_ABORT 0x002 /* Journaling has been aborted for errors. */ #define JBD2_ACK_ERR 0x004 /* The errno in the sb has been acked */ #define JBD2_FLUSHED 0x008 /* The journal superblock has been flushed */ #define JBD2_LOADED 0x010 /* The journal superblock has been loaded */ #define JBD2_BARRIER 0x020 /* Use IDE barriers */ #define JBD2_ABORT_ON_SYNCDATA_ERR 0x040 /* Abort the journal on file * data write error in ordered * mode */ #define JBD2_CYCLE_RECORD 0x080 /* Journal cycled record log on * clean and empty filesystem * logging area */ #define JBD2_FAST_COMMIT_ONGOING 0x100 /* Fast commit is ongoing */ #define JBD2_FULL_COMMIT_ONGOING 0x200 /* Full commit is ongoing */ #define JBD2_JOURNAL_FLUSH_DISCARD 0x0001 #define JBD2_JOURNAL_FLUSH_ZEROOUT 0x0002 #define JBD2_JOURNAL_FLUSH_VALID (JBD2_JOURNAL_FLUSH_DISCARD | \ JBD2_JOURNAL_FLUSH_ZEROOUT) /* * Function declarations for the journaling transaction and buffer * management */ /* Filing buffers */ extern void jbd2_journal_unfile_buffer(journal_t *, struct journal_head *); extern bool __jbd2_journal_refile_buffer(struct journal_head *); extern void jbd2_journal_refile_buffer(journal_t *, struct journal_head *); extern void __jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); extern void jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); static inline void jbd2_file_log_bh(struct list_head *head, struct buffer_head *bh) { list_add_tail(&bh->b_assoc_buffers, head); } static inline void jbd2_unfile_log_bh(struct buffer_head *bh) { list_del_init(&bh->b_assoc_buffers); } /* Log buffer allocation */ struct buffer_head *jbd2_journal_get_descriptor_buffer(transaction_t *, int); void jbd2_descriptor_block_csum_set(journal_t *, struct buffer_head *); int jbd2_journal_next_log_block(journal_t *, unsigned long long *); int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid, unsigned long *block); int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block); void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block); /* Commit management */ extern void jbd2_journal_commit_transaction(journal_t *); /* Checkpoint list management */ enum jbd2_shrink_type {JBD2_SHRINK_DESTROY, JBD2_SHRINK_BUSY_STOP, JBD2_SHRINK_BUSY_SKIP}; void __jbd2_journal_clean_checkpoint_list(journal_t *journal, enum jbd2_shrink_type type); unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, unsigned long *nr_to_scan); int __jbd2_journal_remove_checkpoint(struct journal_head *); int jbd2_journal_try_remove_checkpoint(struct journal_head *jh); void jbd2_journal_destroy_checkpoint(journal_t *journal); void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *); /* * Triggers */ struct jbd2_buffer_trigger_type { /* * Fired a the moment data to write to the journal are known to be * stable - so either at the moment b_frozen_data is created or just * before a buffer is written to the journal. mapped_data is a mapped * buffer that is the frozen data for commit. */ void (*t_frozen)(struct jbd2_buffer_trigger_type *type, struct buffer_head *bh, void *mapped_data, size_t size); /* * Fired during journal abort for dirty buffers that will not be * committed. */ void (*t_abort)(struct jbd2_buffer_trigger_type *type, struct buffer_head *bh); }; extern void jbd2_buffer_frozen_trigger(struct journal_head *jh, void *mapped_data, struct jbd2_buffer_trigger_type *triggers); extern void jbd2_buffer_abort_trigger(struct journal_head *jh, struct jbd2_buffer_trigger_type *triggers); /* Buffer IO */ extern int jbd2_journal_write_metadata_buffer(transaction_t *transaction, struct journal_head *jh_in, struct buffer_head **bh_out, sector_t blocknr); /* Transaction cache support */ extern void jbd2_journal_destroy_transaction_cache(void); extern int __init jbd2_journal_init_transaction_cache(void); extern void jbd2_journal_free_transaction(transaction_t *); /* * Journal locking. * * We need to lock the journal during transaction state changes so that nobody * ever tries to take a handle on the running transaction while we are in the * middle of moving it to the commit phase. j_state_lock does this. * * Note that the locking is completely interrupt unsafe. We never touch * journal structures from interrupts. */ static inline handle_t *journal_current_handle(void) { return current->journal_info; } /* The journaling code user interface: * * Create and destroy handles * Register buffer modifications against the current transaction. */ extern handle_t *jbd2_journal_start(journal_t *, int nblocks); extern handle_t *jbd2__journal_start(journal_t *, int blocks, int rsv_blocks, int revoke_records, gfp_t gfp_mask, unsigned int type, unsigned int line_no); extern int jbd2_journal_restart(handle_t *, int nblocks); extern int jbd2__journal_restart(handle_t *, int nblocks, int revoke_records, gfp_t gfp_mask); extern int jbd2_journal_start_reserved(handle_t *handle, unsigned int type, unsigned int line_no); extern void jbd2_journal_free_reserved(handle_t *handle); extern int jbd2_journal_extend(handle_t *handle, int nblocks, int revoke_records); extern int jbd2_journal_get_write_access(handle_t *, struct buffer_head *); extern int jbd2_journal_get_create_access (handle_t *, struct buffer_head *); extern int jbd2_journal_get_undo_access(handle_t *, struct buffer_head *); void jbd2_journal_set_triggers(struct buffer_head *, struct jbd2_buffer_trigger_type *type); extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); extern int jbd2_journal_forget (handle_t *, struct buffer_head *); int jbd2_journal_invalidate_folio(journal_t *, struct folio *, size_t offset, size_t length); bool jbd2_journal_try_to_free_buffers(journal_t *journal, struct folio *folio); extern int jbd2_journal_stop(handle_t *); extern int jbd2_journal_flush(journal_t *journal, unsigned int flags); extern void jbd2_journal_lock_updates (journal_t *); extern void jbd2_journal_unlock_updates (journal_t *); void jbd2_journal_wait_updates(journal_t *); extern journal_t * jbd2_journal_init_dev(struct block_device *bdev, struct block_device *fs_dev, unsigned long long start, int len, int bsize); extern journal_t * jbd2_journal_init_inode (struct inode *); extern int jbd2_journal_update_format (journal_t *); extern int jbd2_journal_check_used_features (journal_t *, unsigned long, unsigned long, unsigned long); extern int jbd2_journal_check_available_features (journal_t *, unsigned long, unsigned long, unsigned long); extern int jbd2_journal_set_features (journal_t *, unsigned long, unsigned long, unsigned long); extern void jbd2_journal_clear_features (journal_t *, unsigned long, unsigned long, unsigned long); extern int jbd2_journal_load (journal_t *journal); extern int jbd2_journal_destroy (journal_t *); extern int jbd2_journal_recover (journal_t *journal); extern int jbd2_journal_wipe (journal_t *, int); extern int jbd2_journal_skip_recovery (journal_t *); extern void jbd2_journal_update_sb_errno(journal_t *); extern int jbd2_journal_update_sb_log_tail (journal_t *, tid_t, unsigned long, blk_opf_t); extern void jbd2_journal_abort (journal_t *, int); extern int jbd2_journal_errno (journal_t *); extern void jbd2_journal_ack_err (journal_t *); extern int jbd2_journal_clear_err (journal_t *); extern int jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *); extern int jbd2_journal_force_commit(journal_t *); extern int jbd2_journal_force_commit_nested(journal_t *); extern int jbd2_journal_inode_ranged_write(handle_t *handle, struct jbd2_inode *inode, loff_t start_byte, loff_t length); extern int jbd2_journal_inode_ranged_wait(handle_t *handle, struct jbd2_inode *inode, loff_t start_byte, loff_t length); extern int jbd2_journal_finish_inode_data_buffers( struct jbd2_inode *jinode); extern int jbd2_journal_begin_ordered_truncate(journal_t *journal, struct jbd2_inode *inode, loff_t new_size); extern void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode); extern void jbd2_journal_release_jbd_inode(journal_t *journal, struct jbd2_inode *jinode); /* * journal_head management */ struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh); struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh); void jbd2_journal_put_journal_head(struct journal_head *jh); /* * handle management */ extern struct kmem_cache *jbd2_handle_cache; /* * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). The typecast is * intentional to enforce typesafety. */ #define jbd2_alloc_handle(_gfp_flags) \ ((handle_t *)kmem_cache_zalloc(jbd2_handle_cache, _gfp_flags)) static inline void jbd2_free_handle(handle_t *handle) { kmem_cache_free(jbd2_handle_cache, handle); } /* * jbd2_inode management (optional, for those file systems that want to use * dynamically allocated jbd2_inode structures) */ extern struct kmem_cache *jbd2_inode_cache; /* * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). The typecast is * intentional to enforce typesafety. */ #define jbd2_alloc_inode(_gfp_flags) \ ((struct jbd2_inode *)kmem_cache_alloc(jbd2_inode_cache, _gfp_flags)) static inline void jbd2_free_inode(struct jbd2_inode *jinode) { kmem_cache_free(jbd2_inode_cache, jinode); } /* Primary revoke support */ #define JOURNAL_REVOKE_DEFAULT_HASH 256 extern int jbd2_journal_init_revoke(journal_t *, int); extern void jbd2_journal_destroy_revoke_record_cache(void); extern void jbd2_journal_destroy_revoke_table_cache(void); extern int __init jbd2_journal_init_revoke_record_cache(void); extern int __init jbd2_journal_init_revoke_table_cache(void); extern void jbd2_journal_destroy_revoke(journal_t *); extern int jbd2_journal_revoke (handle_t *, unsigned long long, struct buffer_head *); extern int jbd2_journal_cancel_revoke(handle_t *, struct journal_head *); extern void jbd2_journal_write_revoke_records(transaction_t *transaction, struct list_head *log_bufs); /* Recovery revoke support */ extern int jbd2_journal_set_revoke(journal_t *, unsigned long long, tid_t); extern int jbd2_journal_test_revoke(journal_t *, unsigned long long, tid_t); extern void jbd2_journal_clear_revoke(journal_t *); extern void jbd2_journal_switch_revoke_table(journal_t *journal); extern void jbd2_clear_buffer_revoked_flags(journal_t *journal); /* * The log thread user interface: * * Request space in the current transaction, and force transaction commit * transitions on demand. */ int jbd2_log_start_commit(journal_t *journal, tid_t tid); int jbd2_journal_start_commit(journal_t *journal, tid_t *tid); int jbd2_log_wait_commit(journal_t *journal, tid_t tid); int jbd2_transaction_committed(journal_t *journal, tid_t tid); int jbd2_complete_transaction(journal_t *journal, tid_t tid); int jbd2_log_do_checkpoint(journal_t *journal); int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid); void __jbd2_log_wait_for_space(journal_t *journal); extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *); extern int jbd2_cleanup_journal_tail(journal_t *); /* Fast commit related APIs */ int jbd2_fc_begin_commit(journal_t *journal, tid_t tid); int jbd2_fc_end_commit(journal_t *journal); int jbd2_fc_end_commit_fallback(journal_t *journal); int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out); int jbd2_submit_inode_data(journal_t *journal, struct jbd2_inode *jinode); int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode); int jbd2_fc_wait_bufs(journal_t *journal, int num_blks); int jbd2_fc_release_bufs(journal_t *journal); /* * is_journal_abort * * Simple test wrapper function to test the JBD2_ABORT state flag. This * bit, when set, indicates that we have had a fatal error somewhere, * either inside the journaling layer or indicated to us by the client * (eg. ext3), and that we and should not commit any further * transactions. */ static inline int is_journal_aborted(journal_t *journal) { return journal->j_flags & JBD2_ABORT; } static inline int is_handle_aborted(handle_t *handle) { if (handle->h_aborted || !handle->h_transaction) return 1; return is_journal_aborted(handle->h_transaction->t_journal); } static inline void jbd2_journal_abort_handle(handle_t *handle) { handle->h_aborted = 1; } static inline void jbd2_init_fs_dev_write_error(journal_t *journal) { struct address_space *mapping = journal->j_fs_dev->bd_mapping; /* * Save the original wb_err value of client fs's bdev mapping which * could be used to detect the client fs's metadata async write error. */ errseq_check_and_advance(&mapping->wb_err, &journal->j_fs_dev_wb_err); } static inline int jbd2_check_fs_dev_write_error(journal_t *journal) { struct address_space *mapping = journal->j_fs_dev->bd_mapping; return errseq_check(&mapping->wb_err, READ_ONCE(journal->j_fs_dev_wb_err)); } #endif /* __KERNEL__ */ /* Comparison functions for transaction IDs: perform comparisons using * modulo arithmetic so that they work over sequence number wraps. */ static inline int tid_gt(tid_t x, tid_t y) { int difference = (x - y); return (difference > 0); } static inline int tid_geq(tid_t x, tid_t y) { int difference = (x - y); return (difference >= 0); } extern int jbd2_journal_blocks_per_page(struct inode *inode); extern size_t journal_tag_bytes(journal_t *journal); static inline bool jbd2_journal_has_csum_v2or3_feature(journal_t *j) { return jbd2_has_feature_csum2(j) || jbd2_has_feature_csum3(j); } static inline int jbd2_journal_has_csum_v2or3(journal_t *journal) { WARN_ON_ONCE(jbd2_journal_has_csum_v2or3_feature(journal) && journal->j_chksum_driver == NULL); return journal->j_chksum_driver != NULL; } static inline int jbd2_journal_get_num_fc_blks(journal_superblock_t *jsb) { int num_fc_blocks = be32_to_cpu(jsb->s_num_fc_blks); return num_fc_blocks ? num_fc_blocks : JBD2_DEFAULT_FAST_COMMIT_BLOCKS; } /* * Return number of free blocks in the log. Must be called under j_state_lock. */ static inline unsigned long jbd2_log_space_left(journal_t *journal) { /* Allow for rounding errors */ long free = journal->j_free - 32; if (journal->j_committing_transaction) { free -= atomic_read(&journal-> j_committing_transaction->t_outstanding_credits); } return max_t(long, free, 0); } /* * Definitions which augment the buffer_head layer */ /* journaling buffer types */ #define BJ_None 0 /* Not journaled */ #define BJ_Metadata 1 /* Normal journaled metadata */ #define BJ_Forget 2 /* Buffer superseded by this transaction */ #define BJ_Shadow 3 /* Buffer contents being shadowed to the log */ #define BJ_Reserved 4 /* Buffer is reserved for access by journal */ #define BJ_Types 5 /* JBD uses a CRC32 checksum */ #define JBD_MAX_CHECKSUM_SIZE 4 static inline u32 jbd2_chksum(journal_t *journal, u32 crc, const void *address, unsigned int length) { struct { struct shash_desc shash; char ctx[JBD_MAX_CHECKSUM_SIZE]; } desc; int err; BUG_ON(crypto_shash_descsize(journal->j_chksum_driver) > JBD_MAX_CHECKSUM_SIZE); desc.shash.tfm = journal->j_chksum_driver; *(u32 *)desc.ctx = crc; err = crypto_shash_update(&desc.shash, address, length); BUG_ON(err); return *(u32 *)desc.ctx; } /* Return most recent uncommitted transaction */ static inline tid_t jbd2_get_latest_transaction(journal_t *journal) { tid_t tid; read_lock(&journal->j_state_lock); tid = journal->j_commit_request; if (journal->j_running_transaction) tid = journal->j_running_transaction->t_tid; read_unlock(&journal->j_state_lock); return tid; } static inline int jbd2_handle_buffer_credits(handle_t *handle) { journal_t *journal; if (!handle->h_reserved) journal = handle->h_transaction->t_journal; else journal = handle->h_journal; return handle->h_total_credits - DIV_ROUND_UP(handle->h_revoke_credits_requested, journal->j_revoke_records_per_block); } #ifdef __KERNEL__ #define buffer_trace_init(bh) do {} while (0) #define print_buffer_fields(bh) do {} while (0) #define print_buffer_trace(bh) do {} while (0) #define BUFFER_TRACE(bh, info) do {} while (0) #define BUFFER_TRACE2(bh, bh2, info) do {} while (0) #define JBUFFER_TRACE(jh, info) do {} while (0) #endif /* __KERNEL__ */ #define EFSBADCRC EBADMSG /* Bad CRC detected */ #define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */ #endif /* _LINUX_JBD2_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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHEFS_COMPRESS_H #define _BCACHEFS_COMPRESS_H #include "extents_types.h" static const unsigned __bch2_compression_opt_to_type[] = { #define x(t, n) [BCH_COMPRESSION_OPT_##t] = BCH_COMPRESSION_TYPE_##t, BCH_COMPRESSION_OPTS() #undef x }; struct bch_compression_opt { u8 type:4, level:4; }; static inline struct bch_compression_opt __bch2_compression_decode(unsigned v) { return (struct bch_compression_opt) { .type = v & 15, .level = v >> 4, }; } static inline bool bch2_compression_opt_valid(unsigned v) { struct bch_compression_opt opt = __bch2_compression_decode(v); return opt.type < ARRAY_SIZE(__bch2_compression_opt_to_type) && !(!opt.type && opt.level); } static inline struct bch_compression_opt bch2_compression_decode(unsigned v) { return bch2_compression_opt_valid(v) ? __bch2_compression_decode(v) : (struct bch_compression_opt) { 0 }; } static inline unsigned bch2_compression_encode(struct bch_compression_opt opt) { return opt.type|(opt.level << 4); } static inline enum bch_compression_type bch2_compression_opt_to_type(unsigned v) { return __bch2_compression_opt_to_type[bch2_compression_decode(v).type]; } int bch2_bio_uncompress_inplace(struct bch_fs *, struct bio *, struct bch_extent_crc_unpacked *); int bch2_bio_uncompress(struct bch_fs *, struct bio *, struct bio *, struct bvec_iter, struct bch_extent_crc_unpacked); unsigned bch2_bio_compress(struct bch_fs *, struct bio *, size_t *, struct bio *, size_t *, unsigned); int bch2_check_set_has_compressed_data(struct bch_fs *, unsigned); void bch2_fs_compress_exit(struct bch_fs *); int bch2_fs_compress_init(struct bch_fs *); void bch2_compression_opt_to_text(struct printbuf *, u64); int bch2_opt_compression_parse(struct bch_fs *, const char *, u64 *, struct printbuf *); void bch2_opt_compression_to_text(struct printbuf *, struct bch_fs *, struct bch_sb *, u64); int bch2_opt_compression_validate(u64, struct printbuf *); #define bch2_opt_compression (struct bch_opt_fn) { \ .parse = bch2_opt_compression_parse, \ .to_text = bch2_opt_compression_to_text, \ .validate = bch2_opt_compression_validate, \ } #endif /* _BCACHEFS_COMPRESS_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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * NFS internal definitions */ #include "nfs4_fs.h" #include <linux/fs_context.h> #include <linux/security.h> #include <linux/crc32.h> #include <linux/sunrpc/addr.h> #include <linux/nfs_page.h> #include <linux/wait_bit.h> #define NFS_SB_MASK (SB_RDONLY|SB_NOSUID|SB_NODEV|SB_NOEXEC|SB_SYNCHRONOUS) extern const struct export_operations nfs_export_ops; struct nfs_string; struct nfs_pageio_descriptor; static inline void nfs_attr_check_mountpoint(struct super_block *parent, struct nfs_fattr *fattr) { if (!nfs_fsid_equal(&NFS_SB(parent)->fsid, &fattr->fsid)) fattr->valid |= NFS_ATTR_FATTR_MOUNTPOINT; } static inline int nfs_attr_use_mounted_on_fileid(struct nfs_fattr *fattr) { if (((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) == 0) || (((fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT) == 0) && ((fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) == 0))) return 0; return 1; } static inline bool nfs_lookup_is_soft_revalidate(const struct dentry *dentry) { if (!(NFS_SB(dentry->d_sb)->flags & NFS_MOUNT_SOFTREVAL)) return false; if (!d_is_positive(dentry) || !NFS_FH(d_inode(dentry))->size) return false; return true; } static inline fmode_t flags_to_mode(int flags) { fmode_t res = (__force fmode_t)flags & FMODE_EXEC; if ((flags & O_ACCMODE) != O_WRONLY) res |= FMODE_READ; if ((flags & O_ACCMODE) != O_RDONLY) res |= FMODE_WRITE; return res; } /* * Note: RFC 1813 doesn't limit the number of auth flavors that * a server can return, so make something up. */ #define NFS_MAX_SECFLAVORS (12) /* * Value used if the user did not specify a port value. */ #define NFS_UNSPEC_PORT (-1) #define NFS_UNSPEC_RETRANS (UINT_MAX) #define NFS_UNSPEC_TIMEO (UINT_MAX) struct nfs_client_initdata { unsigned long init_flags; const char *hostname; /* Hostname of the server */ const struct sockaddr_storage *addr; /* Address of the server */ const char *nodename; /* Hostname of the client */ const char *ip_addr; /* IP address of the client */ size_t addrlen; struct nfs_subversion *nfs_mod; int proto; u32 minorversion; unsigned int nconnect; unsigned int max_connect; struct net *net; const struct rpc_timeout *timeparms; const struct cred *cred; struct xprtsec_parms xprtsec; unsigned long connect_timeout; unsigned long reconnect_timeout; }; /* * In-kernel mount arguments */ struct nfs_fs_context { bool internal; bool skip_reconfig_option_check; bool need_mount; bool sloppy; unsigned int flags; /* NFS{,4}_MOUNT_* flags */ unsigned int rsize, wsize; unsigned int timeo, retrans; unsigned int acregmin, acregmax; unsigned int acdirmin, acdirmax; unsigned int namlen; unsigned int options; unsigned int bsize; struct nfs_auth_info auth_info; rpc_authflavor_t selected_flavor; struct xprtsec_parms xprtsec; char *client_address; unsigned int version; unsigned int minorversion; char *fscache_uniq; unsigned short protofamily; unsigned short mountfamily; bool has_sec_mnt_opts; int lock_status; struct { union { struct sockaddr address; struct sockaddr_storage _address; }; size_t addrlen; char *hostname; u32 version; int port; unsigned short protocol; } mount_server; struct { union { struct sockaddr address; struct sockaddr_storage _address; }; size_t addrlen; char *hostname; char *export_path; int port; unsigned short protocol; unsigned short nconnect; unsigned short max_connect; unsigned short export_path_len; } nfs_server; struct nfs_fh *mntfh; struct nfs_server *server; struct nfs_subversion *nfs_mod; /* Information for a cloned mount. */ struct nfs_clone_mount { struct super_block *sb; struct dentry *dentry; struct nfs_fattr *fattr; unsigned int inherited_bsize; } clone_data; }; enum nfs_lock_status { NFS_LOCK_NOT_SET = 0, NFS_LOCK_LOCK = 1, NFS_LOCK_NOLOCK = 2, }; #define nfs_errorf(fc, fmt, ...) ((fc)->log.log ? \ errorf(fc, fmt, ## __VA_ARGS__) : \ ({ dprintk(fmt "\n", ## __VA_ARGS__); })) #define nfs_ferrorf(fc, fac, fmt, ...) ((fc)->log.log ? \ errorf(fc, fmt, ## __VA_ARGS__) : \ ({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); })) #define nfs_invalf(fc, fmt, ...) ((fc)->log.log ? \ invalf(fc, fmt, ## __VA_ARGS__) : \ ({ dprintk(fmt "\n", ## __VA_ARGS__); -EINVAL; })) #define nfs_finvalf(fc, fac, fmt, ...) ((fc)->log.log ? \ invalf(fc, fmt, ## __VA_ARGS__) : \ ({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); -EINVAL; })) #define nfs_warnf(fc, fmt, ...) ((fc)->log.log ? \ warnf(fc, fmt, ## __VA_ARGS__) : \ ({ dprintk(fmt "\n", ## __VA_ARGS__); })) #define nfs_fwarnf(fc, fac, fmt, ...) ((fc)->log.log ? \ warnf(fc, fmt, ## __VA_ARGS__) : \ ({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); })) static inline struct nfs_fs_context *nfs_fc2context(const struct fs_context *fc) { return fc->fs_private; } /* mount_clnt.c */ struct nfs_mount_request { struct sockaddr_storage *sap; size_t salen; char *hostname; char *dirpath; u32 version; unsigned short protocol; struct nfs_fh *fh; int noresvport; unsigned int *auth_flav_len; rpc_authflavor_t *auth_flavs; struct net *net; }; extern int nfs_mount(struct nfs_mount_request *info, int timeo, int retrans); extern void nfs_umount(const struct nfs_mount_request *info); /* client.c */ extern const struct rpc_program nfs_program; extern void nfs_clients_init(struct net *net); extern void nfs_clients_exit(struct net *net); extern struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *); int nfs_create_rpc_client(struct nfs_client *, const struct nfs_client_initdata *, rpc_authflavor_t); struct nfs_client *nfs_get_client(const struct nfs_client_initdata *); int nfs_probe_server(struct nfs_server *, struct nfs_fh *); void nfs_server_insert_lists(struct nfs_server *); void nfs_server_remove_lists(struct nfs_server *); void nfs_init_timeout_values(struct rpc_timeout *to, int proto, int timeo, int retrans); int nfs_init_server_rpcclient(struct nfs_server *, const struct rpc_timeout *t, rpc_authflavor_t); struct nfs_server *nfs_alloc_server(void); void nfs_server_copy_userdata(struct nfs_server *, struct nfs_server *); extern void nfs_put_client(struct nfs_client *); extern void nfs_free_client(struct nfs_client *); extern struct nfs_client *nfs4_find_client_ident(struct net *, int); extern struct nfs_client * nfs4_find_client_sessionid(struct net *, const struct sockaddr *, struct nfs4_sessionid *, u32); extern struct nfs_server *nfs_create_server(struct fs_context *); extern void nfs4_server_set_init_caps(struct nfs_server *); extern struct nfs_server *nfs4_create_server(struct fs_context *); extern struct nfs_server *nfs4_create_referral_server(struct fs_context *); extern int nfs4_update_server(struct nfs_server *server, const char *hostname, struct sockaddr_storage *sap, size_t salen, struct net *net); extern void nfs_free_server(struct nfs_server *server); extern struct nfs_server *nfs_clone_server(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, rpc_authflavor_t); extern bool nfs_client_init_is_complete(const struct nfs_client *clp); extern int nfs_client_init_status(const struct nfs_client *clp); extern int nfs_wait_client_init_complete(const struct nfs_client *clp); extern void nfs_mark_client_ready(struct nfs_client *clp, int state); extern struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv, const struct sockaddr_storage *ds_addr, int ds_addrlen, int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans, u32 minor_version); extern struct rpc_clnt *nfs4_find_or_create_ds_client(struct nfs_client *, struct inode *); extern struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv, const struct sockaddr_storage *ds_addr, int ds_addrlen, int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans); #ifdef CONFIG_PROC_FS extern int __init nfs_fs_proc_init(void); extern void nfs_fs_proc_exit(void); extern int nfs_fs_proc_net_init(struct net *net); extern void nfs_fs_proc_net_exit(struct net *net); #else static inline int nfs_fs_proc_net_init(struct net *net) { return 0; } static inline void nfs_fs_proc_net_exit(struct net *net) { } static inline int nfs_fs_proc_init(void) { return 0; } static inline void nfs_fs_proc_exit(void) { } #endif /* callback_xdr.c */ extern const struct svc_version nfs4_callback_version1; extern const struct svc_version nfs4_callback_version4; /* fs_context.c */ extern struct file_system_type nfs_fs_type; /* pagelist.c */ extern int __init nfs_init_nfspagecache(void); extern void nfs_destroy_nfspagecache(void); extern int __init nfs_init_readpagecache(void); extern void nfs_destroy_readpagecache(void); extern int __init nfs_init_writepagecache(void); extern void nfs_destroy_writepagecache(void); extern int __init nfs_init_directcache(void); extern void nfs_destroy_directcache(void); extern void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr, void (*release)(struct nfs_pgio_header *hdr)); void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos); int nfs_iocounter_wait(struct nfs_lock_context *l_ctx); extern const struct nfs_pageio_ops nfs_pgio_rw_ops; struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *); void nfs_pgio_header_free(struct nfs_pgio_header *); int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *); int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr, const struct cred *cred, const struct nfs_rpc_ops *rpc_ops, const struct rpc_call_ops *call_ops, int how, int flags); void nfs_free_request(struct nfs_page *req); struct nfs_pgio_mirror * nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc); static inline bool nfs_match_open_context(const struct nfs_open_context *ctx1, const struct nfs_open_context *ctx2) { return cred_fscmp(ctx1->cred, ctx2->cred) == 0 && ctx1->state == ctx2->state; } /* nfs2xdr.c */ extern const struct rpc_procinfo nfs_procedures[]; extern int nfs2_decode_dirent(struct xdr_stream *, struct nfs_entry *, bool); /* nfs3xdr.c */ extern const struct rpc_procinfo nfs3_procedures[]; extern int nfs3_decode_dirent(struct xdr_stream *, struct nfs_entry *, bool); /* nfs4xdr.c */ #if IS_ENABLED(CONFIG_NFS_V4) extern int nfs4_decode_dirent(struct xdr_stream *, struct nfs_entry *, bool); #endif #ifdef CONFIG_NFS_V4_1 extern const u32 nfs41_maxread_overhead; extern const u32 nfs41_maxwrite_overhead; extern const u32 nfs41_maxgetdevinfo_overhead; #endif /* nfs4proc.c */ #if IS_ENABLED(CONFIG_NFS_V4) extern const struct rpc_procinfo nfs4_procedures[]; #endif #ifdef CONFIG_NFS_V4_SECURITY_LABEL extern struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags); static inline struct nfs4_label * nfs4_label_copy(struct nfs4_label *dst, struct nfs4_label *src) { if (!dst || !src) return NULL; if (src->len > NFS4_MAXLABELLEN) return NULL; dst->lfs = src->lfs; dst->pi = src->pi; dst->len = src->len; memcpy(dst->label, src->label, src->len); return dst; } static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi) { if (nfs_server_capable(&nfsi->vfs_inode, NFS_CAP_SECURITY_LABEL)) nfsi->cache_validity |= NFS_INO_INVALID_LABEL; } #else static inline struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { return NULL; } static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi) { } static inline struct nfs4_label * nfs4_label_copy(struct nfs4_label *dst, struct nfs4_label *src) { return NULL; } #endif /* CONFIG_NFS_V4_SECURITY_LABEL */ /* proc.c */ void nfs_close_context(struct nfs_open_context *ctx, int is_sync); extern struct nfs_client *nfs_init_client(struct nfs_client *clp, const struct nfs_client_initdata *); /* dir.c */ extern void nfs_readdir_record_entry_cache_hit(struct inode *dir); extern void nfs_readdir_record_entry_cache_miss(struct inode *dir); extern unsigned long nfs_access_cache_count(struct shrinker *shrink, struct shrink_control *sc); extern unsigned long nfs_access_cache_scan(struct shrinker *shrink, struct shrink_control *sc); struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int); void nfs_d_prune_case_insensitive_aliases(struct inode *inode); int nfs_create(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, bool); int nfs_mkdir(struct mnt_idmap *, struct inode *, struct dentry *, umode_t); int nfs_rmdir(struct inode *, struct dentry *); int nfs_unlink(struct inode *, struct dentry *); int nfs_symlink(struct mnt_idmap *, struct inode *, struct dentry *, const char *); int nfs_link(struct dentry *, struct inode *, struct dentry *); int nfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, dev_t); int nfs_rename(struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); #ifdef CONFIG_NFS_V4_2 static inline __u32 nfs_access_xattr_mask(const struct nfs_server *server) { if (!(server->caps & NFS_CAP_XATTR)) return 0; return NFS4_ACCESS_XAREAD | NFS4_ACCESS_XAWRITE | NFS4_ACCESS_XALIST; } #else static inline __u32 nfs_access_xattr_mask(const struct nfs_server *server) { return 0; } #endif /* file.c */ int nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync); loff_t nfs_file_llseek(struct file *, loff_t, int); ssize_t nfs_file_read(struct kiocb *, struct iov_iter *); ssize_t nfs_file_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); int nfs_file_mmap(struct file *, struct vm_area_struct *); ssize_t nfs_file_write(struct kiocb *, struct iov_iter *); int nfs_file_release(struct inode *, struct file *); int nfs_lock(struct file *, int, struct file_lock *); int nfs_flock(struct file *, int, struct file_lock *); int nfs_check_flags(int); /* inode.c */ extern struct workqueue_struct *nfsiod_workqueue; extern struct inode *nfs_alloc_inode(struct super_block *sb); extern void nfs_free_inode(struct inode *); extern int nfs_write_inode(struct inode *, struct writeback_control *); extern int nfs_drop_inode(struct inode *); extern void nfs_clear_inode(struct inode *); extern void nfs_evict_inode(struct inode *); extern void nfs_zap_acl_cache(struct inode *inode); extern void nfs_set_cache_invalid(struct inode *inode, unsigned long flags); extern bool nfs_check_cache_invalid(struct inode *, unsigned long); extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode); /* super.c */ extern const struct super_operations nfs_sops; bool nfs_auth_info_match(const struct nfs_auth_info *, rpc_authflavor_t); int nfs_try_get_tree(struct fs_context *); int nfs_get_tree_common(struct fs_context *); void nfs_kill_super(struct super_block *); extern int __init register_nfs_fs(void); extern void __exit unregister_nfs_fs(void); extern bool nfs_sb_active(struct super_block *sb); extern void nfs_sb_deactive(struct super_block *sb); extern int nfs_client_for_each_server(struct nfs_client *clp, int (*fn)(struct nfs_server *, void *), void *data); #ifdef CONFIG_NFS_FSCACHE extern const struct netfs_request_ops nfs_netfs_ops; #endif /* io.c */ extern void nfs_start_io_read(struct inode *inode); extern void nfs_end_io_read(struct inode *inode); extern void nfs_start_io_write(struct inode *inode); extern void nfs_end_io_write(struct inode *inode); extern void nfs_start_io_direct(struct inode *inode); extern void nfs_end_io_direct(struct inode *inode); static inline bool nfs_file_io_is_buffered(struct nfs_inode *nfsi) { return test_bit(NFS_INO_ODIRECT, &nfsi->flags) == 0; } /* namespace.c */ #define NFS_PATH_CANONICAL 1 extern char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen, unsigned flags); extern struct vfsmount *nfs_d_automount(struct path *path); int nfs_submount(struct fs_context *, struct nfs_server *); int nfs_do_submount(struct fs_context *); /* getroot.c */ extern int nfs_get_root(struct super_block *s, struct fs_context *fc); #if IS_ENABLED(CONFIG_NFS_V4) extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh, bool); #endif struct nfs_pgio_completion_ops; /* read.c */ extern const struct nfs_pgio_completion_ops nfs_async_read_completion_ops; extern void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode, bool force_mds, const struct nfs_pgio_completion_ops *compl_ops); extern bool nfs_read_alloc_scratch(struct nfs_pgio_header *hdr, size_t size); extern int nfs_read_add_folio(struct nfs_pageio_descriptor *pgio, struct nfs_open_context *ctx, struct folio *folio); extern void nfs_pageio_complete_read(struct nfs_pageio_descriptor *pgio); extern void nfs_read_prepare(struct rpc_task *task, void *calldata); extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio); /* super.c */ void nfs_umount_begin(struct super_block *); int nfs_statfs(struct dentry *, struct kstatfs *); int nfs_show_options(struct seq_file *, struct dentry *); int nfs_show_devname(struct seq_file *, struct dentry *); int nfs_show_path(struct seq_file *, struct dentry *); int nfs_show_stats(struct seq_file *, struct dentry *); int nfs_reconfigure(struct fs_context *); /* write.c */ extern void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags, bool force_mds, const struct nfs_pgio_completion_ops *compl_ops); extern void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio); extern void nfs_commit_free(struct nfs_commit_data *p); extern void nfs_commit_prepare(struct rpc_task *task, void *calldata); extern int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data, const struct nfs_rpc_ops *nfs_ops, const struct rpc_call_ops *call_ops, int how, int flags); extern void nfs_init_commit(struct nfs_commit_data *data, struct list_head *head, struct pnfs_layout_segment *lseg, struct nfs_commit_info *cinfo); int nfs_scan_commit_list(struct list_head *src, struct list_head *dst, struct nfs_commit_info *cinfo, int max); unsigned long nfs_reqs_to_commit(struct nfs_commit_info *); int nfs_scan_commit(struct inode *inode, struct list_head *dst, struct nfs_commit_info *cinfo); void nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, struct nfs_commit_info *cinfo, u32 ds_commit_idx); int nfs_write_need_commit(struct nfs_pgio_header *); void nfs_writeback_update_inode(struct nfs_pgio_header *hdr); int nfs_generic_commit_list(struct inode *inode, struct list_head *head, int how, struct nfs_commit_info *cinfo); void nfs_retry_commit(struct list_head *page_list, struct pnfs_layout_segment *lseg, struct nfs_commit_info *cinfo, u32 ds_commit_idx); void nfs_commitdata_release(struct nfs_commit_data *data); void nfs_request_add_commit_list(struct nfs_page *req, struct nfs_commit_info *cinfo); void nfs_request_add_commit_list_locked(struct nfs_page *req, struct list_head *dst, struct nfs_commit_info *cinfo); void nfs_request_remove_commit_list(struct nfs_page *req, struct nfs_commit_info *cinfo); void nfs_init_cinfo(struct nfs_commit_info *cinfo, struct inode *inode, struct nfs_direct_req *dreq); int nfs_key_timeout_notify(struct file *filp, struct inode *inode); bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx, struct inode *inode); void nfs_pageio_stop_mirroring(struct nfs_pageio_descriptor *pgio); int nfs_filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); #ifdef CONFIG_NFS_V4_1 static inline void pnfs_bucket_clear_pnfs_ds_commit_verifiers(struct pnfs_commit_bucket *buckets, unsigned int nbuckets) { unsigned int i; for (i = 0; i < nbuckets; i++) buckets[i].direct_verf.committed = NFS_INVALID_STABLE_HOW; } static inline void nfs_clear_pnfs_ds_commit_verifiers(struct pnfs_ds_commit_info *cinfo) { struct pnfs_commit_array *array; rcu_read_lock(); list_for_each_entry_rcu(array, &cinfo->commits, cinfo_list) pnfs_bucket_clear_pnfs_ds_commit_verifiers(array->buckets, array->nbuckets); rcu_read_unlock(); } #else static inline void nfs_clear_pnfs_ds_commit_verifiers(struct pnfs_ds_commit_info *cinfo) { } #endif #ifdef CONFIG_MIGRATION int nfs_migrate_folio(struct address_space *, struct folio *dst, struct folio *src, enum migrate_mode); #else #define nfs_migrate_folio NULL #endif static inline int nfs_write_verifier_cmp(const struct nfs_write_verifier *v1, const struct nfs_write_verifier *v2) { return memcmp(v1->data, v2->data, sizeof(v1->data)); } static inline bool nfs_write_match_verf(const struct nfs_writeverf *verf, struct nfs_page *req) { return verf->committed > NFS_UNSTABLE && !nfs_write_verifier_cmp(&req->wb_verf, &verf->verifier); } static inline gfp_t nfs_io_gfp_mask(void) { if (current->flags & PF_WQ_WORKER) return GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; return GFP_KERNEL; } /* * Special version of should_remove_suid() that ignores capabilities. */ static inline int nfs_should_remove_suid(const struct inode *inode) { umode_t mode = inode->i_mode; int kill = 0; /* suid always must be killed */ if (unlikely(mode & S_ISUID)) kill = ATTR_KILL_SUID; /* * sgid without any exec bits is just a mandatory locking mark; leave * it alone. If some exec bits are set, it's a real sgid; kill it. */ if (unlikely((mode & S_ISGID) && (mode & S_IXGRP))) kill |= ATTR_KILL_SGID; if (unlikely(kill && S_ISREG(mode))) return kill; return 0; } /* unlink.c */ extern struct rpc_task * nfs_async_rename(struct inode *old_dir, struct inode *new_dir, struct dentry *old_dentry, struct dentry *new_dentry, void (*complete)(struct rpc_task *, struct nfs_renamedata *)); extern int nfs_sillyrename(struct inode *dir, struct dentry *dentry); /* direct.c */ void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo, struct nfs_direct_req *dreq); extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq, loff_t offset); /* nfs4proc.c */ extern struct nfs_client *nfs4_init_client(struct nfs_client *clp, const struct nfs_client_initdata *); extern int nfs40_walk_client_list(struct nfs_client *clp, struct nfs_client **result, const struct cred *cred); extern int nfs41_walk_client_list(struct nfs_client *clp, struct nfs_client **result, const struct cred *cred); extern void nfs4_test_session_trunk(struct rpc_clnt *clnt, struct rpc_xprt *xprt, void *data); static inline struct inode *nfs_igrab_and_active(struct inode *inode) { struct super_block *sb = inode->i_sb; if (sb && nfs_sb_active(sb)) { if (igrab(inode)) return inode; nfs_sb_deactive(sb); } return NULL; } static inline void nfs_iput_and_deactive(struct inode *inode) { if (inode != NULL) { struct super_block *sb = inode->i_sb; iput(inode); nfs_sb_deactive(sb); } } /* * Determine the device name as a string */ static inline char *nfs_devname(struct dentry *dentry, char *buffer, ssize_t buflen) { char *dummy; return nfs_path(&dummy, dentry, buffer, buflen, NFS_PATH_CANONICAL); } /* * Determine the actual block size (and log2 thereof) */ static inline unsigned long nfs_block_bits(unsigned long bsize, unsigned char *nrbitsp) { /* make sure blocksize is a power of two */ if ((bsize & (bsize - 1)) || nrbitsp) { unsigned char nrbits; for (nrbits = 31; nrbits && !(bsize & (1UL << nrbits)); nrbits--) ; bsize = 1UL << nrbits; if (nrbitsp) *nrbitsp = nrbits; } return bsize; } /* * Calculate the number of 512byte blocks used. */ static inline blkcnt_t nfs_calc_block_size(u64 tsize) { blkcnt_t used = (tsize + 511) >> 9; return (used > ULONG_MAX) ? ULONG_MAX : used; } /* * Compute and set NFS server blocksize */ static inline unsigned long nfs_block_size(unsigned long bsize, unsigned char *nrbitsp) { if (bsize < NFS_MIN_FILE_IO_SIZE) bsize = NFS_DEF_FILE_IO_SIZE; else if (bsize >= NFS_MAX_FILE_IO_SIZE) bsize = NFS_MAX_FILE_IO_SIZE; return nfs_block_bits(bsize, nrbitsp); } /* * Compute and set NFS server rsize / wsize */ static inline unsigned long nfs_io_size(unsigned long iosize, enum xprt_transports proto) { if (iosize < NFS_MIN_FILE_IO_SIZE) iosize = NFS_DEF_FILE_IO_SIZE; else if (iosize >= NFS_MAX_FILE_IO_SIZE) iosize = NFS_MAX_FILE_IO_SIZE; if (proto == XPRT_TRANSPORT_UDP || iosize < PAGE_SIZE) return nfs_block_bits(iosize, NULL); return iosize & PAGE_MASK; } /* * Determine the maximum file size for a superblock */ static inline void nfs_super_set_maxbytes(struct super_block *sb, __u64 maxfilesize) { sb->s_maxbytes = (loff_t)maxfilesize; if (sb->s_maxbytes > MAX_LFS_FILESIZE || sb->s_maxbytes <= 0) sb->s_maxbytes = MAX_LFS_FILESIZE; } /* * Record the page as unstable (an extra writeback period) and mark its * inode as dirty. */ static inline void nfs_folio_mark_unstable(struct folio *folio, struct nfs_commit_info *cinfo) { if (folio && !cinfo->dreq) { struct inode *inode = folio->mapping->host; long nr = folio_nr_pages(folio); /* This page is really still in write-back - just that the * writeback is happening on the server now. */ node_stat_mod_folio(folio, NR_WRITEBACK, nr); wb_stat_mod(&inode_to_bdi(inode)->wb, WB_WRITEBACK, nr); __mark_inode_dirty(inode, I_DIRTY_DATASYNC); } } /* * Determine the number of bytes of data the page contains */ static inline size_t nfs_folio_length(struct folio *folio) { loff_t i_size = i_size_read(folio->mapping->host); if (i_size > 0) { pgoff_t index = folio->index >> folio_order(folio); pgoff_t end_index = (i_size - 1) >> folio_shift(folio); if (index < end_index) return folio_size(folio); if (index == end_index) return offset_in_folio(folio, i_size - 1) + 1; } return 0; } /* * Convert a umode to a dirent->d_type */ static inline unsigned char nfs_umode_to_dtype(umode_t mode) { return (mode >> 12) & 15; } /* * Determine the number of pages in an array of length 'len' and * with a base offset of 'base' */ static inline unsigned int nfs_page_array_len(unsigned int base, size_t len) { return ((unsigned long)len + (unsigned long)base + PAGE_SIZE - 1) >> PAGE_SHIFT; } /* * Convert a struct timespec64 into a 64-bit change attribute * * This does approximately the same thing as timespec64_to_ns(), * but for calculation efficiency, we multiply the seconds by * 1024*1024*1024. */ static inline u64 nfs_timespec_to_change_attr(const struct timespec64 *ts) { return ((u64)ts->tv_sec << 30) + ts->tv_nsec; } #ifdef CONFIG_CRC32 static inline u32 nfs_stateid_hash(const nfs4_stateid *stateid) { return ~crc32_le(0xFFFFFFFF, &stateid->other[0], NFS4_STATEID_OTHER_SIZE); } #else static inline u32 nfs_stateid_hash(nfs4_stateid *stateid) { return 0; } #endif static inline bool nfs_error_is_fatal(int err) { switch (err) { case -ERESTARTSYS: case -EINTR: case -EACCES: case -EDQUOT: case -EFBIG: case -EIO: case -ENOSPC: case -EROFS: case -ESTALE: case -E2BIG: case -ENOMEM: case -ETIMEDOUT: return true; default: return false; } } static inline bool nfs_error_is_fatal_on_server(int err) { switch (err) { case 0: case -ERESTARTSYS: case -EINTR: case -ENOMEM: return false; } return nfs_error_is_fatal(err); } /* * Select between a default port value and a user-specified port value. * If a zero value is set, then autobind will be used. */ static inline void nfs_set_port(struct sockaddr_storage *sap, int *port, const unsigned short default_port) { if (*port == NFS_UNSPEC_PORT) *port = default_port; rpc_set_port((struct sockaddr *)sap, *port); } struct nfs_direct_req { struct kref kref; /* release manager */ /* I/O parameters */ struct nfs_open_context *ctx; /* file open context info */ struct nfs_lock_context *l_ctx; /* Lock context info */ struct kiocb * iocb; /* controlling i/o request */ struct inode * inode; /* target file of i/o */ /* completion state */ atomic_t io_count; /* i/os we're waiting for */ spinlock_t lock; /* protect completion state */ loff_t io_start; /* Start offset for I/O */ ssize_t count, /* bytes actually processed */ max_count, /* max expected count */ error; /* any reported error */ struct completion completion; /* wait for i/o completion */ /* commit state */ struct nfs_mds_commit_info mds_cinfo; /* Storage for cinfo */ struct pnfs_ds_commit_info ds_cinfo; /* Storage for cinfo */ struct work_struct work; int flags; /* for write */ #define NFS_ODIRECT_DO_COMMIT (1) /* an unstable reply was received */ #define NFS_ODIRECT_RESCHED_WRITES (2) /* write verification failed */ /* for read */ #define NFS_ODIRECT_SHOULD_DIRTY (3) /* dirty user-space page after read */ #define NFS_ODIRECT_DONE INT_MAX /* write verification failed */ }; |
| 956 6403 14 6401 1022 8 1024 8 114 949 6750 15 6743 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PERCPU_RWSEM_H #define _LINUX_PERCPU_RWSEM_H #include <linux/atomic.h> #include <linux/percpu.h> #include <linux/rcuwait.h> #include <linux/wait.h> #include <linux/rcu_sync.h> #include <linux/lockdep.h> struct percpu_rw_semaphore { struct rcu_sync rss; unsigned int __percpu *read_count; struct rcuwait writer; wait_queue_head_t waiters; atomic_t block; #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif }; #ifdef CONFIG_DEBUG_LOCK_ALLOC #define __PERCPU_RWSEM_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname }, #else #define __PERCPU_RWSEM_DEP_MAP_INIT(lockname) #endif #define __DEFINE_PERCPU_RWSEM(name, is_static) \ static DEFINE_PER_CPU(unsigned int, __percpu_rwsem_rc_##name); \ is_static struct percpu_rw_semaphore name = { \ .rss = __RCU_SYNC_INITIALIZER(name.rss), \ .read_count = &__percpu_rwsem_rc_##name, \ .writer = __RCUWAIT_INITIALIZER(name.writer), \ .waiters = __WAIT_QUEUE_HEAD_INITIALIZER(name.waiters), \ .block = ATOMIC_INIT(0), \ __PERCPU_RWSEM_DEP_MAP_INIT(name) \ } #define DEFINE_PERCPU_RWSEM(name) \ __DEFINE_PERCPU_RWSEM(name, /* not static */) #define DEFINE_STATIC_PERCPU_RWSEM(name) \ __DEFINE_PERCPU_RWSEM(name, static) extern bool __percpu_down_read(struct percpu_rw_semaphore *, bool); static inline void percpu_down_read(struct percpu_rw_semaphore *sem) { might_sleep(); rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_); preempt_disable(); /* * We are in an RCU-sched read-side critical section, so the writer * cannot both change sem->state from readers_fast and start checking * counters while we are here. So if we see !sem->state, we know that * the writer won't be checking until we're past the preempt_enable() * and that once the synchronize_rcu() is done, the writer will see * anything we did within this RCU-sched read-size critical section. */ if (likely(rcu_sync_is_idle(&sem->rss))) this_cpu_inc(*sem->read_count); else __percpu_down_read(sem, false); /* Unconditional memory barrier */ /* * The preempt_enable() prevents the compiler from * bleeding the critical section out. */ preempt_enable(); } static inline bool percpu_down_read_trylock(struct percpu_rw_semaphore *sem) { bool ret = true; preempt_disable(); /* * Same as in percpu_down_read(). */ if (likely(rcu_sync_is_idle(&sem->rss))) this_cpu_inc(*sem->read_count); else ret = __percpu_down_read(sem, true); /* Unconditional memory barrier */ preempt_enable(); /* * The barrier() from preempt_enable() prevents the compiler from * bleeding the critical section out. */ if (ret) rwsem_acquire_read(&sem->dep_map, 0, 1, _RET_IP_); return ret; } static inline void percpu_up_read(struct percpu_rw_semaphore *sem) { rwsem_release(&sem->dep_map, _RET_IP_); preempt_disable(); /* * Same as in percpu_down_read(). */ if (likely(rcu_sync_is_idle(&sem->rss))) { this_cpu_dec(*sem->read_count); } else { /* * slowpath; reader will only ever wake a single blocked * writer. */ smp_mb(); /* B matches C */ /* * In other words, if they see our decrement (presumably to * aggregate zero, as that is the only time it matters) they * will also see our critical section. */ this_cpu_dec(*sem->read_count); rcuwait_wake_up(&sem->writer); } preempt_enable(); } extern bool percpu_is_read_locked(struct percpu_rw_semaphore *); extern void percpu_down_write(struct percpu_rw_semaphore *); extern void percpu_up_write(struct percpu_rw_semaphore *); static inline bool percpu_is_write_locked(struct percpu_rw_semaphore *sem) { return atomic_read(&sem->block); } extern int __percpu_init_rwsem(struct percpu_rw_semaphore *, const char *, struct lock_class_key *); extern void percpu_free_rwsem(struct percpu_rw_semaphore *); #define percpu_init_rwsem(sem) \ ({ \ static struct lock_class_key rwsem_key; \ __percpu_init_rwsem(sem, #sem, &rwsem_key); \ }) #define percpu_rwsem_is_held(sem) lockdep_is_held(sem) #define percpu_rwsem_assert_held(sem) lockdep_assert_held(sem) static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem, bool read, unsigned long ip) { lock_release(&sem->dep_map, ip); } static inline void percpu_rwsem_acquire(struct percpu_rw_semaphore *sem, bool read, unsigned long ip) { lock_acquire(&sem->dep_map, 0, 1, read, 1, NULL, ip); } #endif |
| 9 5 1 1 5 4 1 8 8 8 819 8 819 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM cgroup #if !defined(_TRACE_CGROUP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_CGROUP_H #include <linux/cgroup.h> #include <linux/tracepoint.h> DECLARE_EVENT_CLASS(cgroup_root, TP_PROTO(struct cgroup_root *root), TP_ARGS(root), TP_STRUCT__entry( __field( int, root ) __field( u16, ss_mask ) __string( name, root->name ) ), TP_fast_assign( __entry->root = root->hierarchy_id; __entry->ss_mask = root->subsys_mask; __assign_str(name); ), TP_printk("root=%d ss_mask=%#x name=%s", __entry->root, __entry->ss_mask, __get_str(name)) ); DEFINE_EVENT(cgroup_root, cgroup_setup_root, TP_PROTO(struct cgroup_root *root), TP_ARGS(root) ); DEFINE_EVENT(cgroup_root, cgroup_destroy_root, TP_PROTO(struct cgroup_root *root), TP_ARGS(root) ); DEFINE_EVENT(cgroup_root, cgroup_remount, TP_PROTO(struct cgroup_root *root), TP_ARGS(root) ); DECLARE_EVENT_CLASS(cgroup, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path), TP_STRUCT__entry( __field( int, root ) __field( int, level ) __field( u64, id ) __string( path, path ) ), TP_fast_assign( __entry->root = cgrp->root->hierarchy_id; __entry->id = cgroup_id(cgrp); __entry->level = cgrp->level; __assign_str(path); ), TP_printk("root=%d id=%llu level=%d path=%s", __entry->root, __entry->id, __entry->level, __get_str(path)) ); DEFINE_EVENT(cgroup, cgroup_mkdir, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_rmdir, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_release, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_rename, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_freeze, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_unfreeze, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DECLARE_EVENT_CLASS(cgroup_migrate, TP_PROTO(struct cgroup *dst_cgrp, const char *path, struct task_struct *task, bool threadgroup), TP_ARGS(dst_cgrp, path, task, threadgroup), TP_STRUCT__entry( __field( int, dst_root ) __field( int, dst_level ) __field( u64, dst_id ) __field( int, pid ) __string( dst_path, path ) __string( comm, task->comm ) ), TP_fast_assign( __entry->dst_root = dst_cgrp->root->hierarchy_id; __entry->dst_id = cgroup_id(dst_cgrp); __entry->dst_level = dst_cgrp->level; __assign_str(dst_path); __entry->pid = task->pid; __assign_str(comm); ), TP_printk("dst_root=%d dst_id=%llu dst_level=%d dst_path=%s pid=%d comm=%s", __entry->dst_root, __entry->dst_id, __entry->dst_level, __get_str(dst_path), __entry->pid, __get_str(comm)) ); DEFINE_EVENT(cgroup_migrate, cgroup_attach_task, TP_PROTO(struct cgroup *dst_cgrp, const char *path, struct task_struct *task, bool threadgroup), TP_ARGS(dst_cgrp, path, task, threadgroup) ); DEFINE_EVENT(cgroup_migrate, cgroup_transfer_tasks, TP_PROTO(struct cgroup *dst_cgrp, const char *path, struct task_struct *task, bool threadgroup), TP_ARGS(dst_cgrp, path, task, threadgroup) ); DECLARE_EVENT_CLASS(cgroup_event, TP_PROTO(struct cgroup *cgrp, const char *path, int val), TP_ARGS(cgrp, path, val), TP_STRUCT__entry( __field( int, root ) __field( int, level ) __field( u64, id ) __string( path, path ) __field( int, val ) ), TP_fast_assign( __entry->root = cgrp->root->hierarchy_id; __entry->id = cgroup_id(cgrp); __entry->level = cgrp->level; __assign_str(path); __entry->val = val; ), TP_printk("root=%d id=%llu level=%d path=%s val=%d", __entry->root, __entry->id, __entry->level, __get_str(path), __entry->val) ); DEFINE_EVENT(cgroup_event, cgroup_notify_populated, TP_PROTO(struct cgroup *cgrp, const char *path, int val), TP_ARGS(cgrp, path, val) ); DEFINE_EVENT(cgroup_event, cgroup_notify_frozen, TP_PROTO(struct cgroup *cgrp, const char *path, int val), TP_ARGS(cgrp, path, val) ); DECLARE_EVENT_CLASS(cgroup_rstat, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended), TP_STRUCT__entry( __field( int, root ) __field( int, level ) __field( u64, id ) __field( int, cpu ) __field( bool, contended ) ), TP_fast_assign( __entry->root = cgrp->root->hierarchy_id; __entry->id = cgroup_id(cgrp); __entry->level = cgrp->level; __entry->cpu = cpu; __entry->contended = contended; ), TP_printk("root=%d id=%llu level=%d cpu=%d lock contended:%d", __entry->root, __entry->id, __entry->level, __entry->cpu, __entry->contended) ); /* Related to global: cgroup_rstat_lock */ DEFINE_EVENT(cgroup_rstat, cgroup_rstat_lock_contended, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_locked, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_unlock, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); /* Related to per CPU: cgroup_rstat_cpu_lock */ DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_lock_contended, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_lock_contended_fastpath, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_locked, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_locked_fastpath, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_unlock, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_unlock_fastpath, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); #endif /* _TRACE_CGROUP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_GFP_H #define __LINUX_GFP_H #include <linux/gfp_types.h> #include <linux/mmzone.h> #include <linux/topology.h> #include <linux/alloc_tag.h> #include <linux/sched.h> struct vm_area_struct; struct mempolicy; /* Convert GFP flags to their corresponding migrate type */ #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE) #define GFP_MOVABLE_SHIFT 3 static inline int gfp_migratetype(const gfp_t gfp_flags) { VM_WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK); BUILD_BUG_ON((1UL << GFP_MOVABLE_SHIFT) != ___GFP_MOVABLE); BUILD_BUG_ON((___GFP_MOVABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_MOVABLE); BUILD_BUG_ON((___GFP_RECLAIMABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_RECLAIMABLE); BUILD_BUG_ON(((___GFP_MOVABLE | ___GFP_RECLAIMABLE) >> GFP_MOVABLE_SHIFT) != MIGRATE_HIGHATOMIC); if (unlikely(page_group_by_mobility_disabled)) return MIGRATE_UNMOVABLE; /* Group based on mobility */ return (__force unsigned long)(gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT; } #undef GFP_MOVABLE_MASK #undef GFP_MOVABLE_SHIFT static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) { return !!(gfp_flags & __GFP_DIRECT_RECLAIM); } #ifdef CONFIG_HIGHMEM #define OPT_ZONE_HIGHMEM ZONE_HIGHMEM #else #define OPT_ZONE_HIGHMEM ZONE_NORMAL #endif #ifdef CONFIG_ZONE_DMA #define OPT_ZONE_DMA ZONE_DMA #else #define OPT_ZONE_DMA ZONE_NORMAL #endif #ifdef CONFIG_ZONE_DMA32 #define OPT_ZONE_DMA32 ZONE_DMA32 #else #define OPT_ZONE_DMA32 ZONE_NORMAL #endif /* * GFP_ZONE_TABLE is a word size bitstring that is used for looking up the * zone to use given the lowest 4 bits of gfp_t. Entries are GFP_ZONES_SHIFT * bits long and there are 16 of them to cover all possible combinations of * __GFP_DMA, __GFP_DMA32, __GFP_MOVABLE and __GFP_HIGHMEM. * * The zone fallback order is MOVABLE=>HIGHMEM=>NORMAL=>DMA32=>DMA. * But GFP_MOVABLE is not only a zone specifier but also an allocation * policy. Therefore __GFP_MOVABLE plus another zone selector is valid. * Only 1 bit of the lowest 3 bits (DMA,DMA32,HIGHMEM) can be set to "1". * * bit result * ================= * 0x0 => NORMAL * 0x1 => DMA or NORMAL * 0x2 => HIGHMEM or NORMAL * 0x3 => BAD (DMA+HIGHMEM) * 0x4 => DMA32 or NORMAL * 0x5 => BAD (DMA+DMA32) * 0x6 => BAD (HIGHMEM+DMA32) * 0x7 => BAD (HIGHMEM+DMA32+DMA) * 0x8 => NORMAL (MOVABLE+0) * 0x9 => DMA or NORMAL (MOVABLE+DMA) * 0xa => MOVABLE (Movable is valid only if HIGHMEM is set too) * 0xb => BAD (MOVABLE+HIGHMEM+DMA) * 0xc => DMA32 or NORMAL (MOVABLE+DMA32) * 0xd => BAD (MOVABLE+DMA32+DMA) * 0xe => BAD (MOVABLE+DMA32+HIGHMEM) * 0xf => BAD (MOVABLE+DMA32+HIGHMEM+DMA) * * GFP_ZONES_SHIFT must be <= 2 on 32 bit platforms. */ #if defined(CONFIG_ZONE_DEVICE) && (MAX_NR_ZONES-1) <= 4 /* ZONE_DEVICE is not a valid GFP zone specifier */ #define GFP_ZONES_SHIFT 2 #else #define GFP_ZONES_SHIFT ZONES_SHIFT #endif #if 16 * GFP_ZONES_SHIFT > BITS_PER_LONG #error GFP_ZONES_SHIFT too large to create GFP_ZONE_TABLE integer #endif #define GFP_ZONE_TABLE ( \ (ZONE_NORMAL << 0 * GFP_ZONES_SHIFT) \ | (OPT_ZONE_DMA << ___GFP_DMA * GFP_ZONES_SHIFT) \ | (OPT_ZONE_HIGHMEM << ___GFP_HIGHMEM * GFP_ZONES_SHIFT) \ | (OPT_ZONE_DMA32 << ___GFP_DMA32 * GFP_ZONES_SHIFT) \ | (ZONE_NORMAL << ___GFP_MOVABLE * GFP_ZONES_SHIFT) \ | (OPT_ZONE_DMA << (___GFP_MOVABLE | ___GFP_DMA) * GFP_ZONES_SHIFT) \ | (ZONE_MOVABLE << (___GFP_MOVABLE | ___GFP_HIGHMEM) * GFP_ZONES_SHIFT)\ | (OPT_ZONE_DMA32 << (___GFP_MOVABLE | ___GFP_DMA32) * GFP_ZONES_SHIFT)\ ) /* * GFP_ZONE_BAD is a bitmap for all combinations of __GFP_DMA, __GFP_DMA32 * __GFP_HIGHMEM and __GFP_MOVABLE that are not permitted. One flag per * entry starting with bit 0. Bit is set if the combination is not * allowed. */ #define GFP_ZONE_BAD ( \ 1 << (___GFP_DMA | ___GFP_HIGHMEM) \ | 1 << (___GFP_DMA | ___GFP_DMA32) \ | 1 << (___GFP_DMA32 | ___GFP_HIGHMEM) \ | 1 << (___GFP_DMA | ___GFP_DMA32 | ___GFP_HIGHMEM) \ | 1 << (___GFP_MOVABLE | ___GFP_HIGHMEM | ___GFP_DMA) \ | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA) \ | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_HIGHMEM) \ | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA | ___GFP_HIGHMEM) \ ) static inline enum zone_type gfp_zone(gfp_t flags) { enum zone_type z; int bit = (__force int) (flags & GFP_ZONEMASK); z = (GFP_ZONE_TABLE >> (bit * GFP_ZONES_SHIFT)) & ((1 << GFP_ZONES_SHIFT) - 1); VM_BUG_ON((GFP_ZONE_BAD >> bit) & 1); return z; } /* * There is only one page-allocator function, and two main namespaces to * it. The alloc_page*() variants return 'struct page *' and as such * can allocate highmem pages, the *get*page*() variants return * virtual kernel addresses to the allocated page(s). */ static inline int gfp_zonelist(gfp_t flags) { #ifdef CONFIG_NUMA if (unlikely(flags & __GFP_THISNODE)) return ZONELIST_NOFALLBACK; #endif return ZONELIST_FALLBACK; } /* * gfp flag masking for nested internal allocations. * * For code that needs to do allocations inside the public allocation API (e.g. * memory allocation tracking code) the allocations need to obey the caller * allocation context constrains to prevent allocation context mismatches (e.g. * GFP_KERNEL allocations in GFP_NOFS contexts) from potential deadlock * situations. * * It is also assumed that these nested allocations are for internal kernel * object storage purposes only and are not going to be used for DMA, etc. Hence * we strip out all the zone information and leave just the context information * intact. * * Further, internal allocations must fail before the higher level allocation * can fail, so we must make them fail faster and fail silently. We also don't * want them to deplete emergency reserves. Hence nested allocations must be * prepared for these allocations to fail. */ static inline gfp_t gfp_nested_mask(gfp_t flags) { return ((flags & (GFP_KERNEL | GFP_ATOMIC | __GFP_NOLOCKDEP)) | (__GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN)); } /* * We get the zone list from the current node and the gfp_mask. * This zone list contains a maximum of MAX_NUMNODES*MAX_NR_ZONES zones. * There are two zonelists per node, one for all zones with memory and * one containing just zones from the node the zonelist belongs to. * * For the case of non-NUMA systems the NODE_DATA() gets optimized to * &contig_page_data at compile-time. */ static inline struct zonelist *node_zonelist(int nid, gfp_t flags) { return NODE_DATA(nid)->node_zonelists + gfp_zonelist(flags); } #ifndef HAVE_ARCH_FREE_PAGE static inline void arch_free_page(struct page *page, int order) { } #endif #ifndef HAVE_ARCH_ALLOC_PAGE static inline void arch_alloc_page(struct page *page, int order) { } #endif struct page *__alloc_pages_noprof(gfp_t gfp, unsigned int order, int preferred_nid, nodemask_t *nodemask); #define __alloc_pages(...) alloc_hooks(__alloc_pages_noprof(__VA_ARGS__)) struct folio *__folio_alloc_noprof(gfp_t gfp, unsigned int order, int preferred_nid, nodemask_t *nodemask); #define __folio_alloc(...) alloc_hooks(__folio_alloc_noprof(__VA_ARGS__)) unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid, nodemask_t *nodemask, int nr_pages, struct list_head *page_list, struct page **page_array); #define __alloc_pages_bulk(...) alloc_hooks(alloc_pages_bulk_noprof(__VA_ARGS__)) unsigned long alloc_pages_bulk_array_mempolicy_noprof(gfp_t gfp, unsigned long nr_pages, struct page **page_array); #define alloc_pages_bulk_array_mempolicy(...) \ alloc_hooks(alloc_pages_bulk_array_mempolicy_noprof(__VA_ARGS__)) /* Bulk allocate order-0 pages */ #define alloc_pages_bulk_list(_gfp, _nr_pages, _list) \ __alloc_pages_bulk(_gfp, numa_mem_id(), NULL, _nr_pages, _list, NULL) #define alloc_pages_bulk_array(_gfp, _nr_pages, _page_array) \ __alloc_pages_bulk(_gfp, numa_mem_id(), NULL, _nr_pages, NULL, _page_array) static inline unsigned long alloc_pages_bulk_array_node_noprof(gfp_t gfp, int nid, unsigned long nr_pages, struct page **page_array) { if (nid == NUMA_NO_NODE) nid = numa_mem_id(); return alloc_pages_bulk_noprof(gfp, nid, NULL, nr_pages, NULL, page_array); } #define alloc_pages_bulk_array_node(...) \ alloc_hooks(alloc_pages_bulk_array_node_noprof(__VA_ARGS__)) static inline void warn_if_node_offline(int this_node, gfp_t gfp_mask) { gfp_t warn_gfp = gfp_mask & (__GFP_THISNODE|__GFP_NOWARN); if (warn_gfp != (__GFP_THISNODE|__GFP_NOWARN)) return; if (node_online(this_node)) return; pr_warn("%pGg allocation from offline node %d\n", &gfp_mask, this_node); dump_stack(); } /* * Allocate pages, preferring the node given as nid. The node must be valid and * online. For more general interface, see alloc_pages_node(). */ static inline struct page * __alloc_pages_node_noprof(int nid, gfp_t gfp_mask, unsigned int order) { VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); warn_if_node_offline(nid, gfp_mask); return __alloc_pages_noprof(gfp_mask, order, nid, NULL); } #define __alloc_pages_node(...) alloc_hooks(__alloc_pages_node_noprof(__VA_ARGS__)) static inline struct folio *__folio_alloc_node_noprof(gfp_t gfp, unsigned int order, int nid) { VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); warn_if_node_offline(nid, gfp); return __folio_alloc_noprof(gfp, order, nid, NULL); } #define __folio_alloc_node(...) alloc_hooks(__folio_alloc_node_noprof(__VA_ARGS__)) /* * Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE, * prefer the current CPU's closest node. Otherwise node must be valid and * online. */ static inline struct page *alloc_pages_node_noprof(int nid, gfp_t gfp_mask, unsigned int order) { if (nid == NUMA_NO_NODE) nid = numa_mem_id(); return __alloc_pages_node_noprof(nid, gfp_mask, order); } #define alloc_pages_node(...) alloc_hooks(alloc_pages_node_noprof(__VA_ARGS__)) #ifdef CONFIG_NUMA struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order); struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *mpol, pgoff_t ilx, int nid); struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order); struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *mpol, pgoff_t ilx, int nid); struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr, bool hugepage); #else static inline struct page *alloc_pages_noprof(gfp_t gfp_mask, unsigned int order) { return alloc_pages_node_noprof(numa_node_id(), gfp_mask, order); } static inline struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *mpol, pgoff_t ilx, int nid) { return alloc_pages_noprof(gfp, order); } static inline struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order) { return __folio_alloc_node(gfp, order, numa_node_id()); } static inline struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *mpol, pgoff_t ilx, int nid) { return folio_alloc_noprof(gfp, order); } #define vma_alloc_folio_noprof(gfp, order, vma, addr, hugepage) \ folio_alloc_noprof(gfp, order) #endif #define alloc_pages(...) alloc_hooks(alloc_pages_noprof(__VA_ARGS__)) #define alloc_pages_mpol(...) alloc_hooks(alloc_pages_mpol_noprof(__VA_ARGS__)) #define folio_alloc(...) alloc_hooks(folio_alloc_noprof(__VA_ARGS__)) #define folio_alloc_mpol(...) alloc_hooks(folio_alloc_mpol_noprof(__VA_ARGS__)) #define vma_alloc_folio(...) alloc_hooks(vma_alloc_folio_noprof(__VA_ARGS__)) #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) static inline struct page *alloc_page_vma_noprof(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr) { struct folio *folio = vma_alloc_folio_noprof(gfp, 0, vma, addr, false); return &folio->page; } #define alloc_page_vma(...) alloc_hooks(alloc_page_vma_noprof(__VA_ARGS__)) extern unsigned long get_free_pages_noprof(gfp_t gfp_mask, unsigned int order); #define __get_free_pages(...) alloc_hooks(get_free_pages_noprof(__VA_ARGS__)) extern unsigned long get_zeroed_page_noprof(gfp_t gfp_mask); #define get_zeroed_page(...) alloc_hooks(get_zeroed_page_noprof(__VA_ARGS__)) void *alloc_pages_exact_noprof(size_t size, gfp_t gfp_mask) __alloc_size(1); #define alloc_pages_exact(...) alloc_hooks(alloc_pages_exact_noprof(__VA_ARGS__)) void free_pages_exact(void *virt, size_t size); __meminit void *alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mask) __alloc_size(2); #define alloc_pages_exact_nid(...) \ alloc_hooks(alloc_pages_exact_nid_noprof(__VA_ARGS__)) #define __get_free_page(gfp_mask) \ __get_free_pages((gfp_mask), 0) #define __get_dma_pages(gfp_mask, order) \ __get_free_pages((gfp_mask) | GFP_DMA, (order)) extern void __free_pages(struct page *page, unsigned int order); extern void free_pages(unsigned long addr, unsigned int order); struct page_frag_cache; void page_frag_cache_drain(struct page_frag_cache *nc); extern void __page_frag_cache_drain(struct page *page, unsigned int count); void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz, gfp_t gfp_mask, unsigned int align_mask); static inline void *page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz, gfp_t gfp_mask, unsigned int align) { WARN_ON_ONCE(!is_power_of_2(align)); return __page_frag_alloc_align(nc, fragsz, gfp_mask, -align); } static inline void *page_frag_alloc(struct page_frag_cache *nc, unsigned int fragsz, gfp_t gfp_mask) { return __page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u); } extern void page_frag_free(void *addr); #define __free_page(page) __free_pages((page), 0) #define free_page(addr) free_pages((addr), 0) void page_alloc_init_cpuhp(void); int decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp); void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp); void drain_all_pages(struct zone *zone); void drain_local_pages(struct zone *zone); void page_alloc_init_late(void); void setup_pcp_cacheinfo(unsigned int cpu); /* * gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what * GFP flags are used before interrupts are enabled. Once interrupts are * enabled, it is set to __GFP_BITS_MASK while the system is running. During * hibernation, it is used by PM to avoid I/O during memory allocation while * devices are suspended. */ extern gfp_t gfp_allowed_mask; /* Returns true if the gfp_mask allows use of ALLOC_NO_WATERMARK */ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask); static inline bool gfp_has_io_fs(gfp_t gfp) { return (gfp & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS); } /* * Check if the gfp flags allow compaction - GFP_NOIO is a really * tricky context because the migration might require IO. */ static inline bool gfp_compaction_allowed(gfp_t gfp_mask) { return IS_ENABLED(CONFIG_COMPACTION) && (gfp_mask & __GFP_IO); } extern gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma); #ifdef CONFIG_CONTIG_ALLOC /* The below functions must be run on a range from a single zone. */ extern int alloc_contig_range_noprof(unsigned long start, unsigned long end, unsigned migratetype, gfp_t gfp_mask); #define alloc_contig_range(...) alloc_hooks(alloc_contig_range_noprof(__VA_ARGS__)) extern struct page *alloc_contig_pages_noprof(unsigned long nr_pages, gfp_t gfp_mask, int nid, nodemask_t *nodemask); #define alloc_contig_pages(...) alloc_hooks(alloc_contig_pages_noprof(__VA_ARGS__)) #endif void free_contig_range(unsigned long pfn, unsigned long nr_pages); #endif /* __LINUX_GFP_H */ |
| 118 118 116 56 59 3 12 49 49 3 12 12 46 46 46 46 46 46 46 14 40 52 29 35 22 45 2 1778 118 59 2 1 43 13 56 56 1922 1921 1923 12 1921 1890 47 118 14 117 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991-1998 Linus Torvalds * Re-organised Feb 1998 Russell King * Copyright (C) 2020 Christoph Hellwig */ #include <linux/fs.h> #include <linux/major.h> #include <linux/slab.h> #include <linux/ctype.h> #include <linux/vmalloc.h> #include <linux/raid/detect.h> #include "check.h" static int (*const check_part[])(struct parsed_partitions *) = { /* * Probe partition formats with tables at disk address 0 * that also have an ADFS boot block at 0xdc0. */ #ifdef CONFIG_ACORN_PARTITION_ICS adfspart_check_ICS, #endif #ifdef CONFIG_ACORN_PARTITION_POWERTEC adfspart_check_POWERTEC, #endif #ifdef CONFIG_ACORN_PARTITION_EESOX adfspart_check_EESOX, #endif /* * Now move on to formats that only have partition info at * disk address 0xdc0. Since these may also have stale * PC/BIOS partition tables, they need to come before * the msdos entry. */ #ifdef CONFIG_ACORN_PARTITION_CUMANA adfspart_check_CUMANA, #endif #ifdef CONFIG_ACORN_PARTITION_ADFS adfspart_check_ADFS, #endif #ifdef CONFIG_CMDLINE_PARTITION cmdline_partition, #endif #ifdef CONFIG_EFI_PARTITION efi_partition, /* this must come before msdos */ #endif #ifdef CONFIG_SGI_PARTITION sgi_partition, #endif #ifdef CONFIG_LDM_PARTITION ldm_partition, /* this must come before msdos */ #endif #ifdef CONFIG_MSDOS_PARTITION msdos_partition, #endif #ifdef CONFIG_OSF_PARTITION osf_partition, #endif #ifdef CONFIG_SUN_PARTITION sun_partition, #endif #ifdef CONFIG_AMIGA_PARTITION amiga_partition, #endif #ifdef CONFIG_ATARI_PARTITION atari_partition, #endif #ifdef CONFIG_MAC_PARTITION mac_partition, #endif #ifdef CONFIG_ULTRIX_PARTITION ultrix_partition, #endif #ifdef CONFIG_IBM_PARTITION ibm_partition, #endif #ifdef CONFIG_KARMA_PARTITION karma_partition, #endif #ifdef CONFIG_SYSV68_PARTITION sysv68_partition, #endif NULL }; static struct parsed_partitions *allocate_partitions(struct gendisk *hd) { struct parsed_partitions *state; int nr = DISK_MAX_PARTS; state = kzalloc(sizeof(*state), GFP_KERNEL); if (!state) return NULL; state->parts = vzalloc(array_size(nr, sizeof(state->parts[0]))); if (!state->parts) { kfree(state); return NULL; } state->limit = nr; return state; } static void free_partitions(struct parsed_partitions *state) { vfree(state->parts); kfree(state); } static struct parsed_partitions *check_partition(struct gendisk *hd) { struct parsed_partitions *state; int i, res, err; state = allocate_partitions(hd); if (!state) return NULL; state->pp_buf = (char *)__get_free_page(GFP_KERNEL); if (!state->pp_buf) { free_partitions(state); return NULL; } state->pp_buf[0] = '\0'; state->disk = hd; snprintf(state->name, BDEVNAME_SIZE, "%s", hd->disk_name); snprintf(state->pp_buf, PAGE_SIZE, " %s:", state->name); if (isdigit(state->name[strlen(state->name)-1])) sprintf(state->name, "p"); i = res = err = 0; while (!res && check_part[i]) { memset(state->parts, 0, state->limit * sizeof(state->parts[0])); res = check_part[i++](state); if (res < 0) { /* * We have hit an I/O error which we don't report now. * But record it, and let the others do their job. */ err = res; res = 0; } } if (res > 0) { printk(KERN_INFO "%s", state->pp_buf); free_page((unsigned long)state->pp_buf); return state; } if (state->access_beyond_eod) err = -ENOSPC; /* * The partition is unrecognized. So report I/O errors if there were any */ if (err) res = err; if (res) { strlcat(state->pp_buf, " unable to read partition table\n", PAGE_SIZE); printk(KERN_INFO "%s", state->pp_buf); } free_page((unsigned long)state->pp_buf); free_partitions(state); return ERR_PTR(res); } static ssize_t part_partition_show(struct device *dev, struct device_attribute *attr, char *buf) { return sprintf(buf, "%d\n", bdev_partno(dev_to_bdev(dev))); } static ssize_t part_start_show(struct device *dev, struct device_attribute *attr, char *buf) { return sprintf(buf, "%llu\n", dev_to_bdev(dev)->bd_start_sect); } static ssize_t part_ro_show(struct device *dev, struct device_attribute *attr, char *buf) { return sprintf(buf, "%d\n", bdev_read_only(dev_to_bdev(dev))); } static ssize_t part_alignment_offset_show(struct device *dev, struct device_attribute *attr, char *buf) { return sprintf(buf, "%u\n", bdev_alignment_offset(dev_to_bdev(dev))); } static ssize_t part_discard_alignment_show(struct device *dev, struct device_attribute *attr, char *buf) { return sprintf(buf, "%u\n", bdev_discard_alignment(dev_to_bdev(dev))); } static DEVICE_ATTR(partition, 0444, part_partition_show, NULL); static DEVICE_ATTR(start, 0444, part_start_show, NULL); static DEVICE_ATTR(size, 0444, part_size_show, NULL); static DEVICE_ATTR(ro, 0444, part_ro_show, NULL); static DEVICE_ATTR(alignment_offset, 0444, part_alignment_offset_show, NULL); static DEVICE_ATTR(discard_alignment, 0444, part_discard_alignment_show, NULL); static DEVICE_ATTR(stat, 0444, part_stat_show, NULL); static DEVICE_ATTR(inflight, 0444, part_inflight_show, NULL); #ifdef CONFIG_FAIL_MAKE_REQUEST static struct device_attribute dev_attr_fail = __ATTR(make-it-fail, 0644, part_fail_show, part_fail_store); #endif static struct attribute *part_attrs[] = { &dev_attr_partition.attr, &dev_attr_start.attr, &dev_attr_size.attr, &dev_attr_ro.attr, &dev_attr_alignment_offset.attr, &dev_attr_discard_alignment.attr, &dev_attr_stat.attr, &dev_attr_inflight.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST &dev_attr_fail.attr, #endif NULL }; static const struct attribute_group part_attr_group = { .attrs = part_attrs, }; static const struct attribute_group *part_attr_groups[] = { &part_attr_group, #ifdef CONFIG_BLK_DEV_IO_TRACE &blk_trace_attr_group, #endif NULL }; static void part_release(struct device *dev) { put_disk(dev_to_bdev(dev)->bd_disk); bdev_drop(dev_to_bdev(dev)); } static int part_uevent(const struct device *dev, struct kobj_uevent_env *env) { const struct block_device *part = dev_to_bdev(dev); add_uevent_var(env, "PARTN=%u", bdev_partno(part)); if (part->bd_meta_info && part->bd_meta_info->volname[0]) add_uevent_var(env, "PARTNAME=%s", part->bd_meta_info->volname); return 0; } const struct device_type part_type = { .name = "partition", .groups = part_attr_groups, .release = part_release, .uevent = part_uevent, }; void drop_partition(struct block_device *part) { lockdep_assert_held(&part->bd_disk->open_mutex); xa_erase(&part->bd_disk->part_tbl, bdev_partno(part)); kobject_put(part->bd_holder_dir); device_del(&part->bd_device); put_device(&part->bd_device); } static ssize_t whole_disk_show(struct device *dev, struct device_attribute *attr, char *buf) { return 0; } static const DEVICE_ATTR(whole_disk, 0444, whole_disk_show, NULL); /* * Must be called either with open_mutex held, before a disk can be opened or * after all disk users are gone. */ static struct block_device *add_partition(struct gendisk *disk, int partno, sector_t start, sector_t len, int flags, struct partition_meta_info *info) { dev_t devt = MKDEV(0, 0); struct device *ddev = disk_to_dev(disk); struct device *pdev; struct block_device *bdev; const char *dname; int err; lockdep_assert_held(&disk->open_mutex); if (partno >= DISK_MAX_PARTS) return ERR_PTR(-EINVAL); /* * Partitions are not supported on zoned block devices that are used as * such. */ if (bdev_is_zoned(disk->part0)) { pr_warn("%s: partitions not supported on host managed zoned block device\n", disk->disk_name); return ERR_PTR(-ENXIO); } if (xa_load(&disk->part_tbl, partno)) return ERR_PTR(-EBUSY); /* ensure we always have a reference to the whole disk */ get_device(disk_to_dev(disk)); err = -ENOMEM; bdev = bdev_alloc(disk, partno); if (!bdev) goto out_put_disk; bdev->bd_start_sect = start; bdev_set_nr_sectors(bdev, len); pdev = &bdev->bd_device; dname = dev_name(ddev); if (isdigit(dname[strlen(dname) - 1])) dev_set_name(pdev, "%sp%d", dname, partno); else dev_set_name(pdev, "%s%d", dname, partno); device_initialize(pdev); pdev->class = &block_class; pdev->type = &part_type; pdev->parent = ddev; /* in consecutive minor range? */ if (bdev_partno(bdev) < disk->minors) { devt = MKDEV(disk->major, disk->first_minor + bdev_partno(bdev)); } else { err = blk_alloc_ext_minor(); if (err < 0) goto out_put; devt = MKDEV(BLOCK_EXT_MAJOR, err); } pdev->devt = devt; if (info) { err = -ENOMEM; bdev->bd_meta_info = kmemdup(info, sizeof(*info), GFP_KERNEL); if (!bdev->bd_meta_info) goto out_put; } /* delay uevent until 'holders' subdir is created */ dev_set_uevent_suppress(pdev, 1); err = device_add(pdev); if (err) goto out_put; err = -ENOMEM; bdev->bd_holder_dir = kobject_create_and_add("holders", &pdev->kobj); if (!bdev->bd_holder_dir) goto out_del; dev_set_uevent_suppress(pdev, 0); if (flags & ADDPART_FLAG_WHOLEDISK) { err = device_create_file(pdev, &dev_attr_whole_disk); if (err) goto out_del; } /* everything is up and running, commence */ err = xa_insert(&disk->part_tbl, partno, bdev, GFP_KERNEL); if (err) goto out_del; bdev_add(bdev, devt); /* suppress uevent if the disk suppresses it */ if (!dev_get_uevent_suppress(ddev)) kobject_uevent(&pdev->kobj, KOBJ_ADD); return bdev; out_del: kobject_put(bdev->bd_holder_dir); device_del(pdev); out_put: put_device(pdev); return ERR_PTR(err); out_put_disk: put_disk(disk); return ERR_PTR(err); } static bool partition_overlaps(struct gendisk *disk, sector_t start, sector_t length, int skip_partno) { struct block_device *part; bool overlap = false; unsigned long idx; rcu_read_lock(); xa_for_each_start(&disk->part_tbl, idx, part, 1) { if (bdev_partno(part) != skip_partno && start < part->bd_start_sect + bdev_nr_sectors(part) && start + length > part->bd_start_sect) { overlap = true; break; } } rcu_read_unlock(); return overlap; } int bdev_add_partition(struct gendisk *disk, int partno, sector_t start, sector_t length) { struct block_device *part; int ret; mutex_lock(&disk->open_mutex); if (!disk_live(disk)) { ret = -ENXIO; goto out; } if (disk->flags & GENHD_FL_NO_PART) { ret = -EINVAL; goto out; } if (partition_overlaps(disk, start, length, -1)) { ret = -EBUSY; goto out; } part = add_partition(disk, partno, start, length, ADDPART_FLAG_NONE, NULL); ret = PTR_ERR_OR_ZERO(part); out: mutex_unlock(&disk->open_mutex); return ret; } int bdev_del_partition(struct gendisk *disk, int partno) { struct block_device *part = NULL; int ret = -ENXIO; mutex_lock(&disk->open_mutex); part = xa_load(&disk->part_tbl, partno); if (!part) goto out_unlock; ret = -EBUSY; if (atomic_read(&part->bd_openers)) goto out_unlock; /* * We verified that @part->bd_openers is zero above and so * @part->bd_holder{_ops} can't be set. And since we hold * @disk->open_mutex the device can't be claimed by anyone. * * So no need to call @part->bd_holder_ops->mark_dead() here. * Just delete the partition and invalidate it. */ bdev_unhash(part); invalidate_bdev(part); drop_partition(part); ret = 0; out_unlock: mutex_unlock(&disk->open_mutex); return ret; } int bdev_resize_partition(struct gendisk *disk, int partno, sector_t start, sector_t length) { struct block_device *part = NULL; int ret = -ENXIO; mutex_lock(&disk->open_mutex); part = xa_load(&disk->part_tbl, partno); if (!part) goto out_unlock; ret = -EINVAL; if (start != part->bd_start_sect) goto out_unlock; ret = -EBUSY; if (partition_overlaps(disk, start, length, partno)) goto out_unlock; bdev_set_nr_sectors(part, length); ret = 0; out_unlock: mutex_unlock(&disk->open_mutex); return ret; } static bool disk_unlock_native_capacity(struct gendisk *disk) { if (!disk->fops->unlock_native_capacity || test_and_set_bit(GD_NATIVE_CAPACITY, &disk->state)) { printk(KERN_CONT "truncated\n"); return false; } printk(KERN_CONT "enabling native capacity\n"); disk->fops->unlock_native_capacity(disk); return true; } static bool blk_add_partition(struct gendisk *disk, struct parsed_partitions *state, int p) { sector_t size = state->parts[p].size; sector_t from = state->parts[p].from; struct block_device *part; if (!size) return true; if (from >= get_capacity(disk)) { printk(KERN_WARNING "%s: p%d start %llu is beyond EOD, ", disk->disk_name, p, (unsigned long long) from); if (disk_unlock_native_capacity(disk)) return false; return true; } if (from + size > get_capacity(disk)) { printk(KERN_WARNING "%s: p%d size %llu extends beyond EOD, ", disk->disk_name, p, (unsigned long long) size); if (disk_unlock_native_capacity(disk)) return false; /* * We can not ignore partitions of broken tables created by for * example camera firmware, but we limit them to the end of the * disk to avoid creating invalid block devices. */ size = get_capacity(disk) - from; } part = add_partition(disk, p, from, size, state->parts[p].flags, &state->parts[p].info); if (IS_ERR(part) && PTR_ERR(part) != -ENXIO) { printk(KERN_ERR " %s: p%d could not be added: %pe\n", disk->disk_name, p, part); return true; } if (IS_BUILTIN(CONFIG_BLK_DEV_MD) && (state->parts[p].flags & ADDPART_FLAG_RAID)) md_autodetect_dev(part->bd_dev); return true; } static int blk_add_partitions(struct gendisk *disk) { struct parsed_partitions *state; int ret = -EAGAIN, p; if (!disk_has_partscan(disk)) return 0; state = check_partition(disk); if (!state) return 0; if (IS_ERR(state)) { /* * I/O error reading the partition table. If we tried to read * beyond EOD, retry after unlocking the native capacity. */ if (PTR_ERR(state) == -ENOSPC) { printk(KERN_WARNING "%s: partition table beyond EOD, ", disk->disk_name); if (disk_unlock_native_capacity(disk)) return -EAGAIN; } return -EIO; } /* * Partitions are not supported on host managed zoned block devices. */ if (bdev_is_zoned(disk->part0)) { pr_warn("%s: ignoring partition table on host managed zoned block device\n", disk->disk_name); ret = 0; goto out_free_state; } /* * If we read beyond EOD, try unlocking native capacity even if the * partition table was successfully read as we could be missing some * partitions. */ if (state->access_beyond_eod) { printk(KERN_WARNING "%s: partition table partially beyond EOD, ", disk->disk_name); if (disk_unlock_native_capacity(disk)) goto out_free_state; } /* tell userspace that the media / partition table may have changed */ kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE); for (p = 1; p < state->limit; p++) if (!blk_add_partition(disk, state, p)) goto out_free_state; ret = 0; out_free_state: free_partitions(state); return ret; } int bdev_disk_changed(struct gendisk *disk, bool invalidate) { struct block_device *part; unsigned long idx; int ret = 0; lockdep_assert_held(&disk->open_mutex); if (!disk_live(disk)) return -ENXIO; rescan: if (disk->open_partitions) return -EBUSY; sync_blockdev(disk->part0); invalidate_bdev(disk->part0); xa_for_each_start(&disk->part_tbl, idx, part, 1) { /* * Remove the block device from the inode hash, so that * it cannot be looked up any more even when openers * still hold references. */ bdev_unhash(part); /* * If @disk->open_partitions isn't elevated but there's * still an active holder of that block device things * are broken. */ WARN_ON_ONCE(atomic_read(&part->bd_openers)); invalidate_bdev(part); drop_partition(part); } clear_bit(GD_NEED_PART_SCAN, &disk->state); /* * Historically we only set the capacity to zero for devices that * support partitions (independ of actually having partitions created). * Doing that is rather inconsistent, but changing it broke legacy * udisks polling for legacy ide-cdrom devices. Use the crude check * below to get the sane behavior for most device while not breaking * userspace for this particular setup. */ if (invalidate) { if (!(disk->flags & GENHD_FL_NO_PART) || !(disk->flags & GENHD_FL_REMOVABLE)) set_capacity(disk, 0); } if (get_capacity(disk)) { ret = blk_add_partitions(disk); if (ret == -EAGAIN) goto rescan; } else if (invalidate) { /* * Tell userspace that the media / partition table may have * changed. */ kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE); } return ret; } /* * Only exported for loop and dasd for historic reasons. Don't use in new * code! */ EXPORT_SYMBOL_GPL(bdev_disk_changed); void *read_part_sector(struct parsed_partitions *state, sector_t n, Sector *p) { struct address_space *mapping = state->disk->part0->bd_mapping; struct folio *folio; if (n >= get_capacity(state->disk)) { state->access_beyond_eod = true; goto out; } folio = read_mapping_folio(mapping, n >> PAGE_SECTORS_SHIFT, NULL); if (IS_ERR(folio)) goto out; p->v = folio; return folio_address(folio) + offset_in_folio(folio, n * SECTOR_SIZE); out: p->v = NULL; return NULL; } |
| 269 1 512 1779 269 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* fs/ internal definitions * * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ struct super_block; struct file_system_type; struct iomap; struct iomap_ops; struct linux_binprm; struct path; struct mount; struct shrink_control; struct fs_context; struct pipe_inode_info; struct iov_iter; struct mnt_idmap; struct ns_common; /* * block/bdev.c */ #ifdef CONFIG_BLOCK extern void __init bdev_cache_init(void); #else static inline void bdev_cache_init(void) { } #endif /* CONFIG_BLOCK */ /* * buffer.c */ int __block_write_begin_int(struct folio *folio, loff_t pos, unsigned len, get_block_t *get_block, const struct iomap *iomap); /* * char_dev.c */ extern void __init chrdev_init(void); /* * fs_context.c */ extern const struct fs_context_operations legacy_fs_context_ops; extern int parse_monolithic_mount_data(struct fs_context *, void *); extern void vfs_clean_context(struct fs_context *fc); extern int finish_clean_context(struct fs_context *fc); /* * namei.c */ extern int filename_lookup(int dfd, struct filename *name, unsigned flags, struct path *path, struct path *root); int do_rmdir(int dfd, struct filename *name); int do_unlinkat(int dfd, struct filename *name); int may_linkat(struct mnt_idmap *idmap, const struct path *link); int do_renameat2(int olddfd, struct filename *oldname, int newdfd, struct filename *newname, unsigned int flags); int do_mkdirat(int dfd, struct filename *name, umode_t mode); int do_symlinkat(struct filename *from, int newdfd, struct filename *to); int do_linkat(int olddfd, struct filename *old, int newdfd, struct filename *new, int flags); int vfs_tmpfile(struct mnt_idmap *idmap, const struct path *parentpath, struct file *file, umode_t mode); /* * namespace.c */ extern struct vfsmount *lookup_mnt(const struct path *); extern int finish_automount(struct vfsmount *, const struct path *); extern int sb_prepare_remount_readonly(struct super_block *); extern void __init mnt_init(void); int mnt_get_write_access_file(struct file *file); void mnt_put_write_access_file(struct file *file); extern void dissolve_on_fput(struct vfsmount *); extern bool may_mount(void); int path_mount(const char *dev_name, struct path *path, const char *type_page, unsigned long flags, void *data_page); int path_umount(struct path *path, int flags); int show_path(struct seq_file *m, struct dentry *root); /* * fs_struct.c */ extern void chroot_fs_refs(const struct path *, const struct path *); /* * file_table.c */ struct file *alloc_empty_file(int flags, const struct cred *cred); struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred); struct file *alloc_empty_backing_file(int flags, const struct cred *cred); static inline void file_put_write_access(struct file *file) { put_write_access(file->f_inode); mnt_put_write_access(file->f_path.mnt); if (unlikely(file->f_mode & FMODE_BACKING)) mnt_put_write_access(backing_file_user_path(file)->mnt); } static inline void put_file_access(struct file *file) { if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) { i_readcount_dec(file->f_inode); } else if (file->f_mode & FMODE_WRITER) { file_put_write_access(file); } } /* * super.c */ extern int reconfigure_super(struct fs_context *); extern bool super_trylock_shared(struct super_block *sb); struct super_block *user_get_super(dev_t, bool excl); void put_super(struct super_block *sb); extern bool mount_capable(struct fs_context *); int sb_init_dio_done_wq(struct super_block *sb); /* * Prepare superblock for changing its read-only state (i.e., either remount * read-write superblock read-only or vice versa). After this function returns * mnt_is_readonly() will return true for any mount of the superblock if its * caller is able to observe any changes done by the remount. This holds until * sb_end_ro_state_change() is called. */ static inline void sb_start_ro_state_change(struct super_block *sb) { WRITE_ONCE(sb->s_readonly_remount, 1); /* * For RO->RW transition, the barrier pairs with the barrier in * mnt_is_readonly() making sure if mnt_is_readonly() sees SB_RDONLY * cleared, it will see s_readonly_remount set. * For RW->RO transition, the barrier pairs with the barrier in * mnt_get_write_access() before the mnt_is_readonly() check. * The barrier makes sure if mnt_get_write_access() sees MNT_WRITE_HOLD * already cleared, it will see s_readonly_remount set. */ smp_wmb(); } /* * Ends section changing read-only state of the superblock. After this function * returns if mnt_is_readonly() returns false, the caller will be able to * observe all the changes remount did to the superblock. */ static inline void sb_end_ro_state_change(struct super_block *sb) { /* * This barrier provides release semantics that pairs with * the smp_rmb() acquire semantics in mnt_is_readonly(). * This barrier pair ensure that when mnt_is_readonly() sees * 0 for sb->s_readonly_remount, it will also see all the * preceding flag changes that were made during the RO state * change. */ smp_wmb(); WRITE_ONCE(sb->s_readonly_remount, 0); } /* * open.c */ struct open_flags { int open_flag; umode_t mode; int acc_mode; int intent; int lookup_flags; }; extern struct file *do_filp_open(int dfd, struct filename *pathname, const struct open_flags *op); extern struct file *do_file_open_root(const struct path *, const char *, const struct open_flags *); extern struct open_how build_open_how(int flags, umode_t mode); extern int build_open_flags(const struct open_how *how, struct open_flags *op); struct file *file_close_fd_locked(struct files_struct *files, unsigned fd); long do_ftruncate(struct file *file, loff_t length, int small); long do_sys_ftruncate(unsigned int fd, loff_t length, int small); int chmod_common(const struct path *path, umode_t mode); int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group, int flag); int chown_common(const struct path *path, uid_t user, gid_t group); extern int vfs_open(const struct path *, struct file *); /* * inode.c */ extern long prune_icache_sb(struct super_block *sb, struct shrink_control *sc); int dentry_needs_remove_privs(struct mnt_idmap *, struct dentry *dentry); bool in_group_or_capable(struct mnt_idmap *idmap, const struct inode *inode, vfsgid_t vfsgid); /* * fs-writeback.c */ extern long get_nr_dirty_inodes(void); void invalidate_inodes(struct super_block *sb); /* * dcache.c */ extern int d_set_mounted(struct dentry *dentry); extern long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc); extern struct dentry *d_alloc_cursor(struct dentry *); extern struct dentry * d_alloc_pseudo(struct super_block *, const struct qstr *); extern char *simple_dname(struct dentry *, char *, int); extern void dput_to_list(struct dentry *, struct list_head *); extern void shrink_dentry_list(struct list_head *); extern void shrink_dcache_for_umount(struct super_block *); extern struct dentry *__d_lookup(const struct dentry *, const struct qstr *); extern struct dentry *__d_lookup_rcu(const struct dentry *parent, const struct qstr *name, unsigned *seq); extern void d_genocide(struct dentry *); /* * pipe.c */ extern const struct file_operations pipefifo_fops; /* * fs_pin.c */ extern void group_pin_kill(struct hlist_head *p); extern void mnt_pin_kill(struct mount *m); /* * fs/nsfs.c */ extern const struct dentry_operations ns_dentry_operations; int open_namespace(struct ns_common *ns); /* * fs/stat.c: */ int getname_statx_lookup_flags(int flags); int do_statx(int dfd, struct filename *filename, unsigned int flags, unsigned int mask, struct statx __user *buffer); int do_statx_fd(int fd, unsigned int flags, unsigned int mask, struct statx __user *buffer); /* * fs/splice.c: */ ssize_t splice_file_to_pipe(struct file *in, struct pipe_inode_info *opipe, loff_t *offset, size_t len, unsigned int flags); /* * fs/xattr.c: */ struct xattr_name { char name[XATTR_NAME_MAX + 1]; }; struct xattr_ctx { /* Value of attribute */ union { const void __user *cvalue; void __user *value; }; void *kvalue; size_t size; /* Attribute name */ struct xattr_name *kname; unsigned int flags; }; ssize_t do_getxattr(struct mnt_idmap *idmap, struct dentry *d, struct xattr_ctx *ctx); int setxattr_copy(const char __user *name, struct xattr_ctx *ctx); int do_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, struct xattr_ctx *ctx); int may_write_xattr(struct mnt_idmap *idmap, struct inode *inode); #ifdef CONFIG_FS_POSIX_ACL int do_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, const void *kvalue, size_t size); ssize_t do_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, void *kvalue, size_t size); #else static inline int do_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, const void *kvalue, size_t size) { return -EOPNOTSUPP; } static inline ssize_t do_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, void *kvalue, size_t size) { return -EOPNOTSUPP; } #endif ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *pos); /* * fs/attr.c */ struct mnt_idmap *alloc_mnt_idmap(struct user_namespace *mnt_userns); struct mnt_idmap *mnt_idmap_get(struct mnt_idmap *idmap); void mnt_idmap_put(struct mnt_idmap *idmap); struct stashed_operations { void (*put_data)(void *data); int (*init_inode)(struct inode *inode, void *data); }; int path_from_stashed(struct dentry **stashed, struct vfsmount *mnt, void *data, struct path *path); void stashed_dentry_prune(struct dentry *dentry); /** * path_mounted - check whether path is mounted * @path: path to check * * Determine whether @path refers to the root of a mount. * * Return: true if @path is the root of a mount, false if not. */ static inline bool path_mounted(const struct path *path) { return path->mnt->mnt_root == path->dentry; } |
| 147 146 25 147 148 148 148 148 2 2 147 3 1 3 147 147 147 41 30 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 | // SPDX-License-Identifier: GPL-2.0 #include <linux/mm.h> #include <linux/rmap.h> #include <linux/hugetlb.h> #include <linux/swap.h> #include <linux/swapops.h> #include "internal.h" static inline bool not_found(struct page_vma_mapped_walk *pvmw) { page_vma_mapped_walk_done(pvmw); return false; } static bool map_pte(struct page_vma_mapped_walk *pvmw, spinlock_t **ptlp) { pte_t ptent; if (pvmw->flags & PVMW_SYNC) { /* Use the stricter lookup */ pvmw->pte = pte_offset_map_lock(pvmw->vma->vm_mm, pvmw->pmd, pvmw->address, &pvmw->ptl); *ptlp = pvmw->ptl; return !!pvmw->pte; } /* * It is important to return the ptl corresponding to pte, * in case *pvmw->pmd changes underneath us; so we need to * return it even when choosing not to lock, in case caller * proceeds to loop over next ptes, and finds a match later. * Though, in most cases, page lock already protects this. */ pvmw->pte = pte_offset_map_nolock(pvmw->vma->vm_mm, pvmw->pmd, pvmw->address, ptlp); if (!pvmw->pte) return false; ptent = ptep_get(pvmw->pte); if (pvmw->flags & PVMW_MIGRATION) { if (!is_swap_pte(ptent)) return false; } else if (is_swap_pte(ptent)) { swp_entry_t entry; /* * Handle un-addressable ZONE_DEVICE memory. * * We get here when we are trying to unmap a private * device page from the process address space. Such * page is not CPU accessible and thus is mapped as * a special swap entry, nonetheless it still does * count as a valid regular mapping for the page * (and is accounted as such in page maps count). * * So handle this special case as if it was a normal * page mapping ie lock CPU page table and return true. * * For more details on device private memory see HMM * (include/linux/hmm.h or mm/hmm.c). */ entry = pte_to_swp_entry(ptent); if (!is_device_private_entry(entry) && !is_device_exclusive_entry(entry)) return false; } else if (!pte_present(ptent)) { return false; } pvmw->ptl = *ptlp; spin_lock(pvmw->ptl); return true; } /** * check_pte - check if [pvmw->pfn, @pvmw->pfn + @pvmw->nr_pages) is * mapped at the @pvmw->pte * @pvmw: page_vma_mapped_walk struct, includes a pair pte and pfn range * for checking * * page_vma_mapped_walk() found a place where pfn range is *potentially* * mapped. check_pte() has to validate this. * * pvmw->pte may point to empty PTE, swap PTE or PTE pointing to * arbitrary page. * * If PVMW_MIGRATION flag is set, returns true if @pvmw->pte contains migration * entry that points to [pvmw->pfn, @pvmw->pfn + @pvmw->nr_pages) * * If PVMW_MIGRATION flag is not set, returns true if pvmw->pte points to * [pvmw->pfn, @pvmw->pfn + @pvmw->nr_pages) * * Otherwise, return false. * */ static bool check_pte(struct page_vma_mapped_walk *pvmw) { unsigned long pfn; pte_t ptent = ptep_get(pvmw->pte); if (pvmw->flags & PVMW_MIGRATION) { swp_entry_t entry; if (!is_swap_pte(ptent)) return false; entry = pte_to_swp_entry(ptent); if (!is_migration_entry(entry) && !is_device_exclusive_entry(entry)) return false; pfn = swp_offset_pfn(entry); } else if (is_swap_pte(ptent)) { swp_entry_t entry; /* Handle un-addressable ZONE_DEVICE memory */ entry = pte_to_swp_entry(ptent); if (!is_device_private_entry(entry) && !is_device_exclusive_entry(entry)) return false; pfn = swp_offset_pfn(entry); } else { if (!pte_present(ptent)) return false; pfn = pte_pfn(ptent); } return (pfn - pvmw->pfn) < pvmw->nr_pages; } /* Returns true if the two ranges overlap. Careful to not overflow. */ static bool check_pmd(unsigned long pfn, struct page_vma_mapped_walk *pvmw) { if ((pfn + HPAGE_PMD_NR - 1) < pvmw->pfn) return false; if (pfn > pvmw->pfn + pvmw->nr_pages - 1) return false; return true; } static void step_forward(struct page_vma_mapped_walk *pvmw, unsigned long size) { pvmw->address = (pvmw->address + size) & ~(size - 1); if (!pvmw->address) pvmw->address = ULONG_MAX; } /** * page_vma_mapped_walk - check if @pvmw->pfn is mapped in @pvmw->vma at * @pvmw->address * @pvmw: pointer to struct page_vma_mapped_walk. page, vma, address and flags * must be set. pmd, pte and ptl must be NULL. * * Returns true if the page is mapped in the vma. @pvmw->pmd and @pvmw->pte point * to relevant page table entries. @pvmw->ptl is locked. @pvmw->address is * adjusted if needed (for PTE-mapped THPs). * * If @pvmw->pmd is set but @pvmw->pte is not, you have found PMD-mapped page * (usually THP). For PTE-mapped THP, you should run page_vma_mapped_walk() in * a loop to find all PTEs that map the THP. * * For HugeTLB pages, @pvmw->pte is set to the relevant page table entry * regardless of which page table level the page is mapped at. @pvmw->pmd is * NULL. * * Returns false if there are no more page table entries for the page in * the vma. @pvmw->ptl is unlocked and @pvmw->pte is unmapped. * * If you need to stop the walk before page_vma_mapped_walk() returned false, * use page_vma_mapped_walk_done(). It will do the housekeeping. */ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) { struct vm_area_struct *vma = pvmw->vma; struct mm_struct *mm = vma->vm_mm; unsigned long end; spinlock_t *ptl; pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t pmde; /* The only possible pmd mapping has been handled on last iteration */ if (pvmw->pmd && !pvmw->pte) return not_found(pvmw); if (unlikely(is_vm_hugetlb_page(vma))) { struct hstate *hstate = hstate_vma(vma); unsigned long size = huge_page_size(hstate); /* The only possible mapping was handled on last iteration */ if (pvmw->pte) return not_found(pvmw); /* * All callers that get here will already hold the * i_mmap_rwsem. Therefore, no additional locks need to be * taken before calling hugetlb_walk(). */ pvmw->pte = hugetlb_walk(vma, pvmw->address, size); if (!pvmw->pte) return false; pvmw->ptl = huge_pte_lock(hstate, mm, pvmw->pte); if (!check_pte(pvmw)) return not_found(pvmw); return true; } end = vma_address_end(pvmw); if (pvmw->pte) goto next_pte; restart: do { pgd = pgd_offset(mm, pvmw->address); if (!pgd_present(*pgd)) { step_forward(pvmw, PGDIR_SIZE); continue; } p4d = p4d_offset(pgd, pvmw->address); if (!p4d_present(*p4d)) { step_forward(pvmw, P4D_SIZE); continue; } pud = pud_offset(p4d, pvmw->address); if (!pud_present(*pud)) { step_forward(pvmw, PUD_SIZE); continue; } pvmw->pmd = pmd_offset(pud, pvmw->address); /* * Make sure the pmd value isn't cached in a register by the * compiler and used as a stale value after we've observed a * subsequent update. */ pmde = pmdp_get_lockless(pvmw->pmd); if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde) || (pmd_present(pmde) && pmd_devmap(pmde))) { pvmw->ptl = pmd_lock(mm, pvmw->pmd); pmde = *pvmw->pmd; if (!pmd_present(pmde)) { swp_entry_t entry; if (!thp_migration_supported() || !(pvmw->flags & PVMW_MIGRATION)) return not_found(pvmw); entry = pmd_to_swp_entry(pmde); if (!is_migration_entry(entry) || !check_pmd(swp_offset_pfn(entry), pvmw)) return not_found(pvmw); return true; } if (likely(pmd_trans_huge(pmde) || pmd_devmap(pmde))) { if (pvmw->flags & PVMW_MIGRATION) return not_found(pvmw); if (!check_pmd(pmd_pfn(pmde), pvmw)) return not_found(pvmw); return true; } /* THP pmd was split under us: handle on pte level */ spin_unlock(pvmw->ptl); pvmw->ptl = NULL; } else if (!pmd_present(pmde)) { /* * If PVMW_SYNC, take and drop THP pmd lock so that we * cannot return prematurely, while zap_huge_pmd() has * cleared *pmd but not decremented compound_mapcount(). */ if ((pvmw->flags & PVMW_SYNC) && thp_vma_suitable_order(vma, pvmw->address, PMD_ORDER) && (pvmw->nr_pages >= HPAGE_PMD_NR)) { spinlock_t *ptl = pmd_lock(mm, pvmw->pmd); spin_unlock(ptl); } step_forward(pvmw, PMD_SIZE); continue; } if (!map_pte(pvmw, &ptl)) { if (!pvmw->pte) goto restart; goto next_pte; } this_pte: if (check_pte(pvmw)) return true; next_pte: do { pvmw->address += PAGE_SIZE; if (pvmw->address >= end) return not_found(pvmw); /* Did we cross page table boundary? */ if ((pvmw->address & (PMD_SIZE - PAGE_SIZE)) == 0) { if (pvmw->ptl) { spin_unlock(pvmw->ptl); pvmw->ptl = NULL; } pte_unmap(pvmw->pte); pvmw->pte = NULL; goto restart; } pvmw->pte++; } while (pte_none(ptep_get(pvmw->pte))); if (!pvmw->ptl) { pvmw->ptl = ptl; spin_lock(pvmw->ptl); } goto this_pte; } while (pvmw->address < end); return false; } #ifdef CONFIG_MEMORY_FAILURE /** * page_mapped_in_vma - check whether a page is really mapped in a VMA * @page: the page to test * @vma: the VMA to test * * Return: The address the page is mapped at if the page is in the range * covered by the VMA and present in the page table. If the page is * outside the VMA or not present, returns -EFAULT. * Only valid for normal file or anonymous VMAs. */ unsigned long page_mapped_in_vma(struct page *page, struct vm_area_struct *vma) { struct folio *folio = page_folio(page); pgoff_t pgoff = folio->index + folio_page_idx(folio, page); struct page_vma_mapped_walk pvmw = { .pfn = page_to_pfn(page), .nr_pages = 1, .vma = vma, .flags = PVMW_SYNC, }; pvmw.address = vma_address(vma, pgoff, 1); if (pvmw.address == -EFAULT) goto out; if (!page_vma_mapped_walk(&pvmw)) return -EFAULT; page_vma_mapped_walk_done(&pvmw); out: return pvmw.address; } #endif |
| 91 90 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. */ #ifndef __INCORE_DOT_H__ #define __INCORE_DOT_H__ #include <linux/fs.h> #include <linux/kobject.h> #include <linux/workqueue.h> #include <linux/dlm.h> #include <linux/buffer_head.h> #include <linux/rcupdate.h> #include <linux/rculist_bl.h> #include <linux/completion.h> #include <linux/rbtree.h> #include <linux/ktime.h> #include <linux/percpu.h> #include <linux/lockref.h> #include <linux/rhashtable.h> #include <linux/mutex.h> #define DIO_WAIT 0x00000010 #define DIO_METADATA 0x00000020 struct gfs2_log_operations; struct gfs2_bufdata; struct gfs2_holder; struct gfs2_glock; struct gfs2_quota_data; struct gfs2_trans; struct gfs2_jdesc; struct gfs2_sbd; struct lm_lockops; typedef void (*gfs2_glop_bh_t) (struct gfs2_glock *gl, unsigned int ret); struct gfs2_log_header_host { u64 lh_sequence; /* Sequence number of this transaction */ u32 lh_flags; /* GFS2_LOG_HEAD_... */ u32 lh_tail; /* Block number of log tail */ u32 lh_blkno; s64 lh_local_total; s64 lh_local_free; s64 lh_local_dinodes; }; /* * Structure of operations that are associated with each * type of element in the log. */ struct gfs2_log_operations { void (*lo_before_commit) (struct gfs2_sbd *sdp, struct gfs2_trans *tr); void (*lo_after_commit) (struct gfs2_sbd *sdp, struct gfs2_trans *tr); void (*lo_before_scan) (struct gfs2_jdesc *jd, struct gfs2_log_header_host *head, int pass); int (*lo_scan_elements) (struct gfs2_jdesc *jd, unsigned int start, struct gfs2_log_descriptor *ld, __be64 *ptr, int pass); void (*lo_after_scan) (struct gfs2_jdesc *jd, int error, int pass); const char *lo_name; }; #define GBF_FULL 1 /** * Clone bitmaps (bi_clone): * * - When a block is freed, we remember the previous state of the block in the * clone bitmap, and only mark the block as free in the real bitmap. * * - When looking for a block to allocate, we check for a free block in the * clone bitmap, and if no clone bitmap exists, in the real bitmap. * * - For allocating a block, we mark it as allocated in the real bitmap, and if * a clone bitmap exists, also in the clone bitmap. * * - At the end of a log_flush, we copy the real bitmap into the clone bitmap * to make the clone bitmap reflect the current allocation state. * (Alternatively, we could remove the clone bitmap.) * * The clone bitmaps are in-core only, and is never written to disk. * * These steps ensure that blocks which have been freed in a transaction cannot * be reallocated in that same transaction. */ struct gfs2_bitmap { struct buffer_head *bi_bh; char *bi_clone; unsigned long bi_flags; u32 bi_offset; u32 bi_start; u32 bi_bytes; u32 bi_blocks; }; struct gfs2_rgrpd { struct rb_node rd_node; /* Link with superblock */ struct gfs2_glock *rd_gl; /* Glock for this rgrp */ u64 rd_addr; /* grp block disk address */ u64 rd_data0; /* first data location */ u32 rd_length; /* length of rgrp header in fs blocks */ u32 rd_data; /* num of data blocks in rgrp */ u32 rd_bitbytes; /* number of bytes in data bitmaps */ u32 rd_free; u32 rd_requested; /* number of blocks in rd_rstree */ u32 rd_reserved; /* number of reserved blocks */ u32 rd_free_clone; u32 rd_dinodes; u64 rd_igeneration; struct gfs2_bitmap *rd_bits; struct gfs2_sbd *rd_sbd; struct gfs2_rgrp_lvb *rd_rgl; u32 rd_last_alloc; u32 rd_flags; u32 rd_extfail_pt; /* extent failure point */ #define GFS2_RDF_CHECK 0x10000000 /* check for unlinked inodes */ #define GFS2_RDF_ERROR 0x40000000 /* error in rg */ #define GFS2_RDF_PREFERRED 0x80000000 /* This rgrp is preferred */ #define GFS2_RDF_MASK 0xf0000000 /* mask for internal flags */ spinlock_t rd_rsspin; /* protects reservation related vars */ struct mutex rd_mutex; struct rb_root rd_rstree; /* multi-block reservation tree */ }; enum gfs2_state_bits { BH_Pinned = BH_PrivateStart, BH_Escaped = BH_PrivateStart + 1, }; BUFFER_FNS(Pinned, pinned) TAS_BUFFER_FNS(Pinned, pinned) BUFFER_FNS(Escaped, escaped) TAS_BUFFER_FNS(Escaped, escaped) struct gfs2_bufdata { struct buffer_head *bd_bh; struct gfs2_glock *bd_gl; u64 bd_blkno; struct list_head bd_list; struct gfs2_trans *bd_tr; struct list_head bd_ail_st_list; struct list_head bd_ail_gl_list; }; /* * Internally, we prefix things with gdlm_ and GDLM_ (for gfs-dlm) since a * prefix of lock_dlm_ gets awkward. */ #define GDLM_STRNAME_BYTES 25 #define GDLM_LVB_SIZE 32 /* * ls_recover_flags: * * DFL_BLOCK_LOCKS: dlm is in recovery and will grant locks that had been * held by failed nodes whose journals need recovery. Those locks should * only be used for journal recovery until the journal recovery is done. * This is set by the dlm recover_prep callback and cleared by the * gfs2_control thread when journal recovery is complete. To avoid * races between recover_prep setting and gfs2_control clearing, recover_spin * is held while changing this bit and reading/writing recover_block * and recover_start. * * DFL_NO_DLM_OPS: dlm lockspace ops/callbacks are not being used. * * DFL_FIRST_MOUNT: this node is the first to mount this fs and is doing * recovery of all journals before allowing other nodes to mount the fs. * This is cleared when FIRST_MOUNT_DONE is set. * * DFL_FIRST_MOUNT_DONE: this node was the first mounter, and has finished * recovery of all journals, and now allows other nodes to mount the fs. * * DFL_MOUNT_DONE: gdlm_mount has completed successfully and cleared * BLOCK_LOCKS for the first time. The gfs2_control thread should now * control clearing BLOCK_LOCKS for further recoveries. * * DFL_UNMOUNT: gdlm_unmount sets to keep sdp off gfs2_control_wq. * * DFL_DLM_RECOVERY: set while dlm is in recovery, between recover_prep() * and recover_done(), i.e. set while recover_block == recover_start. */ enum { DFL_BLOCK_LOCKS = 0, DFL_NO_DLM_OPS = 1, DFL_FIRST_MOUNT = 2, DFL_FIRST_MOUNT_DONE = 3, DFL_MOUNT_DONE = 4, DFL_UNMOUNT = 5, DFL_DLM_RECOVERY = 6, }; /* * We are using struct lm_lockname as an rhashtable key. Avoid holes within * the struct; padding at the end is fine. */ struct lm_lockname { u64 ln_number; struct gfs2_sbd *ln_sbd; unsigned int ln_type; }; #define lm_name_equal(name1, name2) \ (((name1)->ln_number == (name2)->ln_number) && \ ((name1)->ln_type == (name2)->ln_type) && \ ((name1)->ln_sbd == (name2)->ln_sbd)) struct gfs2_glock_operations { int (*go_sync) (struct gfs2_glock *gl); int (*go_xmote_bh)(struct gfs2_glock *gl); void (*go_inval) (struct gfs2_glock *gl, int flags); int (*go_instantiate) (struct gfs2_glock *gl); int (*go_held)(struct gfs2_holder *gh); void (*go_dump)(struct seq_file *seq, const struct gfs2_glock *gl, const char *fs_id_buf); void (*go_callback)(struct gfs2_glock *gl, bool remote); void (*go_unlocked)(struct gfs2_glock *gl); const int go_subclass; const int go_type; const unsigned long go_flags; #define GLOF_ASPACE 1 /* address space attached */ #define GLOF_LVB 2 /* Lock Value Block attached */ #define GLOF_NONDISK 8 /* not I/O related */ }; enum { GFS2_LKS_SRTT = 0, /* Non blocking smoothed round trip time */ GFS2_LKS_SRTTVAR = 1, /* Non blocking smoothed variance */ GFS2_LKS_SRTTB = 2, /* Blocking smoothed round trip time */ GFS2_LKS_SRTTVARB = 3, /* Blocking smoothed variance */ GFS2_LKS_SIRT = 4, /* Smoothed Inter-request time */ GFS2_LKS_SIRTVAR = 5, /* Smoothed Inter-request variance */ GFS2_LKS_DCOUNT = 6, /* Count of dlm requests */ GFS2_LKS_QCOUNT = 7, /* Count of gfs2_holder queues */ GFS2_NR_LKSTATS }; struct gfs2_lkstats { u64 stats[GFS2_NR_LKSTATS]; }; enum { /* States */ HIF_HOLDER = 6, /* Set for gh that "holds" the glock */ HIF_WAIT = 10, }; struct gfs2_holder { struct list_head gh_list; struct gfs2_glock *gh_gl; struct pid *gh_owner_pid; u16 gh_flags; u16 gh_state; int gh_error; unsigned long gh_iflags; /* HIF_... */ unsigned long gh_ip; }; /* Number of quota types we support */ #define GFS2_MAXQUOTAS 2 struct gfs2_qadata { /* quota allocation data */ /* Quota stuff */ struct gfs2_quota_data *qa_qd[2 * GFS2_MAXQUOTAS]; struct gfs2_holder qa_qd_ghs[2 * GFS2_MAXQUOTAS]; unsigned int qa_qd_num; int qa_ref; }; /* Resource group multi-block reservation, in order of appearance: Step 1. Function prepares to write, allocates a mb, sets the size hint. Step 2. User calls inplace_reserve to target an rgrp, sets the rgrp info Step 3. Function get_local_rgrp locks the rgrp, determines which bits to use Step 4. Bits are assigned from the rgrp based on either the reservation or wherever it can. */ struct gfs2_blkreserv { struct rb_node rs_node; /* node within rd_rstree */ struct gfs2_rgrpd *rs_rgd; u64 rs_start; u32 rs_requested; u32 rs_reserved; /* number of reserved blocks */ }; /* * Allocation parameters * @target: The number of blocks we'd ideally like to allocate * @aflags: The flags (e.g. Orlov flag) * * The intent is to gradually expand this structure over time in * order to give more information, e.g. alignment, min extent size * to the allocation code. */ struct gfs2_alloc_parms { u64 target; u32 min_target; u32 aflags; u64 allowed; }; enum { GLF_LOCK = 1, GLF_INSTANTIATE_NEEDED = 2, /* needs instantiate */ GLF_DEMOTE = 3, GLF_PENDING_DEMOTE = 4, GLF_DEMOTE_IN_PROGRESS = 5, GLF_DIRTY = 6, GLF_LFLUSH = 7, GLF_INVALIDATE_IN_PROGRESS = 8, GLF_HAVE_REPLY = 9, GLF_INITIAL = 10, GLF_HAVE_FROZEN_REPLY = 11, GLF_INSTANTIATE_IN_PROG = 12, /* instantiate happening now */ GLF_LRU = 13, GLF_OBJECT = 14, /* Used only for tracing */ GLF_BLOCKING = 15, GLF_UNLOCKED = 16, /* Wait for glock to be unlocked */ GLF_TRY_TO_EVICT = 17, /* iopen glocks only */ GLF_VERIFY_EVICT = 18, /* iopen glocks only */ }; struct gfs2_glock { unsigned long gl_flags; /* GLF_... */ struct lm_lockname gl_name; struct lockref gl_lockref; /* State fields protected by gl_lockref.lock */ unsigned int gl_state:2, /* Current state */ gl_target:2, /* Target state */ gl_demote_state:2, /* State requested by remote node */ gl_req:2, /* State in last dlm request */ gl_reply:8; /* Last reply from the dlm */ unsigned long gl_demote_time; /* time of first demote request */ long gl_hold_time; struct list_head gl_holders; const struct gfs2_glock_operations *gl_ops; ktime_t gl_dstamp; struct gfs2_lkstats gl_stats; struct dlm_lksb gl_lksb; unsigned long gl_tchange; void *gl_object; struct list_head gl_lru; struct list_head gl_ail_list; atomic_t gl_ail_count; atomic_t gl_revokes; struct delayed_work gl_work; /* For iopen glocks only */ struct { struct delayed_work gl_delete; u64 gl_no_formal_ino; }; struct rcu_head gl_rcu; struct rhash_head gl_node; }; enum { GIF_QD_LOCKED = 1, GIF_ALLOC_FAILED = 2, GIF_SW_PAGED = 3, GIF_FREE_VFS_INODE = 5, GIF_GLOP_PENDING = 6, GIF_DEFERRED_DELETE = 7, }; struct gfs2_inode { struct inode i_inode; u64 i_no_addr; u64 i_no_formal_ino; u64 i_generation; u64 i_eattr; unsigned long i_flags; /* GIF_... */ struct gfs2_glock *i_gl; struct gfs2_holder i_iopen_gh; struct gfs2_qadata *i_qadata; /* quota allocation data */ struct gfs2_holder i_rgd_gh; struct gfs2_blkreserv i_res; /* rgrp multi-block reservation */ u64 i_goal; /* goal block for allocations */ atomic_t i_sizehint; /* hint of the write size */ struct rw_semaphore i_rw_mutex; struct list_head i_ordered; __be64 *i_hash_cache; u32 i_entries; u32 i_diskflags; u8 i_height; u8 i_depth; u16 i_rahead; }; /* * Since i_inode is the first element of struct gfs2_inode, * this is effectively a cast. */ static inline struct gfs2_inode *GFS2_I(struct inode *inode) { return container_of(inode, struct gfs2_inode, i_inode); } static inline struct gfs2_sbd *GFS2_SB(const struct inode *inode) { return inode->i_sb->s_fs_info; } struct gfs2_file { struct mutex f_fl_mutex; struct gfs2_holder f_fl_gh; }; struct gfs2_revoke_replay { struct list_head rr_list; u64 rr_blkno; unsigned int rr_where; }; enum { QDF_CHANGE = 1, QDF_LOCKED = 2, QDF_REFRESH = 3, QDF_QMSG_QUIET = 4, }; struct gfs2_quota_data { struct hlist_bl_node qd_hlist; struct list_head qd_list; struct kqid qd_id; struct gfs2_sbd *qd_sbd; struct lockref qd_lockref; struct list_head qd_lru; unsigned qd_hash; unsigned long qd_flags; /* QDF_... */ s64 qd_change; s64 qd_change_sync; unsigned int qd_slot; unsigned int qd_slot_ref; struct buffer_head *qd_bh; struct gfs2_quota_change *qd_bh_qc; unsigned int qd_bh_count; struct gfs2_glock *qd_gl; struct gfs2_quota_lvb qd_qb; u64 qd_sync_gen; unsigned long qd_last_warn; struct rcu_head qd_rcu; }; enum { TR_TOUCHED = 1, TR_ATTACHED = 2, TR_ONSTACK = 3, }; struct gfs2_trans { unsigned long tr_ip; unsigned int tr_blocks; unsigned int tr_revokes; unsigned int tr_reserved; unsigned long tr_flags; unsigned int tr_num_buf_new; unsigned int tr_num_databuf_new; unsigned int tr_num_buf_rm; unsigned int tr_num_databuf_rm; unsigned int tr_num_revoke; struct list_head tr_list; struct list_head tr_databuf; struct list_head tr_buf; unsigned int tr_first; struct list_head tr_ail1_list; struct list_head tr_ail2_list; }; struct gfs2_journal_extent { struct list_head list; unsigned int lblock; /* First logical block */ u64 dblock; /* First disk block */ u64 blocks; }; struct gfs2_jdesc { struct list_head jd_list; struct list_head extent_list; unsigned int nr_extents; struct work_struct jd_work; struct inode *jd_inode; struct bio *jd_log_bio; unsigned long jd_flags; #define JDF_RECOVERY 1 unsigned int jd_jid; u32 jd_blocks; int jd_recover_error; /* Replay stuff */ unsigned int jd_found_blocks; unsigned int jd_found_revokes; unsigned int jd_replayed_blocks; struct list_head jd_revoke_list; unsigned int jd_replay_tail; u64 jd_no_addr; }; struct gfs2_statfs_change_host { s64 sc_total; s64 sc_free; s64 sc_dinodes; }; #define GFS2_QUOTA_DEFAULT GFS2_QUOTA_OFF #define GFS2_QUOTA_OFF 0 #define GFS2_QUOTA_ACCOUNT 1 #define GFS2_QUOTA_ON 2 #define GFS2_QUOTA_QUIET 3 /* on but not complaining */ #define GFS2_DATA_DEFAULT GFS2_DATA_ORDERED #define GFS2_DATA_WRITEBACK 1 #define GFS2_DATA_ORDERED 2 #define GFS2_ERRORS_DEFAULT GFS2_ERRORS_WITHDRAW #define GFS2_ERRORS_WITHDRAW 0 #define GFS2_ERRORS_CONTINUE 1 /* place holder for future feature */ #define GFS2_ERRORS_RO 2 /* place holder for future feature */ #define GFS2_ERRORS_PANIC 3 struct gfs2_args { char ar_lockproto[GFS2_LOCKNAME_LEN]; /* Name of the Lock Protocol */ char ar_locktable[GFS2_LOCKNAME_LEN]; /* Name of the Lock Table */ char ar_hostdata[GFS2_LOCKNAME_LEN]; /* Host specific data */ unsigned int ar_spectator:1; /* Don't get a journal */ unsigned int ar_localflocks:1; /* Let the VFS do flock|fcntl */ unsigned int ar_debug:1; /* Oops on errors */ unsigned int ar_posix_acl:1; /* Enable posix acls */ unsigned int ar_quota:2; /* off/account/on */ unsigned int ar_suiddir:1; /* suiddir support */ unsigned int ar_data:2; /* ordered/writeback */ unsigned int ar_meta:1; /* mount metafs */ unsigned int ar_discard:1; /* discard requests */ unsigned int ar_errors:2; /* errors=withdraw | panic */ unsigned int ar_nobarrier:1; /* do not send barriers */ unsigned int ar_rgrplvb:1; /* use lvbs for rgrp info */ unsigned int ar_got_rgrplvb:1; /* Was the rgrplvb opt given? */ unsigned int ar_loccookie:1; /* use location based readdir cookies */ s32 ar_commit; /* Commit interval */ s32 ar_statfs_quantum; /* The fast statfs interval */ s32 ar_quota_quantum; /* The quota interval */ s32 ar_statfs_percent; /* The % change to force sync */ }; struct gfs2_tune { spinlock_t gt_spin; unsigned int gt_logd_secs; unsigned int gt_quota_warn_period; /* Secs between quota warn msgs */ unsigned int gt_quota_scale_num; /* Numerator */ unsigned int gt_quota_scale_den; /* Denominator */ unsigned int gt_quota_quantum; /* Secs between syncs to quota file */ unsigned int gt_new_files_jdata; unsigned int gt_max_readahead; /* Max bytes to read-ahead from disk */ unsigned int gt_complain_secs; unsigned int gt_statfs_quantum; unsigned int gt_statfs_slow; }; enum { SDF_JOURNAL_CHECKED = 0, SDF_JOURNAL_LIVE = 1, SDF_WITHDRAWN = 2, SDF_NOBARRIERS = 3, SDF_NORECOVERY = 4, SDF_DEMOTE = 5, SDF_NOJOURNALID = 6, SDF_RORECOVERY = 7, /* read only recovery */ SDF_SKIP_DLM_UNLOCK = 8, SDF_FORCE_AIL_FLUSH = 9, SDF_FREEZE_INITIATOR = 10, SDF_WITHDRAWING = 11, /* Will withdraw eventually */ SDF_WITHDRAW_IN_PROG = 12, /* Withdraw is in progress */ SDF_REMOTE_WITHDRAW = 13, /* Performing remote recovery */ SDF_WITHDRAW_RECOVERY = 14, /* Wait for journal recovery when we are withdrawing */ SDF_KILL = 15, SDF_EVICTING = 16, SDF_FROZEN = 17, }; #define GFS2_FSNAME_LEN 256 struct gfs2_inum_host { u64 no_formal_ino; u64 no_addr; }; struct gfs2_sb_host { u32 sb_magic; u32 sb_type; u32 sb_fs_format; u32 sb_multihost_format; u32 sb_bsize; u32 sb_bsize_shift; struct gfs2_inum_host sb_master_dir; struct gfs2_inum_host sb_root_dir; char sb_lockproto[GFS2_LOCKNAME_LEN]; char sb_locktable[GFS2_LOCKNAME_LEN]; }; /* * lm_mount() return values * * ls_jid - the journal ID this node should use * ls_first - this node is the first to mount the file system * ls_lockspace - lock module's context for this file system * ls_ops - lock module's functions */ struct lm_lockstruct { int ls_jid; unsigned int ls_first; const struct lm_lockops *ls_ops; dlm_lockspace_t *ls_dlm; int ls_recover_jid_done; /* These two are deprecated, */ int ls_recover_jid_status; /* used previously by gfs_controld */ struct dlm_lksb ls_mounted_lksb; /* mounted_lock */ struct dlm_lksb ls_control_lksb; /* control_lock */ char ls_control_lvb[GDLM_LVB_SIZE]; /* control_lock lvb */ struct completion ls_sync_wait; /* {control,mounted}_{lock,unlock} */ char *ls_lvb_bits; spinlock_t ls_recover_spin; /* protects following fields */ unsigned long ls_recover_flags; /* DFL_ */ uint32_t ls_recover_mount; /* gen in first recover_done cb */ uint32_t ls_recover_start; /* gen in last recover_done cb */ uint32_t ls_recover_block; /* copy recover_start in last recover_prep */ uint32_t ls_recover_size; /* size of recover_submit, recover_result */ uint32_t *ls_recover_submit; /* gen in last recover_slot cb per jid */ uint32_t *ls_recover_result; /* result of last jid recovery */ }; struct gfs2_pcpu_lkstats { /* One struct for each glock type */ struct gfs2_lkstats lkstats[10]; }; /* List of local (per node) statfs inodes */ struct local_statfs_inode { struct list_head si_list; struct inode *si_sc_inode; unsigned int si_jid; /* journal id this statfs inode corresponds to */ }; struct gfs2_sbd { struct super_block *sd_vfs; struct gfs2_pcpu_lkstats __percpu *sd_lkstats; struct kobject sd_kobj; struct completion sd_kobj_unregister; unsigned long sd_flags; /* SDF_... */ struct gfs2_sb_host sd_sb; /* Constants computed on mount */ u32 sd_fsb2bb; u32 sd_fsb2bb_shift; u32 sd_diptrs; /* Number of pointers in a dinode */ u32 sd_inptrs; /* Number of pointers in a indirect block */ u32 sd_ldptrs; /* Number of pointers in a log descriptor block */ u32 sd_jbsize; /* Size of a journaled data block */ u32 sd_hash_bsize; /* sizeof(exhash block) */ u32 sd_hash_bsize_shift; u32 sd_hash_ptrs; /* Number of pointers in a hash block */ u32 sd_qc_per_block; u32 sd_blocks_per_bitmap; u32 sd_max_dirres; /* Max blocks needed to add a directory entry */ u32 sd_max_height; /* Max height of a file's metadata tree */ u64 sd_heightsize[GFS2_MAX_META_HEIGHT + 1]; u32 sd_max_dents_per_leaf; /* Max number of dirents in a leaf block */ struct gfs2_args sd_args; /* Mount arguments */ struct gfs2_tune sd_tune; /* Filesystem tuning structure */ /* Lock Stuff */ struct lm_lockstruct sd_lockstruct; struct gfs2_holder sd_live_gh; struct gfs2_glock *sd_rename_gl; struct gfs2_glock *sd_freeze_gl; struct work_struct sd_freeze_work; wait_queue_head_t sd_kill_wait; wait_queue_head_t sd_async_glock_wait; atomic_t sd_glock_disposal; struct completion sd_locking_init; struct completion sd_wdack; struct delayed_work sd_control_work; /* Inode Stuff */ struct dentry *sd_master_dir; struct dentry *sd_root_dir; struct inode *sd_jindex; struct inode *sd_statfs_inode; struct inode *sd_sc_inode; struct list_head sd_sc_inodes_list; struct inode *sd_qc_inode; struct inode *sd_rindex; struct inode *sd_quota_inode; /* StatFS stuff */ spinlock_t sd_statfs_spin; struct gfs2_statfs_change_host sd_statfs_master; struct gfs2_statfs_change_host sd_statfs_local; int sd_statfs_force_sync; /* Resource group stuff */ int sd_rindex_uptodate; spinlock_t sd_rindex_spin; struct rb_root sd_rindex_tree; unsigned int sd_rgrps; unsigned int sd_max_rg_data; /* Journal index stuff */ struct list_head sd_jindex_list; spinlock_t sd_jindex_spin; struct mutex sd_jindex_mutex; unsigned int sd_journals; struct gfs2_jdesc *sd_jdesc; struct gfs2_holder sd_journal_gh; struct gfs2_holder sd_jinode_gh; struct gfs2_glock *sd_jinode_gl; struct gfs2_holder sd_sc_gh; struct buffer_head *sd_sc_bh; struct gfs2_holder sd_qc_gh; struct completion sd_journal_ready; /* Workqueue stuff */ struct workqueue_struct *sd_glock_wq; struct workqueue_struct *sd_delete_wq; /* Daemon stuff */ struct task_struct *sd_logd_process; struct task_struct *sd_quotad_process; /* Quota stuff */ struct list_head sd_quota_list; atomic_t sd_quota_count; struct mutex sd_quota_sync_mutex; wait_queue_head_t sd_quota_wait; unsigned int sd_quota_slots; unsigned long *sd_quota_bitmap; spinlock_t sd_bitmap_lock; u64 sd_quota_sync_gen; /* Log stuff */ struct address_space sd_aspace; spinlock_t sd_log_lock; struct gfs2_trans *sd_log_tr; unsigned int sd_log_blks_reserved; atomic_t sd_log_pinned; unsigned int sd_log_num_revoke; struct list_head sd_log_revokes; struct list_head sd_log_ordered; spinlock_t sd_ordered_lock; atomic_t sd_log_thresh1; atomic_t sd_log_thresh2; atomic_t sd_log_blks_free; atomic_t sd_log_blks_needed; atomic_t sd_log_revokes_available; wait_queue_head_t sd_log_waitq; wait_queue_head_t sd_logd_waitq; u64 sd_log_sequence; int sd_log_idle; struct rw_semaphore sd_log_flush_lock; atomic_t sd_log_in_flight; wait_queue_head_t sd_log_flush_wait; int sd_log_error; /* First log error */ wait_queue_head_t sd_withdraw_wait; unsigned int sd_log_tail; unsigned int sd_log_flush_tail; unsigned int sd_log_head; unsigned int sd_log_flush_head; spinlock_t sd_ail_lock; struct list_head sd_ail1_list; struct list_head sd_ail2_list; /* For quiescing the filesystem */ struct gfs2_holder sd_freeze_gh; struct mutex sd_freeze_mutex; struct list_head sd_dead_glocks; char sd_fsname[GFS2_FSNAME_LEN + 3 * sizeof(int) + 2]; char sd_table_name[GFS2_FSNAME_LEN]; char sd_proto_name[GFS2_FSNAME_LEN]; /* Debugging crud */ unsigned long sd_last_warning; struct dentry *debugfs_dir; /* debugfs directory */ unsigned long sd_glock_dqs_held; }; static inline void gfs2_glstats_inc(struct gfs2_glock *gl, int which) { gl->gl_stats.stats[which]++; } static inline void gfs2_sbstats_inc(const struct gfs2_glock *gl, int which) { const struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; preempt_disable(); this_cpu_ptr(sdp->sd_lkstats)->lkstats[gl->gl_name.ln_type].stats[which]++; preempt_enable(); } struct gfs2_rgrpd *gfs2_glock2rgrp(struct gfs2_glock *gl); static inline unsigned gfs2_max_stuffed_size(const struct gfs2_inode *ip) { return GFS2_SB(&ip->i_inode)->sd_sb.sb_bsize - sizeof(struct gfs2_dinode); } #endif /* __INCORE_DOT_H__ */ |
| 5 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 | // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* * Copyright (c) 2016 Mellanox Technologies Ltd. All rights reserved. * Copyright (c) 2015 System Fabric Works, Inc. All rights reserved. */ #include <linux/skbuff.h> #include <linux/if_arp.h> #include <linux/netdevice.h> #include <linux/if.h> #include <linux/if_vlan.h> #include <net/udp_tunnel.h> #include <net/sch_generic.h> #include <linux/netfilter.h> #include <rdma/ib_addr.h> #include "rxe.h" #include "rxe_net.h" #include "rxe_loc.h" static struct rxe_recv_sockets recv_sockets; static struct dst_entry *rxe_find_route4(struct rxe_qp *qp, struct net_device *ndev, struct in_addr *saddr, struct in_addr *daddr) { struct rtable *rt; struct flowi4 fl = { { 0 } }; memset(&fl, 0, sizeof(fl)); fl.flowi4_oif = ndev->ifindex; memcpy(&fl.saddr, saddr, sizeof(*saddr)); memcpy(&fl.daddr, daddr, sizeof(*daddr)); fl.flowi4_proto = IPPROTO_UDP; rt = ip_route_output_key(&init_net, &fl); if (IS_ERR(rt)) { rxe_dbg_qp(qp, "no route to %pI4\n", &daddr->s_addr); return NULL; } return &rt->dst; } #if IS_ENABLED(CONFIG_IPV6) static struct dst_entry *rxe_find_route6(struct rxe_qp *qp, struct net_device *ndev, struct in6_addr *saddr, struct in6_addr *daddr) { struct dst_entry *ndst; struct flowi6 fl6 = { { 0 } }; memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_oif = ndev->ifindex; memcpy(&fl6.saddr, saddr, sizeof(*saddr)); memcpy(&fl6.daddr, daddr, sizeof(*daddr)); fl6.flowi6_proto = IPPROTO_UDP; ndst = ipv6_stub->ipv6_dst_lookup_flow(sock_net(recv_sockets.sk6->sk), recv_sockets.sk6->sk, &fl6, NULL); if (IS_ERR(ndst)) { rxe_dbg_qp(qp, "no route to %pI6\n", daddr); return NULL; } if (unlikely(ndst->error)) { rxe_dbg_qp(qp, "no route to %pI6\n", daddr); goto put; } return ndst; put: dst_release(ndst); return NULL; } #else static struct dst_entry *rxe_find_route6(struct rxe_qp *qp, struct net_device *ndev, struct in6_addr *saddr, struct in6_addr *daddr) { return NULL; } #endif static struct dst_entry *rxe_find_route(struct net_device *ndev, struct rxe_qp *qp, struct rxe_av *av) { struct dst_entry *dst = NULL; if (qp_type(qp) == IB_QPT_RC) dst = sk_dst_get(qp->sk->sk); if (!dst || !dst_check(dst, qp->dst_cookie)) { if (dst) dst_release(dst); if (av->network_type == RXE_NETWORK_TYPE_IPV4) { struct in_addr *saddr; struct in_addr *daddr; saddr = &av->sgid_addr._sockaddr_in.sin_addr; daddr = &av->dgid_addr._sockaddr_in.sin_addr; dst = rxe_find_route4(qp, ndev, saddr, daddr); } else if (av->network_type == RXE_NETWORK_TYPE_IPV6) { struct in6_addr *saddr6; struct in6_addr *daddr6; saddr6 = &av->sgid_addr._sockaddr_in6.sin6_addr; daddr6 = &av->dgid_addr._sockaddr_in6.sin6_addr; dst = rxe_find_route6(qp, ndev, saddr6, daddr6); #if IS_ENABLED(CONFIG_IPV6) if (dst) qp->dst_cookie = rt6_get_cookie((struct rt6_info *)dst); #endif } if (dst && (qp_type(qp) == IB_QPT_RC)) { dst_hold(dst); sk_dst_set(qp->sk->sk, dst); } } return dst; } static int rxe_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct udphdr *udph; struct rxe_dev *rxe; struct net_device *ndev = skb->dev; struct rxe_pkt_info *pkt = SKB_TO_PKT(skb); /* takes a reference on rxe->ib_dev * drop when skb is freed */ rxe = rxe_get_dev_from_net(ndev); if (!rxe && is_vlan_dev(ndev)) rxe = rxe_get_dev_from_net(vlan_dev_real_dev(ndev)); if (!rxe) goto drop; if (skb_linearize(skb)) { ib_device_put(&rxe->ib_dev); goto drop; } udph = udp_hdr(skb); pkt->rxe = rxe; pkt->port_num = 1; pkt->hdr = (u8 *)(udph + 1); pkt->mask = RXE_GRH_MASK; pkt->paylen = be16_to_cpu(udph->len) - sizeof(*udph); /* remove udp header */ skb_pull(skb, sizeof(struct udphdr)); rxe_rcv(skb); return 0; drop: kfree_skb(skb); return 0; } static struct socket *rxe_setup_udp_tunnel(struct net *net, __be16 port, bool ipv6) { int err; struct socket *sock; struct udp_port_cfg udp_cfg = { }; struct udp_tunnel_sock_cfg tnl_cfg = { }; if (ipv6) { udp_cfg.family = AF_INET6; udp_cfg.ipv6_v6only = 1; } else { udp_cfg.family = AF_INET; } udp_cfg.local_udp_port = port; /* Create UDP socket */ err = udp_sock_create(net, &udp_cfg, &sock); if (err < 0) return ERR_PTR(err); tnl_cfg.encap_type = 1; tnl_cfg.encap_rcv = rxe_udp_encap_recv; /* Setup UDP tunnel */ setup_udp_tunnel_sock(net, sock, &tnl_cfg); return sock; } static void rxe_release_udp_tunnel(struct socket *sk) { if (sk) udp_tunnel_sock_release(sk); } static void prepare_udp_hdr(struct sk_buff *skb, __be16 src_port, __be16 dst_port) { struct udphdr *udph; __skb_push(skb, sizeof(*udph)); skb_reset_transport_header(skb); udph = udp_hdr(skb); udph->dest = dst_port; udph->source = src_port; udph->len = htons(skb->len); udph->check = 0; } static void prepare_ipv4_hdr(struct dst_entry *dst, struct sk_buff *skb, __be32 saddr, __be32 daddr, __u8 proto, __u8 tos, __u8 ttl, __be16 df, bool xnet) { struct iphdr *iph; skb_scrub_packet(skb, xnet); skb_clear_hash(skb); skb_dst_set(skb, dst_clone(dst)); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); skb_push(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); iph = ip_hdr(skb); iph->version = IPVERSION; iph->ihl = sizeof(struct iphdr) >> 2; iph->tot_len = htons(skb->len); iph->frag_off = df; iph->protocol = proto; iph->tos = tos; iph->daddr = daddr; iph->saddr = saddr; iph->ttl = ttl; __ip_select_ident(dev_net(dst->dev), iph, skb_shinfo(skb)->gso_segs ?: 1); } static void prepare_ipv6_hdr(struct dst_entry *dst, struct sk_buff *skb, struct in6_addr *saddr, struct in6_addr *daddr, __u8 proto, __u8 prio, __u8 ttl) { struct ipv6hdr *ip6h; memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); skb_dst_set(skb, dst_clone(dst)); __skb_push(skb, sizeof(*ip6h)); skb_reset_network_header(skb); ip6h = ipv6_hdr(skb); ip6_flow_hdr(ip6h, prio, htonl(0)); ip6h->payload_len = htons(skb->len); ip6h->nexthdr = proto; ip6h->hop_limit = ttl; ip6h->daddr = *daddr; ip6h->saddr = *saddr; ip6h->payload_len = htons(skb->len - sizeof(*ip6h)); } static int prepare4(struct rxe_av *av, struct rxe_pkt_info *pkt, struct sk_buff *skb) { struct rxe_qp *qp = pkt->qp; struct dst_entry *dst; bool xnet = false; __be16 df = htons(IP_DF); struct in_addr *saddr = &av->sgid_addr._sockaddr_in.sin_addr; struct in_addr *daddr = &av->dgid_addr._sockaddr_in.sin_addr; dst = rxe_find_route(skb->dev, qp, av); if (!dst) { rxe_dbg_qp(qp, "Host not reachable\n"); return -EHOSTUNREACH; } prepare_udp_hdr(skb, cpu_to_be16(qp->src_port), cpu_to_be16(ROCE_V2_UDP_DPORT)); prepare_ipv4_hdr(dst, skb, saddr->s_addr, daddr->s_addr, IPPROTO_UDP, av->grh.traffic_class, av->grh.hop_limit, df, xnet); dst_release(dst); return 0; } static int prepare6(struct rxe_av *av, struct rxe_pkt_info *pkt, struct sk_buff *skb) { struct rxe_qp *qp = pkt->qp; struct dst_entry *dst; struct in6_addr *saddr = &av->sgid_addr._sockaddr_in6.sin6_addr; struct in6_addr *daddr = &av->dgid_addr._sockaddr_in6.sin6_addr; dst = rxe_find_route(skb->dev, qp, av); if (!dst) { rxe_dbg_qp(qp, "Host not reachable\n"); return -EHOSTUNREACH; } prepare_udp_hdr(skb, cpu_to_be16(qp->src_port), cpu_to_be16(ROCE_V2_UDP_DPORT)); prepare_ipv6_hdr(dst, skb, saddr, daddr, IPPROTO_UDP, av->grh.traffic_class, av->grh.hop_limit); dst_release(dst); return 0; } int rxe_prepare(struct rxe_av *av, struct rxe_pkt_info *pkt, struct sk_buff *skb) { int err = 0; if (skb->protocol == htons(ETH_P_IP)) err = prepare4(av, pkt, skb); else if (skb->protocol == htons(ETH_P_IPV6)) err = prepare6(av, pkt, skb); if (ether_addr_equal(skb->dev->dev_addr, av->dmac)) pkt->mask |= RXE_LOOPBACK_MASK; return err; } static void rxe_skb_tx_dtor(struct sk_buff *skb) { struct net_device *ndev = skb->dev; struct rxe_dev *rxe; unsigned int qp_index; struct rxe_qp *qp; int skb_out; rxe = rxe_get_dev_from_net(ndev); if (!rxe && is_vlan_dev(ndev)) rxe = rxe_get_dev_from_net(vlan_dev_real_dev(ndev)); if (WARN_ON(!rxe)) return; qp_index = (int)(uintptr_t)skb->sk->sk_user_data; if (!qp_index) return; qp = rxe_pool_get_index(&rxe->qp_pool, qp_index); if (!qp) goto put_dev; skb_out = atomic_dec_return(&qp->skb_out); if (qp->need_req_skb && skb_out < RXE_INFLIGHT_SKBS_PER_QP_LOW) rxe_sched_task(&qp->send_task); rxe_put(qp); put_dev: ib_device_put(&rxe->ib_dev); sock_put(skb->sk); } static int rxe_send(struct sk_buff *skb, struct rxe_pkt_info *pkt) { int err; struct sock *sk = pkt->qp->sk->sk; sock_hold(sk); skb->sk = sk; skb->destructor = rxe_skb_tx_dtor; atomic_inc(&pkt->qp->skb_out); if (skb->protocol == htons(ETH_P_IP)) err = ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); else err = ip6_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); return err; } /* fix up a send packet to match the packets * received from UDP before looping them back */ static int rxe_loopback(struct sk_buff *skb, struct rxe_pkt_info *pkt) { struct sock *sk = pkt->qp->sk->sk; memcpy(SKB_TO_PKT(skb), pkt, sizeof(*pkt)); sock_hold(sk); skb->sk = sk; skb->destructor = rxe_skb_tx_dtor; atomic_inc(&pkt->qp->skb_out); if (skb->protocol == htons(ETH_P_IP)) skb_pull(skb, sizeof(struct iphdr)); else skb_pull(skb, sizeof(struct ipv6hdr)); if (WARN_ON(!ib_device_try_get(&pkt->rxe->ib_dev))) { kfree_skb(skb); return -EIO; } /* remove udp header */ skb_pull(skb, sizeof(struct udphdr)); rxe_rcv(skb); return 0; } int rxe_xmit_packet(struct rxe_qp *qp, struct rxe_pkt_info *pkt, struct sk_buff *skb) { int err; int is_request = pkt->mask & RXE_REQ_MASK; struct rxe_dev *rxe = to_rdev(qp->ibqp.device); unsigned long flags; spin_lock_irqsave(&qp->state_lock, flags); if ((is_request && (qp_state(qp) < IB_QPS_RTS)) || (!is_request && (qp_state(qp) < IB_QPS_RTR))) { spin_unlock_irqrestore(&qp->state_lock, flags); rxe_dbg_qp(qp, "Packet dropped. QP is not in ready state\n"); goto drop; } spin_unlock_irqrestore(&qp->state_lock, flags); rxe_icrc_generate(skb, pkt); if (pkt->mask & RXE_LOOPBACK_MASK) err = rxe_loopback(skb, pkt); else err = rxe_send(skb, pkt); if (err) { rxe_counter_inc(rxe, RXE_CNT_SEND_ERR); return err; } rxe_counter_inc(rxe, RXE_CNT_SENT_PKTS); goto done; drop: kfree_skb(skb); err = 0; done: return err; } struct sk_buff *rxe_init_packet(struct rxe_dev *rxe, struct rxe_av *av, int paylen, struct rxe_pkt_info *pkt) { unsigned int hdr_len; struct sk_buff *skb = NULL; struct net_device *ndev; const struct ib_gid_attr *attr; const int port_num = 1; attr = rdma_get_gid_attr(&rxe->ib_dev, port_num, av->grh.sgid_index); if (IS_ERR(attr)) return NULL; if (av->network_type == RXE_NETWORK_TYPE_IPV4) hdr_len = ETH_HLEN + sizeof(struct udphdr) + sizeof(struct iphdr); else hdr_len = ETH_HLEN + sizeof(struct udphdr) + sizeof(struct ipv6hdr); rcu_read_lock(); ndev = rdma_read_gid_attr_ndev_rcu(attr); if (IS_ERR(ndev)) { rcu_read_unlock(); goto out; } skb = alloc_skb(paylen + hdr_len + LL_RESERVED_SPACE(ndev), GFP_ATOMIC); if (unlikely(!skb)) { rcu_read_unlock(); goto out; } skb_reserve(skb, hdr_len + LL_RESERVED_SPACE(ndev)); /* FIXME: hold reference to this netdev until life of this skb. */ skb->dev = ndev; rcu_read_unlock(); if (av->network_type == RXE_NETWORK_TYPE_IPV4) skb->protocol = htons(ETH_P_IP); else skb->protocol = htons(ETH_P_IPV6); pkt->rxe = rxe; pkt->port_num = port_num; pkt->hdr = skb_put(skb, paylen); pkt->mask |= RXE_GRH_MASK; out: rdma_put_gid_attr(attr); return skb; } /* * this is required by rxe_cfg to match rxe devices in * /sys/class/infiniband up with their underlying ethernet devices */ const char *rxe_parent_name(struct rxe_dev *rxe, unsigned int port_num) { return rxe->ndev->name; } int rxe_net_add(const char *ibdev_name, struct net_device *ndev) { int err; struct rxe_dev *rxe = NULL; rxe = ib_alloc_device(rxe_dev, ib_dev); if (!rxe) return -ENOMEM; rxe->ndev = ndev; ib_mark_name_assigned_by_user(&rxe->ib_dev); err = rxe_add(rxe, ndev->mtu, ibdev_name); if (err) { ib_dealloc_device(&rxe->ib_dev); return err; } return 0; } static void rxe_port_event(struct rxe_dev *rxe, enum ib_event_type event) { struct ib_event ev; ev.device = &rxe->ib_dev; ev.element.port_num = 1; ev.event = event; ib_dispatch_event(&ev); } /* Caller must hold net_info_lock */ void rxe_port_up(struct rxe_dev *rxe) { struct rxe_port *port; port = &rxe->port; port->attr.state = IB_PORT_ACTIVE; rxe_port_event(rxe, IB_EVENT_PORT_ACTIVE); dev_info(&rxe->ib_dev.dev, "set active\n"); } /* Caller must hold net_info_lock */ void rxe_port_down(struct rxe_dev *rxe) { struct rxe_port *port; port = &rxe->port; port->attr.state = IB_PORT_DOWN; rxe_port_event(rxe, IB_EVENT_PORT_ERR); rxe_counter_inc(rxe, RXE_CNT_LINK_DOWNED); dev_info(&rxe->ib_dev.dev, "set down\n"); } void rxe_set_port_state(struct rxe_dev *rxe) { if (netif_running(rxe->ndev) && netif_carrier_ok(rxe->ndev)) rxe_port_up(rxe); else rxe_port_down(rxe); } static int rxe_notify(struct notifier_block *not_blk, unsigned long event, void *arg) { struct net_device *ndev = netdev_notifier_info_to_dev(arg); struct rxe_dev *rxe = rxe_get_dev_from_net(ndev); if (!rxe) return NOTIFY_OK; switch (event) { case NETDEV_UNREGISTER: ib_unregister_device_queued(&rxe->ib_dev); break; case NETDEV_UP: rxe_port_up(rxe); break; case NETDEV_DOWN: rxe_port_down(rxe); break; case NETDEV_CHANGEMTU: rxe_dbg_dev(rxe, "%s changed mtu to %d\n", ndev->name, ndev->mtu); rxe_set_mtu(rxe, ndev->mtu); break; case NETDEV_CHANGE: rxe_set_port_state(rxe); break; case NETDEV_REBOOT: case NETDEV_GOING_DOWN: case NETDEV_CHANGEADDR: case NETDEV_CHANGENAME: case NETDEV_FEAT_CHANGE: default: rxe_dbg_dev(rxe, "ignoring netdev event = %ld for %s\n", event, ndev->name); break; } ib_device_put(&rxe->ib_dev); return NOTIFY_OK; } static struct notifier_block rxe_net_notifier = { .notifier_call = rxe_notify, }; static int rxe_net_ipv4_init(void) { recv_sockets.sk4 = rxe_setup_udp_tunnel(&init_net, htons(ROCE_V2_UDP_DPORT), false); if (IS_ERR(recv_sockets.sk4)) { recv_sockets.sk4 = NULL; pr_err("Failed to create IPv4 UDP tunnel\n"); return -1; } return 0; } static int rxe_net_ipv6_init(void) { #if IS_ENABLED(CONFIG_IPV6) recv_sockets.sk6 = rxe_setup_udp_tunnel(&init_net, htons(ROCE_V2_UDP_DPORT), true); if (PTR_ERR(recv_sockets.sk6) == -EAFNOSUPPORT) { recv_sockets.sk6 = NULL; pr_warn("IPv6 is not supported, can not create a UDPv6 socket\n"); return 0; } if (IS_ERR(recv_sockets.sk6)) { recv_sockets.sk6 = NULL; pr_err("Failed to create IPv6 UDP tunnel\n"); return -1; } #endif return 0; } void rxe_net_exit(void) { rxe_release_udp_tunnel(recv_sockets.sk6); rxe_release_udp_tunnel(recv_sockets.sk4); unregister_netdevice_notifier(&rxe_net_notifier); } int rxe_net_init(void) { int err; recv_sockets.sk6 = NULL; err = rxe_net_ipv4_init(); if (err) return err; err = rxe_net_ipv6_init(); if (err) goto err_out; err = register_netdevice_notifier(&rxe_net_notifier); if (err) { pr_err("Failed to register netdev notifier\n"); goto err_out; } return 0; err_out: rxe_net_exit(); return err; } |
| 4760 4760 | 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 | #ifndef BLK_THROTTLE_H #define BLK_THROTTLE_H #include "blk-cgroup-rwstat.h" /* * To implement hierarchical throttling, throtl_grps form a tree and bios * are dispatched upwards level by level until they reach the top and get * issued. When dispatching bios from the children and local group at each * level, if the bios are dispatched into a single bio_list, there's a risk * of a local or child group which can queue many bios at once filling up * the list starving others. * * To avoid such starvation, dispatched bios are queued separately * according to where they came from. When they are again dispatched to * the parent, they're popped in round-robin order so that no single source * hogs the dispatch window. * * throtl_qnode is used to keep the queued bios separated by their sources. * Bios are queued to throtl_qnode which in turn is queued to * throtl_service_queue and then dispatched in round-robin order. * * It's also used to track the reference counts on blkg's. A qnode always * belongs to a throtl_grp and gets queued on itself or the parent, so * incrementing the reference of the associated throtl_grp when a qnode is * queued and decrementing when dequeued is enough to keep the whole blkg * tree pinned while bios are in flight. */ struct throtl_qnode { struct list_head node; /* service_queue->queued[] */ struct bio_list bios; /* queued bios */ struct throtl_grp *tg; /* tg this qnode belongs to */ }; struct throtl_service_queue { struct throtl_service_queue *parent_sq; /* the parent service_queue */ /* * Bios queued directly to this service_queue or dispatched from * children throtl_grp's. */ struct list_head queued[2]; /* throtl_qnode [READ/WRITE] */ unsigned int nr_queued[2]; /* number of queued bios */ /* * RB tree of active children throtl_grp's, which are sorted by * their ->disptime. */ struct rb_root_cached pending_tree; /* RB tree of active tgs */ unsigned int nr_pending; /* # queued in the tree */ unsigned long first_pending_disptime; /* disptime of the first tg */ struct timer_list pending_timer; /* fires on first_pending_disptime */ }; enum tg_state_flags { THROTL_TG_PENDING = 1 << 0, /* on parent's pending tree */ THROTL_TG_WAS_EMPTY = 1 << 1, /* bio_lists[] became non-empty */ THROTL_TG_CANCELING = 1 << 2, /* starts to cancel bio */ }; struct throtl_grp { /* must be the first member */ struct blkg_policy_data pd; /* active throtl group service_queue member */ struct rb_node rb_node; /* throtl_data this group belongs to */ struct throtl_data *td; /* this group's service queue */ struct throtl_service_queue service_queue; /* * qnode_on_self is used when bios are directly queued to this * throtl_grp so that local bios compete fairly with bios * dispatched from children. qnode_on_parent is used when bios are * dispatched from this throtl_grp into its parent and will compete * with the sibling qnode_on_parents and the parent's * qnode_on_self. */ struct throtl_qnode qnode_on_self[2]; struct throtl_qnode qnode_on_parent[2]; /* * Dispatch time in jiffies. This is the estimated time when group * will unthrottle and is ready to dispatch more bio. It is used as * key to sort active groups in service tree. */ unsigned long disptime; unsigned int flags; /* are there any throtl rules between this group and td? */ bool has_rules_bps[2]; bool has_rules_iops[2]; /* bytes per second rate limits */ uint64_t bps[2]; /* IOPS limits */ unsigned int iops[2]; /* Number of bytes dispatched in current slice */ uint64_t bytes_disp[2]; /* Number of bio's dispatched in current slice */ unsigned int io_disp[2]; unsigned long last_low_overflow_time[2]; uint64_t last_bytes_disp[2]; unsigned int last_io_disp[2]; /* * The following two fields are updated when new configuration is * submitted while some bios are still throttled, they record how many * bytes/ios are waited already in previous configuration, and they will * be used to calculate wait time under new configuration. */ long long carryover_bytes[2]; int carryover_ios[2]; unsigned long last_check_time; /* When did we start a new slice */ unsigned long slice_start[2]; unsigned long slice_end[2]; struct blkg_rwstat stat_bytes; struct blkg_rwstat stat_ios; }; extern struct blkcg_policy blkcg_policy_throtl; static inline struct throtl_grp *pd_to_tg(struct blkg_policy_data *pd) { return pd ? container_of(pd, struct throtl_grp, pd) : NULL; } static inline struct throtl_grp *blkg_to_tg(struct blkcg_gq *blkg) { return pd_to_tg(blkg_to_pd(blkg, &blkcg_policy_throtl)); } /* * Internal throttling interface */ #ifndef CONFIG_BLK_DEV_THROTTLING static inline void blk_throtl_exit(struct gendisk *disk) { } static inline bool blk_throtl_bio(struct bio *bio) { return false; } static inline void blk_throtl_cancel_bios(struct gendisk *disk) { } #else /* CONFIG_BLK_DEV_THROTTLING */ void blk_throtl_exit(struct gendisk *disk); bool __blk_throtl_bio(struct bio *bio); void blk_throtl_cancel_bios(struct gendisk *disk); static inline bool blk_throtl_activated(struct request_queue *q) { return q->td != NULL; } static inline bool blk_should_throtl(struct bio *bio) { struct throtl_grp *tg; int rw = bio_data_dir(bio); /* * This is called under bio_queue_enter(), and it's synchronized with * the activation of blk-throtl, which is protected by * blk_mq_freeze_queue(). */ if (!blk_throtl_activated(bio->bi_bdev->bd_queue)) return false; tg = blkg_to_tg(bio->bi_blkg); if (!cgroup_subsys_on_dfl(io_cgrp_subsys)) { if (!bio_flagged(bio, BIO_CGROUP_ACCT)) { bio_set_flag(bio, BIO_CGROUP_ACCT); blkg_rwstat_add(&tg->stat_bytes, bio->bi_opf, bio->bi_iter.bi_size); } blkg_rwstat_add(&tg->stat_ios, bio->bi_opf, 1); } /* iops limit is always counted */ if (tg->has_rules_iops[rw]) return true; if (tg->has_rules_bps[rw] && !bio_flagged(bio, BIO_BPS_THROTTLED)) return true; return false; } static inline bool blk_throtl_bio(struct bio *bio) { if (!blk_should_throtl(bio)) return false; return __blk_throtl_bio(bio); } #endif /* CONFIG_BLK_DEV_THROTTLING */ #endif |
| 2 2 2 2 1 1 1 53 3 3 1 49 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/drivers/base/map.c * * (C) Copyright Al Viro 2002,2003 * * NOTE: data structure needs to be changed. It works, but for large dev_t * it will be too slow. It is isolated, though, so these changes will be * local to that file. */ #include <linux/module.h> #include <linux/slab.h> #include <linux/mutex.h> #include <linux/kdev_t.h> #include <linux/kobject.h> #include <linux/kobj_map.h> struct kobj_map { struct probe { struct probe *next; dev_t dev; unsigned long range; struct module *owner; kobj_probe_t *get; int (*lock)(dev_t, void *); void *data; } *probes[255]; struct mutex *lock; }; int kobj_map(struct kobj_map *domain, dev_t dev, unsigned long range, struct module *module, kobj_probe_t *probe, int (*lock)(dev_t, void *), void *data) { unsigned int n = MAJOR(dev + range - 1) - MAJOR(dev) + 1; unsigned int index = MAJOR(dev); unsigned int i; struct probe *p; if (n > 255) n = 255; p = kmalloc_array(n, sizeof(struct probe), GFP_KERNEL); if (p == NULL) return -ENOMEM; for (i = 0; i < n; i++, p++) { p->owner = module; p->get = probe; p->lock = lock; p->dev = dev; p->range = range; p->data = data; } mutex_lock(domain->lock); for (i = 0, p -= n; i < n; i++, p++, index++) { struct probe **s = &domain->probes[index % 255]; while (*s && (*s)->range < range) s = &(*s)->next; p->next = *s; *s = p; } mutex_unlock(domain->lock); return 0; } void kobj_unmap(struct kobj_map *domain, dev_t dev, unsigned long range) { unsigned int n = MAJOR(dev + range - 1) - MAJOR(dev) + 1; unsigned int index = MAJOR(dev); unsigned int i; struct probe *found = NULL; if (n > 255) n = 255; mutex_lock(domain->lock); for (i = 0; i < n; i++, index++) { struct probe **s; for (s = &domain->probes[index % 255]; *s; s = &(*s)->next) { struct probe *p = *s; if (p->dev == dev && p->range == range) { *s = p->next; if (!found) found = p; break; } } } mutex_unlock(domain->lock); kfree(found); } struct kobject *kobj_lookup(struct kobj_map *domain, dev_t dev, int *index) { struct kobject *kobj; struct probe *p; unsigned long best = ~0UL; retry: mutex_lock(domain->lock); for (p = domain->probes[MAJOR(dev) % 255]; p; p = p->next) { struct kobject *(*probe)(dev_t, int *, void *); struct module *owner; void *data; if (p->dev > dev || p->dev + p->range - 1 < dev) continue; if (p->range - 1 >= best) break; if (!try_module_get(p->owner)) continue; owner = p->owner; data = p->data; probe = p->get; best = p->range - 1; *index = dev - p->dev; if (p->lock && p->lock(dev, data) < 0) { module_put(owner); continue; } mutex_unlock(domain->lock); kobj = probe(dev, index, data); /* Currently ->owner protects _only_ ->probe() itself. */ module_put(owner); if (kobj) return kobj; goto retry; } mutex_unlock(domain->lock); return NULL; } struct kobj_map *kobj_map_init(kobj_probe_t *base_probe, struct mutex *lock) { struct kobj_map *p = kmalloc(sizeof(struct kobj_map), GFP_KERNEL); struct probe *base = kzalloc(sizeof(*base), GFP_KERNEL); int i; if ((p == NULL) || (base == NULL)) { kfree(p); kfree(base); return NULL; } base->dev = 1; base->range = ~0; base->get = base_probe; for (i = 0; i < 255; i++) p->probes[i] = base; p->lock = lock; return p; } |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2021 Oracle Corporation */ #include <linux/slab.h> #include <linux/completion.h> #include <linux/sched/task.h> #include <linux/sched/vhost_task.h> #include <linux/sched/signal.h> enum vhost_task_flags { VHOST_TASK_FLAGS_STOP, VHOST_TASK_FLAGS_KILLED, }; struct vhost_task { bool (*fn)(void *data); void (*handle_sigkill)(void *data); void *data; struct completion exited; unsigned long flags; struct task_struct *task; /* serialize SIGKILL and vhost_task_stop calls */ struct mutex exit_mutex; }; static int vhost_task_fn(void *data) { struct vhost_task *vtsk = data; for (;;) { bool did_work; if (signal_pending(current)) { struct ksignal ksig; if (get_signal(&ksig)) break; } /* mb paired w/ vhost_task_stop */ set_current_state(TASK_INTERRUPTIBLE); if (test_bit(VHOST_TASK_FLAGS_STOP, &vtsk->flags)) { __set_current_state(TASK_RUNNING); break; } did_work = vtsk->fn(vtsk->data); if (!did_work) schedule(); } mutex_lock(&vtsk->exit_mutex); /* * If a vhost_task_stop and SIGKILL race, we can ignore the SIGKILL. * When the vhost layer has called vhost_task_stop it's already stopped * new work and flushed. */ if (!test_bit(VHOST_TASK_FLAGS_STOP, &vtsk->flags)) { set_bit(VHOST_TASK_FLAGS_KILLED, &vtsk->flags); vtsk->handle_sigkill(vtsk->data); } mutex_unlock(&vtsk->exit_mutex); complete(&vtsk->exited); do_exit(0); } /** * vhost_task_wake - wakeup the vhost_task * @vtsk: vhost_task to wake * * wake up the vhost_task worker thread */ void vhost_task_wake(struct vhost_task *vtsk) { wake_up_process(vtsk->task); } EXPORT_SYMBOL_GPL(vhost_task_wake); /** * vhost_task_stop - stop a vhost_task * @vtsk: vhost_task to stop * * vhost_task_fn ensures the worker thread exits after * VHOST_TASK_FLAGS_STOP becomes true. */ void vhost_task_stop(struct vhost_task *vtsk) { mutex_lock(&vtsk->exit_mutex); if (!test_bit(VHOST_TASK_FLAGS_KILLED, &vtsk->flags)) { set_bit(VHOST_TASK_FLAGS_STOP, &vtsk->flags); vhost_task_wake(vtsk); } mutex_unlock(&vtsk->exit_mutex); /* * Make sure vhost_task_fn is no longer accessing the vhost_task before * freeing it below. */ wait_for_completion(&vtsk->exited); kfree(vtsk); } EXPORT_SYMBOL_GPL(vhost_task_stop); /** * vhost_task_create - create a copy of a task to be used by the kernel * @fn: vhost worker function * @handle_sigkill: vhost function to handle when we are killed * @arg: data to be passed to fn and handled_kill * @name: the thread's name * * This returns a specialized task for use by the vhost layer or NULL on * failure. The returned task is inactive, and the caller must fire it up * through vhost_task_start(). */ struct vhost_task *vhost_task_create(bool (*fn)(void *), void (*handle_sigkill)(void *), void *arg, const char *name) { struct kernel_clone_args args = { .flags = CLONE_FS | CLONE_UNTRACED | CLONE_VM | CLONE_THREAD | CLONE_SIGHAND, .exit_signal = 0, .fn = vhost_task_fn, .name = name, .user_worker = 1, .no_files = 1, }; struct vhost_task *vtsk; struct task_struct *tsk; vtsk = kzalloc(sizeof(*vtsk), GFP_KERNEL); if (!vtsk) return NULL; init_completion(&vtsk->exited); mutex_init(&vtsk->exit_mutex); vtsk->data = arg; vtsk->fn = fn; vtsk->handle_sigkill = handle_sigkill; args.fn_arg = vtsk; tsk = copy_process(NULL, 0, NUMA_NO_NODE, &args); if (IS_ERR(tsk)) { kfree(vtsk); return NULL; } vtsk->task = tsk; return vtsk; } EXPORT_SYMBOL_GPL(vhost_task_create); /** * vhost_task_start - start a vhost_task created with vhost_task_create * @vtsk: vhost_task to wake up */ void vhost_task_start(struct vhost_task *vtsk) { wake_up_new_task(vtsk->task); } EXPORT_SYMBOL_GPL(vhost_task_start); |
| 1 3 4 4 4 9 9 4 9 8 9 14 9 4 4 42 42 13 14 14 14 14 14 14 13 12 1 12 12 12 33 21 9 12 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 | // SPDX-License-Identifier: GPL-2.0 /* * drivers/base/power/wakeup.c - System wakeup events framework * * Copyright (c) 2010 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc. */ #define pr_fmt(fmt) "PM: " fmt #include <linux/device.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/capability.h> #include <linux/export.h> #include <linux/suspend.h> #include <linux/seq_file.h> #include <linux/debugfs.h> #include <linux/pm_wakeirq.h> #include <trace/events/power.h> #include "power.h" #define list_for_each_entry_rcu_locked(pos, head, member) \ list_for_each_entry_rcu(pos, head, member, \ srcu_read_lock_held(&wakeup_srcu)) /* * If set, the suspend/hibernate code will abort transitions to a sleep state * if wakeup events are registered during or immediately before the transition. */ bool events_check_enabled __read_mostly; /* First wakeup IRQ seen by the kernel in the last cycle. */ static unsigned int wakeup_irq[2] __read_mostly; static DEFINE_RAW_SPINLOCK(wakeup_irq_lock); /* If greater than 0 and the system is suspending, terminate the suspend. */ static atomic_t pm_abort_suspend __read_mostly; /* * Combined counters of registered wakeup events and wakeup events in progress. * They need to be modified together atomically, so it's better to use one * atomic variable to hold them both. */ static atomic_t combined_event_count = ATOMIC_INIT(0); #define IN_PROGRESS_BITS (sizeof(int) * 4) #define MAX_IN_PROGRESS ((1 << IN_PROGRESS_BITS) - 1) static void split_counters(unsigned int *cnt, unsigned int *inpr) { unsigned int comb = atomic_read(&combined_event_count); *cnt = (comb >> IN_PROGRESS_BITS); *inpr = comb & MAX_IN_PROGRESS; } /* A preserved old value of the events counter. */ static unsigned int saved_count; static DEFINE_RAW_SPINLOCK(events_lock); static void pm_wakeup_timer_fn(struct timer_list *t); static LIST_HEAD(wakeup_sources); static DECLARE_WAIT_QUEUE_HEAD(wakeup_count_wait_queue); DEFINE_STATIC_SRCU(wakeup_srcu); static struct wakeup_source deleted_ws = { .name = "deleted", .lock = __SPIN_LOCK_UNLOCKED(deleted_ws.lock), }; static DEFINE_IDA(wakeup_ida); /** * wakeup_source_create - Create a struct wakeup_source object. * @name: Name of the new wakeup source. */ struct wakeup_source *wakeup_source_create(const char *name) { struct wakeup_source *ws; const char *ws_name; int id; ws = kzalloc(sizeof(*ws), GFP_KERNEL); if (!ws) goto err_ws; ws_name = kstrdup_const(name, GFP_KERNEL); if (!ws_name) goto err_name; ws->name = ws_name; id = ida_alloc(&wakeup_ida, GFP_KERNEL); if (id < 0) goto err_id; ws->id = id; return ws; err_id: kfree_const(ws->name); err_name: kfree(ws); err_ws: return NULL; } EXPORT_SYMBOL_GPL(wakeup_source_create); /* * Record wakeup_source statistics being deleted into a dummy wakeup_source. */ static void wakeup_source_record(struct wakeup_source *ws) { unsigned long flags; spin_lock_irqsave(&deleted_ws.lock, flags); if (ws->event_count) { deleted_ws.total_time = ktime_add(deleted_ws.total_time, ws->total_time); deleted_ws.prevent_sleep_time = ktime_add(deleted_ws.prevent_sleep_time, ws->prevent_sleep_time); deleted_ws.max_time = ktime_compare(deleted_ws.max_time, ws->max_time) > 0 ? deleted_ws.max_time : ws->max_time; deleted_ws.event_count += ws->event_count; deleted_ws.active_count += ws->active_count; deleted_ws.relax_count += ws->relax_count; deleted_ws.expire_count += ws->expire_count; deleted_ws.wakeup_count += ws->wakeup_count; } spin_unlock_irqrestore(&deleted_ws.lock, flags); } static void wakeup_source_free(struct wakeup_source *ws) { ida_free(&wakeup_ida, ws->id); kfree_const(ws->name); kfree(ws); } /** * wakeup_source_destroy - Destroy a struct wakeup_source object. * @ws: Wakeup source to destroy. * * Use only for wakeup source objects created with wakeup_source_create(). */ void wakeup_source_destroy(struct wakeup_source *ws) { if (!ws) return; __pm_relax(ws); wakeup_source_record(ws); wakeup_source_free(ws); } EXPORT_SYMBOL_GPL(wakeup_source_destroy); /** * wakeup_source_add - Add given object to the list of wakeup sources. * @ws: Wakeup source object to add to the list. */ void wakeup_source_add(struct wakeup_source *ws) { unsigned long flags; if (WARN_ON(!ws)) return; spin_lock_init(&ws->lock); timer_setup(&ws->timer, pm_wakeup_timer_fn, 0); ws->active = false; raw_spin_lock_irqsave(&events_lock, flags); list_add_rcu(&ws->entry, &wakeup_sources); raw_spin_unlock_irqrestore(&events_lock, flags); } EXPORT_SYMBOL_GPL(wakeup_source_add); /** * wakeup_source_remove - Remove given object from the wakeup sources list. * @ws: Wakeup source object to remove from the list. */ void wakeup_source_remove(struct wakeup_source *ws) { unsigned long flags; if (WARN_ON(!ws)) return; raw_spin_lock_irqsave(&events_lock, flags); list_del_rcu(&ws->entry); raw_spin_unlock_irqrestore(&events_lock, flags); synchronize_srcu(&wakeup_srcu); del_timer_sync(&ws->timer); /* * Clear timer.function to make wakeup_source_not_registered() treat * this wakeup source as not registered. */ ws->timer.function = NULL; } EXPORT_SYMBOL_GPL(wakeup_source_remove); /** * wakeup_source_register - Create wakeup source and add it to the list. * @dev: Device this wakeup source is associated with (or NULL if virtual). * @name: Name of the wakeup source to register. */ struct wakeup_source *wakeup_source_register(struct device *dev, const char *name) { struct wakeup_source *ws; int ret; ws = wakeup_source_create(name); if (ws) { if (!dev || device_is_registered(dev)) { ret = wakeup_source_sysfs_add(dev, ws); if (ret) { wakeup_source_free(ws); return NULL; } } wakeup_source_add(ws); } return ws; } EXPORT_SYMBOL_GPL(wakeup_source_register); /** * wakeup_source_unregister - Remove wakeup source from the list and remove it. * @ws: Wakeup source object to unregister. */ void wakeup_source_unregister(struct wakeup_source *ws) { if (ws) { wakeup_source_remove(ws); if (ws->dev) wakeup_source_sysfs_remove(ws); wakeup_source_destroy(ws); } } EXPORT_SYMBOL_GPL(wakeup_source_unregister); /** * wakeup_sources_read_lock - Lock wakeup source list for read. * * Returns an index of srcu lock for struct wakeup_srcu. * This index must be passed to the matching wakeup_sources_read_unlock(). */ int wakeup_sources_read_lock(void) { return srcu_read_lock(&wakeup_srcu); } EXPORT_SYMBOL_GPL(wakeup_sources_read_lock); /** * wakeup_sources_read_unlock - Unlock wakeup source list. * @idx: return value from corresponding wakeup_sources_read_lock() */ void wakeup_sources_read_unlock(int idx) { srcu_read_unlock(&wakeup_srcu, idx); } EXPORT_SYMBOL_GPL(wakeup_sources_read_unlock); /** * wakeup_sources_walk_start - Begin a walk on wakeup source list * * Returns first object of the list of wakeup sources. * * Note that to be safe, wakeup sources list needs to be locked by calling * wakeup_source_read_lock() for this. */ struct wakeup_source *wakeup_sources_walk_start(void) { struct list_head *ws_head = &wakeup_sources; return list_entry_rcu(ws_head->next, struct wakeup_source, entry); } EXPORT_SYMBOL_GPL(wakeup_sources_walk_start); /** * wakeup_sources_walk_next - Get next wakeup source from the list * @ws: Previous wakeup source object * * Note that to be safe, wakeup sources list needs to be locked by calling * wakeup_source_read_lock() for this. */ struct wakeup_source *wakeup_sources_walk_next(struct wakeup_source *ws) { struct list_head *ws_head = &wakeup_sources; return list_next_or_null_rcu(ws_head, &ws->entry, struct wakeup_source, entry); } EXPORT_SYMBOL_GPL(wakeup_sources_walk_next); /** * device_wakeup_attach - Attach a wakeup source object to a device object. * @dev: Device to handle. * @ws: Wakeup source object to attach to @dev. * * This causes @dev to be treated as a wakeup device. */ static int device_wakeup_attach(struct device *dev, struct wakeup_source *ws) { spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { spin_unlock_irq(&dev->power.lock); return -EEXIST; } dev->power.wakeup = ws; if (dev->power.wakeirq) device_wakeup_attach_irq(dev, dev->power.wakeirq); spin_unlock_irq(&dev->power.lock); return 0; } /** * device_wakeup_enable - Enable given device to be a wakeup source. * @dev: Device to handle. * * Create a wakeup source object, register it and attach it to @dev. */ int device_wakeup_enable(struct device *dev) { struct wakeup_source *ws; int ret; if (!dev || !dev->power.can_wakeup) return -EINVAL; if (pm_suspend_target_state != PM_SUSPEND_ON) dev_dbg(dev, "Suspicious %s() during system transition!\n", __func__); ws = wakeup_source_register(dev, dev_name(dev)); if (!ws) return -ENOMEM; ret = device_wakeup_attach(dev, ws); if (ret) wakeup_source_unregister(ws); return ret; } EXPORT_SYMBOL_GPL(device_wakeup_enable); /** * device_wakeup_attach_irq - Attach a wakeirq to a wakeup source * @dev: Device to handle * @wakeirq: Device specific wakeirq entry * * Attach a device wakeirq to the wakeup source so the device * wake IRQ can be configured automatically for suspend and * resume. * * Call under the device's power.lock lock. */ void device_wakeup_attach_irq(struct device *dev, struct wake_irq *wakeirq) { struct wakeup_source *ws; ws = dev->power.wakeup; if (!ws) return; if (ws->wakeirq) dev_err(dev, "Leftover wakeup IRQ found, overriding\n"); ws->wakeirq = wakeirq; } /** * device_wakeup_detach_irq - Detach a wakeirq from a wakeup source * @dev: Device to handle * * Removes a device wakeirq from the wakeup source. * * Call under the device's power.lock lock. */ void device_wakeup_detach_irq(struct device *dev) { struct wakeup_source *ws; ws = dev->power.wakeup; if (ws) ws->wakeirq = NULL; } /** * device_wakeup_arm_wake_irqs - * * Iterates over the list of device wakeirqs to arm them. */ void device_wakeup_arm_wake_irqs(void) { struct wakeup_source *ws; int srcuidx; srcuidx = srcu_read_lock(&wakeup_srcu); list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) dev_pm_arm_wake_irq(ws->wakeirq); srcu_read_unlock(&wakeup_srcu, srcuidx); } /** * device_wakeup_disarm_wake_irqs - * * Iterates over the list of device wakeirqs to disarm them. */ void device_wakeup_disarm_wake_irqs(void) { struct wakeup_source *ws; int srcuidx; srcuidx = srcu_read_lock(&wakeup_srcu); list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) dev_pm_disarm_wake_irq(ws->wakeirq); srcu_read_unlock(&wakeup_srcu, srcuidx); } /** * device_wakeup_detach - Detach a device's wakeup source object from it. * @dev: Device to detach the wakeup source object from. * * After it returns, @dev will not be treated as a wakeup device any more. */ static struct wakeup_source *device_wakeup_detach(struct device *dev) { struct wakeup_source *ws; spin_lock_irq(&dev->power.lock); ws = dev->power.wakeup; dev->power.wakeup = NULL; spin_unlock_irq(&dev->power.lock); return ws; } /** * device_wakeup_disable - Do not regard a device as a wakeup source any more. * @dev: Device to handle. * * Detach the @dev's wakeup source object from it, unregister this wakeup source * object and destroy it. */ void device_wakeup_disable(struct device *dev) { struct wakeup_source *ws; if (!dev || !dev->power.can_wakeup) return; ws = device_wakeup_detach(dev); wakeup_source_unregister(ws); } EXPORT_SYMBOL_GPL(device_wakeup_disable); /** * device_set_wakeup_capable - Set/reset device wakeup capability flag. * @dev: Device to handle. * @capable: Whether or not @dev is capable of waking up the system from sleep. * * If @capable is set, set the @dev's power.can_wakeup flag and add its * wakeup-related attributes to sysfs. Otherwise, unset the @dev's * power.can_wakeup flag and remove its wakeup-related attributes from sysfs. * * This function may sleep and it can't be called from any context where * sleeping is not allowed. */ void device_set_wakeup_capable(struct device *dev, bool capable) { if (!!dev->power.can_wakeup == !!capable) return; dev->power.can_wakeup = capable; if (device_is_registered(dev) && !list_empty(&dev->power.entry)) { if (capable) { int ret = wakeup_sysfs_add(dev); if (ret) dev_info(dev, "Wakeup sysfs attributes not added\n"); } else { wakeup_sysfs_remove(dev); } } } EXPORT_SYMBOL_GPL(device_set_wakeup_capable); /** * device_set_wakeup_enable - Enable or disable a device to wake up the system. * @dev: Device to handle. * @enable: enable/disable flag */ int device_set_wakeup_enable(struct device *dev, bool enable) { if (enable) return device_wakeup_enable(dev); device_wakeup_disable(dev); return 0; } EXPORT_SYMBOL_GPL(device_set_wakeup_enable); /** * wakeup_source_not_registered - validate the given wakeup source. * @ws: Wakeup source to be validated. */ static bool wakeup_source_not_registered(struct wakeup_source *ws) { /* * Use timer struct to check if the given source is initialized * by wakeup_source_add. */ return ws->timer.function != pm_wakeup_timer_fn; } /* * The functions below use the observation that each wakeup event starts a * period in which the system should not be suspended. The moment this period * will end depends on how the wakeup event is going to be processed after being * detected and all of the possible cases can be divided into two distinct * groups. * * First, a wakeup event may be detected by the same functional unit that will * carry out the entire processing of it and possibly will pass it to user space * for further processing. In that case the functional unit that has detected * the event may later "close" the "no suspend" period associated with it * directly as soon as it has been dealt with. The pair of pm_stay_awake() and * pm_relax(), balanced with each other, is supposed to be used in such * situations. * * Second, a wakeup event may be detected by one functional unit and processed * by another one. In that case the unit that has detected it cannot really * "close" the "no suspend" period associated with it, unless it knows in * advance what's going to happen to the event during processing. This * knowledge, however, may not be available to it, so it can simply specify time * to wait before the system can be suspended and pass it as the second * argument of pm_wakeup_event(). * * It is valid to call pm_relax() after pm_wakeup_event(), in which case the * "no suspend" period will be ended either by the pm_relax(), or by the timer * function executed when the timer expires, whichever comes first. */ /** * wakeup_source_activate - Mark given wakeup source as active. * @ws: Wakeup source to handle. * * Update the @ws' statistics and, if @ws has just been activated, notify the PM * core of the event by incrementing the counter of the wakeup events being * processed. */ static void wakeup_source_activate(struct wakeup_source *ws) { unsigned int cec; if (WARN_ONCE(wakeup_source_not_registered(ws), "unregistered wakeup source\n")) return; ws->active = true; ws->active_count++; ws->last_time = ktime_get(); if (ws->autosleep_enabled) ws->start_prevent_time = ws->last_time; /* Increment the counter of events in progress. */ cec = atomic_inc_return(&combined_event_count); trace_wakeup_source_activate(ws->name, cec); } /** * wakeup_source_report_event - Report wakeup event using the given source. * @ws: Wakeup source to report the event for. * @hard: If set, abort suspends in progress and wake up from suspend-to-idle. */ static void wakeup_source_report_event(struct wakeup_source *ws, bool hard) { ws->event_count++; /* This is racy, but the counter is approximate anyway. */ if (events_check_enabled) ws->wakeup_count++; if (!ws->active) wakeup_source_activate(ws); if (hard) pm_system_wakeup(); } /** * __pm_stay_awake - Notify the PM core of a wakeup event. * @ws: Wakeup source object associated with the source of the event. * * It is safe to call this function from interrupt context. */ void __pm_stay_awake(struct wakeup_source *ws) { unsigned long flags; if (!ws) return; spin_lock_irqsave(&ws->lock, flags); wakeup_source_report_event(ws, false); del_timer(&ws->timer); ws->timer_expires = 0; spin_unlock_irqrestore(&ws->lock, flags); } EXPORT_SYMBOL_GPL(__pm_stay_awake); /** * pm_stay_awake - Notify the PM core that a wakeup event is being processed. * @dev: Device the wakeup event is related to. * * Notify the PM core of a wakeup event (signaled by @dev) by calling * __pm_stay_awake for the @dev's wakeup source object. * * Call this function after detecting of a wakeup event if pm_relax() is going * to be called directly after processing the event (and possibly passing it to * user space for further processing). */ void pm_stay_awake(struct device *dev) { unsigned long flags; if (!dev) return; spin_lock_irqsave(&dev->power.lock, flags); __pm_stay_awake(dev->power.wakeup); spin_unlock_irqrestore(&dev->power.lock, flags); } EXPORT_SYMBOL_GPL(pm_stay_awake); #ifdef CONFIG_PM_AUTOSLEEP static void update_prevent_sleep_time(struct wakeup_source *ws, ktime_t now) { ktime_t delta = ktime_sub(now, ws->start_prevent_time); ws->prevent_sleep_time = ktime_add(ws->prevent_sleep_time, delta); } #else static inline void update_prevent_sleep_time(struct wakeup_source *ws, ktime_t now) {} #endif /** * wakeup_source_deactivate - Mark given wakeup source as inactive. * @ws: Wakeup source to handle. * * Update the @ws' statistics and notify the PM core that the wakeup source has * become inactive by decrementing the counter of wakeup events being processed * and incrementing the counter of registered wakeup events. */ static void wakeup_source_deactivate(struct wakeup_source *ws) { unsigned int cnt, inpr, cec; ktime_t duration; ktime_t now; ws->relax_count++; /* * __pm_relax() may be called directly or from a timer function. * If it is called directly right after the timer function has been * started, but before the timer function calls __pm_relax(), it is * possible that __pm_stay_awake() will be called in the meantime and * will set ws->active. Then, ws->active may be cleared immediately * by the __pm_relax() called from the timer function, but in such a * case ws->relax_count will be different from ws->active_count. */ if (ws->relax_count != ws->active_count) { ws->relax_count--; return; } ws->active = false; now = ktime_get(); duration = ktime_sub(now, ws->last_time); ws->total_time = ktime_add(ws->total_time, duration); if (ktime_to_ns(duration) > ktime_to_ns(ws->max_time)) ws->max_time = duration; ws->last_time = now; del_timer(&ws->timer); ws->timer_expires = 0; if (ws->autosleep_enabled) update_prevent_sleep_time(ws, now); /* * Increment the counter of registered wakeup events and decrement the * counter of wakeup events in progress simultaneously. */ cec = atomic_add_return(MAX_IN_PROGRESS, &combined_event_count); trace_wakeup_source_deactivate(ws->name, cec); split_counters(&cnt, &inpr); if (!inpr && waitqueue_active(&wakeup_count_wait_queue)) wake_up(&wakeup_count_wait_queue); } /** * __pm_relax - Notify the PM core that processing of a wakeup event has ended. * @ws: Wakeup source object associated with the source of the event. * * Call this function for wakeup events whose processing started with calling * __pm_stay_awake(). * * It is safe to call it from interrupt context. */ void __pm_relax(struct wakeup_source *ws) { unsigned long flags; if (!ws) return; spin_lock_irqsave(&ws->lock, flags); if (ws->active) wakeup_source_deactivate(ws); spin_unlock_irqrestore(&ws->lock, flags); } EXPORT_SYMBOL_GPL(__pm_relax); /** * pm_relax - Notify the PM core that processing of a wakeup event has ended. * @dev: Device that signaled the event. * * Execute __pm_relax() for the @dev's wakeup source object. */ void pm_relax(struct device *dev) { unsigned long flags; if (!dev) return; spin_lock_irqsave(&dev->power.lock, flags); __pm_relax(dev->power.wakeup); spin_unlock_irqrestore(&dev->power.lock, flags); } EXPORT_SYMBOL_GPL(pm_relax); /** * pm_wakeup_timer_fn - Delayed finalization of a wakeup event. * @t: timer list * * Call wakeup_source_deactivate() for the wakeup source whose address is stored * in @data if it is currently active and its timer has not been canceled and * the expiration time of the timer is not in future. */ static void pm_wakeup_timer_fn(struct timer_list *t) { struct wakeup_source *ws = from_timer(ws, t, timer); unsigned long flags; spin_lock_irqsave(&ws->lock, flags); if (ws->active && ws->timer_expires && time_after_eq(jiffies, ws->timer_expires)) { wakeup_source_deactivate(ws); ws->expire_count++; } spin_unlock_irqrestore(&ws->lock, flags); } /** * pm_wakeup_ws_event - Notify the PM core of a wakeup event. * @ws: Wakeup source object associated with the event source. * @msec: Anticipated event processing time (in milliseconds). * @hard: If set, abort suspends in progress and wake up from suspend-to-idle. * * Notify the PM core of a wakeup event whose source is @ws that will take * approximately @msec milliseconds to be processed by the kernel. If @ws is * not active, activate it. If @msec is nonzero, set up the @ws' timer to * execute pm_wakeup_timer_fn() in future. * * It is safe to call this function from interrupt context. */ void pm_wakeup_ws_event(struct wakeup_source *ws, unsigned int msec, bool hard) { unsigned long flags; unsigned long expires; if (!ws) return; spin_lock_irqsave(&ws->lock, flags); wakeup_source_report_event(ws, hard); if (!msec) { wakeup_source_deactivate(ws); goto unlock; } expires = jiffies + msecs_to_jiffies(msec); if (!expires) expires = 1; if (!ws->timer_expires || time_after(expires, ws->timer_expires)) { mod_timer(&ws->timer, expires); ws->timer_expires = expires; } unlock: spin_unlock_irqrestore(&ws->lock, flags); } EXPORT_SYMBOL_GPL(pm_wakeup_ws_event); /** * pm_wakeup_dev_event - Notify the PM core of a wakeup event. * @dev: Device the wakeup event is related to. * @msec: Anticipated event processing time (in milliseconds). * @hard: If set, abort suspends in progress and wake up from suspend-to-idle. * * Call pm_wakeup_ws_event() for the @dev's wakeup source object. */ void pm_wakeup_dev_event(struct device *dev, unsigned int msec, bool hard) { unsigned long flags; if (!dev) return; spin_lock_irqsave(&dev->power.lock, flags); pm_wakeup_ws_event(dev->power.wakeup, msec, hard); spin_unlock_irqrestore(&dev->power.lock, flags); } EXPORT_SYMBOL_GPL(pm_wakeup_dev_event); void pm_print_active_wakeup_sources(void) { struct wakeup_source *ws; int srcuidx, active = 0; struct wakeup_source *last_activity_ws = NULL; srcuidx = srcu_read_lock(&wakeup_srcu); list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) { if (ws->active) { pm_pr_dbg("active wakeup source: %s\n", ws->name); active = 1; } else if (!active && (!last_activity_ws || ktime_to_ns(ws->last_time) > ktime_to_ns(last_activity_ws->last_time))) { last_activity_ws = ws; } } if (!active && last_activity_ws) pm_pr_dbg("last active wakeup source: %s\n", last_activity_ws->name); srcu_read_unlock(&wakeup_srcu, srcuidx); } EXPORT_SYMBOL_GPL(pm_print_active_wakeup_sources); /** * pm_wakeup_pending - Check if power transition in progress should be aborted. * * Compare the current number of registered wakeup events with its preserved * value from the past and return true if new wakeup events have been registered * since the old value was stored. Also return true if the current number of * wakeup events being processed is different from zero. */ bool pm_wakeup_pending(void) { unsigned long flags; bool ret = false; raw_spin_lock_irqsave(&events_lock, flags); if (events_check_enabled) { unsigned int cnt, inpr; split_counters(&cnt, &inpr); ret = (cnt != saved_count || inpr > 0); events_check_enabled = !ret; } raw_spin_unlock_irqrestore(&events_lock, flags); if (ret) { pm_pr_dbg("Wakeup pending, aborting suspend\n"); pm_print_active_wakeup_sources(); } return ret || atomic_read(&pm_abort_suspend) > 0; } EXPORT_SYMBOL_GPL(pm_wakeup_pending); void pm_system_wakeup(void) { atomic_inc(&pm_abort_suspend); s2idle_wake(); } EXPORT_SYMBOL_GPL(pm_system_wakeup); void pm_system_cancel_wakeup(void) { atomic_dec_if_positive(&pm_abort_suspend); } void pm_wakeup_clear(unsigned int irq_number) { raw_spin_lock_irq(&wakeup_irq_lock); if (irq_number && wakeup_irq[0] == irq_number) wakeup_irq[0] = wakeup_irq[1]; else wakeup_irq[0] = 0; wakeup_irq[1] = 0; raw_spin_unlock_irq(&wakeup_irq_lock); if (!irq_number) atomic_set(&pm_abort_suspend, 0); } void pm_system_irq_wakeup(unsigned int irq_number) { unsigned long flags; raw_spin_lock_irqsave(&wakeup_irq_lock, flags); if (wakeup_irq[0] == 0) wakeup_irq[0] = irq_number; else if (wakeup_irq[1] == 0) wakeup_irq[1] = irq_number; else irq_number = 0; pm_pr_dbg("Triggering wakeup from IRQ %d\n", irq_number); raw_spin_unlock_irqrestore(&wakeup_irq_lock, flags); if (irq_number) pm_system_wakeup(); } unsigned int pm_wakeup_irq(void) { return wakeup_irq[0]; } /** * pm_get_wakeup_count - Read the number of registered wakeup events. * @count: Address to store the value at. * @block: Whether or not to block. * * Store the number of registered wakeup events at the address in @count. If * @block is set, block until the current number of wakeup events being * processed is zero. * * Return 'false' if the current number of wakeup events being processed is * nonzero. Otherwise return 'true'. */ bool pm_get_wakeup_count(unsigned int *count, bool block) { unsigned int cnt, inpr; if (block) { DEFINE_WAIT(wait); for (;;) { prepare_to_wait(&wakeup_count_wait_queue, &wait, TASK_INTERRUPTIBLE); split_counters(&cnt, &inpr); if (inpr == 0 || signal_pending(current)) break; pm_print_active_wakeup_sources(); schedule(); } finish_wait(&wakeup_count_wait_queue, &wait); } split_counters(&cnt, &inpr); *count = cnt; return !inpr; } /** * pm_save_wakeup_count - Save the current number of registered wakeup events. * @count: Value to compare with the current number of registered wakeup events. * * If @count is equal to the current number of registered wakeup events and the * current number of wakeup events being processed is zero, store @count as the * old number of registered wakeup events for pm_check_wakeup_events(), enable * wakeup events detection and return 'true'. Otherwise disable wakeup events * detection and return 'false'. */ bool pm_save_wakeup_count(unsigned int count) { unsigned int cnt, inpr; unsigned long flags; events_check_enabled = false; raw_spin_lock_irqsave(&events_lock, flags); split_counters(&cnt, &inpr); if (cnt == count && inpr == 0) { saved_count = count; events_check_enabled = true; } raw_spin_unlock_irqrestore(&events_lock, flags); return events_check_enabled; } #ifdef CONFIG_PM_AUTOSLEEP /** * pm_wakep_autosleep_enabled - Modify autosleep_enabled for all wakeup sources. * @set: Whether to set or to clear the autosleep_enabled flags. */ void pm_wakep_autosleep_enabled(bool set) { struct wakeup_source *ws; ktime_t now = ktime_get(); int srcuidx; srcuidx = srcu_read_lock(&wakeup_srcu); list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) { spin_lock_irq(&ws->lock); if (ws->autosleep_enabled != set) { ws->autosleep_enabled = set; if (ws->active) { if (set) ws->start_prevent_time = now; else update_prevent_sleep_time(ws, now); } } spin_unlock_irq(&ws->lock); } srcu_read_unlock(&wakeup_srcu, srcuidx); } #endif /* CONFIG_PM_AUTOSLEEP */ /** * print_wakeup_source_stats - Print wakeup source statistics information. * @m: seq_file to print the statistics into. * @ws: Wakeup source object to print the statistics for. */ static int print_wakeup_source_stats(struct seq_file *m, struct wakeup_source *ws) { unsigned long flags; ktime_t total_time; ktime_t max_time; unsigned long active_count; ktime_t active_time; ktime_t prevent_sleep_time; spin_lock_irqsave(&ws->lock, flags); total_time = ws->total_time; max_time = ws->max_time; prevent_sleep_time = ws->prevent_sleep_time; active_count = ws->active_count; if (ws->active) { ktime_t now = ktime_get(); active_time = ktime_sub(now, ws->last_time); total_time = ktime_add(total_time, active_time); if (active_time > max_time) max_time = active_time; if (ws->autosleep_enabled) prevent_sleep_time = ktime_add(prevent_sleep_time, ktime_sub(now, ws->start_prevent_time)); } else { active_time = 0; } seq_printf(m, "%-12s\t%lu\t\t%lu\t\t%lu\t\t%lu\t\t%lld\t\t%lld\t\t%lld\t\t%lld\t\t%lld\n", ws->name, active_count, ws->event_count, ws->wakeup_count, ws->expire_count, ktime_to_ms(active_time), ktime_to_ms(total_time), ktime_to_ms(max_time), ktime_to_ms(ws->last_time), ktime_to_ms(prevent_sleep_time)); spin_unlock_irqrestore(&ws->lock, flags); return 0; } static void *wakeup_sources_stats_seq_start(struct seq_file *m, loff_t *pos) { struct wakeup_source *ws; loff_t n = *pos; int *srcuidx = m->private; if (n == 0) { seq_puts(m, "name\t\tactive_count\tevent_count\twakeup_count\t" "expire_count\tactive_since\ttotal_time\tmax_time\t" "last_change\tprevent_suspend_time\n"); } *srcuidx = srcu_read_lock(&wakeup_srcu); list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) { if (n-- <= 0) return ws; } return NULL; } static void *wakeup_sources_stats_seq_next(struct seq_file *m, void *v, loff_t *pos) { struct wakeup_source *ws = v; struct wakeup_source *next_ws = NULL; ++(*pos); list_for_each_entry_continue_rcu(ws, &wakeup_sources, entry) { next_ws = ws; break; } if (!next_ws) print_wakeup_source_stats(m, &deleted_ws); return next_ws; } static void wakeup_sources_stats_seq_stop(struct seq_file *m, void *v) { int *srcuidx = m->private; srcu_read_unlock(&wakeup_srcu, *srcuidx); } /** * wakeup_sources_stats_seq_show - Print wakeup sources statistics information. * @m: seq_file to print the statistics into. * @v: wakeup_source of each iteration */ static int wakeup_sources_stats_seq_show(struct seq_file *m, void *v) { struct wakeup_source *ws = v; print_wakeup_source_stats(m, ws); return 0; } static const struct seq_operations wakeup_sources_stats_seq_ops = { .start = wakeup_sources_stats_seq_start, .next = wakeup_sources_stats_seq_next, .stop = wakeup_sources_stats_seq_stop, .show = wakeup_sources_stats_seq_show, }; static int wakeup_sources_stats_open(struct inode *inode, struct file *file) { return seq_open_private(file, &wakeup_sources_stats_seq_ops, sizeof(int)); } static const struct file_operations wakeup_sources_stats_fops = { .owner = THIS_MODULE, .open = wakeup_sources_stats_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release_private, }; static int __init wakeup_sources_debugfs_init(void) { debugfs_create_file("wakeup_sources", 0444, NULL, NULL, &wakeup_sources_stats_fops); return 0; } postcore_initcall(wakeup_sources_debugfs_init); |
| 54 225 225 225 88 105 77 133 61 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2007 Oracle. All rights reserved. */ #ifndef BTRFS_INODE_H #define BTRFS_INODE_H #include <linux/hash.h> #include <linux/refcount.h> #include <linux/spinlock.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/compiler.h> #include <linux/fscrypt.h> #include <linux/lockdep.h> #include <uapi/linux/btrfs_tree.h> #include <trace/events/btrfs.h> #include "block-rsv.h" #include "extent_map.h" #include "extent_io.h" #include "extent-io-tree.h" #include "ordered-data.h" #include "delayed-inode.h" struct extent_state; struct posix_acl; struct iov_iter; struct writeback_control; struct btrfs_root; struct btrfs_fs_info; struct btrfs_trans_handle; /* * Since we search a directory based on f_pos (struct dir_context::pos) we have * to start at 2 since '.' and '..' have f_pos of 0 and 1 respectively, so * everybody else has to start at 2 (see btrfs_real_readdir() and dir_emit_dots()). */ #define BTRFS_DIR_START_INDEX 2 /* * ordered_data_close is set by truncate when a file that used * to have good data has been truncated to zero. When it is set * the btrfs file release call will add this inode to the * ordered operations list so that we make sure to flush out any * new data the application may have written before commit. */ enum { BTRFS_INODE_FLUSH_ON_CLOSE, BTRFS_INODE_DUMMY, BTRFS_INODE_IN_DEFRAG, BTRFS_INODE_HAS_ASYNC_EXTENT, /* * Always set under the VFS' inode lock, otherwise it can cause races * during fsync (we start as a fast fsync and then end up in a full * fsync racing with ordered extent completion). */ BTRFS_INODE_NEEDS_FULL_SYNC, BTRFS_INODE_COPY_EVERYTHING, BTRFS_INODE_HAS_PROPS, BTRFS_INODE_SNAPSHOT_FLUSH, /* * Set and used when logging an inode and it serves to signal that an * inode does not have xattrs, so subsequent fsyncs can avoid searching * for xattrs to log. This bit must be cleared whenever a xattr is added * to an inode. */ BTRFS_INODE_NO_XATTRS, /* * Set when we are in a context where we need to start a transaction and * have dirty pages with the respective file range locked. This is to * ensure that when reserving space for the transaction, if we are low * on available space and need to flush delalloc, we will not flush * delalloc for this inode, because that could result in a deadlock (on * the file range, inode's io_tree). */ BTRFS_INODE_NO_DELALLOC_FLUSH, /* * Set when we are working on enabling verity for a file. Computing and * writing the whole Merkle tree can take a while so we want to prevent * races where two separate tasks attempt to simultaneously start verity * on the same file. */ BTRFS_INODE_VERITY_IN_PROGRESS, /* Set when this inode is a free space inode. */ BTRFS_INODE_FREE_SPACE_INODE, /* Set when there are no capabilities in XATTs for the inode. */ BTRFS_INODE_NO_CAP_XATTR, /* * Set if an error happened when doing a COW write before submitting a * bio or during writeback. Used for both buffered writes and direct IO * writes. This is to signal a fast fsync that it has to wait for * ordered extents to complete and therefore not log extent maps that * point to unwritten extents (when an ordered extent completes and it * has the BTRFS_ORDERED_IOERR flag set, it drops extent maps in its * range). */ BTRFS_INODE_COW_WRITE_ERROR, /* * Indicate this is a directory that points to a subvolume for which * there is no root reference item. That's a case like the following: * * $ btrfs subvolume create /mnt/parent * $ btrfs subvolume create /mnt/parent/child * $ btrfs subvolume snapshot /mnt/parent /mnt/snap * * If subvolume "parent" is root 256, subvolume "child" is root 257 and * snapshot "snap" is root 258, then there's no root reference item (key * BTRFS_ROOT_REF_KEY in the root tree) for the subvolume "child" * associated to root 258 (the snapshot) - there's only for the root * of the "parent" subvolume (root 256). In the chunk root we have a * (256 BTRFS_ROOT_REF_KEY 257) key but we don't have a * (258 BTRFS_ROOT_REF_KEY 257) key - the sames goes for backrefs, we * have a (257 BTRFS_ROOT_BACKREF_KEY 256) but we don't have a * (257 BTRFS_ROOT_BACKREF_KEY 258) key. * * So when opening the "child" dentry from the snapshot's directory, * we don't find a root ref item and we create a stub inode. This is * done at new_simple_dir(), called from btrfs_lookup_dentry(). */ BTRFS_INODE_ROOT_STUB, }; /* in memory btrfs inode */ struct btrfs_inode { /* which subvolume this inode belongs to */ struct btrfs_root *root; #if BITS_PER_LONG == 32 /* * The objectid of the corresponding BTRFS_INODE_ITEM_KEY. * On 64 bits platforms we can get it from vfs_inode.i_ino, which is an * unsigned long and therefore 64 bits on such platforms. */ u64 objectid; #endif /* Cached value of inode property 'compression'. */ u8 prop_compress; /* * Force compression on the file using the defrag ioctl, could be * different from prop_compress and takes precedence if set. */ u8 defrag_compress; /* * Lock for counters and all fields used to determine if the inode is in * the log or not (last_trans, last_sub_trans, last_log_commit, * logged_trans), to access/update delalloc_bytes, new_delalloc_bytes, * defrag_bytes, disk_i_size, outstanding_extents, csum_bytes and to * update the VFS' inode number of bytes used. */ spinlock_t lock; /* the extent_tree has caches of all the extent mappings to disk */ struct extent_map_tree extent_tree; /* the io_tree does range state (DIRTY, LOCKED etc) */ struct extent_io_tree io_tree; /* * Keep track of where the inode has extent items mapped in order to * make sure the i_size adjustments are accurate. Not required when the * filesystem is NO_HOLES, the status can't be set while mounted as * it's a mkfs-time feature. */ struct extent_io_tree *file_extent_tree; /* held while logging the inode in tree-log.c */ struct mutex log_mutex; /* * Counters to keep track of the number of extent item's we may use due * to delalloc and such. outstanding_extents is the number of extent * items we think we'll end up using, and reserved_extents is the number * of extent items we've reserved metadata for. Protected by 'lock'. */ unsigned outstanding_extents; /* used to order data wrt metadata */ spinlock_t ordered_tree_lock; struct rb_root ordered_tree; struct rb_node *ordered_tree_last; /* list of all the delalloc inodes in the FS. There are times we need * to write all the delalloc pages to disk, and this list is used * to walk them all. */ struct list_head delalloc_inodes; unsigned long runtime_flags; /* full 64 bit generation number, struct vfs_inode doesn't have a big * enough field for this. */ u64 generation; /* * ID of the transaction handle that last modified this inode. * Protected by 'lock'. */ u64 last_trans; /* * ID of the transaction that last logged this inode. * Protected by 'lock'. */ u64 logged_trans; /* * Log transaction ID when this inode was last modified. * Protected by 'lock'. */ int last_sub_trans; /* A local copy of root's last_log_commit. Protected by 'lock'. */ int last_log_commit; union { /* * Total number of bytes pending delalloc, used by stat to * calculate the real block usage of the file. This is used * only for files. Protected by 'lock'. */ u64 delalloc_bytes; /* * The lowest possible index of the next dir index key which * points to an inode that needs to be logged. * This is used only for directories. * Use the helpers btrfs_get_first_dir_index_to_log() and * btrfs_set_first_dir_index_to_log() to access this field. */ u64 first_dir_index_to_log; }; union { /* * Total number of bytes pending delalloc that fall within a file * range that is either a hole or beyond EOF (and no prealloc extent * exists in the range). This is always <= delalloc_bytes and this * is used only for files. Protected by 'lock'. */ u64 new_delalloc_bytes; /* * The offset of the last dir index key that was logged. * This is used only for directories. */ u64 last_dir_index_offset; }; union { /* * Total number of bytes pending defrag, used by stat to check whether * it needs COW. Protected by 'lock'. * Used by inodes other than the data relocation inode. */ u64 defrag_bytes; /* * Logical address of the block group being relocated. * Used only by the data relocation inode. */ u64 reloc_block_group_start; }; /* * The size of the file stored in the metadata on disk. data=ordered * means the in-memory i_size might be larger than the size on disk * because not all the blocks are written yet. Protected by 'lock'. */ u64 disk_i_size; union { /* * If this is a directory then index_cnt is the counter for the * index number for new files that are created. For an empty * directory, this must be initialized to BTRFS_DIR_START_INDEX. */ u64 index_cnt; /* * If this is not a directory, this is the number of bytes * outstanding that are going to need csums. This is used in * ENOSPC accounting. Protected by 'lock'. */ u64 csum_bytes; }; /* Cache the directory index number to speed the dir/file remove */ u64 dir_index; /* the fsync log has some corner cases that mean we have to check * directories to see if any unlinks have been done before * the directory was logged. See tree-log.c for all the * details */ u64 last_unlink_trans; union { /* * The id/generation of the last transaction where this inode * was either the source or the destination of a clone/dedupe * operation. Used when logging an inode to know if there are * shared extents that need special care when logging checksum * items, to avoid duplicate checksum items in a log (which can * lead to a corruption where we end up with missing checksum * ranges after log replay). Protected by the VFS inode lock. * Used for regular files only. */ u64 last_reflink_trans; /* * In case this a root stub inode (BTRFS_INODE_ROOT_STUB flag set), * the ID of that root. */ u64 ref_root_id; }; /* Backwards incompatible flags, lower half of inode_item::flags */ u32 flags; /* Read-only compatibility flags, upper half of inode_item::flags */ u32 ro_flags; struct btrfs_block_rsv block_rsv; struct btrfs_delayed_node *delayed_node; /* File creation time. */ u64 i_otime_sec; u32 i_otime_nsec; /* Hook into fs_info->delayed_iputs */ struct list_head delayed_iput; struct rw_semaphore i_mmap_lock; struct inode vfs_inode; }; static inline u64 btrfs_get_first_dir_index_to_log(const struct btrfs_inode *inode) { return READ_ONCE(inode->first_dir_index_to_log); } static inline void btrfs_set_first_dir_index_to_log(struct btrfs_inode *inode, u64 index) { WRITE_ONCE(inode->first_dir_index_to_log, index); } static inline struct btrfs_inode *BTRFS_I(const struct inode *inode) { return container_of(inode, struct btrfs_inode, vfs_inode); } static inline unsigned long btrfs_inode_hash(u64 objectid, const struct btrfs_root *root) { u64 h = objectid ^ (root->root_key.objectid * GOLDEN_RATIO_PRIME); #if BITS_PER_LONG == 32 h = (h >> 32) ^ (h & 0xffffffff); #endif return (unsigned long)h; } #if BITS_PER_LONG == 32 /* * On 32 bit systems the i_ino of struct inode is 32 bits (unsigned long), so * we use the inode's location objectid which is a u64 to avoid truncation. */ static inline u64 btrfs_ino(const struct btrfs_inode *inode) { u64 ino = inode->objectid; if (test_bit(BTRFS_INODE_ROOT_STUB, &inode->runtime_flags)) ino = inode->vfs_inode.i_ino; return ino; } #else static inline u64 btrfs_ino(const struct btrfs_inode *inode) { return inode->vfs_inode.i_ino; } #endif static inline void btrfs_get_inode_key(const struct btrfs_inode *inode, struct btrfs_key *key) { key->objectid = btrfs_ino(inode); key->type = BTRFS_INODE_ITEM_KEY; key->offset = 0; } static inline void btrfs_set_inode_number(struct btrfs_inode *inode, u64 ino) { #if BITS_PER_LONG == 32 inode->objectid = ino; #endif inode->vfs_inode.i_ino = ino; } static inline void btrfs_i_size_write(struct btrfs_inode *inode, u64 size) { i_size_write(&inode->vfs_inode, size); inode->disk_i_size = size; } static inline bool btrfs_is_free_space_inode(const struct btrfs_inode *inode) { return test_bit(BTRFS_INODE_FREE_SPACE_INODE, &inode->runtime_flags); } static inline bool is_data_inode(const struct btrfs_inode *inode) { return btrfs_ino(inode) != BTRFS_BTREE_INODE_OBJECTID; } static inline void btrfs_mod_outstanding_extents(struct btrfs_inode *inode, int mod) { lockdep_assert_held(&inode->lock); inode->outstanding_extents += mod; if (btrfs_is_free_space_inode(inode)) return; trace_btrfs_inode_mod_outstanding_extents(inode->root, btrfs_ino(inode), mod, inode->outstanding_extents); } /* * Called every time after doing a buffered, direct IO or memory mapped write. * * This is to ensure that if we write to a file that was previously fsynced in * the current transaction, then try to fsync it again in the same transaction, * we will know that there were changes in the file and that it needs to be * logged. */ static inline void btrfs_set_inode_last_sub_trans(struct btrfs_inode *inode) { spin_lock(&inode->lock); inode->last_sub_trans = inode->root->log_transid; spin_unlock(&inode->lock); } /* * Should be called while holding the inode's VFS lock in exclusive mode, or * while holding the inode's mmap lock (struct btrfs_inode::i_mmap_lock) in * either shared or exclusive mode, or in a context where no one else can access * the inode concurrently (during inode creation or when loading an inode from * disk). */ static inline void btrfs_set_inode_full_sync(struct btrfs_inode *inode) { set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags); /* * The inode may have been part of a reflink operation in the last * transaction that modified it, and then a fsync has reset the * last_reflink_trans to avoid subsequent fsyncs in the same * transaction to do unnecessary work. So update last_reflink_trans * to the last_trans value (we have to be pessimistic and assume a * reflink happened). * * The ->last_trans is protected by the inode's spinlock and we can * have a concurrent ordered extent completion update it. Also set * last_reflink_trans to ->last_trans only if the former is less than * the later, because we can be called in a context where * last_reflink_trans was set to the current transaction generation * while ->last_trans was not yet updated in the current transaction, * and therefore has a lower value. */ spin_lock(&inode->lock); if (inode->last_reflink_trans < inode->last_trans) inode->last_reflink_trans = inode->last_trans; spin_unlock(&inode->lock); } static inline bool btrfs_inode_in_log(struct btrfs_inode *inode, u64 generation) { bool ret = false; spin_lock(&inode->lock); if (inode->logged_trans == generation && inode->last_sub_trans <= inode->last_log_commit && inode->last_sub_trans <= btrfs_get_root_last_log_commit(inode->root)) ret = true; spin_unlock(&inode->lock); return ret; } /* * Check if the inode has flags compatible with compression */ static inline bool btrfs_inode_can_compress(const struct btrfs_inode *inode) { if (inode->flags & BTRFS_INODE_NODATACOW || inode->flags & BTRFS_INODE_NODATASUM) return false; return true; } /* Array of bytes with variable length, hexadecimal format 0x1234 */ #define CSUM_FMT "0x%*phN" #define CSUM_FMT_VALUE(size, bytes) size, bytes int btrfs_check_sector_csum(struct btrfs_fs_info *fs_info, struct page *page, u32 pgoff, u8 *csum, const u8 * const csum_expected); bool btrfs_data_csum_ok(struct btrfs_bio *bbio, struct btrfs_device *dev, u32 bio_offset, struct bio_vec *bv); noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, struct btrfs_file_extent *file_extent, bool nowait, bool strict); void btrfs_del_delalloc_inode(struct btrfs_inode *inode); struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry); int btrfs_set_inode_index(struct btrfs_inode *dir, u64 *index); int btrfs_unlink_inode(struct btrfs_trans_handle *trans, struct btrfs_inode *dir, struct btrfs_inode *inode, const struct fscrypt_str *name); int btrfs_add_link(struct btrfs_trans_handle *trans, struct btrfs_inode *parent_inode, struct btrfs_inode *inode, const struct fscrypt_str *name, int add_backref, u64 index); int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry); int btrfs_truncate_block(struct btrfs_inode *inode, loff_t from, loff_t len, int front); int btrfs_start_delalloc_snapshot(struct btrfs_root *root, bool in_reclaim_context); int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr, bool in_reclaim_context); int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end, unsigned int extra_bits, struct extent_state **cached_state); struct btrfs_new_inode_args { /* Input */ struct inode *dir; struct dentry *dentry; struct inode *inode; bool orphan; bool subvol; /* Output from btrfs_new_inode_prepare(), input to btrfs_create_new_inode(). */ struct posix_acl *default_acl; struct posix_acl *acl; struct fscrypt_name fname; }; int btrfs_new_inode_prepare(struct btrfs_new_inode_args *args, unsigned int *trans_num_items); int btrfs_create_new_inode(struct btrfs_trans_handle *trans, struct btrfs_new_inode_args *args); void btrfs_new_inode_args_destroy(struct btrfs_new_inode_args *args); struct inode *btrfs_new_subvol_inode(struct mnt_idmap *idmap, struct inode *dir); void btrfs_set_delalloc_extent(struct btrfs_inode *inode, struct extent_state *state, u32 bits); void btrfs_clear_delalloc_extent(struct btrfs_inode *inode, struct extent_state *state, u32 bits); void btrfs_merge_delalloc_extent(struct btrfs_inode *inode, struct extent_state *new, struct extent_state *other); void btrfs_split_delalloc_extent(struct btrfs_inode *inode, struct extent_state *orig, u64 split); void btrfs_set_range_writeback(struct btrfs_inode *inode, u64 start, u64 end); void btrfs_evict_inode(struct inode *inode); struct inode *btrfs_alloc_inode(struct super_block *sb); void btrfs_destroy_inode(struct inode *inode); void btrfs_free_inode(struct inode *inode); int btrfs_drop_inode(struct inode *inode); int __init btrfs_init_cachep(void); void __cold btrfs_destroy_cachep(void); struct inode *btrfs_iget_path(u64 ino, struct btrfs_root *root, struct btrfs_path *path); struct inode *btrfs_iget(u64 ino, struct btrfs_root *root); struct extent_map *btrfs_get_extent(struct btrfs_inode *inode, struct page *page, u64 start, u64 len); int btrfs_update_inode(struct btrfs_trans_handle *trans, struct btrfs_inode *inode); int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans, struct btrfs_inode *inode); int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct btrfs_inode *inode); int btrfs_orphan_cleanup(struct btrfs_root *root); int btrfs_cont_expand(struct btrfs_inode *inode, loff_t oldsize, loff_t size); void btrfs_add_delayed_iput(struct btrfs_inode *inode); void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info); int btrfs_wait_on_delayed_iputs(struct btrfs_fs_info *fs_info); int btrfs_prealloc_file_range(struct inode *inode, int mode, u64 start, u64 num_bytes, u64 min_size, loff_t actual_len, u64 *alloc_hint); int btrfs_prealloc_file_range_trans(struct inode *inode, struct btrfs_trans_handle *trans, int mode, u64 start, u64 num_bytes, u64 min_size, loff_t actual_len, u64 *alloc_hint); int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page, u64 start, u64 end, struct writeback_control *wbc); int btrfs_writepage_cow_fixup(struct page *page); int btrfs_encoded_io_compression_from_extent(struct btrfs_fs_info *fs_info, int compress_type); int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode, u64 file_offset, u64 disk_bytenr, u64 disk_io_size, struct page **pages); ssize_t btrfs_encoded_read(struct kiocb *iocb, struct iov_iter *iter, struct btrfs_ioctl_encoded_io_args *encoded); ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from, const struct btrfs_ioctl_encoded_io_args *encoded); struct btrfs_inode *btrfs_find_first_inode(struct btrfs_root *root, u64 min_ino); extern const struct dentry_operations btrfs_dentry_operations; /* Inode locking type flags, by default the exclusive lock is taken. */ enum btrfs_ilock_type { ENUM_BIT(BTRFS_ILOCK_SHARED), ENUM_BIT(BTRFS_ILOCK_TRY), ENUM_BIT(BTRFS_ILOCK_MMAP), }; int btrfs_inode_lock(struct btrfs_inode *inode, unsigned int ilock_flags); void btrfs_inode_unlock(struct btrfs_inode *inode, unsigned int ilock_flags); void btrfs_update_inode_bytes(struct btrfs_inode *inode, const u64 add_bytes, const u64 del_bytes); void btrfs_assert_inode_range_clean(struct btrfs_inode *inode, u64 start, u64 end); u64 btrfs_get_extent_allocation_hint(struct btrfs_inode *inode, u64 start, u64 num_bytes); struct extent_map *btrfs_create_io_em(struct btrfs_inode *inode, u64 start, const struct btrfs_file_extent *file_extent, int type); #endif |
| 5016 5027 5022 4980 4980 189 189 5023 5036 559 560 4759 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BLK_CGROUP_PRIVATE_H #define _BLK_CGROUP_PRIVATE_H /* * block cgroup private header * * Based on ideas and code from CFQ, CFS and BFQ: * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk> * * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it> * Paolo Valente <paolo.valente@unimore.it> * * Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com> * Nauman Rafique <nauman@google.com> */ #include <linux/blk-cgroup.h> #include <linux/cgroup.h> #include <linux/kthread.h> #include <linux/blk-mq.h> #include <linux/llist.h> #include "blk.h" struct blkcg_gq; struct blkg_policy_data; /* percpu_counter batch for blkg_[rw]stats, per-cpu drift doesn't matter */ #define BLKG_STAT_CPU_BATCH (INT_MAX / 2) #ifdef CONFIG_BLK_CGROUP enum blkg_iostat_type { BLKG_IOSTAT_READ, BLKG_IOSTAT_WRITE, BLKG_IOSTAT_DISCARD, BLKG_IOSTAT_NR, }; struct blkg_iostat { u64 bytes[BLKG_IOSTAT_NR]; u64 ios[BLKG_IOSTAT_NR]; }; struct blkg_iostat_set { struct u64_stats_sync sync; struct blkcg_gq *blkg; struct llist_node lnode; int lqueued; /* queued in llist */ struct blkg_iostat cur; struct blkg_iostat last; }; /* association between a blk cgroup and a request queue */ struct blkcg_gq { /* Pointer to the associated request_queue */ struct request_queue *q; struct list_head q_node; struct hlist_node blkcg_node; struct blkcg *blkcg; /* all non-root blkcg_gq's are guaranteed to have access to parent */ struct blkcg_gq *parent; /* reference count */ struct percpu_ref refcnt; /* is this blkg online? protected by both blkcg and q locks */ bool online; struct blkg_iostat_set __percpu *iostat_cpu; struct blkg_iostat_set iostat; struct blkg_policy_data *pd[BLKCG_MAX_POLS]; #ifdef CONFIG_BLK_CGROUP_PUNT_BIO spinlock_t async_bio_lock; struct bio_list async_bios; #endif union { struct work_struct async_bio_work; struct work_struct free_work; }; atomic_t use_delay; atomic64_t delay_nsec; atomic64_t delay_start; u64 last_delay; int last_use; struct rcu_head rcu_head; }; struct blkcg { struct cgroup_subsys_state css; spinlock_t lock; refcount_t online_pin; /* If there is block congestion on this cgroup. */ atomic_t congestion_count; struct radix_tree_root blkg_tree; struct blkcg_gq __rcu *blkg_hint; struct hlist_head blkg_list; struct blkcg_policy_data *cpd[BLKCG_MAX_POLS]; struct list_head all_blkcgs_node; /* * List of updated percpu blkg_iostat_set's since the last flush. */ struct llist_head __percpu *lhead; #ifdef CONFIG_BLK_CGROUP_FC_APPID char fc_app_id[FC_APPID_LEN]; #endif #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; #endif }; static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) { return css ? container_of(css, struct blkcg, css) : NULL; } /* * A blkcg_gq (blkg) is association between a block cgroup (blkcg) and a * request_queue (q). This is used by blkcg policies which need to track * information per blkcg - q pair. * * There can be multiple active blkcg policies and each blkg:policy pair is * represented by a blkg_policy_data which is allocated and freed by each * policy's pd_alloc/free_fn() methods. A policy can allocate private data * area by allocating larger data structure which embeds blkg_policy_data * at the beginning. */ struct blkg_policy_data { /* the blkg and policy id this per-policy data belongs to */ struct blkcg_gq *blkg; int plid; bool online; }; /* * Policies that need to keep per-blkcg data which is independent from any * request_queue associated to it should implement cpd_alloc/free_fn() * methods. A policy can allocate private data area by allocating larger * data structure which embeds blkcg_policy_data at the beginning. * cpd_init() is invoked to let each policy handle per-blkcg data. */ struct blkcg_policy_data { /* the blkcg and policy id this per-policy data belongs to */ struct blkcg *blkcg; int plid; }; typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp); typedef void (blkcg_pol_init_cpd_fn)(struct blkcg_policy_data *cpd); typedef void (blkcg_pol_free_cpd_fn)(struct blkcg_policy_data *cpd); typedef void (blkcg_pol_bind_cpd_fn)(struct blkcg_policy_data *cpd); typedef struct blkg_policy_data *(blkcg_pol_alloc_pd_fn)(struct gendisk *disk, struct blkcg *blkcg, gfp_t gfp); typedef void (blkcg_pol_init_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd, struct seq_file *s); struct blkcg_policy { int plid; /* cgroup files for the policy */ struct cftype *dfl_cftypes; struct cftype *legacy_cftypes; /* operations */ blkcg_pol_alloc_cpd_fn *cpd_alloc_fn; blkcg_pol_free_cpd_fn *cpd_free_fn; blkcg_pol_alloc_pd_fn *pd_alloc_fn; blkcg_pol_init_pd_fn *pd_init_fn; blkcg_pol_online_pd_fn *pd_online_fn; blkcg_pol_offline_pd_fn *pd_offline_fn; blkcg_pol_free_pd_fn *pd_free_fn; blkcg_pol_reset_pd_stats_fn *pd_reset_stats_fn; blkcg_pol_stat_pd_fn *pd_stat_fn; }; extern struct blkcg blkcg_root; extern bool blkcg_debug_stats; void blkg_init_queue(struct request_queue *q); int blkcg_init_disk(struct gendisk *disk); void blkcg_exit_disk(struct gendisk *disk); /* Blkio controller policy registration */ int blkcg_policy_register(struct blkcg_policy *pol); void blkcg_policy_unregister(struct blkcg_policy *pol); int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol); void blkcg_deactivate_policy(struct gendisk *disk, const struct blkcg_policy *pol); const char *blkg_dev_name(struct blkcg_gq *blkg); void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg, u64 (*prfill)(struct seq_file *, struct blkg_policy_data *, int), const struct blkcg_policy *pol, int data, bool show_total); u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v); struct blkg_conf_ctx { char *input; char *body; struct block_device *bdev; struct blkcg_gq *blkg; }; void blkg_conf_init(struct blkg_conf_ctx *ctx, char *input); int blkg_conf_open_bdev(struct blkg_conf_ctx *ctx); int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, struct blkg_conf_ctx *ctx); void blkg_conf_exit(struct blkg_conf_ctx *ctx); /** * bio_issue_as_root_blkg - see if this bio needs to be issued as root blkg * @return: true if this bio needs to be submitted with the root blkg context. * * In order to avoid priority inversions we sometimes need to issue a bio as if * it were attached to the root blkg, and then backcharge to the actual owning * blkg. The idea is we do bio_blkcg_css() to look up the actual context for * the bio and attach the appropriate blkg to the bio. Then we call this helper * and if it is true run with the root blkg for that queue and then do any * backcharging to the originating cgroup once the io is complete. */ static inline bool bio_issue_as_root_blkg(struct bio *bio) { return (bio->bi_opf & (REQ_META | REQ_SWAP)) != 0; } /** * blkg_lookup - lookup blkg for the specified blkcg - q pair * @blkcg: blkcg of interest * @q: request_queue of interest * * Lookup blkg for the @blkcg - @q pair. * Must be called in a RCU critical section. */ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, struct request_queue *q) { struct blkcg_gq *blkg; if (blkcg == &blkcg_root) return q->root_blkg; blkg = rcu_dereference_check(blkcg->blkg_hint, lockdep_is_held(&q->queue_lock)); if (blkg && blkg->q == q) return blkg; blkg = radix_tree_lookup(&blkcg->blkg_tree, q->id); if (blkg && blkg->q != q) blkg = NULL; return blkg; } /** * blkg_to_pdata - get policy private data * @blkg: blkg of interest * @pol: policy of interest * * Return pointer to private data associated with the @blkg-@pol pair. */ static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, struct blkcg_policy *pol) { return blkg ? blkg->pd[pol->plid] : NULL; } static inline struct blkcg_policy_data *blkcg_to_cpd(struct blkcg *blkcg, struct blkcg_policy *pol) { return blkcg ? blkcg->cpd[pol->plid] : NULL; } /** * pdata_to_blkg - get blkg associated with policy private data * @pd: policy private data of interest * * @pd is policy private data. Determine the blkg it's associated with. */ static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd) { return pd ? pd->blkg : NULL; } static inline struct blkcg *cpd_to_blkcg(struct blkcg_policy_data *cpd) { return cpd ? cpd->blkcg : NULL; } /** * blkg_get - get a blkg reference * @blkg: blkg to get * * The caller should be holding an existing reference. */ static inline void blkg_get(struct blkcg_gq *blkg) { percpu_ref_get(&blkg->refcnt); } /** * blkg_tryget - try and get a blkg reference * @blkg: blkg to get * * This is for use when doing an RCU lookup of the blkg. We may be in the midst * of freeing this blkg, so we can only use it if the refcnt is not zero. */ static inline bool blkg_tryget(struct blkcg_gq *blkg) { return blkg && percpu_ref_tryget(&blkg->refcnt); } /** * blkg_put - put a blkg reference * @blkg: blkg to put */ static inline void blkg_put(struct blkcg_gq *blkg) { percpu_ref_put(&blkg->refcnt); } /** * blkg_for_each_descendant_pre - pre-order walk of a blkg's descendants * @d_blkg: loop cursor pointing to the current descendant * @pos_css: used for iteration * @p_blkg: target blkg to walk descendants of * * Walk @c_blkg through the descendants of @p_blkg. Must be used with RCU * read locked. If called under either blkcg or queue lock, the iteration * is guaranteed to include all and only online blkgs. The caller may * update @pos_css by calling css_rightmost_descendant() to skip subtree. * @p_blkg is included in the iteration and the first node to be visited. */ #define blkg_for_each_descendant_pre(d_blkg, pos_css, p_blkg) \ css_for_each_descendant_pre((pos_css), &(p_blkg)->blkcg->css) \ if (((d_blkg) = blkg_lookup(css_to_blkcg(pos_css), \ (p_blkg)->q))) /** * blkg_for_each_descendant_post - post-order walk of a blkg's descendants * @d_blkg: loop cursor pointing to the current descendant * @pos_css: used for iteration * @p_blkg: target blkg to walk descendants of * * Similar to blkg_for_each_descendant_pre() but performs post-order * traversal instead. Synchronization rules are the same. @p_blkg is * included in the iteration and the last node to be visited. */ #define blkg_for_each_descendant_post(d_blkg, pos_css, p_blkg) \ css_for_each_descendant_post((pos_css), &(p_blkg)->blkcg->css) \ if (((d_blkg) = blkg_lookup(css_to_blkcg(pos_css), \ (p_blkg)->q))) static inline void blkcg_bio_issue_init(struct bio *bio) { bio_issue_init(&bio->bi_issue, bio_sectors(bio)); } static inline void blkcg_use_delay(struct blkcg_gq *blkg) { if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0)) return; if (atomic_add_return(1, &blkg->use_delay) == 1) atomic_inc(&blkg->blkcg->congestion_count); } static inline int blkcg_unuse_delay(struct blkcg_gq *blkg) { int old = atomic_read(&blkg->use_delay); if (WARN_ON_ONCE(old < 0)) return 0; if (old == 0) return 0; /* * We do this song and dance because we can race with somebody else * adding or removing delay. If we just did an atomic_dec we'd end up * negative and we'd already be in trouble. We need to subtract 1 and * then check to see if we were the last delay so we can drop the * congestion count on the cgroup. */ while (old && !atomic_try_cmpxchg(&blkg->use_delay, &old, old - 1)) ; if (old == 0) return 0; if (old == 1) atomic_dec(&blkg->blkcg->congestion_count); return 1; } /** * blkcg_set_delay - Enable allocator delay mechanism with the specified delay amount * @blkg: target blkg * @delay: delay duration in nsecs * * When enabled with this function, the delay is not decayed and must be * explicitly cleared with blkcg_clear_delay(). Must not be mixed with * blkcg_[un]use_delay() and blkcg_add_delay() usages. */ static inline void blkcg_set_delay(struct blkcg_gq *blkg, u64 delay) { int old = atomic_read(&blkg->use_delay); /* We only want 1 person setting the congestion count for this blkg. */ if (!old && atomic_try_cmpxchg(&blkg->use_delay, &old, -1)) atomic_inc(&blkg->blkcg->congestion_count); atomic64_set(&blkg->delay_nsec, delay); } /** * blkcg_clear_delay - Disable allocator delay mechanism * @blkg: target blkg * * Disable use_delay mechanism. See blkcg_set_delay(). */ static inline void blkcg_clear_delay(struct blkcg_gq *blkg) { int old = atomic_read(&blkg->use_delay); /* We only want 1 person clearing the congestion count for this blkg. */ if (old && atomic_try_cmpxchg(&blkg->use_delay, &old, 0)) atomic_dec(&blkg->blkcg->congestion_count); } /** * blk_cgroup_mergeable - Determine whether to allow or disallow merges * @rq: request to merge into * @bio: bio to merge * * @bio and @rq should belong to the same cgroup and their issue_as_root should * match. The latter is necessary as we don't want to throttle e.g. a metadata * update because it happens to be next to a regular IO. */ static inline bool blk_cgroup_mergeable(struct request *rq, struct bio *bio) { return rq->bio->bi_blkg == bio->bi_blkg && bio_issue_as_root_blkg(rq->bio) == bio_issue_as_root_blkg(bio); } void blk_cgroup_bio_start(struct bio *bio); void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta); #else /* CONFIG_BLK_CGROUP */ struct blkg_policy_data { }; struct blkcg_policy_data { }; struct blkcg_policy { }; struct blkcg { }; static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; } static inline void blkg_init_queue(struct request_queue *q) { } static inline int blkcg_init_disk(struct gendisk *disk) { return 0; } static inline void blkcg_exit_disk(struct gendisk *disk) { } static inline int blkcg_policy_register(struct blkcg_policy *pol) { return 0; } static inline void blkcg_policy_unregister(struct blkcg_policy *pol) { } static inline int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol) { return 0; } static inline void blkcg_deactivate_policy(struct gendisk *disk, const struct blkcg_policy *pol) { } static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, struct blkcg_policy *pol) { return NULL; } static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd) { return NULL; } static inline char *blkg_path(struct blkcg_gq *blkg) { return NULL; } static inline void blkg_get(struct blkcg_gq *blkg) { } static inline void blkg_put(struct blkcg_gq *blkg) { } static inline void blkcg_bio_issue_init(struct bio *bio) { } static inline void blk_cgroup_bio_start(struct bio *bio) { } static inline bool blk_cgroup_mergeable(struct request *rq, struct bio *bio) { return true; } #define blk_queue_for_each_rl(rl, q) \ for ((rl) = &(q)->root_rl; (rl); (rl) = NULL) #endif /* CONFIG_BLK_CGROUP */ #endif /* _BLK_CGROUP_PRIVATE_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) by Jaroslav Kysela <perex@perex.cz> * Takashi Iwai <tiwai@suse.de> * * Generic memory allocators */ #include <linux/slab.h> #include <linux/mm.h> #include <linux/dma-mapping.h> #include <linux/dma-map-ops.h> #include <linux/genalloc.h> #include <linux/highmem.h> #include <linux/vmalloc.h> #ifdef CONFIG_X86 #include <asm/set_memory.h> #endif #include <sound/memalloc.h> #include "memalloc_local.h" #define DEFAULT_GFP \ (GFP_KERNEL | \ __GFP_RETRY_MAYFAIL | /* don't trigger OOM-killer */ \ __GFP_NOWARN) /* no stack trace print - this call is non-critical */ static const struct snd_malloc_ops *snd_dma_get_ops(struct snd_dma_buffer *dmab); #ifdef CONFIG_SND_DMA_SGBUF static void *snd_dma_sg_fallback_alloc(struct snd_dma_buffer *dmab, size_t size); #endif static void *__snd_dma_alloc_pages(struct snd_dma_buffer *dmab, size_t size) { const struct snd_malloc_ops *ops = snd_dma_get_ops(dmab); if (WARN_ON_ONCE(!ops || !ops->alloc)) return NULL; return ops->alloc(dmab, size); } /** * snd_dma_alloc_dir_pages - allocate the buffer area according to the given * type and direction * @type: the DMA buffer type * @device: the device pointer * @dir: DMA direction * @size: the buffer size to allocate * @dmab: buffer allocation record to store the allocated data * * Calls the memory-allocator function for the corresponding * buffer type. * * Return: Zero if the buffer with the given size is allocated successfully, * otherwise a negative value on error. */ int snd_dma_alloc_dir_pages(int type, struct device *device, enum dma_data_direction dir, size_t size, struct snd_dma_buffer *dmab) { if (WARN_ON(!size)) return -ENXIO; if (WARN_ON(!dmab)) return -ENXIO; size = PAGE_ALIGN(size); dmab->dev.type = type; dmab->dev.dev = device; dmab->dev.dir = dir; dmab->bytes = 0; dmab->addr = 0; dmab->private_data = NULL; dmab->area = __snd_dma_alloc_pages(dmab, size); if (!dmab->area) return -ENOMEM; dmab->bytes = size; return 0; } EXPORT_SYMBOL(snd_dma_alloc_dir_pages); /** * snd_dma_alloc_pages_fallback - allocate the buffer area according to the given type with fallback * @type: the DMA buffer type * @device: the device pointer * @size: the buffer size to allocate * @dmab: buffer allocation record to store the allocated data * * Calls the memory-allocator function for the corresponding * buffer type. When no space is left, this function reduces the size and * tries to allocate again. The size actually allocated is stored in * res_size argument. * * Return: Zero if the buffer with the given size is allocated successfully, * otherwise a negative value on error. */ int snd_dma_alloc_pages_fallback(int type, struct device *device, size_t size, struct snd_dma_buffer *dmab) { int err; while ((err = snd_dma_alloc_pages(type, device, size, dmab)) < 0) { if (err != -ENOMEM) return err; if (size <= PAGE_SIZE) return -ENOMEM; size >>= 1; size = PAGE_SIZE << get_order(size); } if (! dmab->area) return -ENOMEM; return 0; } EXPORT_SYMBOL(snd_dma_alloc_pages_fallback); /** * snd_dma_free_pages - release the allocated buffer * @dmab: the buffer allocation record to release * * Releases the allocated buffer via snd_dma_alloc_pages(). */ void snd_dma_free_pages(struct snd_dma_buffer *dmab) { const struct snd_malloc_ops *ops = snd_dma_get_ops(dmab); if (ops && ops->free) ops->free(dmab); } EXPORT_SYMBOL(snd_dma_free_pages); /* called by devres */ static void __snd_release_pages(struct device *dev, void *res) { snd_dma_free_pages(res); } /** * snd_devm_alloc_dir_pages - allocate the buffer and manage with devres * @dev: the device pointer * @type: the DMA buffer type * @dir: DMA direction * @size: the buffer size to allocate * * Allocate buffer pages depending on the given type and manage using devres. * The pages will be released automatically at the device removal. * * Unlike snd_dma_alloc_pages(), this function requires the real device pointer, * hence it can't work with SNDRV_DMA_TYPE_CONTINUOUS or * SNDRV_DMA_TYPE_VMALLOC type. * * Return: the snd_dma_buffer object at success, or NULL if failed */ struct snd_dma_buffer * snd_devm_alloc_dir_pages(struct device *dev, int type, enum dma_data_direction dir, size_t size) { struct snd_dma_buffer *dmab; int err; if (WARN_ON(type == SNDRV_DMA_TYPE_CONTINUOUS || type == SNDRV_DMA_TYPE_VMALLOC)) return NULL; dmab = devres_alloc(__snd_release_pages, sizeof(*dmab), GFP_KERNEL); if (!dmab) return NULL; err = snd_dma_alloc_dir_pages(type, dev, dir, size, dmab); if (err < 0) { devres_free(dmab); return NULL; } devres_add(dev, dmab); return dmab; } EXPORT_SYMBOL_GPL(snd_devm_alloc_dir_pages); /** * snd_dma_buffer_mmap - perform mmap of the given DMA buffer * @dmab: buffer allocation information * @area: VM area information * * Return: zero if successful, or a negative error code */ int snd_dma_buffer_mmap(struct snd_dma_buffer *dmab, struct vm_area_struct *area) { const struct snd_malloc_ops *ops; if (!dmab) return -ENOENT; ops = snd_dma_get_ops(dmab); if (ops && ops->mmap) return ops->mmap(dmab, area); else return -ENOENT; } EXPORT_SYMBOL(snd_dma_buffer_mmap); #ifdef CONFIG_HAS_DMA /** * snd_dma_buffer_sync - sync DMA buffer between CPU and device * @dmab: buffer allocation information * @mode: sync mode */ void snd_dma_buffer_sync(struct snd_dma_buffer *dmab, enum snd_dma_sync_mode mode) { const struct snd_malloc_ops *ops; if (!dmab || !dmab->dev.need_sync) return; ops = snd_dma_get_ops(dmab); if (ops && ops->sync) ops->sync(dmab, mode); } EXPORT_SYMBOL_GPL(snd_dma_buffer_sync); #endif /* CONFIG_HAS_DMA */ /** * snd_sgbuf_get_addr - return the physical address at the corresponding offset * @dmab: buffer allocation information * @offset: offset in the ring buffer * * Return: the physical address */ dma_addr_t snd_sgbuf_get_addr(struct snd_dma_buffer *dmab, size_t offset) { const struct snd_malloc_ops *ops = snd_dma_get_ops(dmab); if (ops && ops->get_addr) return ops->get_addr(dmab, offset); else return dmab->addr + offset; } EXPORT_SYMBOL(snd_sgbuf_get_addr); /** * snd_sgbuf_get_page - return the physical page at the corresponding offset * @dmab: buffer allocation information * @offset: offset in the ring buffer * * Return: the page pointer */ struct page *snd_sgbuf_get_page(struct snd_dma_buffer *dmab, size_t offset) { const struct snd_malloc_ops *ops = snd_dma_get_ops(dmab); if (ops && ops->get_page) return ops->get_page(dmab, offset); else return virt_to_page(dmab->area + offset); } EXPORT_SYMBOL(snd_sgbuf_get_page); /** * snd_sgbuf_get_chunk_size - compute the max chunk size with continuous pages * on sg-buffer * @dmab: buffer allocation information * @ofs: offset in the ring buffer * @size: the requested size * * Return: the chunk size */ unsigned int snd_sgbuf_get_chunk_size(struct snd_dma_buffer *dmab, unsigned int ofs, unsigned int size) { const struct snd_malloc_ops *ops = snd_dma_get_ops(dmab); if (ops && ops->get_chunk_size) return ops->get_chunk_size(dmab, ofs, size); else return size; } EXPORT_SYMBOL(snd_sgbuf_get_chunk_size); /* * Continuous pages allocator */ static void *do_alloc_pages(struct device *dev, size_t size, dma_addr_t *addr, bool wc) { void *p; gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; again: p = alloc_pages_exact(size, gfp); if (!p) return NULL; *addr = page_to_phys(virt_to_page(p)); if (!dev) return p; if ((*addr + size - 1) & ~dev->coherent_dma_mask) { if (IS_ENABLED(CONFIG_ZONE_DMA32) && !(gfp & GFP_DMA32)) { gfp |= GFP_DMA32; goto again; } if (IS_ENABLED(CONFIG_ZONE_DMA) && !(gfp & GFP_DMA)) { gfp = (gfp & ~GFP_DMA32) | GFP_DMA; goto again; } } #ifdef CONFIG_X86 if (wc) set_memory_wc((unsigned long)(p), size >> PAGE_SHIFT); #endif return p; } static void do_free_pages(void *p, size_t size, bool wc) { #ifdef CONFIG_X86 if (wc) set_memory_wb((unsigned long)(p), size >> PAGE_SHIFT); #endif free_pages_exact(p, size); } static void *snd_dma_continuous_alloc(struct snd_dma_buffer *dmab, size_t size) { return do_alloc_pages(dmab->dev.dev, size, &dmab->addr, false); } static void snd_dma_continuous_free(struct snd_dma_buffer *dmab) { do_free_pages(dmab->area, dmab->bytes, false); } static int snd_dma_continuous_mmap(struct snd_dma_buffer *dmab, struct vm_area_struct *area) { return remap_pfn_range(area, area->vm_start, dmab->addr >> PAGE_SHIFT, area->vm_end - area->vm_start, area->vm_page_prot); } static const struct snd_malloc_ops snd_dma_continuous_ops = { .alloc = snd_dma_continuous_alloc, .free = snd_dma_continuous_free, .mmap = snd_dma_continuous_mmap, }; /* * VMALLOC allocator */ static void *snd_dma_vmalloc_alloc(struct snd_dma_buffer *dmab, size_t size) { return vmalloc(size); } static void snd_dma_vmalloc_free(struct snd_dma_buffer *dmab) { vfree(dmab->area); } static int snd_dma_vmalloc_mmap(struct snd_dma_buffer *dmab, struct vm_area_struct *area) { return remap_vmalloc_range(area, dmab->area, 0); } #define get_vmalloc_page_addr(dmab, offset) \ page_to_phys(vmalloc_to_page((dmab)->area + (offset))) static dma_addr_t snd_dma_vmalloc_get_addr(struct snd_dma_buffer *dmab, size_t offset) { return get_vmalloc_page_addr(dmab, offset) + offset % PAGE_SIZE; } static struct page *snd_dma_vmalloc_get_page(struct snd_dma_buffer *dmab, size_t offset) { return vmalloc_to_page(dmab->area + offset); } static unsigned int snd_dma_vmalloc_get_chunk_size(struct snd_dma_buffer *dmab, unsigned int ofs, unsigned int size) { unsigned int start, end; unsigned long addr; start = ALIGN_DOWN(ofs, PAGE_SIZE); end = ofs + size - 1; /* the last byte address */ /* check page continuity */ addr = get_vmalloc_page_addr(dmab, start); for (;;) { start += PAGE_SIZE; if (start > end) break; addr += PAGE_SIZE; if (get_vmalloc_page_addr(dmab, start) != addr) return start - ofs; } /* ok, all on continuous pages */ return size; } static const struct snd_malloc_ops snd_dma_vmalloc_ops = { .alloc = snd_dma_vmalloc_alloc, .free = snd_dma_vmalloc_free, .mmap = snd_dma_vmalloc_mmap, .get_addr = snd_dma_vmalloc_get_addr, .get_page = snd_dma_vmalloc_get_page, .get_chunk_size = snd_dma_vmalloc_get_chunk_size, }; #ifdef CONFIG_HAS_DMA /* * IRAM allocator */ #ifdef CONFIG_GENERIC_ALLOCATOR static void *snd_dma_iram_alloc(struct snd_dma_buffer *dmab, size_t size) { struct device *dev = dmab->dev.dev; struct gen_pool *pool; void *p; if (dev->of_node) { pool = of_gen_pool_get(dev->of_node, "iram", 0); /* Assign the pool into private_data field */ dmab->private_data = pool; p = gen_pool_dma_alloc_align(pool, size, &dmab->addr, PAGE_SIZE); if (p) return p; } /* Internal memory might have limited size and no enough space, * so if we fail to malloc, try to fetch memory traditionally. */ dmab->dev.type = SNDRV_DMA_TYPE_DEV; return __snd_dma_alloc_pages(dmab, size); } static void snd_dma_iram_free(struct snd_dma_buffer *dmab) { struct gen_pool *pool = dmab->private_data; if (pool && dmab->area) gen_pool_free(pool, (unsigned long)dmab->area, dmab->bytes); } static int snd_dma_iram_mmap(struct snd_dma_buffer *dmab, struct vm_area_struct *area) { area->vm_page_prot = pgprot_writecombine(area->vm_page_prot); return remap_pfn_range(area, area->vm_start, dmab->addr >> PAGE_SHIFT, area->vm_end - area->vm_start, area->vm_page_prot); } static const struct snd_malloc_ops snd_dma_iram_ops = { .alloc = snd_dma_iram_alloc, .free = snd_dma_iram_free, .mmap = snd_dma_iram_mmap, }; #endif /* CONFIG_GENERIC_ALLOCATOR */ /* * Coherent device pages allocator */ static void *snd_dma_dev_alloc(struct snd_dma_buffer *dmab, size_t size) { return dma_alloc_coherent(dmab->dev.dev, size, &dmab->addr, DEFAULT_GFP); } static void snd_dma_dev_free(struct snd_dma_buffer *dmab) { dma_free_coherent(dmab->dev.dev, dmab->bytes, dmab->area, dmab->addr); } static int snd_dma_dev_mmap(struct snd_dma_buffer *dmab, struct vm_area_struct *area) { return dma_mmap_coherent(dmab->dev.dev, area, dmab->area, dmab->addr, dmab->bytes); } static const struct snd_malloc_ops snd_dma_dev_ops = { .alloc = snd_dma_dev_alloc, .free = snd_dma_dev_free, .mmap = snd_dma_dev_mmap, }; /* * Write-combined pages */ /* x86-specific allocations */ #ifdef CONFIG_SND_DMA_SGBUF static void *snd_dma_wc_alloc(struct snd_dma_buffer *dmab, size_t size) { return do_alloc_pages(dmab->dev.dev, size, &dmab->addr, true); } static void snd_dma_wc_free(struct snd_dma_buffer *dmab) { do_free_pages(dmab->area, dmab->bytes, true); } static int snd_dma_wc_mmap(struct snd_dma_buffer *dmab, struct vm_area_struct *area) { area->vm_page_prot = pgprot_writecombine(area->vm_page_prot); return snd_dma_continuous_mmap(dmab, area); } #else static void *snd_dma_wc_alloc(struct snd_dma_buffer *dmab, size_t size) { return dma_alloc_wc(dmab->dev.dev, size, &dmab->addr, DEFAULT_GFP); } static void snd_dma_wc_free(struct snd_dma_buffer *dmab) { dma_free_wc(dmab->dev.dev, dmab->bytes, dmab->area, dmab->addr); } static int snd_dma_wc_mmap(struct snd_dma_buffer *dmab, struct vm_area_struct *area) { return dma_mmap_wc(dmab->dev.dev, area, dmab->area, dmab->addr, dmab->bytes); } #endif /* CONFIG_SND_DMA_SGBUF */ static const struct snd_malloc_ops snd_dma_wc_ops = { .alloc = snd_dma_wc_alloc, .free = snd_dma_wc_free, .mmap = snd_dma_wc_mmap, }; /* * Non-contiguous pages allocator */ static void *snd_dma_noncontig_alloc(struct snd_dma_buffer *dmab, size_t size) { struct sg_table *sgt; void *p; #ifdef CONFIG_SND_DMA_SGBUF if (cpu_feature_enabled(X86_FEATURE_XENPV)) return snd_dma_sg_fallback_alloc(dmab, size); #endif sgt = dma_alloc_noncontiguous(dmab->dev.dev, size, dmab->dev.dir, DEFAULT_GFP, 0); #ifdef CONFIG_SND_DMA_SGBUF if (!sgt && !get_dma_ops(dmab->dev.dev)) return snd_dma_sg_fallback_alloc(dmab, size); #endif if (!sgt) return NULL; dmab->dev.need_sync = dma_need_sync(dmab->dev.dev, sg_dma_address(sgt->sgl)); p = dma_vmap_noncontiguous(dmab->dev.dev, size, sgt); if (p) { dmab->private_data = sgt; /* store the first page address for convenience */ dmab->addr = snd_sgbuf_get_addr(dmab, 0); } else { dma_free_noncontiguous(dmab->dev.dev, size, sgt, dmab->dev.dir); } return p; } static void snd_dma_noncontig_free(struct snd_dma_buffer *dmab) { dma_vunmap_noncontiguous(dmab->dev.dev, dmab->area); dma_free_noncontiguous(dmab->dev.dev, dmab->bytes, dmab->private_data, dmab->dev.dir); } static int snd_dma_noncontig_mmap(struct snd_dma_buffer *dmab, struct vm_area_struct *area) { return dma_mmap_noncontiguous(dmab->dev.dev, area, dmab->bytes, dmab->private_data); } static void snd_dma_noncontig_sync(struct snd_dma_buffer *dmab, enum snd_dma_sync_mode mode) { if (mode == SNDRV_DMA_SYNC_CPU) { if (dmab->dev.dir == DMA_TO_DEVICE) return; invalidate_kernel_vmap_range(dmab->area, dmab->bytes); dma_sync_sgtable_for_cpu(dmab->dev.dev, dmab->private_data, dmab->dev.dir); } else { if (dmab->dev.dir == DMA_FROM_DEVICE) return; flush_kernel_vmap_range(dmab->area, dmab->bytes); dma_sync_sgtable_for_device(dmab->dev.dev, dmab->private_data, dmab->dev.dir); } } static inline void snd_dma_noncontig_iter_set(struct snd_dma_buffer *dmab, struct sg_page_iter *piter, size_t offset) { struct sg_table *sgt = dmab->private_data; __sg_page_iter_start(piter, sgt->sgl, sgt->orig_nents, offset >> PAGE_SHIFT); } static dma_addr_t snd_dma_noncontig_get_addr(struct snd_dma_buffer *dmab, size_t offset) { struct sg_dma_page_iter iter; snd_dma_noncontig_iter_set(dmab, &iter.base, offset); __sg_page_iter_dma_next(&iter); return sg_page_iter_dma_address(&iter) + offset % PAGE_SIZE; } static struct page *snd_dma_noncontig_get_page(struct snd_dma_buffer *dmab, size_t offset) { struct sg_page_iter iter; snd_dma_noncontig_iter_set(dmab, &iter, offset); __sg_page_iter_next(&iter); return sg_page_iter_page(&iter); } static unsigned int snd_dma_noncontig_get_chunk_size(struct snd_dma_buffer *dmab, unsigned int ofs, unsigned int size) { struct sg_dma_page_iter iter; unsigned int start, end; unsigned long addr; start = ALIGN_DOWN(ofs, PAGE_SIZE); end = ofs + size - 1; /* the last byte address */ snd_dma_noncontig_iter_set(dmab, &iter.base, start); if (!__sg_page_iter_dma_next(&iter)) return 0; /* check page continuity */ addr = sg_page_iter_dma_address(&iter); for (;;) { start += PAGE_SIZE; if (start > end) break; addr += PAGE_SIZE; if (!__sg_page_iter_dma_next(&iter) || sg_page_iter_dma_address(&iter) != addr) return start - ofs; } /* ok, all on continuous pages */ return size; } static const struct snd_malloc_ops snd_dma_noncontig_ops = { .alloc = snd_dma_noncontig_alloc, .free = snd_dma_noncontig_free, .mmap = snd_dma_noncontig_mmap, .sync = snd_dma_noncontig_sync, .get_addr = snd_dma_noncontig_get_addr, .get_page = snd_dma_noncontig_get_page, .get_chunk_size = snd_dma_noncontig_get_chunk_size, }; /* x86-specific SG-buffer with WC pages */ #ifdef CONFIG_SND_DMA_SGBUF #define sg_wc_address(it) ((unsigned long)page_address(sg_page_iter_page(it))) static void *snd_dma_sg_wc_alloc(struct snd_dma_buffer *dmab, size_t size) { void *p = snd_dma_noncontig_alloc(dmab, size); struct sg_table *sgt = dmab->private_data; struct sg_page_iter iter; if (!p) return NULL; if (dmab->dev.type != SNDRV_DMA_TYPE_DEV_WC_SG) return p; for_each_sgtable_page(sgt, &iter, 0) set_memory_wc(sg_wc_address(&iter), 1); return p; } static void snd_dma_sg_wc_free(struct snd_dma_buffer *dmab) { struct sg_table *sgt = dmab->private_data; struct sg_page_iter iter; for_each_sgtable_page(sgt, &iter, 0) set_memory_wb(sg_wc_address(&iter), 1); snd_dma_noncontig_free(dmab); } static int snd_dma_sg_wc_mmap(struct snd_dma_buffer *dmab, struct vm_area_struct *area) { area->vm_page_prot = pgprot_writecombine(area->vm_page_prot); return dma_mmap_noncontiguous(dmab->dev.dev, area, dmab->bytes, dmab->private_data); } static const struct snd_malloc_ops snd_dma_sg_wc_ops = { .alloc = snd_dma_sg_wc_alloc, .free = snd_dma_sg_wc_free, .mmap = snd_dma_sg_wc_mmap, .sync = snd_dma_noncontig_sync, .get_addr = snd_dma_noncontig_get_addr, .get_page = snd_dma_noncontig_get_page, .get_chunk_size = snd_dma_noncontig_get_chunk_size, }; /* Fallback SG-buffer allocations for x86 */ struct snd_dma_sg_fallback { bool use_dma_alloc_coherent; size_t count; struct page **pages; /* DMA address array; the first page contains #pages in ~PAGE_MASK */ dma_addr_t *addrs; }; static void __snd_dma_sg_fallback_free(struct snd_dma_buffer *dmab, struct snd_dma_sg_fallback *sgbuf) { size_t i, size; if (sgbuf->pages && sgbuf->addrs) { i = 0; while (i < sgbuf->count) { if (!sgbuf->pages[i] || !sgbuf->addrs[i]) break; size = sgbuf->addrs[i] & ~PAGE_MASK; if (WARN_ON(!size)) break; if (sgbuf->use_dma_alloc_coherent) dma_free_coherent(dmab->dev.dev, size << PAGE_SHIFT, page_address(sgbuf->pages[i]), sgbuf->addrs[i] & PAGE_MASK); else do_free_pages(page_address(sgbuf->pages[i]), size << PAGE_SHIFT, false); i += size; } } kvfree(sgbuf->pages); kvfree(sgbuf->addrs); kfree(sgbuf); } static void *snd_dma_sg_fallback_alloc(struct snd_dma_buffer *dmab, size_t size) { struct snd_dma_sg_fallback *sgbuf; struct page **pagep, *curp; size_t chunk, npages; dma_addr_t *addrp; dma_addr_t addr; void *p; /* correct the type */ if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_SG) dmab->dev.type = SNDRV_DMA_TYPE_DEV_SG_FALLBACK; else if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG) dmab->dev.type = SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK; sgbuf = kzalloc(sizeof(*sgbuf), GFP_KERNEL); if (!sgbuf) return NULL; sgbuf->use_dma_alloc_coherent = cpu_feature_enabled(X86_FEATURE_XENPV); size = PAGE_ALIGN(size); sgbuf->count = size >> PAGE_SHIFT; sgbuf->pages = kvcalloc(sgbuf->count, sizeof(*sgbuf->pages), GFP_KERNEL); sgbuf->addrs = kvcalloc(sgbuf->count, sizeof(*sgbuf->addrs), GFP_KERNEL); if (!sgbuf->pages || !sgbuf->addrs) goto error; pagep = sgbuf->pages; addrp = sgbuf->addrs; chunk = (PAGE_SIZE - 1) << PAGE_SHIFT; /* to fit in low bits in addrs */ while (size > 0) { chunk = min(size, chunk); if (sgbuf->use_dma_alloc_coherent) p = dma_alloc_coherent(dmab->dev.dev, chunk, &addr, DEFAULT_GFP); else p = do_alloc_pages(dmab->dev.dev, chunk, &addr, false); if (!p) { if (chunk <= PAGE_SIZE) goto error; chunk >>= 1; chunk = PAGE_SIZE << get_order(chunk); continue; } size -= chunk; /* fill pages */ npages = chunk >> PAGE_SHIFT; *addrp = npages; /* store in lower bits */ curp = virt_to_page(p); while (npages--) { *pagep++ = curp++; *addrp++ |= addr; addr += PAGE_SIZE; } } p = vmap(sgbuf->pages, sgbuf->count, VM_MAP, PAGE_KERNEL); if (!p) goto error; if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK) set_pages_array_wc(sgbuf->pages, sgbuf->count); dmab->private_data = sgbuf; /* store the first page address for convenience */ dmab->addr = sgbuf->addrs[0] & PAGE_MASK; return p; error: __snd_dma_sg_fallback_free(dmab, sgbuf); return NULL; } static void snd_dma_sg_fallback_free(struct snd_dma_buffer *dmab) { struct snd_dma_sg_fallback *sgbuf = dmab->private_data; if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK) set_pages_array_wb(sgbuf->pages, sgbuf->count); vunmap(dmab->area); __snd_dma_sg_fallback_free(dmab, dmab->private_data); } static dma_addr_t snd_dma_sg_fallback_get_addr(struct snd_dma_buffer *dmab, size_t offset) { struct snd_dma_sg_fallback *sgbuf = dmab->private_data; size_t index = offset >> PAGE_SHIFT; return (sgbuf->addrs[index] & PAGE_MASK) | (offset & ~PAGE_MASK); } static int snd_dma_sg_fallback_mmap(struct snd_dma_buffer *dmab, struct vm_area_struct *area) { struct snd_dma_sg_fallback *sgbuf = dmab->private_data; if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK) area->vm_page_prot = pgprot_writecombine(area->vm_page_prot); return vm_map_pages(area, sgbuf->pages, sgbuf->count); } static const struct snd_malloc_ops snd_dma_sg_fallback_ops = { .alloc = snd_dma_sg_fallback_alloc, .free = snd_dma_sg_fallback_free, .mmap = snd_dma_sg_fallback_mmap, .get_addr = snd_dma_sg_fallback_get_addr, /* reuse vmalloc helpers */ .get_page = snd_dma_vmalloc_get_page, .get_chunk_size = snd_dma_vmalloc_get_chunk_size, }; #endif /* CONFIG_SND_DMA_SGBUF */ /* * Non-coherent pages allocator */ static void *snd_dma_noncoherent_alloc(struct snd_dma_buffer *dmab, size_t size) { void *p; p = dma_alloc_noncoherent(dmab->dev.dev, size, &dmab->addr, dmab->dev.dir, DEFAULT_GFP); if (p) dmab->dev.need_sync = dma_need_sync(dmab->dev.dev, dmab->addr); return p; } static void snd_dma_noncoherent_free(struct snd_dma_buffer *dmab) { dma_free_noncoherent(dmab->dev.dev, dmab->bytes, dmab->area, dmab->addr, dmab->dev.dir); } static int snd_dma_noncoherent_mmap(struct snd_dma_buffer *dmab, struct vm_area_struct *area) { area->vm_page_prot = vm_get_page_prot(area->vm_flags); return dma_mmap_pages(dmab->dev.dev, area, area->vm_end - area->vm_start, virt_to_page(dmab->area)); } static void snd_dma_noncoherent_sync(struct snd_dma_buffer *dmab, enum snd_dma_sync_mode mode) { if (mode == SNDRV_DMA_SYNC_CPU) { if (dmab->dev.dir != DMA_TO_DEVICE) dma_sync_single_for_cpu(dmab->dev.dev, dmab->addr, dmab->bytes, dmab->dev.dir); } else { if (dmab->dev.dir != DMA_FROM_DEVICE) dma_sync_single_for_device(dmab->dev.dev, dmab->addr, dmab->bytes, dmab->dev.dir); } } static const struct snd_malloc_ops snd_dma_noncoherent_ops = { .alloc = snd_dma_noncoherent_alloc, .free = snd_dma_noncoherent_free, .mmap = snd_dma_noncoherent_mmap, .sync = snd_dma_noncoherent_sync, }; #endif /* CONFIG_HAS_DMA */ /* * Entry points */ static const struct snd_malloc_ops *snd_dma_ops[] = { [SNDRV_DMA_TYPE_CONTINUOUS] = &snd_dma_continuous_ops, [SNDRV_DMA_TYPE_VMALLOC] = &snd_dma_vmalloc_ops, #ifdef CONFIG_HAS_DMA [SNDRV_DMA_TYPE_DEV] = &snd_dma_dev_ops, [SNDRV_DMA_TYPE_DEV_WC] = &snd_dma_wc_ops, [SNDRV_DMA_TYPE_NONCONTIG] = &snd_dma_noncontig_ops, [SNDRV_DMA_TYPE_NONCOHERENT] = &snd_dma_noncoherent_ops, #ifdef CONFIG_SND_DMA_SGBUF [SNDRV_DMA_TYPE_DEV_WC_SG] = &snd_dma_sg_wc_ops, #endif #ifdef CONFIG_GENERIC_ALLOCATOR [SNDRV_DMA_TYPE_DEV_IRAM] = &snd_dma_iram_ops, #endif /* CONFIG_GENERIC_ALLOCATOR */ #ifdef CONFIG_SND_DMA_SGBUF [SNDRV_DMA_TYPE_DEV_SG_FALLBACK] = &snd_dma_sg_fallback_ops, [SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK] = &snd_dma_sg_fallback_ops, #endif #endif /* CONFIG_HAS_DMA */ }; static const struct snd_malloc_ops *snd_dma_get_ops(struct snd_dma_buffer *dmab) { if (WARN_ON_ONCE(!dmab)) return NULL; if (WARN_ON_ONCE(dmab->dev.type <= SNDRV_DMA_TYPE_UNKNOWN || dmab->dev.type >= ARRAY_SIZE(snd_dma_ops))) return NULL; return snd_dma_ops[dmab->dev.type]; } |
| 1 1 1 5 4 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * G8BPQ compatible "AX.25 via ethernet" driver release 004 * * This code REQUIRES 2.0.0 or higher/ NET3.029 * * This is a "pseudo" network driver to allow AX.25 over Ethernet * using G8BPQ encapsulation. It has been extracted from the protocol * implementation because * * - things got unreadable within the protocol stack * - to cure the protocol stack from "feature-ism" * - a protocol implementation shouldn't need to know on * which hardware it is running * - user-level programs like the AX.25 utilities shouldn't * need to know about the hardware. * - IP over ethernet encapsulated AX.25 was impossible * - rxecho.c did not work * - to have room for extensions * - it just deserves to "live" as an own driver * * This driver can use any ethernet destination address, and can be * limited to accept frames from one dedicated ethernet card only. * * Note that the driver sets up the BPQ devices automagically on * startup or (if started before the "insmod" of an ethernet device) * on "ifconfig up". It hopefully will remove the BPQ on "rmmod"ing * the ethernet device (in fact: as soon as another ethernet or bpq * device gets "ifconfig"ured). * * I have heard that several people are thinking of experiments * with highspeed packet radio using existing ethernet cards. * Well, this driver is prepared for this purpose, just add * your tx key control and a txdelay / tailtime algorithm, * probably some buffering, and /voila/... * * History * BPQ 001 Joerg(DL1BKE) Extracted BPQ code from AX.25 * protocol stack and added my own * yet existing patches * BPQ 002 Joerg(DL1BKE) Scan network device list on * startup. * BPQ 003 Joerg(DL1BKE) Ethernet destination address * and accepted source address * can be configured by an ioctl() * call. * Fixed to match Linux networking * changes - 2.1.15. * BPQ 004 Joerg(DL1BKE) Fixed to not lock up on ifconfig. */ #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/net.h> #include <linux/slab.h> #include <net/ax25.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <net/sock.h> #include <linux/uaccess.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/notifier.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/stat.h> #include <linux/module.h> #include <linux/init.h> #include <linux/rtnetlink.h> #include <net/ip.h> #include <net/arp.h> #include <net/net_namespace.h> #include <linux/bpqether.h> static const char banner[] __initconst = KERN_INFO \ "AX.25: bpqether driver version 004\n"; static int bpq_rcv(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *); static int bpq_device_event(struct notifier_block *, unsigned long, void *); static struct packet_type bpq_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_BPQ), .func = bpq_rcv, }; static struct notifier_block bpq_dev_notifier = { .notifier_call = bpq_device_event, }; struct bpqdev { struct list_head bpq_list; /* list of bpq devices chain */ struct net_device *ethdev; /* link to ethernet device */ struct net_device *axdev; /* bpq device (bpq#) */ char dest_addr[6]; /* ether destination address */ char acpt_addr[6]; /* accept ether frames from this address only */ }; static LIST_HEAD(bpq_devices); /* * bpqether network devices are paired with ethernet devices below them, so * form a special "super class" of normal ethernet devices; split their locks * off into a separate class since they always nest. */ static struct lock_class_key bpq_netdev_xmit_lock_key; static struct lock_class_key bpq_netdev_addr_lock_key; static void bpq_set_lockdep_class_one(struct net_device *dev, struct netdev_queue *txq, void *_unused) { lockdep_set_class(&txq->_xmit_lock, &bpq_netdev_xmit_lock_key); } static void bpq_set_lockdep_class(struct net_device *dev) { lockdep_set_class(&dev->addr_list_lock, &bpq_netdev_addr_lock_key); netdev_for_each_tx_queue(dev, bpq_set_lockdep_class_one, NULL); } /* ------------------------------------------------------------------------ */ /* * Get the ethernet device for a BPQ device */ static inline struct net_device *bpq_get_ether_dev(struct net_device *dev) { struct bpqdev *bpq = netdev_priv(dev); return bpq ? bpq->ethdev : NULL; } /* * Get the BPQ device for the ethernet device */ static inline struct net_device *bpq_get_ax25_dev(struct net_device *dev) { struct bpqdev *bpq; list_for_each_entry_rcu(bpq, &bpq_devices, bpq_list, lockdep_rtnl_is_held()) { if (bpq->ethdev == dev) return bpq->axdev; } return NULL; } static inline int dev_is_ethdev(struct net_device *dev) { return dev->type == ARPHRD_ETHER && strncmp(dev->name, "dummy", 5); } /* ------------------------------------------------------------------------ */ /* * Receive an AX.25 frame via an ethernet interface. */ static int bpq_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *ptype, struct net_device *orig_dev) { int len; char * ptr; struct ethhdr *eth; struct bpqdev *bpq; if (!net_eq(dev_net(dev), &init_net)) goto drop; if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) return NET_RX_DROP; if (!pskb_may_pull(skb, sizeof(struct ethhdr))) goto drop; rcu_read_lock(); dev = bpq_get_ax25_dev(dev); if (dev == NULL || !netif_running(dev)) goto drop_unlock; /* * if we want to accept frames from just one ethernet device * we check the source address of the sender. */ bpq = netdev_priv(dev); eth = eth_hdr(skb); if (!(bpq->acpt_addr[0] & 0x01) && !ether_addr_equal(eth->h_source, bpq->acpt_addr)) goto drop_unlock; if (skb_cow(skb, sizeof(struct ethhdr))) goto drop_unlock; len = skb->data[0] + skb->data[1] * 256 - 5; skb_pull(skb, 2); /* Remove the length bytes */ skb_trim(skb, len); /* Set the length of the data */ dev->stats.rx_packets++; dev->stats.rx_bytes += len; ptr = skb_push(skb, 1); *ptr = 0; skb->protocol = ax25_type_trans(skb, dev); netif_rx(skb); unlock: rcu_read_unlock(); return 0; drop_unlock: kfree_skb(skb); goto unlock; drop: kfree_skb(skb); return 0; } /* * Send an AX.25 frame via an ethernet interface */ static netdev_tx_t bpq_xmit(struct sk_buff *skb, struct net_device *dev) { unsigned char *ptr; struct bpqdev *bpq; struct net_device *orig_dev; int size; if (skb->protocol == htons(ETH_P_IP)) return ax25_ip_xmit(skb); /* * Just to be *really* sure not to send anything if the interface * is down, the ethernet device may have gone. */ if (!netif_running(dev)) { kfree_skb(skb); return NETDEV_TX_OK; } skb_pull(skb, 1); /* Drop KISS byte */ size = skb->len; /* * We're about to mess with the skb which may still shared with the * generic networking code so unshare and ensure it's got enough * space for the BPQ headers. */ if (skb_cow(skb, AX25_BPQ_HEADER_LEN)) { if (net_ratelimit()) pr_err("bpqether: out of memory\n"); kfree_skb(skb); return NETDEV_TX_OK; } ptr = skb_push(skb, 2); /* Make space for length */ *ptr++ = (size + 5) % 256; *ptr++ = (size + 5) / 256; bpq = netdev_priv(dev); orig_dev = dev; if ((dev = bpq_get_ether_dev(dev)) == NULL) { orig_dev->stats.tx_dropped++; kfree_skb(skb); return NETDEV_TX_OK; } skb->protocol = ax25_type_trans(skb, dev); skb_reset_network_header(skb); dev_hard_header(skb, dev, ETH_P_BPQ, bpq->dest_addr, NULL, 0); dev->stats.tx_packets++; dev->stats.tx_bytes+=skb->len; dev_queue_xmit(skb); netif_wake_queue(dev); return NETDEV_TX_OK; } /* * Set AX.25 callsign */ static int bpq_set_mac_address(struct net_device *dev, void *addr) { struct sockaddr *sa = (struct sockaddr *)addr; dev_addr_set(dev, sa->sa_data); return 0; } /* Ioctl commands * * SIOCSBPQETHOPT reserved for enhancements * SIOCSBPQETHADDR set the destination and accepted * source ethernet address (broadcast * or multicast: accept all) */ static int bpq_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd) { struct bpq_ethaddr __user *ethaddr = data; struct bpqdev *bpq = netdev_priv(dev); struct bpq_req req; if (!capable(CAP_NET_ADMIN)) return -EPERM; switch (cmd) { case SIOCSBPQETHOPT: if (copy_from_user(&req, data, sizeof(struct bpq_req))) return -EFAULT; switch (req.cmd) { case SIOCGBPQETHPARAM: case SIOCSBPQETHPARAM: default: return -EINVAL; } break; case SIOCSBPQETHADDR: if (copy_from_user(bpq->dest_addr, ethaddr->destination, ETH_ALEN)) return -EFAULT; if (copy_from_user(bpq->acpt_addr, ethaddr->accept, ETH_ALEN)) return -EFAULT; break; default: return -EINVAL; } return 0; } /* * open/close a device */ static int bpq_open(struct net_device *dev) { netif_start_queue(dev); return 0; } static int bpq_close(struct net_device *dev) { netif_stop_queue(dev); return 0; } /* ------------------------------------------------------------------------ */ #ifdef CONFIG_PROC_FS /* * Proc filesystem */ static void *bpq_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { int i = 1; struct bpqdev *bpqdev; rcu_read_lock(); if (*pos == 0) return SEQ_START_TOKEN; list_for_each_entry_rcu(bpqdev, &bpq_devices, bpq_list) { if (i == *pos) return bpqdev; } return NULL; } static void *bpq_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct list_head *p; struct bpqdev *bpqdev = v; ++*pos; if (v == SEQ_START_TOKEN) p = rcu_dereference(list_next_rcu(&bpq_devices)); else p = rcu_dereference(list_next_rcu(&bpqdev->bpq_list)); return (p == &bpq_devices) ? NULL : list_entry(p, struct bpqdev, bpq_list); } static void bpq_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static int bpq_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_puts(seq, "dev ether destination accept from\n"); else { const struct bpqdev *bpqdev = v; seq_printf(seq, "%-5s %-10s %pM ", bpqdev->axdev->name, bpqdev->ethdev->name, bpqdev->dest_addr); if (is_multicast_ether_addr(bpqdev->acpt_addr)) seq_printf(seq, "*\n"); else seq_printf(seq, "%pM\n", bpqdev->acpt_addr); } return 0; } static const struct seq_operations bpq_seqops = { .start = bpq_seq_start, .next = bpq_seq_next, .stop = bpq_seq_stop, .show = bpq_seq_show, }; #endif /* ------------------------------------------------------------------------ */ static const struct net_device_ops bpq_netdev_ops = { .ndo_open = bpq_open, .ndo_stop = bpq_close, .ndo_start_xmit = bpq_xmit, .ndo_set_mac_address = bpq_set_mac_address, .ndo_siocdevprivate = bpq_siocdevprivate, }; static void bpq_setup(struct net_device *dev) { dev->netdev_ops = &bpq_netdev_ops; dev->needs_free_netdev = true; dev->flags = 0; dev->features = NETIF_F_LLTX; /* Allow recursion */ #if IS_ENABLED(CONFIG_AX25) dev->header_ops = &ax25_header_ops; #endif dev->type = ARPHRD_AX25; dev->hard_header_len = AX25_MAX_HEADER_LEN + AX25_BPQ_HEADER_LEN; dev->mtu = AX25_DEF_PACLEN; dev->addr_len = AX25_ADDR_LEN; memcpy(dev->broadcast, &ax25_bcast, AX25_ADDR_LEN); dev_addr_set(dev, (u8 *)&ax25_defaddr); } /* * Setup a new device. */ static int bpq_new_device(struct net_device *edev) { int err; struct net_device *ndev; struct bpqdev *bpq; ndev = alloc_netdev(sizeof(struct bpqdev), "bpq%d", NET_NAME_UNKNOWN, bpq_setup); if (!ndev) return -ENOMEM; bpq = netdev_priv(ndev); dev_hold(edev); bpq->ethdev = edev; bpq->axdev = ndev; eth_broadcast_addr(bpq->dest_addr); eth_broadcast_addr(bpq->acpt_addr); err = register_netdevice(ndev); if (err) goto error; bpq_set_lockdep_class(ndev); /* List protected by RTNL */ list_add_rcu(&bpq->bpq_list, &bpq_devices); return 0; error: dev_put(edev); free_netdev(ndev); return err; } static void bpq_free_device(struct net_device *ndev) { struct bpqdev *bpq = netdev_priv(ndev); dev_put(bpq->ethdev); list_del_rcu(&bpq->bpq_list); unregister_netdevice(ndev); } /* * Handle device status changes. */ static int bpq_device_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; if (!dev_is_ethdev(dev) && !bpq_get_ax25_dev(dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UP: /* new ethernet device -> new BPQ interface */ if (bpq_get_ax25_dev(dev) == NULL) bpq_new_device(dev); break; case NETDEV_DOWN: /* ethernet device closed -> close BPQ interface */ if ((dev = bpq_get_ax25_dev(dev)) != NULL) dev_close(dev); break; case NETDEV_UNREGISTER: /* ethernet device removed -> free BPQ interface */ if ((dev = bpq_get_ax25_dev(dev)) != NULL) bpq_free_device(dev); break; default: break; } return NOTIFY_DONE; } /* ------------------------------------------------------------------------ */ /* * Initialize driver. To be called from af_ax25 if not compiled as a * module */ static int __init bpq_init_driver(void) { #ifdef CONFIG_PROC_FS if (!proc_create_seq("bpqether", 0444, init_net.proc_net, &bpq_seqops)) { printk(KERN_ERR "bpq: cannot create /proc/net/bpqether entry.\n"); return -ENOENT; } #endif /* CONFIG_PROC_FS */ dev_add_pack(&bpq_packet_type); register_netdevice_notifier(&bpq_dev_notifier); printk(banner); return 0; } static void __exit bpq_cleanup_driver(void) { struct bpqdev *bpq; dev_remove_pack(&bpq_packet_type); unregister_netdevice_notifier(&bpq_dev_notifier); remove_proc_entry("bpqether", init_net.proc_net); rtnl_lock(); while (!list_empty(&bpq_devices)) { bpq = list_entry(bpq_devices.next, struct bpqdev, bpq_list); bpq_free_device(bpq->axdev); } rtnl_unlock(); } MODULE_AUTHOR("Joerg Reuter DL1BKE <jreuter@yaina.de>"); MODULE_DESCRIPTION("Transmit and receive AX.25 packets over Ethernet"); MODULE_LICENSE("GPL"); module_init(bpq_init_driver); module_exit(bpq_cleanup_driver); |
| 3051 121 3027 825 4 1227 2 1 11 4029 1077 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RCULIST_H #define _LINUX_RCULIST_H #ifdef __KERNEL__ /* * RCU-protected list version */ #include <linux/list.h> #include <linux/rcupdate.h> /* * INIT_LIST_HEAD_RCU - Initialize a list_head visible to RCU readers * @list: list to be initialized * * You should instead use INIT_LIST_HEAD() for normal initialization and * cleanup tasks, when readers have no access to the list being initialized. * However, if the list being initialized is visible to readers, you * need to keep the compiler from being too mischievous. */ static inline void INIT_LIST_HEAD_RCU(struct list_head *list) { WRITE_ONCE(list->next, list); WRITE_ONCE(list->prev, list); } /* * return the ->next pointer of a list_head in an rcu safe * way, we must not access it directly */ #define list_next_rcu(list) (*((struct list_head __rcu **)(&(list)->next))) /** * list_tail_rcu - returns the prev pointer of the head of the list * @head: the head of the list * * Note: This should only be used with the list header, and even then * only if list_del() and similar primitives are not also used on the * list header. */ #define list_tail_rcu(head) (*((struct list_head __rcu **)(&(head)->prev))) /* * Check during list traversal that we are within an RCU reader */ #define check_arg_count_one(dummy) #ifdef CONFIG_PROVE_RCU_LIST #define __list_check_rcu(dummy, cond, extra...) \ ({ \ check_arg_count_one(extra); \ RCU_LOCKDEP_WARN(!(cond) && !rcu_read_lock_any_held(), \ "RCU-list traversed in non-reader section!"); \ }) #define __list_check_srcu(cond) \ ({ \ RCU_LOCKDEP_WARN(!(cond), \ "RCU-list traversed without holding the required lock!");\ }) #else #define __list_check_rcu(dummy, cond, extra...) \ ({ check_arg_count_one(extra); }) #define __list_check_srcu(cond) ({ }) #endif /* * Insert a new entry between two known consecutive entries. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_add_rcu(struct list_head *new, struct list_head *prev, struct list_head *next) { if (!__list_add_valid(new, prev, next)) return; new->next = next; new->prev = prev; rcu_assign_pointer(list_next_rcu(prev), new); next->prev = new; } /** * list_add_rcu - add a new entry to rcu-protected list * @new: new entry to be added * @head: list head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_add_rcu() * or list_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). */ static inline void list_add_rcu(struct list_head *new, struct list_head *head) { __list_add_rcu(new, head, head->next); } /** * list_add_tail_rcu - add a new entry to rcu-protected list * @new: new entry to be added * @head: list head to add it before * * Insert a new entry before the specified head. * This is useful for implementing queues. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_add_tail_rcu() * or list_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). */ static inline void list_add_tail_rcu(struct list_head *new, struct list_head *head) { __list_add_rcu(new, head->prev, head); } /** * list_del_rcu - deletes entry from list without re-initialization * @entry: the element to delete from the list. * * Note: list_empty() on entry does not return true after this, * the entry is in an undefined state. It is useful for RCU based * lockfree traversal. * * In particular, it means that we can not poison the forward * pointers that may still be used for walking the list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_del_rcu() * or list_add_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). * * Note that the caller is not permitted to immediately free * the newly deleted entry. Instead, either synchronize_rcu() * or call_rcu() must be used to defer freeing until an RCU * grace period has elapsed. */ static inline void list_del_rcu(struct list_head *entry) { __list_del_entry(entry); entry->prev = LIST_POISON2; } /** * hlist_del_init_rcu - deletes entry from hash list with re-initialization * @n: the element to delete from the hash list. * * Note: list_unhashed() on the node return true after this. It is * useful for RCU based read lockfree traversal if the writer side * must know if the list entry is still hashed or already unhashed. * * In particular, it means that we can not poison the forward pointers * that may still be used for walking the hash list and we can only * zero the pprev pointer so list_unhashed() will return true after * this. * * The caller must take whatever precautions are necessary (such as * holding appropriate locks) to avoid racing with another * list-mutation primitive, such as hlist_add_head_rcu() or * hlist_del_rcu(), running on this same list. However, it is * perfectly legal to run concurrently with the _rcu list-traversal * primitives, such as hlist_for_each_entry_rcu(). */ static inline void hlist_del_init_rcu(struct hlist_node *n) { if (!hlist_unhashed(n)) { __hlist_del(n); WRITE_ONCE(n->pprev, NULL); } } /** * list_replace_rcu - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * The @old entry will be replaced with the @new entry atomically. * Note: @old should not be empty. */ static inline void list_replace_rcu(struct list_head *old, struct list_head *new) { new->next = old->next; new->prev = old->prev; rcu_assign_pointer(list_next_rcu(new->prev), new); new->next->prev = new; old->prev = LIST_POISON2; } /** * __list_splice_init_rcu - join an RCU-protected list into an existing list. * @list: the RCU-protected list to splice * @prev: points to the last element of the existing list * @next: points to the first element of the existing list * @sync: synchronize_rcu, synchronize_rcu_expedited, ... * * The list pointed to by @prev and @next can be RCU-read traversed * concurrently with this function. * * Note that this function blocks. * * Important note: the caller must take whatever action is necessary to prevent * any other updates to the existing list. In principle, it is possible to * modify the list as soon as sync() begins execution. If this sort of thing * becomes necessary, an alternative version based on call_rcu() could be * created. But only if -really- needed -- there is no shortage of RCU API * members. */ static inline void __list_splice_init_rcu(struct list_head *list, struct list_head *prev, struct list_head *next, void (*sync)(void)) { struct list_head *first = list->next; struct list_head *last = list->prev; /* * "first" and "last" tracking list, so initialize it. RCU readers * have access to this list, so we must use INIT_LIST_HEAD_RCU() * instead of INIT_LIST_HEAD(). */ INIT_LIST_HEAD_RCU(list); /* * At this point, the list body still points to the source list. * Wait for any readers to finish using the list before splicing * the list body into the new list. Any new readers will see * an empty list. */ sync(); ASSERT_EXCLUSIVE_ACCESS(*first); ASSERT_EXCLUSIVE_ACCESS(*last); /* * Readers are finished with the source list, so perform splice. * The order is important if the new list is global and accessible * to concurrent RCU readers. Note that RCU readers are not * permitted to traverse the prev pointers without excluding * this function. */ last->next = next; rcu_assign_pointer(list_next_rcu(prev), first); first->prev = prev; next->prev = last; } /** * list_splice_init_rcu - splice an RCU-protected list into an existing list, * designed for stacks. * @list: the RCU-protected list to splice * @head: the place in the existing list to splice the first list into * @sync: synchronize_rcu, synchronize_rcu_expedited, ... */ static inline void list_splice_init_rcu(struct list_head *list, struct list_head *head, void (*sync)(void)) { if (!list_empty(list)) __list_splice_init_rcu(list, head, head->next, sync); } /** * list_splice_tail_init_rcu - splice an RCU-protected list into an existing * list, designed for queues. * @list: the RCU-protected list to splice * @head: the place in the existing list to splice the first list into * @sync: synchronize_rcu, synchronize_rcu_expedited, ... */ static inline void list_splice_tail_init_rcu(struct list_head *list, struct list_head *head, void (*sync)(void)) { if (!list_empty(list)) __list_splice_init_rcu(list, head->prev, head, sync); } /** * list_entry_rcu - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_entry_rcu(ptr, type, member) \ container_of(READ_ONCE(ptr), type, member) /* * Where are list_empty_rcu() and list_first_entry_rcu()? * * They do not exist because they would lead to subtle race conditions: * * if (!list_empty_rcu(mylist)) { * struct foo *bar = list_first_entry_rcu(mylist, struct foo, list_member); * do_something(bar); * } * * The list might be non-empty when list_empty_rcu() checks it, but it * might have become empty by the time that list_first_entry_rcu() rereads * the ->next pointer, which would result in a SEGV. * * When not using RCU, it is OK for list_first_entry() to re-read that * pointer because both functions should be protected by some lock that * blocks writers. * * When using RCU, list_empty() uses READ_ONCE() to fetch the * RCU-protected ->next pointer and then compares it to the address of the * list head. However, it neither dereferences this pointer nor provides * this pointer to its caller. Thus, READ_ONCE() suffices (that is, * rcu_dereference() is not needed), which means that list_empty() can be * used anywhere you would want to use list_empty_rcu(). Just don't * expect anything useful to happen if you do a subsequent lockless * call to list_first_entry_rcu()!!! * * See list_first_or_null_rcu for an alternative. */ /** * list_first_or_null_rcu - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the list is empty, it returns NULL. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_first_or_null_rcu(ptr, type, member) \ ({ \ struct list_head *__ptr = (ptr); \ struct list_head *__next = READ_ONCE(__ptr->next); \ likely(__ptr != __next) ? list_entry_rcu(__next, type, member) : NULL; \ }) /** * list_next_or_null_rcu - get the next element from a list * @head: the head for the list. * @ptr: the list head to take the next element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the ptr is at the end of the list, NULL is returned. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_next_or_null_rcu(head, ptr, type, member) \ ({ \ struct list_head *__head = (head); \ struct list_head *__ptr = (ptr); \ struct list_head *__next = READ_ONCE(__ptr->next); \ likely(__next != __head) ? list_entry_rcu(__next, type, \ member) : NULL; \ }) /** * list_for_each_entry_rcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * @cond: optional lockdep expression if called from non-RCU protection. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as list_add_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define list_for_each_entry_rcu(pos, head, member, cond...) \ for (__list_check_rcu(dummy, ## cond, 0), \ pos = list_entry_rcu((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_srcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * @cond: lockdep expression for the lock required to traverse the list. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as list_add_rcu() * as long as the traversal is guarded by srcu_read_lock(). * The lockdep expression srcu_read_lock_held() can be passed as the * cond argument from read side. */ #define list_for_each_entry_srcu(pos, head, member, cond) \ for (__list_check_srcu(cond), \ pos = list_entry_rcu((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_entry_lockless - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * This primitive may safely run concurrently with the _rcu * list-mutation primitives such as list_add_rcu(), but requires some * implicit RCU read-side guarding. One example is running within a special * exception-time environment where preemption is disabled and where lockdep * cannot be invoked. Another example is when items are added to the list, * but never deleted. */ #define list_entry_lockless(ptr, type, member) \ container_of((typeof(ptr))READ_ONCE(ptr), type, member) /** * list_for_each_entry_lockless - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_struct within the struct. * * This primitive may safely run concurrently with the _rcu * list-mutation primitives such as list_add_rcu(), but requires some * implicit RCU read-side guarding. One example is running within a special * exception-time environment where preemption is disabled and where lockdep * cannot be invoked. Another example is when items are added to the list, * but never deleted. */ #define list_for_each_entry_lockless(pos, head, member) \ for (pos = list_entry_lockless((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_lockless(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_continue_rcu - continue iteration over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Continue to iterate over list of given type, continuing after * the current position which must have been in the list when the RCU read * lock was taken. * This would typically require either that you obtained the node from a * previous walk of the list in the same RCU read-side critical section, or * that you held some sort of non-RCU reference (such as a reference count) * to keep the node alive *and* in the list. * * This iterator is similar to list_for_each_entry_from_rcu() except * this starts after the given position and that one starts at the given * position. */ #define list_for_each_entry_continue_rcu(pos, head, member) \ for (pos = list_entry_rcu(pos->member.next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_from_rcu - iterate over a list from current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_node within the struct. * * Iterate over the tail of a list starting from a given position, * which must have been in the list when the RCU read lock was taken. * This would typically require either that you obtained the node from a * previous walk of the list in the same RCU read-side critical section, or * that you held some sort of non-RCU reference (such as a reference count) * to keep the node alive *and* in the list. * * This iterator is similar to list_for_each_entry_continue_rcu() except * this starts from the given position and that one starts from the position * after the given position. */ #define list_for_each_entry_from_rcu(pos, head, member) \ for (; &(pos)->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*(pos)), member)) /** * hlist_del_rcu - deletes entry from hash list without re-initialization * @n: the element to delete from the hash list. * * Note: list_unhashed() on entry does not return true after this, * the entry is in an undefined state. It is useful for RCU based * lockfree traversal. * * In particular, it means that we can not poison the forward * pointers that may still be used for walking the hash list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry(). */ static inline void hlist_del_rcu(struct hlist_node *n) { __hlist_del(n); WRITE_ONCE(n->pprev, LIST_POISON2); } /** * hlist_replace_rcu - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * The @old entry will be replaced with the @new entry atomically. */ static inline void hlist_replace_rcu(struct hlist_node *old, struct hlist_node *new) { struct hlist_node *next = old->next; new->next = next; WRITE_ONCE(new->pprev, old->pprev); rcu_assign_pointer(*(struct hlist_node __rcu **)new->pprev, new); if (next) WRITE_ONCE(new->next->pprev, &new->next); WRITE_ONCE(old->pprev, LIST_POISON2); } /** * hlists_swap_heads_rcu - swap the lists the hlist heads point to * @left: The hlist head on the left * @right: The hlist head on the right * * The lists start out as [@left ][node1 ... ] and * [@right ][node2 ... ] * The lists end up as [@left ][node2 ... ] * [@right ][node1 ... ] */ static inline void hlists_swap_heads_rcu(struct hlist_head *left, struct hlist_head *right) { struct hlist_node *node1 = left->first; struct hlist_node *node2 = right->first; rcu_assign_pointer(left->first, node2); rcu_assign_pointer(right->first, node1); WRITE_ONCE(node2->pprev, &left->first); WRITE_ONCE(node1->pprev, &right->first); } /* * return the first or the next element in an RCU protected hlist */ #define hlist_first_rcu(head) (*((struct hlist_node __rcu **)(&(head)->first))) #define hlist_next_rcu(node) (*((struct hlist_node __rcu **)(&(node)->next))) #define hlist_pprev_rcu(node) (*((struct hlist_node __rcu **)((node)->pprev))) /** * hlist_add_head_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_add_head_rcu(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *first = h->first; n->next = first; WRITE_ONCE(n->pprev, &h->first); rcu_assign_pointer(hlist_first_rcu(h), n); if (first) WRITE_ONCE(first->pprev, &n->next); } /** * hlist_add_tail_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_add_tail_rcu(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *i, *last = NULL; /* Note: write side code, so rcu accessors are not needed. */ for (i = h->first; i; i = i->next) last = i; if (last) { n->next = last->next; WRITE_ONCE(n->pprev, &last->next); rcu_assign_pointer(hlist_next_rcu(last), n); } else { hlist_add_head_rcu(n, h); } } /** * hlist_add_before_rcu * @n: the new element to add to the hash list. * @next: the existing element to add the new element before. * * Description: * Adds the specified element to the specified hlist * before the specified node while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. */ static inline void hlist_add_before_rcu(struct hlist_node *n, struct hlist_node *next) { WRITE_ONCE(n->pprev, next->pprev); n->next = next; rcu_assign_pointer(hlist_pprev_rcu(n), n); WRITE_ONCE(next->pprev, &n->next); } /** * hlist_add_behind_rcu * @n: the new element to add to the hash list. * @prev: the existing element to add the new element after. * * Description: * Adds the specified element to the specified hlist * after the specified node while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. */ static inline void hlist_add_behind_rcu(struct hlist_node *n, struct hlist_node *prev) { n->next = prev->next; WRITE_ONCE(n->pprev, &prev->next); rcu_assign_pointer(hlist_next_rcu(prev), n); if (n->next) WRITE_ONCE(n->next->pprev, &n->next); } #define __hlist_for_each_rcu(pos, head) \ for (pos = rcu_dereference(hlist_first_rcu(head)); \ pos; \ pos = rcu_dereference(hlist_next_rcu(pos))) /** * hlist_for_each_entry_rcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * @cond: optional lockdep expression if called from non-RCU protection. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define hlist_for_each_entry_rcu(pos, head, member, cond...) \ for (__list_check_rcu(dummy, ## cond, 0), \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_srcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * @cond: lockdep expression for the lock required to traverse the list. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by srcu_read_lock(). * The lockdep expression srcu_read_lock_held() can be passed as the * cond argument from read side. */ #define hlist_for_each_entry_srcu(pos, head, member, cond) \ for (__list_check_srcu(cond), \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_rcu_notrace - iterate over rcu list of given type (for tracing) * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). * * This is the same as hlist_for_each_entry_rcu() except that it does * not do any RCU debugging or tracing. */ #define hlist_for_each_entry_rcu_notrace(pos, head, member) \ for (pos = hlist_entry_safe(rcu_dereference_raw_check(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw_check(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_rcu_bh - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define hlist_for_each_entry_rcu_bh(pos, head, member) \ for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue_rcu(pos, member) \ for (pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu_bh - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue_rcu_bh(pos, member) \ for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_from_rcu - iterate over a hlist continuing from current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_from_rcu(pos, member) \ for (; pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) #endif /* __KERNEL__ */ #endif |
| 88 46 144 31 75 8 434 24 135 469 176 154 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2009-2021 Christoph Hellwig * * NOTE: none of these tracepoints shall be considered a stable kernel ABI * as they can change at any time. * * Current conventions for printing numbers measuring specific units: * * offset: byte offset into a subcomponent of a file operation * pos: file offset, in bytes * length: length of a file operation, in bytes * ino: inode number * * Numbers describing space allocations should be formatted in hexadecimal. */ #undef TRACE_SYSTEM #define TRACE_SYSTEM iomap #if !defined(_IOMAP_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) #define _IOMAP_TRACE_H #include <linux/tracepoint.h> struct inode; DECLARE_EVENT_CLASS(iomap_readpage_class, TP_PROTO(struct inode *inode, int nr_pages), TP_ARGS(inode, nr_pages), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(int, nr_pages) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->nr_pages = nr_pages; ), TP_printk("dev %d:%d ino 0x%llx nr_pages %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->nr_pages) ) #define DEFINE_READPAGE_EVENT(name) \ DEFINE_EVENT(iomap_readpage_class, name, \ TP_PROTO(struct inode *inode, int nr_pages), \ TP_ARGS(inode, nr_pages)) DEFINE_READPAGE_EVENT(iomap_readpage); DEFINE_READPAGE_EVENT(iomap_readahead); DECLARE_EVENT_CLASS(iomap_range_class, TP_PROTO(struct inode *inode, loff_t off, u64 len), TP_ARGS(inode, off, len), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(loff_t, size) __field(loff_t, offset) __field(u64, length) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->size = i_size_read(inode); __entry->offset = off; __entry->length = len; ), TP_printk("dev %d:%d ino 0x%llx size 0x%llx offset 0x%llx length 0x%llx", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->size, __entry->offset, __entry->length) ) #define DEFINE_RANGE_EVENT(name) \ DEFINE_EVENT(iomap_range_class, name, \ TP_PROTO(struct inode *inode, loff_t off, u64 len),\ TP_ARGS(inode, off, len)) DEFINE_RANGE_EVENT(iomap_writepage); DEFINE_RANGE_EVENT(iomap_release_folio); DEFINE_RANGE_EVENT(iomap_invalidate_folio); DEFINE_RANGE_EVENT(iomap_dio_invalidate_fail); DEFINE_RANGE_EVENT(iomap_dio_rw_queued); #define IOMAP_TYPE_STRINGS \ { IOMAP_HOLE, "HOLE" }, \ { IOMAP_DELALLOC, "DELALLOC" }, \ { IOMAP_MAPPED, "MAPPED" }, \ { IOMAP_UNWRITTEN, "UNWRITTEN" }, \ { IOMAP_INLINE, "INLINE" } #define IOMAP_FLAGS_STRINGS \ { IOMAP_WRITE, "WRITE" }, \ { IOMAP_ZERO, "ZERO" }, \ { IOMAP_REPORT, "REPORT" }, \ { IOMAP_FAULT, "FAULT" }, \ { IOMAP_DIRECT, "DIRECT" }, \ { IOMAP_NOWAIT, "NOWAIT" } #define IOMAP_F_FLAGS_STRINGS \ { IOMAP_F_NEW, "NEW" }, \ { IOMAP_F_DIRTY, "DIRTY" }, \ { IOMAP_F_SHARED, "SHARED" }, \ { IOMAP_F_MERGED, "MERGED" }, \ { IOMAP_F_BUFFER_HEAD, "BH" }, \ { IOMAP_F_SIZE_CHANGED, "SIZE_CHANGED" } #define IOMAP_DIO_STRINGS \ {IOMAP_DIO_FORCE_WAIT, "DIO_FORCE_WAIT" }, \ {IOMAP_DIO_OVERWRITE_ONLY, "DIO_OVERWRITE_ONLY" }, \ {IOMAP_DIO_PARTIAL, "DIO_PARTIAL" } DECLARE_EVENT_CLASS(iomap_class, TP_PROTO(struct inode *inode, struct iomap *iomap), TP_ARGS(inode, iomap), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(u64, addr) __field(loff_t, offset) __field(u64, length) __field(u16, type) __field(u16, flags) __field(dev_t, bdev) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->addr = iomap->addr; __entry->offset = iomap->offset; __entry->length = iomap->length; __entry->type = iomap->type; __entry->flags = iomap->flags; __entry->bdev = iomap->bdev ? iomap->bdev->bd_dev : 0; ), TP_printk("dev %d:%d ino 0x%llx bdev %d:%d addr 0x%llx offset 0x%llx " "length 0x%llx type %s flags %s", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, MAJOR(__entry->bdev), MINOR(__entry->bdev), __entry->addr, __entry->offset, __entry->length, __print_symbolic(__entry->type, IOMAP_TYPE_STRINGS), __print_flags(__entry->flags, "|", IOMAP_F_FLAGS_STRINGS)) ) #define DEFINE_IOMAP_EVENT(name) \ DEFINE_EVENT(iomap_class, name, \ TP_PROTO(struct inode *inode, struct iomap *iomap), \ TP_ARGS(inode, iomap)) DEFINE_IOMAP_EVENT(iomap_iter_dstmap); DEFINE_IOMAP_EVENT(iomap_iter_srcmap); TRACE_EVENT(iomap_writepage_map, TP_PROTO(struct inode *inode, u64 pos, unsigned int dirty_len, struct iomap *iomap), TP_ARGS(inode, pos, dirty_len, iomap), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(u64, pos) __field(u64, dirty_len) __field(u64, addr) __field(loff_t, offset) __field(u64, length) __field(u16, type) __field(u16, flags) __field(dev_t, bdev) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pos = pos; __entry->dirty_len = dirty_len; __entry->addr = iomap->addr; __entry->offset = iomap->offset; __entry->length = iomap->length; __entry->type = iomap->type; __entry->flags = iomap->flags; __entry->bdev = iomap->bdev ? iomap->bdev->bd_dev : 0; ), TP_printk("dev %d:%d ino 0x%llx bdev %d:%d pos 0x%llx dirty len 0x%llx " "addr 0x%llx offset 0x%llx length 0x%llx type %s flags %s", MAJOR(__entry->dev), MINOR(__entry->dev), |